COMPASSFull Papers
| Paper Title | Authors | Affiliations | Abstract | Video |
|---|---|---|---|---|
| Analyzing the Energy Usage of a Community and the Benefits of Energy Storage | John Wamburu, Stephen Lee, Srinivasan Iyengar, David Irwin, Prashant Shenoy | University of Massachusetts Amherst, IBM Research - Africa, University of Massachusetts Amherst, Microsoft Corp, University of Pittsburgh | Understanding the energy usage of a community is crucial for policymaking, energy planning, and achieving sustainable development. The advent of the smart grid has made it feasible to gather fine-grain energy usage data at large-scales, providing us with new opportunities to understand demand patterns at different spatial and temporal scales. In this paper, we conduct a large-scale empirical study of energy usage of 14,849 residential and commercial energy consumers from a small city in the United States. We conduct a wide ranging analysis of energy usage at multiple granularities—citywide, transformer-level, and individual home levels. In doing so, we demonstrate how city-wide smart meter datasets can answer a variety of questions on energy consumption, such as the impact of weather on energy usage. For example, we show that extreme weather events significantly increase energy usage, e.g., by 36% and 11.5% on hot summer and cold winter days, respectively. As another example, we show 19.2% of transformers in the grid get overloaded during peak load periods. Finally, we evaluate the impact of incorporating varying amounts of energy storage within the distribution grid and the impact such deployments will have on the peak demand patterns seen by the grid as well as the ability to reduce overloads seen by distribution transformers during peak periods. | link |
| Assessing the Feasibility and Ethics of Economic Status Prediction using Deep Learning on Household Images | Aatif Nisar Dar, Nandana Sengupta, Chetan Arora | Indian Institute of Technology Delhi, IIT Delhi, Indian Institute of Technology Delhi | link | |
| Augmented Reality Waste Accumulation Visualizations. | Ambre Assor, Arnaud Prouzeau, Pierre Dragicevic, Martin Hachet | Inria, Université de Bordeaux, CNRS., Inria, Université de Bordeaux, CNRS., Inria, Université de Bordeaux, CNRS., Inria, Université de Bordeaux, CNRS. | The negative impact humans have on the environment is partly caused by thoughtless consumption leading to unnecessary waste. A likely contributing factor is the relative invisibility of waste: waste produced by individuals is either out of their sight or quickly taken away. Nevertheless, waste disposal systems sometimes break down, creating natural information displays of waste production that can have educational value. We take inspiration from such natural displays and introduce a class of situated visualizations we call augmented reality waste accumulation visualizations, or ARwavs, which are literal representations of waste data embedded in users’ familiar environment. We implemented examples of ARwavs and demonstrated them in feedback sessions with experts in pro-environmental behavior, and during a large tech exhibition event. We discuss general design considerations for ARwavs. Finally, we conducted a study with 20 participants suggesting that ARwavs yield stronger emotional responses than nonimmersive waste accumulation visualizations and plain numbers. | link |
| Carbon Rebellion: Empowerment using Data-Driven Narratives | Ambika Shahu, Martin Wölfer, Florian Michahelles | link | ||
| Decoding The Playbook: Multi-Modal Characterization of Coordinated Influence Operations on Indian Social Media | Saloni Dash, Tanu Mitra | University of Washington, University of Washington | link | |
| EcoSketch: promoting sustainable design through iterative environmental assessment during early-stage product development | Tejaswini Chatty, Bryton Moeller, Ioana Andrada Pantelimon, Catherine Parnell, Tahsin Khan, Lise Laurin, Jeremy Faludi, Elizabeth Murnane | Thayer School of Engineering at Dartmouth, EarthShift Global Inc. , Thayer School of Engineering at Dartmouth, Thayer School of Engineering at Dartmouth, TU Delft IDE, EarthShift Global Inc. , Thayer School of Engineering at Dartmouth, Thayer School of Engineering at Dartmouth | Sustainability has long been a topic of substantial interest the design and human-centered computing communities. With industries increasingly prioritizing climate targets, there is a growing demand for sustainable product design. This paper addresses this need through EcoSketch, a digital tool designed to democratize environmental impact assessments for product designers. Shifting typically retrospective evaluations to the early stages of product development, EcoSketch enables proactive consideration and adoption of sustainable alternatives. Unlike software tailored to environmental scientists, it minimizes the need for specialized training or extensive data inputs. We delve into the development and evaluation of EcoSketch, highlighting its unique features and usability strengths. The paper concludes by discussing design implications and proposing future research avenues to strengthen the intersection of human-computer interaction and sustainable product design, advancing progress on environmental challenges at the systems level. | link |
| ELEV-VISION: Automated Lowest Floor Elevation Estimation from Segmenting Street View Images | Yu-Hsuan Ho, Cheng-Chun Lee, Nicholas Diaz, Samuel Brody, Ali Mostafavi | Texas A&M University, Texas A&M University at Galveston, Texas A&M University, Texas A&M University at Galveston, Texas A&M University | We propose an automated lowest floor elevation (LFE) estimation algorithm based on computer vision techniques to leverage the latent information in street view images. Flood depth-damage models use a combination of LFE and flood depth for determining flood risk and extent of damage to properties. We used image segmentation for detecting door bottoms and roadside edges from Google Street View images. The characteristic of equirectangular projection with constant spacing representation of horizontal and vertical angles allows extraction of the pitch angle from the camera to the door bottom. The depth from the camera to the door bottom was obtained from the depthmap paired with the Google Street View image. LFEs were calculated from the pitch angle and the depth. The testbed for application of the proposed method is Meyerland (Harris County, Texas). The results show that the proposed method achieved mean absolute error of 0.190 m (1.18 %) in estimating LFE. The height difference between the street and the lowest floor (HDSL) was estimated to provide information for flood damage estimation. The proposed automatic LFE estimation algorithm using street view images and image segmentation provides a rapid and cost-effective method for LFE estimation compared with the surveys using total station theodolite and unmanned aerial systems. By obtaining more accurate and up-to-date LFE data using the proposed method, city planners, emergency planners and insurance companies could make a more precise estimation of flood damage. | link |
| Examining Factors Influencing Technology Integration in Indian Classrooms: A Teacher’s Perspective | Tarini Naik, Meena Shankaranarayanan, Manohar Swaminathan, Kalika Bali, Mohit Jain | Microsoft Research India, Microsoft Research India, Microsoft Research India, Microsoft Research India, Microsoft Research India | link | |
| Experiences from Running a Voice-Based Education Platform for Children and Teachers with Visual Impairments | Roshni Poddar, Tarini Naik, Manikanteswar Punnam, Kavyansh Chourasia, Pradyumna Yalandur Muralidhar, Rajeswari Pandurangan, Rajesh S Paali, Nagarathna R Bhat, Bhagyashree Biradar, Venkatesh Deshpande, Devidatta Ghosh, Sudipta Ray Chaudhuri, Dipanjan Chakraborty | International Institute of Information Technology, Vision Empower Trust, Vision Empower Trust, BITS Pilani - Hyderabad Campus, Microsoft Research India, Microsoft Research India, Vision Empower Trust, Microsoft Research India, Vision Empower Trust, Vision Empower Trust, Microsoft Research India, Vision Empower Trust, Microsoft Research India, Vision Empower Trust | link | |
| Exploring Indoor Air Quality Dynamics in Developing Nations: A Perspective from India | Prasenjit Karmakar, Swadhin Pradhan, Sandip Chakraborty | link | ||
| ForestQB: Enhancing Linked Data Exploration through Graphical and Conversational UIs Integration | Omar Mussa, Omer Rana, Benoit Goossens, Pablo Orozco Ter Wengel, Charith Perera | Cardiff University, Cardiff University, Cardiff University, Cardiff University, Cardiff University | link | |
| FrugalLight : Symmetry-Aware Cyclic Heterogeneous Intersection Control using Deep Reinforcement Learning with Model Compression, Distillation and Domain Knowledge | Sachin Chauhan, Rijurekha Sen | IIT Delhi, IIT Delhi | Developing countries need to better manage fast increasing traffic flows, owing to rapid urbanization. Else, increasing traffic congestion would increase fatalities due to reckless driving, as well as keep vehicular emissions and air pollution critically high in cities like New Delhi. State-of-the-art traffic signal control methods in developed countries, however, use expensive sensing, computation, and communication resources. How far can control algorithms go, under resource constraints, is explored through the design and evaluation of FrugalLight (FL) in this article. We also captured and processed a real traffic dataset at a busy intersection in New Delhi, India, using efficient techniques on low cost embedded devices. This dataset (https://delhi-trafficdensity-dataset.github.io) contains traffic density information at fine time granularity of one measurement every second, from all approaches of the intersection for 40 days. FrugalLight ( https://github.com/sachin-iitd/FrugalLight ) is evaluated on the collected traffic dataset from New Delhi and another open source traffic dataset from New York. FrugalLight matches the performance of state-of-the-art Convolutional Neural Network (CNN) based sensing and Deep Reinforcement Learning (DRL) based control algorithms, while utilizing resources less by an order of magnitude. We further explore improvements using a careful combination of knowledge distillation and domain knowledge based DRL model compression, with employing Model-Agnostic Meta-Learning to quickly adapt to traffic at new intersections. The collected real dataset and FrugalLight therefore opens up opportunities for resource efficient RL based intersection control design for the ML research community, where the controller should have limited carbon footprint. Such intelligent, green, intersection controllers can help reduce traffic congestion and associated vehicular emissions, even if compute and communication infrastructure is limited in low resource regions. This is a critical step toward achieving two of the United Nations Sustainable Development Goals (SDG), namely sustainable cities and communities and climate action. | link |
