Papers by Moushumi Sharmin
Lecture Notes in Computer Science, 2023
A significant proportion of autistic children are considered 'nonverbal or minimally verbal' and ... more A significant proportion of autistic children are considered 'nonverbal or minimally verbal' and have difficulty expressing their emotions. Commercial alternative and assistive communication (AAC) apps are often inaccessible and ineffective in aiding autistic children in expressing emotions. Lack of access to adequate AACs is more prevalent in lower and middle-income communities (LMICs), which neither have sufficient infrastructure to aid the development of autistic children nor the resources to make expensive technology affordable. We propose the design of a prototype app that is accessible and multi-modal and caters to the specific needs of non-verbal and minimally verbal autistic children. Our design is grounded in research in autism and strength-based technology design. We incorporate accessibility guidelines and universal design features to make our design appropriate and effective for target users. CCS CONCEPTS • Human-centered computing → Accessibility; Ubiquitous and mobile computing.
We present the design, implementation, and evaluation of Bangladesh Emergency Services (BES), a m... more We present the design, implementation, and evaluation of Bangladesh Emergency Services (BES), a mobile application that provides 911-like services in Bangladesh. The involvement of A2I, a government agency, helped in the nationwide deployment of BES. To date, 120,382 unique users downloaded BES and 27,117 users are actively using it. Analysis of user ratings (N=3,788) and reviews (N=1,231) from Google Play Store, an online survey (N=137), and face-to-face interviews (N=10) revealed that users considered BES effective. Currently, BES is used to report aggressive behavior, street fight, harassment, fire-related incidents, and for locating nearby hospitals for medical emergencies. Our findings highlight the importance of trustworthiness, scalability of service, and iterative and participatory design for successful deployment of such services. We believe our research will inspire the design of mobile-based emergency applications in other developing countries that lack 911-like services.
2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)
2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), 2021
College students with autism have an estimated retention rate of 38.8% in the USA, which is attri... more College students with autism have an estimated retention rate of 38.8% in the USA, which is attributed to challenges resulting from mental and behavioral problems, lack of adequate support from colleges, and a lack of awareness of their unique needs. We propose visualizations guided by the self-determination theory to help understand the experiences and needs of college students with autism and to empower them to manage their behavior. The visualizations are created based on physiological and contextual data collected from 20 college students (10 with autism, 10 neurotypical) using Fitbit and smartphone, and are incorporated in a dashboard to offer seamless access. We evaluated the effectiveness of these visualizations by conducting a lab study (N=18) and learned that such visualizations can highlight experiences of students with autism, can enhance awareness about individuals’ behaviors and habits, and can help to identify areas that can potentially improve the college experience.
The 21st International ACM SIGACCESS Conference on Computers and Accessibility - ASSETS '19, 2019
Many neurodiverse individuals experience isolation in adult life with a significant percentage re... more Many neurodiverse individuals experience isolation in adult life with a significant percentage reporting never engaging in long term romantic relationships. Such social isolation can result in critical behavioral and mental health problems such as anxiety, addiction, and depression. Online socialization platforms can aid in relationship building as they are void of many complexities present in face-to-face communication. We conducted an exploratory study (N=10) with neurodiverse and neurotypical young adults to investigate how to design online socialization platforms that enables creating and maintaining lasting relationships, especially for neurodiverse individuals. We focused on understanding their experiences surrounding online socialization platforms, challenges in using them, and unmet needs. To elicit requirements, we designed a prototype socialization platform, Connection. Our findings reveal that there is indeed a great desire for such platforms among neurotypical and neurodiverse individuals.
Proceedings of the 2012 ACM international conference on Intelligent User Interfaces - IUI '12, 2012
ABSTRACT Reuse of existing presentation materials is prevalent among knowledge workers. However, ... more ABSTRACT Reuse of existing presentation materials is prevalent among knowledge workers. However, finding the most appropriate material for reuse is challenging. Existing information management and search tools provide inadequate support for reuse due to their dependence on users' ability to effectively categorize, recall, and recognize existing materials. Based on our findings from an online survey and contextual interviews, we designed and implemented a slide-based contextual recommender, ConReP, for supporting reuse of presentation materials. ConReP utilizes a user-selected slide as a search-key, recommends materials based on similarity to the selected slide, and provides a local-context-based visual representation of the recommendations. Users input provides new insight into presentation reuse and reveals that slide-based search is more effective than keyword-based search, local-context-based visual representation helps in better recall and recognition, and shows the promise of this general approach of exploiting individual slides and local-context for better presentation reuse.