| Implementing e-participation in Africa: What roles can public officials play? | Paul Plantinga, Nonkululeko Dlamini, Tanja Gordon | Human Sciences Research Council, Human Sciences Research Council, Human Sciences Research Council | A key question in e-participation is what roles public officials can play to harness the benefits of emerging technologies and practices, mitigate potential harms, and, ultimately, ensure more inclusive and effective public involvement in decision making. This article presents results from a desktop analysis of e-participation projects from the African continent to highlight the diversity of public official roles and associated skills and perspectives that would be relevant to e-participation implementation. The identified roles and activities range from legal specialists developing guidelines to comply with personal data protection legislation and stakeholder managers designing models of collaboration with commons-based platforms to communications officials learning how to moderate social media conversations and technology developers exploring new ways of verifying online identity. | link |
| Learning through Annotating: Financial Knowledge Acquisition via Speech Data Generation | Advait Bhat, Nidhi Kulkarni, Safiya Husain, Aditya Yadavalli, Monali Shelar, Jivat Kaur, Vivek Seshadri | link | ||
| Mapping Opium Poppy Cultivation: Socioeconomic Insights from Satellite Imagery | Arogya Koirala, Suraj R Nair, Xiao Hui Tai | University of California Berkeley, UC Berkeley, UC Davis | Over 30 million people globally consume illicit opiates. In recent decades, Afghanistan has accounted for 70–90% of the world’s illicit supply of opium. This production provides livelihoods to millions of Afghans, while also funneling hundreds of millions of dollars to insurgent groups every year, exacerbating corruption and insecurity, and impeding development. Remote sensing and field surveys are currently used in official estimates of total poppy cultivation area. These aggregate estimates are not suited to study the local socioeconomic conditions surrounding cultivation. Few avenues exist to generate comprehensive, fine-grained data under poor security conditions, without the use of costly surveys or data collection efforts. Here, we develop and test a new unsupervised approach to mapping cultivation using only freely available satellite imagery. For districts accounting for over 90% of total cultivation, our aggregate estimates track official statistics closely (correlation coefficient of 0.76 to 0.81). We combine these predictions with other grid-level data sources, finding that areas with poppy cultivation have poorer outcomes such as infant mortality and education, compared to areas with exclusively other agriculture. Surprisingly, poppy-growing areas have better healthcare accessibility. We discuss these findings, the limitations of mapping opium poppy cultivation, and associated ethical concerns. | link |
| Net Loss: An econometric method to measure the impact of Internet shutdowns | Anirudh Tagat, Amreesh Phokeer, Hanna M. Kreitem | Internet Society International, Internet Society International, Internet Society International | The economic costs of Internet shutdowns are far-reaching and widespread, and span beyond the simple disruption to communication networks that are reliant on access to the Internet. Existing work on the impacts of the Internet shutdowns does not extensively exploit the fact that they can have adverse effects on the local economy in terms of output, employment, and investments. There is a lack of rigorous economic analysis of the impacts of shutdowns that can be more broadly applied to specific regions that account for variations in the intensity (or type) of shutdowns, as well as go beyond providing broad GDP cost estimates which may be misleading. This paper aims to bridge this gap by providing an econometric approach to estimate the impact of Internet shutdowns on GDP, employment, and foreign direct investment using panel data on 92 countries. We show that a point increase in the likelihood of an Internet shutdown was statistically significantly associated with a 15.6 percentage point reduction in the GDP per capita on average and every additional day of an Internet shutdown costs $86.58 per person on average. | link |
| On the Influence and Political Leaning of Overlap between Propaganda Communities | Anirban Sen, Soumyasis Gun, Soham De, Joyojeet Pal | Ashoka University, IIIT Hyderabad, University of Michigan, Microsoft Research India | Social media offers increasingly diverse mechanisms for the distribution of motivated information, with multiple propaganda communities exhibiting overlaps with respect to user, content, and network characteristics. This has particularly been an issue in the Global South, where recent work has shown various forms of strife related to polarizing speech online. It has also emerged that propagandist information, including fringe positions on issues, can find its way into the mainstream when sufficiently reinforced in tone and frequency, some of which often requires sophisticated organizing and information manipulation. In this study, we analyze the overlap between three events with varying degrees of propagandist messaging by analyzing the content and network characteristics of users leading to overlap between their users and discourse. We find that a significant fraction of users leading to overlap between the three event communities are influential in information spread across the three event networks, and political leaning is one of the factors that helps explain what brings the communities together. Our work sheds light on the importance of network characteristics of users, which can prove to be instrumental in establishing the role of political leaning on overlap between multiple propaganda communities. | link |
| RELand: Risk Estimation of Landmines via Interpretable Invariant Risk Minimization | Mateo Dulce Rubio, Siqi Zeng, Qi Wang, Didier Alvarado, Francisco Moreno Rivera, Hoda Heidari, Fei Fang | UNMAS, Colombian Campaign to Ban Landmines, Carnegie Mellon University, Carnegie Mellon University, Carnegie Mellon University, Carnegie Mellon University, Carnegie Mellon University | Landmines remain a threat to war-affected communities for years after conflicts have ended, partly due to the laborious nature of demining tasks. Humanitarian demining operations begin by collecting relevant information from the sites to be cleared, which is then analyzed by human experts to determine the potential risk of remaining landmines. In this paper, we propose RELand system to support these tasks, which consists of three major components. We (1) provide general feature engineering and label assigning guidelines to enhance datasets for landmine risk modeling, which are widely applicable to global demining routines, (2) formulate landmine presence as a classification problem and design a novel interpretable model based on sparse feature masking and invariant risk minimization, and run extensive evaluation under proper protocols that resemble real-world demining operations to show a significant improvement over the state-of-the-art, and (3) build an interactive web interface to suggest priority areas for demining organizations. We are currently collaborating with a humanitarian demining NGO in Colombia that is using our system as part of their field operations in two areas recently prioritized for demining. The resulting dataset and developed code can be found here. | link |
| RFDrive: Tagged Human-Vehicle Interaction for All | Wei Sun, Kannan Srinivasan | The Ohio State University, The Ohio State University | Human–vehicle interaction is an important factor for safe driving. The driver needs to interact with the in-vehicle steering wheel and infotainment system properly during driving. Specifically, driving guidelines require the driver to hold the steering wheel at the 3 o’clock and 9 o’clock positions. Moreover, the in-vehicle infotainment system should be more adaptive for the driver and front-seat passenger during driving (i.e., the in-vehicle infotainment system should be part and even fully disabled for the driver, whereas the front-seat passenger should be able to enjoy the full in-vehicle infotainment system). However, affordable vehicles are usually designed to achieve basic driving functions without considering safe human–vehicle interactions, which require an add-on, affordable, and ready-to-use human–vehicle interaction monitoring system. In this article, we present RFDrive, a system that can simultaneously locate the driver’s hand positions on the steering wheel and automate in-vehicle infotainment system touch discrimination for safe driving using commodity passive RFID tags. Since these commodity passive RFID tags are low cost (i.e., around 5 cents per tag), battery free, and are small, like a sticker, our design will enable not only safe driving but is also low cost, which can lead to sustainable solutions. To do so, we attach RFID tags on the steering wheel for the driver’s hand position location and attach RFID tags on the roof of the vehicle’s interior for in-vehicle infotainment system touch discrimination (i.e., differentiating the driver’s infotainment system touch and front-seat passenger’s infotainment system touch). However, the wheel steering will distort the wireless channel-based driver’s hand position location on the steering wheel. Thus, we propose a novel tag ID-based algorithm to locate the driver’s hand position on the steering wheel by harnessing the human body as part of the RFID tag’s antenna. Since the in-vehicle infotainment system touch from the driver or front-seat passenger will affect different RFID tags attached to the roof of the vehicle’s interior, we propose to use the differential amplitude of backscattered signals from all the tags to discriminate in-vehicle infotainment system touch sources. Our experiments show that RFDrive can achieve the average accuracy of 0.98 and 0.98 for in-vehicle touch source discrimination and driver’s hand position location, respectively. | link |
| Roles of Technology for Risk Communication and Community Engagement in Bangladesh during COVID-19 Pandemic | Anik Sinha, Nova Ahmed, Md. Ahmed, Ifti Azad Abeer, Rahat Rony, Anik Saha, Syeda Khan, Shajnush Amir, Shabana Khan | North South University, North South University, North South University, Indian Research Academy, North South University, North South University, Cardiff University, North South University, North South University | The COVID-19 pandemic required clear communication of risk and community engagement. A gap is noted in scholarly studies portraying strong community engagement for risk handling, particularly in resource-constrained regions in the HCI community. This study covers community engagement and its use of technology during COVID-19 through a qualitative study of Bangladesh. The study looks at marginalized communities who have struggled through the pandemic yet handled the difficult time through their effective problem solving, working together as a community when there was not enough support from authorities. It is a qualitative study during the pandemic consisting of nine communities, including 58 participants (N = 58, Female = 33, Male = 23, Transgender = 2) across four divisions of Bangladesh covering urban, semi-urban, and rural regions. The study uncovers the challenges and close community structures. It also shows the enhanced and increased positive role of technology during the pandemic while also pointing out that a few communities were digitally disconnected and could benefit from digital connectivity in the future through increased awareness and support. | link |
| Speaking in Terms of Money: Financial Knowledge Acquisition via Speech Data Generation | Advait Bhat, Nidhi Kulkarni, Safiya Husain, Aditya Yadavalli, Jivat Neet Kaur, Anurag Shukla, Monali Shelar, Vivek Seshadri | Karya, Microsoft Research India, Karya, University of California Berkeley, Karya, Karya, Karya, Karya | link | |
| Sustainable innovation: A framework for sustainable community innovation center | Mizan Rehman, Michael Best | Georgia Institute of Technology, Georgia Institute of Technology | link | |
| The Devil You Know": Barriers and Opportunities for Co-Designing Microclimate Sensors, A Case Study of Manoomin | Eric Greenlee, Blaine Rothrock, Hyeonwook Kim, Ellen Zegura, Josiah Hester | link | ||
| Understanding Driving Stress in Urban Bangladesh: An Exploratory Study, Wearable Development and Experiment | Anik Sinha, Nova Ahmed, Md. Ahmed, Ifti Azad Abeer, Rahat Rony, Anik Saha, Syeda Khan, Shajnush Amir, Shabana Kha | Birmingham City University - City Centre Campus, University of Virginia, North South University, Cardiff University | Driving stress significantly impacts driving behavior primarily from roadside factors, where driving is more challenging in developing countries (i.e., Bangladesh) for unique cultural and infrastructural setups. We conduct an exploratory study (Qualitative n = 26, and Subjective Feedback n = 80) and a correlational analysis involving professional and private car drivers in urban Bangladesh. The study reveals drivers' demography and driving stress factors on the road. These findings motivate us to identify driving stress from physiological factors by developing a low-cost wearable, Stress Wear. This can detect stress from varying Heart Rates, validated by expensive commercial wearables. Between subject experiments on drivers (total n = 14 in two phases) with wearables, we also found that road factors are responsible for driving stress. Therefore, the developed system is helpful for these drivers to self-sense their stress. | link |
| Understanding Teens Online Behavior and Vulnerabilities: Recommending Support Interventions on Teens Online Safety in Bangladesh | Rahat Rony, Nova Ahmed | link | ||
| Understanding the Longitudinal Impact of a Chatbot to Facilitate a Virtual Community of Practice for Teachers in Rural Côte d’Ivoire | Vikram Kamath Cannanure, Tricia Ngoon, Sharon Wolf, Kaja Jasińska, Tim Brown, Amy Ogan | Carnegie Mellon University, University of Toronto, Carnegie Mellon University, Carnegie Mellon University, Carnegie Mellon University, University of Pennsylvania | link | |
| Understanding Urban Women’s Interaction with Domestic Technologies in Malawi: Advancing Feminist Theories in HCI | George Hope Chidziwisano, Adam Cummings, Devendra Potnis, Maureen Jalakasi | The University of Tennessee Knoxville College of Communication and Information, The University of Tennessee Knoxville, The University of Tennessee Knoxville College of Communication and Information, Independent Researcher | In sub-Saharan Africa, women are caretakers of their homes. Despite the gendered nature of technology use, human-computer interaction research has rarely focused on women's interaction with domestic technologies in this context. We explore how urban women in Malawi use domestic technologies to support activities in their homes. We conducted semi-structured interviews, observations, and focus group discussions with 33 married women living with their husbands and other family members. Our findings suggest that women are the primary users of utilitarian domestic technologies; however, their spouses have control over how they use these technologies. Further, we found that purpose and time influence women's decision-making process for selecting domestic technologies to use, especially cooking appliances. The structure of some Malawian homes—which consist of a combination of modern and traditional structures—also influences women's decision-making process. Our findings contribute to feminist theories in human-computer interaction through the application of ecology, pluralism, and self-disclosure aspects. | link |
| Unveiling Social Anxiety: Analyzing Acoustic and Linguistic Traits in Impromptu Speech within a Controlled Study | Nilesh Kumar Sahu, Manjeet Yadav, Haroon Lone | Indian Institute of Science Education and Research Bhopal, Indian Institute of Science Education and Research Bhopal, IISER Bhopal | Early detection and treatment of Social Anxiety Disorder (SAD) is crucial. However, current diagnostic methods have several drawbacks, including being time-consuming for clinical interviews, susceptible to emotional bias for self-reports, and inconclusive for physiological measures. Our research focuses on a digital approach using acoustic and linguistic features extracted from participants’ “speech” for diagnosing SAD. Our methodology involves identifying correlations between extracted features and SAD severity, selecting the effective features, and comparing classical machine learning and deep learning methods for predicting SAD. Our results demonstrate that both acoustic and linguistic features outperform deep learning approaches when considered individually. Logistic Regression proves effective for acoustic features, while Random Forest excels with linguistic features, achieving the highest accuracy of 85.71%. Our findings pave the way for non-intrusive SAD diagnosing that can be used conveniently anywhere, facilitating early detection. | link |
| Is Model Accuracy Enough? A Field Evaluation Of A Machine Learning Model To Catch Bogus Firms | Aprajit Mahajan, Shekhar Mittal, Ofir Reich, Taha Barwahwala | University of California Berkeley, Amazon.com Inc, Independent Data Scientist, Columbia University | link | |
| Wearable Technology Insights: Unveiling Physiological Responses During Three Different Socially Anxious Activities | Nilesh Kumar Snehil Gupta, Haroon Lone | Indian Institute of Science Education and Research Bhopal, IISER Bhopal, AIIMS Bhopal | Wearable technology holds promise for monitoring and managing Social Anxiety Disorder (SAD), yet the absence of clear biomarkers specific to SAD hampers its effectiveness. This paper explores this issue by presenting a study investigating variances in heart rate, heart rate variability, and skin conductance between socially anxious and non-anxious individuals. One hundred eleven non-clinical student participants participated in groups of three in three anxiety-provoking activities (i.e., speech, group discussion, and interview) in a controlled lab-based study. During the study, electrocardiogram (ECG) and electrodermal activity (EDA) signals were captured via on-body electrodes. During data analysis, participants were divided into four groups based on their self-reported anxiety level (“None”, “mild”, “moderate”, and “severe”). Between-group analysis shows that discriminating ECG features (i.e., HR and MeanNN) could identify anxious individuals during anxiety-provoking activities, while EDA could not. Moreover, the discriminating ECG features improved the classification accuracy of anxious and non-anxious individuals in different machine-learning techniques. The findings need to be further scrutinized in real-world settings for the generalizability of the results. | link |
| What’s Up On The Roof: Tracking Cool Roofs in India with Satellite Imaging | Varchita Lalwani, Anupam Sobti, Vishal Garg | link | ||
| Zero-configuration Alarms: Towards Reducing Distracting Smartphone Interactions while Driving | Sugandh Pargal, Neha Dalmia, Harsh Borse, Bivas Mitra, Sandip Chakraborty | Indian Institute of Technology Kharagpur, Indian Institute of Technology Kharagpur, Indian Institute of Technology Kharagpur, Indian Institute of Technology Kharagpur, Indian Institute of Technology Kharagpur | link |
Short Papers
| Paper Title | Authors | Affiliations | Abstract | Video |
|---|---|---|---|---|
| Towards Deep Learning for Predicting Microbial Fuel Cell Energy Output | Adam Hess-Dunlop, Harshitha Kakani, Colleen Josephson | UC Santa Cruz, UC Santa Cruz | Soil microbial fuel cells (SMFCs) are an emerging technology which offer clean and renewable energy in environments where more traditional power sources, such as chemical batteries or solar, are not suitable. With further development, SMFCs show great promise for use in robust and affordable outdoor sensor networks, particularly for farmers. One of the greatest challenges in the development of this technology is understanding and predicting the fluctuations of SMFC energy generation, as the electro-generative process is not yet fully understood. Very little work currently exists attempting to model and predict the relationship between soil conditions and SMFC energy generation, and we are the first to use machine learning to do so. In this paper, we train Long Short Term Memory (LSTM) models to predict the future energy generation of SMFCs across timescales ranging from 3 minutes to 1 hour, with results ranging from 2.33% to 5.71% MAPE for median voltage prediction. For each timescale, we use quantile regression to obtain point estimates and to establish bounds on the uncertainty of these estimates. When comparing the median predicted vs. actual values for the total energy generated during the testing period, the magnitude of prediction errors ranged from 2.29% to 16.05%. To demonstrate the real-world utility of this research, we also simulate how the models could be used in an automated environment where SMFC-powered devices shut down and activate intermittently to preserve charge, with promising initial results. Our deep learning-based prediction and simulation framework would allow a fully automated SMFCpowered device to achieve a median 100+% increase in successful operations, compared to a naive model that schedules operations based on the average voltage generated in the past. | link |