Mobile Health, 2017
With every advancement in mHealth sensing technology, we are presented with an abundance of data ... more With every advancement in mHealth sensing technology, we are presented with an abundance of data streams and models that enable us to make sense of health information we record. To distill this diverse and ever-growing data into meaningful information, we must first develop tools that can represent data intuitively and are flexible enough to handle the special characteristics of mHealth records. For example, whereas traditional health data such as electronic health records (EHR) often consist of discrete events that may be readily analyzed and visualized, mHealth entails sensor ensembles that generate continuous, multivariate data streams of high-resolution and often noisy measurements. Drawing from methodologies in machine learning and visualization, interactive visual analytics tools are an increasingly important aid to making sense of this complexity. Still, these computational and visual techniques must be employed attentively to represent this data not only intuitively, but also accurately, transparently, and in a way that is driven by user needs. Acknowledging these challenges, we review existing visual analytic tools to identify design solutions that are both useful for and adaptable to the demands of mHealth data analysis tasks. In doing so, we identify open problems for representing and understanding mHealth data, suggesting future research directions for developers in the field.
2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC)
Job interviews are uniquely challenging for individuals with Autism Spectrum Disorder. While digi... more Job interviews are uniquely challenging for individuals with Autism Spectrum Disorder. While digital interview training tools have shown promising results for improving vocational outcomes for individuals with Autism, existing solutions are largely limited in the degree to which they can simulate a realistic interview environment, collect performance data from the user, and provide actionable feedback for continued improvement. To address these shortcomings and understand how to create an effective training tool, we designed InterViewR, a simulation-based interview training system that combines virtual reality and wearable smart technology in an integrated platform. Our design emphasizes an immersive user experience for training effectiveness and utilizes physiological sensing to provide intelligent affective biofeedback. We report findings from a usability study (N=11) where participants evaluated InterViewR on feasibility, usability, and perceived usefulness.
Early childhood education and teachers providing them play an imperative role in the development ... more Early childhood education and teachers providing them play an imperative role in the development of children with autism, which motivated us to examine the current educational practices, teachers’ experiences, needs, and expectations in Bangladesh. Findings from our qualitative study with teachers (N = 20) from four schools specializing in autism reveal that despite not having the required training for these kids they join the profession and even after getting a meager salary they continue to teach them. We also found that their relationship with the parents is complex, resulting from lack of effective communication about student progress. We propose a set of guidelines to design ICT tools which are a first step in addressing how to improve the educational experience of the teachers and their students by leveraging existing ICT tools. We believe our findings will open avenues for future researchers and guide them in envisioning robust technology to aid the existing educational process.
Smoking is one of the most challenging behavioral health problems. In the past, failed quit attem... more Smoking is one of the most challenging behavioral health problems. In the past, failed quit attempts have been attributed to factors including stress, presence of smoking cues, and negative affect – most of which were self-reported and prone to recall-bias. The first step in designing effective smoking cessation systems is to objectively identify factors that contribute to lapse. In our research, we collected physiological data utilizing wearable sensors from a four day pre-quit, post-quit study (N=55). We also collected self-report measures (n=3120), which offer rich contextual information about users' social, emotional, geographical, and physiological conditions. Analysis of collected data informed the design of MyQuitPal, a participant-centric cessation support system, which aims to assist individuals to better understand their smoking behavior. The design of MyQuitPal is also grounded on theories of long term health-behavior change. We believe our research advances understan...
Proceedings : AutomotiveUI 2014 : 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications : September 17-19, 2014, Seattle, Washington, USA / Linda Ng Boyle [and 3 others] ; in cooperation with ..., Jan 17, 2014
Driving is known to be a daily stressor. Measurement of driver's stress in real-time can enab... more Driving is known to be a daily stressor. Measurement of driver's stress in real-time can enable better stress management by increasing self-awareness. Recent advances in sensing technology has made it feasible to continuously assess driver's stress in real-time, but it requires equipping the driver with these sensors and/or instrumenting the car. In this paper, we present…
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2009
ABSTRACT Prior knowledge is a critical resource for design, especially when designers are strivin... more ABSTRACT Prior knowledge is a critical resource for design, especially when designers are striving to generate new ideas for complex problems. Systems that improve access to relevant prior knowledge and promote reuse can improve design efficiency and outcomes. ...