| Navigating Truth in the Sea of Content: Exploring Influential Factors Shaping User Perceptions of Trustworthiness in YouTube Content | Aditto Baidya Alok, Fardin Huq, Shamsil Arafin Ullah, Riya Ghosh, Jannatun Noor | Brac University Dhaka, Brac University Dhaka, Brac University Dhaka, Brac University Dhaka, Brac University Dhaka | In today's digital age, YouTube stands as a vital hub for information across various domains, from entertainment to education. However, the persistent challenge of misinformation threatens its integrity. This study explores the complex dynamics of trust and legitimacy within YouTube's content ecosystem, uncovering factors shaping user perceptions. We highlight the crucial roles of creator reputation, content presentation, and social validation in building trust while emphasizing the need to address misleading content effectively. Employing a mixed-methods approach, we conducted surveys (n=71) and interviews (n-19) to gain insights into user experiences comprehensively. By addressing gaps in current research, our study contributes to the HCI and ICT4D communities, illuminating critical issues in the digital realm. As YouTube continues to influence our online landscape, grasping trust and misinformation becomes essential for fostering an informed and trustworthy online community. | link |
| EvolveUI: User Interfaces that Evolve with User Proficiency | Ali Saif, Mohammad Taha Zakir, Agha Ali Raza, Mustafa Naseem | Aitchison, LUMS - Lahore-Pakistan, LUMS - Lahore-Pakistan, University of Michigan | Recent studies have highlighted the challenges low-literacy users face with complex user interfaces, often preventing them from utilizing essential smartphone applications for an improved quality of life. This paper introduces the EvolveUI design approach that diverges from conventional interface design by evolving in complexity alongside a user’s growing proficiency. Initially presenting a single navigation point to simplify interaction, EvolveUI systematically expands, introducing more features and navigation points as users become more adept at interacting with the interface. We build upon previous adaptive user interface research by uniquely focusing on expanding functionality based on user proficiency, offering a tailored experience that aligns with individual learning curves. By conceptualizing the interface as a dynamically expanding hierarchy, starting as a minimalist “tree” and unfolding into a more complex structure, EvolveUI facilitates a more accessible and engaging user experience. Our study compares this evolving interface approach with conventional designs through usability tests on a mobile health application, demonstrating EvolveUI’s potential to enhance technology accessibility for low-literacy users and suggesting new directions for inclusive design practices. | link |
| Simulation-based Analysis of Car-sharing Electrification in Schleswig-Holstein, Germany | Aliyu Tanko Ali, Andreas Schuldei, Martin Sachenbacher, Martin Leucker, Aliyu Tanko Ali | University of Luebeck, University of Luebeck, University of Luebeck, University of Luebeck, University of Luebeck | We present a study to assess the feasibility and implications of replacing internal combustion engine vehicles with battery-powered electric vehicles (EVs) in a car-sharing fleet. For the analysis, we used operational data from a local car-sharing company, which encompasses various aspects such as trip distance, start and duration, vehicle type, and pickup and return locations. To evaluate the impact of transitioning the entire fleet to EVs, we used EV and charger models to simulate the battery-powered trips and also the necessary post-trip recharging. Both could affect the service quality of car sharing services, as the requested trip distance might not be covered by an electric vehicle due to range or charging time limitations. Specifically, in our simulation-based analysis, we identified chains of consecutive bookings as a critical factor for car-sharing electrification. Furthermore, to assess the potential impact of electrification on the energy grid, we used data about the local grid load and its composition to relate it to the predicted vehicle charging times. | link |
| Demo: A Low-Cost Honeynet Infrastructure For Smishing Data Collection | Bernard Lamptey, Assane Gueye, Mohammed Seidu, Edith Luhanga, Karen Sowon | Upanzi Network / CyLab-Africa, Carnegie Mellon University - Africa, Upanzi Network / CyLab-Africa, Carnegie Mellon University - Africa, Upanzi Network / CyLab-Africa | Research on mobile money smishing is hindered, especially in the African context, as there is a lack of data. The absence of datasets and the fact that Mobile Network Operators don't maintain such data pose a significant challenge. Additionally, the absence of a message collection infrastructure further complicates the data acquisition process. In response to this challenge, we developed a scalable and cost-effective honeynet infrastructure tailored for the efficient collection of organic Short Message Service (SMS) messages. The innovative approach involves harnessing the capabilities of Raspberry Pi units, USB multipliers, SIM cards from MNOs and GSM modems to create a scalable and adaptable solution. This aims to enhance smishing data collection, facilitating more efficient research into mobile money smishing. | link |
| Bridging the Gap: Exploring the Factors Influencing Women's Adoption of Mobile Financial Services (MFS) in Rural Areas of Bangladesh | Bishal Deb Roy, Sumaia Arefin Ritu, Anika Priodorshinee Mrittika, Jannatun Noor | Brac University, Brac University, Brac University, Brac University | In regions where traditional gender norms and limited access to resources have historically posed significant challenges, mobile financial services (MFS) have emerged as a potent instrument for enhancing the economic and social empowerment of women. This study delves into the impact of sustainable development on rural Bangladeshi women, with a particular focus on their utilization of MFS. Through qualitative interviews conducted with 39 participants, including 35 rural women and 4 MFS agents, our research sheds light on the broader societal implications stemming from women's increasing involvement in economic activities. It also highlights advancements in women's rights and their growing levels of influence. Nevertheless, the study recognizes persistent obstacles such as unequal pay, limited access to education, and cultural biases that continue to impede women's full economic participation, particularly in rural settings. Ultimately, our study underscores the significance of financial stability and savings for both families and society at large. | link |
| Fluxbot: The Next Generation - Design and Validation of a Wireless, Open-Source Mechatronic CO2 Flux Sensing Chamber | Connor Pan, Vatsal Patel, Jonathan Gewirtzman, Ian Richardson, Ravish Dubey, Kelly Caylor, Aaron Dollar, Elizabeth Forbes | Yale University, Yale University, Yale School of the Environment, Yale University, Yale School of the Environment, University of California Santa Barbara, Yale University, Yale School of the Environment | Precision gas analyzers are widely used in ecological research for manual measurement of soil carbon flux, a key metric used in the study of climate change. We present a generational update to the first low-cost, autonomous, closed-chamber style soil CO2 flux sensors (Fluxbots). Fluxbot 2.0 is the first such low-cost autonomous flux chamber capable of real-time wireless data transmission, which enables ecologists conducting \textit{in situ} soil carbon flux surveys to set up their own wireless sensor arrays, reporting carbon flux data in real time at a very high level of temporal resolution. The system's low cost (less than 500 USD per unit) and long-range cellular data transmission capabilities also allow for greatly improved spatial resolution. Additionally, the updated system consumes significantly less power, resulting in the ability to be deployed for longer than 10$\times$ the battery lifetime of the original version on a single charge. | link |
| Towards Improved Sustainability in The Textile Lifecycle with Deep Learning | Danika Gupta, Atul Dubey | The Harker School, AIClub Research Institute | The garment industry is one of the world’s largest carbon and waste polluters, expected to produce 150 billion garments per year in the next decade while recycling about 1%. The lack of reliable fabric identification limits scalable recycling. Without traceability, governments cannot enforce circular economy legislation. We propose solutions to both issues that leverage low-cost hardware and deep learning. Using microscope fabric images and Convolutional Neural Networks, we demonstrate classification accuracy of over 90% for 14 fabric classes. By marking fabrics with a UV-visible code readable via YOLOv8 object detection, we demonstrate a mAP50 of over 0.98, retaining up to 0.93 after wash cycles while remaining resilient to fabric-unique challenges such as creasing. These methods can be implemented worldwide at low cost to enable fabric identification and traceability for a textile circular economy. We demonstrate a prototype reader application and discuss pathways to impact. We also provide three new datasets for future research. | link |
| Design Opportunities to Facilitate Tangible Play and Promote Healthy Nutrition in Low-resource Healthcare Settings in Peru | Deysi Ortega, Rosario Bartolini, Rossina Pareja, Katarzyna Stawarz, Hilary Creed-Kanashiro, Michelle Holdsworth, Emily Rousham, Nervo Verdezoto Dias | Cardiff University, Instituto de Investigación Nutricional, Instituto de Investigación Nutricional, Cardiff University, Instituto de Investigación Nutricional, Research and Development Institute IRD, Montpellier Loughborough University, Cardiff University | Complementary feeding is crucial to promote healthy nutrition in infant and young children (IYC) and prevent malnutrition. Mothers, families, and healthcare professionals (HCPs) play a key role in helping IYC develop healthy eating habits. However, the limited access to adequate nutritional information and health services impact children's nutrition, especially in low-resource settings. Technology opens up opportunities to address these challenges and potentially improve IYC feeding practices. Taking a co-design approach, we conducted low-fidelity prototyping workshops with caregivers and HCPs to explore the potential of tangible interfaces to facilitate play and promote healthy nutrition for IYC in two low-resource healthcare settings in Peru. Participants envisioned diverse tangible objects and interactions that could augment the space of the healthcare centres to encourage play, promote healthy nutrition and dietary diversity. Based on our findings, we outline design opportunities to facilitate tangible play, shared playful experiences, and promote healthy nutrition in low-resource healthcare settings. | link |
| Towards Safer Roads: Deep Learning for Rash Driving Detection using Smartphone Sensors Data | Durgesh Mishra, Manoj Gulati, Haroon R. Lone | DRDO Young Scientist Laboratory, National University of Singapore Indian Institute of Science Education and Research Bhopal | Rash driving detection is vital to prevent accidents and improve public safety. Existing rash driving solutions using hand-crafted features have several limitations. We propose a simple yet efficient two-step process to overcome the limitations of the existing works by leveraging smartphone sensor (accelerometer and gyroscope) data. The first step filters out normal driving data and retains only the abnormal driving data with the proposed Adaptive Time Window (ATW) algorithm. This not only enhances the accuracy of detection but also reduces computation time, making our solution more efficient. Importantly, the proposed ATW algorithm completely eliminates window overlap redundancy and edge effects in the system. The second step classifies abnormal driving patterns with the proposed 1D CNN model. Our results demonstrate that the proposed solution is highly accurate and has a weighted accuracy of 97.14\%. Additionally, as part of this research, we have curated and released a labeled Indian dataset comprising five distinct rash driving patterns: Lane Weaving, Lane Swerving, Hard Braking, Hard Cornering, and Quick U-turn. This dataset can be valuable for further studies and aid in developing multimodal rash driving detection systems. | link |
| AAVE Corpus Generation and Low-Resource Dialect Machine Translation | Eric Graves, Shreyas Aswar, Rujuta Desai, Srilekha Nampelli, Sunandan Chakraborty, Ted Hall | Indiana University, Indiana University, Indiana University, Indiana University, Indiana University, Indiana University | African American Vernacular English (AAVE) is a dialect of the English language spoken in the United States by members of the Black community. The stark differences between AAVE and Standard American English (SAE), as well as a historically negative stigma towards its use, have contributed to an academic performance gap between Black students and their non-Black counterparts. This research works to generate educational resources similar to what is available in English Second Language (ESL) classrooms. Exposure to these resources has been shown to both improve the negative stigma towards the use of AAVE as well as facilitate code-switching between AAVE and SAE. The resources to be generated in this research are a parallel corpora for AAVE and SAE using both professionally translated text and AI-generated text, and a Neural Machine Translation (NMT) model to translate SAE into AAVE using novel network architectures used language to language translation including LSTM, Bi-LSTM, Attention, and Transformer network components. The parallel corpora will be quantitatively reviewed and validated before using tested dialect translation model methods. Methodology will additionally be focused on low-resource machine translation due to the lack of large corpora containing AAVE. Both professional translators and large language model, ChatGPT, will be used to create parallel corpora containing AAVE and SAE. This short paper details the preliminary results of the assessment of these generated corpora as well as the accuracy of dialect machine translation models trained on them. | link |
| CR-Cross: Cross Domain Coral Recognitions with Reject Options For Coral Conservation | Hongyong Han, Wei Wang, Gaowei Zhang, Mingjie Li, Yi Wang | Beijing University of Posts and Telecommunications, Beijing University of Posts and Telecommunications, Beijing University of Posts and Telecommunications, South China Sea Institute of Planning and Environmental Research - State Oceanic Administration, Beijing University of Posts and Telecommunications | Although coral reefs are special and vital marine ecosystems, massive coral degradation began to occur due to the increase in global temperatures and the intensification of human industrial activities. Coral reef protection requires accurate coral recognition because it is the foundation for learning the distribution, disease, and growth of coral reefs, hereby informing the proper ways for further action. Recently, CNNs have been applied in automated coral image classification. These classifier models, however, are difficult to be generalized from the trained coral images in a marine region (source domain) to the coral images in a different marine region (target domain) since the corals have significant within-species morphological variability among the different geographic location domains. In this paper, a novel coral recognition algorithm is introduced via knowledge transfer across domains and its advantages lie in the following aspects. (1) It simultaneously transfers corals’ texture and structure features across domains thus providing useful knowledge to assist the coral recognition tasks in the target marine domain. (2) To overcome the difficulty that the confusing coral images (e.g., bleached corals) are prone to be misclassified and transfer useless or even negative information, our algorithm is equipped with the reject option for the confusing corals while adapting. These corals can be sent to an expert or a more expensive but accurate system, resulting in strengthened transferability and reliability. Furthermore, we develop a new cross-domain coral image dataset to enhance coral research. Without the label information from the target marine region, our method significantly reduces the distribution gap and domain shift among the different marine regions. In addition, CR-Cross goes a step further in tackling the challenges of missing coral data, maximizing the utilization of available coral datasets, and enhancing the reusability of both coral data and coral recognition models. A series of empirical studies show that our method remarkably outperforms a broad range of baselines. | link |
| AI-Driven Healthcare Delivery in Pakistan: A Framework for Systemic Improvement | Imama Zahoor, Shiza Ihtsham, Umar Ramzan, Agha Ali Raza, Basmaa Ali | Lahore University of Management Sciences, Lahore University of Management Sciences, Lahore University of Management Sciences, Lahore University of Management Sciences, Lahore University of Management Sciences | In Low- and Middle-Income Countries (LMICs), poor health outcomes come from a high burden of disease, a shortage of healthcare professionals, and inefficient health information exchange leading to substantial economic losses. In this paper, we highlight critical gaps in healthcare delivery in Pakistan and propose solutions to improve patient outcomes in resource-constrained environments. We have built Darcheeni, an AI-driven healthcare framework that leverages artificial intelligence to assist and supplement physicians, streamline healthcare processes, and prioritize patient-centered care. Darcheeni analyzes doctor-patient interactions in real-time, integrates lab and imaging data, generates and distributes care plans customized to the patient’s needs, and sends them directly to patients' smartphones. We also discuss the challenges and limitations associated with sustainable AI integration by centering our learnings from the pilot deployment of Darcheeni. By focusing on Pakistan as a case study, this work offers practical insights and strategies for deploying AI-driven technologies sustainably in similar resource-constrained environments and contributes to the broader discourse on the role of AI in global health improvement. | link |
| Interpretable Checklist for Delirium Detection | Joel Forman, Ramya Srinivasan, Kanji Uchino, Gen Shinozaki | University of California Berkeley, Fujitsu Research of America, Fujitsu Research of America, Stanford University | Delirium is a syndrome characterized by acute and fluctuating change in attention, awareness, and cognition. Common in older adults, especially those with underlying medical conditions, delirium is associated with higher mortality rates, longer hospital stays, and increased healthcare costs. Early identification and management of delirium therefore becomes essential in order to prevent adverse outcomes, improve patient health, and reduce healthcare costs. As multiple predisposing (e.g., neurological disorders) and precipitating factors (e.g., medications) can be involved in the aetiology of delirium, detecting the syndrome early on can be challenging. In this work, we present an interpretable multimodal checklist that can aid clinicians in delirium detection. Specifically, we leverage causal decision trees to extract most relevant features for delirium detection which are then used in learning the predictive checklist. Experiments demonstrate the efficacy of the approach over existing methods in terms of both detection accuracy and interpretability. | link |
| Enhancing Wireless Connectivity in Skip Zones via Energy-Efficient Reconfigurable Intelligent Surface | Khagendra Joshi, Deepak Kumar Sahoo, Debidas Kundu, Vivek Ashok Bohara, Amalendu Patnaik | Indraprastha Institute of Information Technology - Delhi, Indian Institute of Technology - Roorkee, Indraprastha Institute of Information Technology - Delhi, Indraprastha Institute of Information Technology - Delhi, Indian Institute of Technology - Roorkee | The efficacy of a reconfigurable intelligent surface (RIS)-aided network for enhanced connectivity in skip zones is demonstrated through real-time video streaming. The demonstration is carried out with the help of National Instruments universal software radio peripheral (NI-USRP) devices integrated with an RIS prototype. The RIS prototype is designed and fabricated using a 16×10 metasurface operating at 5.3 GHz carrier frequency. Utilizing LabVIEW’s long-term evolution (LTE) application framework module, good connectivity between the transmitter and receiver in an otherwise skip zone is exhibited. Various modulation and coding schemes have been applied to the streamed data to observe the throughput, SINR, and constellation diagrams with respect to different positions of the receiver in the non-line of sight (NLOS) skip zone. The demonstration ratifies the potential of the RIS system in practical applications related to future wireless communications. | link |
| Nobody Can See Us: An Overview of Online Dating Site Experiences | Nova Ahmed, Monisha Dey, Abdul Wohab | North South University - Design Inclusion and Access Lab, North South University, North South University | Although Bangladesh is a country that values matchmaking and matchmakers greatly, online dating is a relatively new phenomenon that became popular only recently mostly among the young population. While anecdotal reports suggest a considerable number of individuals utilize online dating platforms in Bangladesh, a comprehensive investigation of their experiences and the potential impact on their well-being has yet to be conducted. Given the growing prevalence of online dating apps among young adults in Bangladesh, the present study aims to conduct in-depth interviews with a sample of 33 participants between the ages of 18 and 25 who actively use these platforms. The sample comprises 14 male and 19 female participants, each of whom has experience using online dating apps. By gaining insights into the experiences of young adult users of dating apps in Bangladesh and examining the effects of such platforms on their physical and mental well-being, the findings of this study highlight three areas: a) youth’s intention to fight existing social norms, b) gender experiences relating to abuse and harassment in online dating platforms, c) alternative usage of online dating application space, particularly during the Covid-19 pandemic period. This study also seeks to raise awareness of online usage patterns among young adults in Bangladesh and identify potential interventions that may address any negative outcomes associated with excessive online activity. | link |
| “We are blessed to live in the countryside”: Unpacking Rural and Small-Town Older Adults’ Resilient Nature in Times of the COVID-19 Pandemic | Novia Nurain, Chia-Fang Chung, Clara Caldeira, Kay Connelly | Indiana University, University of California Santa Cruz, Google - São Paulo-Brazil, Indiana University | The COVID-19 pandemic has threatened disproportionately rural older adults’ health and well-being as they suffer from unique social exclusion due to a lack of services, such as transportation, communication infrastructure, healthcare, and social services. Although older adults can uniquely cope with pandemic adversity compared to younger adults, less attention has been directed to investigating the coping and resilience of rural older adults. To understand how diverse coping strategies impact the resilience of rural older adults, we conducted interviews with 26 rural and small-town older adults. Older adult participants adopted different coping strategies, such as following protective measures, keeping themselves busy, providing and receiving social support, and having a positive mindset. They experienced positive changes, such as increased interpersonal connectivity. Older adults’ individual-level coping processes are influenced by their social and physical environments. We explore design opportunities to support older adults’ resilient practices and harness their skills to facilitate community | link |
| Demo: SensiTrain: A Crowd Supported Platform to Understand Context and Improve Sensitivity in Online Communication | Pushwitha Krishnappa, Tahmid Ahmed, Otabek Abduraufov, Tathagata Mukherjee, Xiaoti Fan, Sriram Chellappan | The University of Alabama in Huntsville, University of South Florida, University of South Florida, The University of Alabama in Huntsville, The University of Alabama in Huntsville, University of South Florida | In this work we present SensiTrain - a data collection system designed with the goal of curating a dataset for understanding how differences in cultural backgrounds, sexualmorientation, gender, race and national origin affect the way one perceives statements made on social media as being either benign or hurtful and sometimes even hateful and aggressive. SensiTrain displays social media posts to users and asks them to categorize the posts as being either benign or hurtful while providing a reason for such classification. We plan to use the data thus collected to build a public dataset repository and use the same to train a baseline system for identifying potentially hurtful statements before they are posted on social media platforms. The resulting system would be able to explain why a given statement could be perceived as hurtful by one or more groups thus making the inference more trustworthy to the users of the system. We hope that through this endeavor we will be able to mitigate unintentional harm caused due to lack of understanding of different cultures and backgrounds, thus making the world a kinder place. | link |
| Assessing the impact of farm ponds on agricultural productivity in Northern India | Ramneek Kaur, Kshitiz Bansal, Devang Garg, Ramita Sardana, Saketh Vishnubhatla, Sanjali Agrawal, Shruti Kumari, Parag Singla, Aaditeshwar Seth | Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi | Government welfare schemes such as the Mahatma Gandhi National Rural Employment Guarantee Act (MGNREGA) fund creation of assets for natural resource management in the rural villages of India to support farmers for their agricultural and livelihoods-based needs. With most agriculture in India being rainfed, structures such as farm ponds, checkdams, trenches and bunds play a crucial role in providing critical lifesaving irrigation to the crops in cases of dry spells and droughts. In this study, we investigate the impact of farm ponds built under the MGNREGA scheme in Northern India as a source of protective irrigation in their immediate neighbourhood. Our assessment of the impact of farm ponds is threefold: (i) we study their impact on agricultural productivity, (ii) we investigate if their impact is significant during drought years, (iii) we study if farms ponds are able to narrow the gap in productivity between drought and non-drought years. A causal analysis framework was designed for the investigation and the difference-in-differences approach was employed to compute the treatment effect. Remote sensing data was processed to compute changes in vegetation indices around the treated and control locations between two time periods. Our results indicate that farm ponds have been instrumental in improving the agricultural productivity during the monsoon season in general. The impact during the monsoon season in drought years, although much lower in magnitude, is also positive. Furthermore, farm ponds have also facilitated in narrowing the productivity gap between drought and non-drought years during the monsoon season. The impact during the post-monsoon season was found to be lower than that of the monsoon season, and the impact in summers was found to be the least. | link |
| Designing A Sustainable Marine Debris Clean-up Framework without Human Labels | Raymond Wang, Nicholas R. Record, D. Whitney King, Tahiya Chowdhury | Colby College, Bigelow Laboratory for Ocean Sciences, Colby College, Colby College | Marine debris poses a significant ecological threat to birds, fish, and other animal life. Traditional methods for assessing debris accumulation involve labor-intensive and costly manual surveys. This study introduces a framework that utilizes aerial imagery captured by drones to conduct remote trash surveys. Leveraging computer vision techniques, our approach detects, classifies, and maps marine debris distributions. The framework uses Grounding DINO, a transformer-based zero-shot object detector, and CLIP, a vision-language model for zero-shot object classification, enabling the detection and classification of debris objects based on material type without the need for training labels. To mitigate over-counting due to different views of the same object, Scale-Invariant Feature Transform (SIFT) is employed for duplicate matching using local object features. Additionally, we have developed a user-friendly web application that facilitates end-to-end analysis of drone images, including object detection, classification, and visualization on a map to support cleanup efforts. Our method achieves competitive performance in detection (0.69 mean IoU) and classification (0.74 F1 score) across seven debris object classes without labeled data, comparable to state-of-the-art supervised methods. This framework has the potential to streamline automated trash sampling surveys, fostering efficient and sustainable community-led cleanup initiatives. | link |
| Quantifying the role of maternal recall in estimates of routine immunisation rates in India: a large-scale sub-national Bayesian modelling study | Ritika Singh, Sumeet Agarwal, Alex De Figueiredo, Misha Mishra, Devyani Agarwal | Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, London School of Hygiene & Tropical Medicine, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi | Childhood vaccinations are vital for protecting children from preventable disease and improving overall public health. However, generating reliable estimates of routine immunisation uptake, essential for appropriate policy planning and resource allocation is complicated by various data challenges. A specific challenge in estimating coverage with household surveys such as the National Family Health Survey is that the presence of vaccination is obtained via maternal recall if a health-based record is absent. This study examines the extent to which estimates of childhood immunisation coverage derived using depend on maternal recall: a mother's ability to correctly identify which vaccines a child has received. In this study, we leverage spatial Bayesian models to estimate routine childhood immunisation rates at sub-national resolutions in 2015 and 2020 using various assumptions about the accuracy of maternal recall. This modelling approach and explicit consideration of maternal recall allows us to identify local regions whose previous estimates of vaccine coverage rates may be overstated due to low rates of the presence of health-based records. We create detailed vaccination coverage maps to analyze the models with and without maternal recall data. By highlighting vaccination "coldspots'' and their change over time, this study reveals the potential benefits or limitations of using maternal recall in generating vaccine coverage estimates and provides a basis for more informed decision-making for immunization interventions in India and similar contexts. | link |
| WebLight: DRL based Intersection Control in Developing Countries without Reliable Cameras | Sachin Chauhan, Rijurekha Sen | Indian Institute of Technology Delhi, Indian Institute of Technology Delhi | Effective traffic intersection control is crucial for urban sustainability. State of the art research seeking Artificial Intelligence (AI), for example Deep Reinforcement Learning (DRL) based traffic control requires environment states through various Computer Vision methods, where the collective state of multiple cameras across an intersection constitute the single state for AI. This brings in serious robustness or fault-tolerance concerns on the deployed system. Camera systems are highly susceptible to faults due to multiple possible points of failure. A single fault collapses the AI state and hence the capacity of AI controller to manage the traffic is gone. Also, infrastructure deployment and maintenance is a slow bureaucratic process in these countries, which makes camera faults a regular event. In the given paper, we build a web based, independent and alternative, traffic state processing method which can replace the camera dependency completely, or support as a backup mechanism until the camera system is back online, making the AI intersection control robust to camera failures. | link |
| Intelligent Data Solution Disaster Risk Reduction | Sai Krishna Dammalapati, Jeeno George, Rakhi Kashyap, Apoorv Anand, Sai Krishna Dammalapati | CivicDataLab, CivicDataLab, CivicDataLab, CivicDataLab, CivicDataLab | Several Indian states are highly vulnerable to flood disasters causing im- mense loss and damage to humans, properties and infrastructure. Governments are the primary responders in the event of a flood disaster. They are responsible for emergency relief and also the long term disaster resilience of a region. However, given the time , data and capacity constraints, this responsibility is not fulfilled in an optimum manner. Resource allocation for flood planning and management happens on a “best guess” basis. Available datasets are not being used as they exist in silos and are not interoperable. To make this process more transparent and data-driven, we propose the Intelligent Data Solution-Disaster Risk Reduction (IDS-DRR). IDS-DRR hosts various datasets that are related to flood management like rainfall, inundation, elevation, losses and damages, flood related public procurement etc., and makes them interoperable at a revenue circle unit level. An algorithm that includes methods like Data Envelopment Analysis (DEA) and TOPSIS is developed using these datasets to calculate the flood risk of each revenue circle. These risk scores would enable authorities to make informed decisions on fund disbursements. IDS-DRR is designed to be an open-source platform that can incorporate language localisation support and mobile alerts for key officials, disaster management authorities, volunteer groups and other stakeholders | link |
| Evaluation of computer vision pipeline for farm-level analytics: A case study in Sugarcane | Sambal Shikhar, Rajiv Ranjan, Aman Sa, Anshika Srivastava, Yash Srivastava, Dinesh Kumar, Shashank Tamaskar, Anupam Sobti | Plaksha University, Plaksha University, Plaksha University, Plaksha University, Plaksha University, Plaksha University, Plaksha University, Plaksha University | Analyzing agricultural imagery for farm level insights has been an active area of research in the recent times. For providing the necessary information to stakeholders - be it farmers, financial institutions or governments, various computer vision tasks have to come together. For example, to provide information to a farmer about crop stress in their farm, accurate localization of the farm, identification of the crop type and a monitoring of the field's micro-climate must be done together. In this work, we set performance benchmarks for three computer vision tasks - farm boundary detection, crop classification and sub-field stress estimation with different modalities of images - Sentinel2, PlanetScope and Drone Imagery. We use public dataset benchmarks for farm boundaries and crop classification and do a controlled field study on a large sugarcane farm in Uttar Pradesh, India for the stress estimation. Our work benchmarks farm boundary detection for small farms with state of the art deep learning algorithms achieving a dice score of 65%, improves the sugarcane classification accuracy by 10% coming to 98% and demonstrates an accuracy of 61% for water and nitrogen stress estimation. | link |
| A Proposed Systematic Framework and Guideline of Birth Declaration in Rural Last-Mile Bangladesh: Aimed at Reducing Child Marriage | Shabab Intishar Rahman, Priom Deb, Ishmam Tahsain, Md. Sadiqul Islam Sakif, Dr. Jannatun Noor | BRAC University Dhaka, BRAC University Dhaka, BRAC University Dhaka, BRAC University Dhaka,BRAC University Dhaka | This research paper proposes a social framework for birth decla ration in rural Bangladesh, utilizing cloud storage technology and ad hoc models, based on interviews with Community Healthcare Workers (n=13). The traditional process of birth registration in rural areas of Bangladesh is paper-based and often subject to errors, leading to incomplete or inaccurate data. The proposed framework addresses this issue by providing a secure and efficient system with minimal hardware requirements for recording and storing birth information in resource-constrained settings. Our paper, integrates HCI principles into a cloud-based solution for rural communities, addressing infrastructure and usability concerns, in line with HCI’s focus on technology in societal contexts. Further, we tackle the digital literacy gap prevalent in rural areas, designing our solution with HCI to bridge this divide effectively. We leverage existing infrastructure to introduce three progressive execution models, each constituting modular components within the overarching solution framework. The initial step in mitigating child marriage rates is securing accurate and easily retrievable birth data since paper trails are prone to manipulation, destruction, and fraud. Therefore, our study advocates for the implementation of the primary and pivotal measure to combat the vulnerable exploitation of children. | link |
| Comuniqa: Exploring Large Language Models for improving English speaking skills | Shikhar Sharma, Manas Mhasakar, Apurv Mehra, Utkarsh Venaik, Ujjwal Singhal, Dhruv Kumar, Kashish Mittal | Indraprastha Institute of Information Technology - Delhi, Microsoft Research India, BlendNet AI, Indraprastha Institute of Information Technology - Delhi, Indraprastha Institute of Information Technology - Delhi, Indraprastha Institute of Information Technology - Delhi, Microsoft Research India | In this paper, we investigate the potential of Large Language Models (LLMs) to improve English speaking skills. This is particularly relevant in countries like India, where English is crucial for academic, professional, and personal communication but remains a non-native language for many. Traditional methods for enhancing speaking skills often rely on human experts, which can be limited in terms of scalability, accessibility, and affordability. Recent advancements in Artificial Intelligence (AI) offer promising solutions to overcome these limitations. We propose Comuniqa, a novel LLM based system designed to enhance English speaking skills. We adopt a human-centric evaluation approach, comparing Comuniqa with the feedback and instructions provided by human experts. In our evaluation, we divide the participants in three groups: those who use LLM-based system for improving speaking skills, those guided by human experts for the same task and those who utilize both the LLM-based system as well as the human experts. Using surveys, interviews, and actual study sessions, we provide a detailed perspective on the effectiveness of different learning modalities. Our preliminary findings suggest that while LLM-based systems have commendable accuracy, they lack human-level cognitive capabilities, both in terms of accuracy and empathy. Nevertheless, Comuniqa represents a significant step towards achieving Sustainable Development Goal 4: Quality Education by providing a valuable learning tool for individuals who may not have access to human experts for improving their speaking skills. | link |
| BLIPS: Bluetooth locator for an Indoor Positioning System in Realtime | Shyama Sastha Krishnamoorthy Srinivasan, Siddharth Singh, Pushpendra Singh, Mohan Kumar | Indraprastha Institute of Information Technology - Delhi , Indraprastha Institute of Information Technology - Delhi , Indraprastha Institute of Information Technology - Delhi, Rochester Institute of Technology | Traditional localization systems often rely on a network of external sensors, making the setups cumbersome, expensive, and requiring significant calibration effort. The advent of Bluetooth 5.1 and later versions brought enhancements that enable precise localization using constant tone extension (CTE) in the signal through Angle of Arrival (AoA) and Angle of Departure (AoD) techniques. This work examines the capacity of a single Bluetooth Low-Energy (BLE) locator with an antenna array based on AoA in terms of performance, efficiency, and latency in real-time indoor positioning. While traditional neural networks train measured entities to match calculated distances, we utilize the azimuth and elevation angle components in the AoA measured and train neural networks to match their theoretical counterparts. We conducted extensive experiments in a real-world lab environment, providing ablation studies in the design. The results demonstrate the system's capability in real-time with many potential interference variables. Under lab conditions, our results show the capacity of a single locator wanes past $4m$ with the best average accuracy of $0.09m$ error in positioning within a $5m$ radius to as much as $\sim$$1m$ of error beyond $6m$ up to the maximum possible measuring distance in the lab. | link |
| Mapping Thermal Footprints: Occupancy Estimation and Localization in Diverse Indoor Settings with Thermal Arrays | Soumya Ranjan Sahoo, Haroon R. Lone | Indian Institute of Science Education and Research Bhopal, Indian Institute of Science Education and Research Bhopal | Estimating and locating occupants indoors is crucial for automating operations within buildings. However, current privacy-preserving occupancy estimation systems using thermal cameras have not been thoroughly evaluated in dense settings, such as classrooms or movie theaters, where occupants sit close to one another. Estimating occupancy in such settings presents challenges, as nearby occupants often lead to clusters of thermal signatures, thereby affecting the accuracy of the estimation. In response to these challenges, our work proposes Machine Learning (ML) and Deep Learning (DL) based methods for occupancy estimation and localization, both in dense and sparse settings. The ML method complements existing occupancy estimation techniques by incorporating new manual features, while the DL method performs automatic feature extraction, accurate occupancy estimation and localization. Remarkably, the results demonstrate a significant enhancement in occupancy estimation accuracy of up to 10\%, achieving an impressive overall accuracy rate of 97\%. Moreover, our evaluation on an edge device confirms the practicality and relevance of the proposed methods in real-world applications. | link |
| Is more better? Testing feature extraction for poverty estimates from telecom data in Cote d'Ivoire | Sveta Milusheva, Oscar Barriga-Cabanillas, Oumaima Makhlouk, Ruiwen Zhang | World Bank, World Bank, Intel, The World Bank Group | Targeting the poor is an integral part of social program design in low-income countries. Geographical targeting gives priority to areas with high concentrations of poverty. However, traditional data sources, such as household surveys often lack the spatial resolution to estimate poverty at a highly disaggregated level and are costly to collect on a regular basis. We leverage the proliferation of big data obtained from mobile devices and satellites to generate poverty measures at a highly disaggregated spatial level in a new country context. Previous applications rely on computationally intensive methods to extract information from raw cellphone transaction data. We show how similar levels of prediction accuracy can be achieved by using key performance indicators (KPIs) that Mobile Network Operators produce regularly as part of their operations, lowering the financial and data access barriers to estimate and update prediction models. | link |
| Unveiling Two-Fold Gamification: Exploring the Agency Of DeliveryWorkers in Urban India | Tanmay Goyal, Nimmi Rangaswamy | IIIT Hyderabad, IIIT Hyderabad | The evolving landscape of gig labor, particularly within food delivery platforms, has been influenced by a shift towards algorithmic management, emphasizing performance metrics as a daily burden to be carried through delivery work. Through a study of Indian food delivery agents, our paper suggests an emerging culture of gamification between delivery platforms and workers. Agents gradually yet consistently adapt to stringent algorithmic management to overcome everyday work’s precarity. Despite the challenges of performance pressure on food delivery labor, we capture the daily rhythms and routines of delivery work punctuated by flashes of agenting, revealing small capacities to make choices and influence work outcomes. By employing a qualitative research framework, we uncover the mechanisms through which delivery platforms manipulate labor, simultaneously exploring delivery agents’ tactics to extract agency and exploit the platforms’ rules. We develop the notion of ‘agency’ to disentangle the idea of ‘gamification by agents’ as a socio-technical derivative governing food delivery agents in urban India. The findings highlight the potential of platform work empowering, albeit with limits, delivery agents with agency and decision-making authority. | link |
| The Devil is in the deployment: Lessons learned while deploying an AI and IoT enabled hydroponics grow tent with rural subsistence farmers in South Africa | Taryn Wilson, Hafeni Mthoko, Yusra Adnan, Sarina Till | Independant Institute of Education (Varsity College), Independant Institute of Education (Varsity College), Independant Institute of Education (Varsity College), Independant Institute of Education (Varsity College) | Hydroponic farming is a sustainable alternative to traditional agriculture, allowing farmers to grow crops more efficiently. This type of farming involves growing plants in water without needing soil. There is increasing agreement that this agricultural approach should be utilized to mitigate food insecurity, particularly considering the fluctuating and unpredictability of weather conditions. However, this approach requires technical expertise in addition to consistent monitoring. Existing research has focused on applying The Internet of Things (IoT) and artificial intelligence (AI) technologies to the automation and monitoring of hydroponic farming systems. However, limited work tested the viability of these systems in the field with farmers. This study focused on including rural subsistence farmers in farming alongside a seven-month and ongoing deployment of an AI and IoT-enabled hydroponics system following a qualitative approach that entailed focus groups with the farmers and observations of the hydroponic systems. This paper discusses the lessons learned regarding unpredictable and uncontrollable extreme weather conditions, equipment failure, choices in nutrient solutions, and pest infestations, which often all have unplanned and unintended consequences for these systems and farmers. We argue that more deployments are needed to better understand how these systems function in real-world settings. | link |
| PRET Printer: Development and Evaluation of a Passive Refreshable Tactile Printer | Tigmanshu Bhatnagar, Cathy Holloway | University College London, University College London | Our work addresses the need for affordable options for tactile learners by presenting a new concept of a Passive Refreshable Tactile (PRET) Printer. Using off-the-shelf components of a laser engraver and the nascent Tacilia technology, our prototype enables the creation of refreshable and accessible tactile graphics. Leveraging Pixel Art as a rendering process, we enhance image production on this medium. Hence, this paper contributes technical specifications, an open-source repository of files for the PRET printer, and qualitative evaluation results from blind and partially sighted tactile learners. Our contribution facilitates rapid and cost-effective development of refreshable tactile media, crucial for improving access to tactile information and concepts, particularly in underserved regions. The work builds upon existing research, furthering the groundwork for advancing the urgent needs of tactile learners worldwide and establishing a solid foundation for further innovation and development in this domain. | link |
| Initial Experiments with a Scalable Machine Learning Based Approach for Downscaling the MOD16A2 Evapotranspiration Product | Vatsal Jingar, Stitiprajna Sahoo, Aaditeshwar Seth | Indian Institute of Technology Delhi, Indian Institute of Technology Delhi, Indian Institute of Technology Delhi | There exist many inequalities related to Groundwater use in India which poses a need to monitor groundwater levels in different rural areas to address and resolve these inequalities. Evapotranspiration constitutes a significant component of the groundwater equation, but traditional datasets that provide evapotranspiration data have sparse spatial and temporal resolution which hampers the accuracy in localised decision making of water-related applications. In this study we employ the machine learning algorithms like random forest to develop downscaling models capable of predicting high-resolution evapotranspiration. The approach leverages remotely sensed data, meteorological variables, and land surface characteristics as input features to capture the complex relationships governing evapotranspiration data. The results demonstrate the efficacy of machine learning to reproduce fine-scale evapotranspiration data which is validated using observational data from multiple geographic locations, representing diverse land use and land cover conditions. The study underscores the potential of machine learning to produce downscaled evapotranspiration maps for PAN-India using google earth engine, which would act as a valuable tool in water-resource management and climate change impact assessments. This research contributes a scalable and adaptable solution to address the growing demand for fine-resolution hydro-climatic information. | link |
| BlendNet: An Assisted Digital Distribution Platform for Underserved Populations | Vishali Sairam, Apurv Mehra, Kashish Mittal | None, BlendNet AI, Microsoft Research | In resource-constrained environments, the adoption of digital services faces formidable barriers. To address these challenges, we introduce BlendNet, an innovative platform designed to foster digital service adoption in remote and rural areas. BlendNet harnesses satellite and intelligent edge technologies and creates a reliable and cost-effective channel for intermediaries to distribute digital content and services in remote areas. Central to this system are hub devices strategically located in local kirana stores, facilitating seamless user access without data expenses, thereby addressing access, awareness, and affordability issues. A pilot study conducted in Bihar, India, involving 258 retailers across rural and urban areas and attracting over 68,000 users in three months, underscored the essential role of intermediaries in driving adoption. This paper offers detailed insights into BlendNet's design and the pilot study's outcomes, emphasizing user and retailer engagement and adoption rates. It explores the platform's potential as a scalable and financially viable solution. | link |
| Developing and Deploying AI and IoT-enabled hydroponic grow tents with subsistence farmers in South Africa | Yusuf Ismail, Sarina Till, Yusuf Ismail | Independent Institute of Education, Independent Institute of Education, None | South Africa is experiencing extreme weather conditions, often resulting in failed crops. The country has many subsistence farmers who rely on small-scale farming for food security and livelihoods. This paper presents [project name omitted to ensure anonymity], an Artificial Intelligence (AI), and Internet of Things (IoT) hydroponic grow tent implementing the Nutrient Film Technique (NFT) approach for leafy green plant production. The system uses a Random Forest Classifier (RFC) and various sensors for the real-time, accurate management of nutrient levels, pH, light, temperature, and humidity to provide an optimal environment for crop growth, in most cases, regardless of the weather patterns outside of the tent. The system further includes a mobile application that allows farmers to interject and manage all the elements in the tent. This paper reports on the design, development, and first deployment of [project name omitted to ensure anonymity] with rural subsistence farmers in South Africa. We found that South African farmers are keen to explore new agricultural technologies and were able to co-farm using [project name omitted to ensure anonymity] to grow crops that are no longer successfully cultivated due to the erratic weather conditions in South Africa. | link |