International Conference on Information Technology: Coding and Computing (ITCC'05) - Volume II, 2005
To facilitate thousands of hand held device users' lookup for services anywhere anytime, the impo... more To facilitate thousands of hand held device users' lookup for services anywhere anytime, the importance of a resource discovery scheme cannot be overlooked. The incorporation of Security, Adaptability, Fault Tolerance, and Efficiency features is the quest for long but there is no existing resource discovery scheme that can be claimed as "the solution". In this paper we propose the design of such a discovery mechanism named SAFE-RD, which is an integral part of MARKS (Adaptive Middleware for Resource discovery, Knowledge usability and Self-healing), on which we are currently working.
Lecture Notes in Computer Science, 2011
Communication associated with artifacts serves a critical role in the creation, refinement, and s... more Communication associated with artifacts serves a critical role in the creation, refinement, and selection of conceptual ideas. Despite the close relationship between ideas and surrounding communication, effective integration ofthese two types of design materials are not well-supported by exiting design tools-resulting in ad-hoc and ineffective strategies for managing communication during the design process. In this paper, we report the results of a contextual inquiry (N=15) aimed at understanding communication practices, its role in the design process, and strategies utilized by designers to manage and utilize communication outcomes in relation to artifacts. Our findings show thatmore than 50% of early design activity consists of three categories of communication (information seeking, brainstorming, and feedback) and communication practice varies as a function of expertise, organizational and social factors. Additionally, novice and freelance designers exhibit greater reliance on online forums to find suitable communication partners to generate and refine ideas whereas experts communicate with other experts or team members for information collection and sharing.
Proceedings of Graphics Interface 2007 on - GI '07, 2007
Requests for communication via mobile devices can be disruptive to the current task or social sit... more Requests for communication via mobile devices can be disruptive to the current task or social situation. To reduce the frequency of disruptive requests, one promising approach is to provide callers with cues of a receiver's context through an awareness display, allowing informed decisions of when to call. Existing displays typically provide cues based on what can be readily sensed, which may not match what is needed during the call decision process. In this paper, we report results of a four week diary study of mobile phone usage, where users recorded what context information they considered when making a call, and what information they wished others had considered when receiving a call. Our results were distilled into lessons that can be used to improve the design of awareness displays for mobile devices, e.g., show frequency of a receiver's recent communication and distance from a receiver to her phone. We discuss technologies that can enable cues indicated in these lessons to be realized within awareness displays, as well as discuss limitations of such displays and issues of privacy.
Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, 2014
Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol... more Stress can lead to headaches and fatigue, precipitate addictive behaviors (e.g., smoking, alcohol and drug use), and lead to cardiovascular diseases and cancer. Continuous assessment of stress from sensors can be used for timely delivery of a variety of interventions to reduce or avoid stress. We investigate the feasibility of continuous stress measurement via two field studies using wireless physiological sensors-a four-week study with illicit drug users (n = 40), and a one-week study with daily smokers and social drinkers (n = 30). We find that 11+ hours/day of usable data can be obtained in a 4-week study. Significant learning effect is observed after the first week and data yield is seen to be increasing over time even in the fourth week. We propose a framework to analyze sensor data yield and find that losses in wireless channel is negligible; the main hurdle in further improving data yield is the attachment constraint. We show the feasibility of measuring stress minutes preceding events of interest and observe the sensor-derived stress to be rising prior to self-reported stress and smoking events.
Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2014
Wearable wireless sensors for health monitoring are enabling the design and delivery of just-inti... more Wearable wireless sensors for health monitoring are enabling the design and delivery of just-intime interventions (JITI). Critical to the success of JITI is to time its delivery so that the user is available to be engaged. We take a first step in modeling users' availability by analyzing 2,064 hours of physiological sensor data and 2,717 self-reports collected from 30 participants in a weeklong field study. We use delay in responding to a prompt to objectively measure availability. We compute 99 features and identify 30 as most discriminating to train a machine learning model for predicting availability. We find that location, affect, activity type, stress, time, and day of the week, play significant roles in predicting availability. We find that users are least available at work and during driving, and most available when walking outside. Our model finally achieves an accuracy of 74.7% in 10-fold cross-validation and 77.9% with leave-one-subject-out.
Proceedings of the 5th …, 2002
Abstract: This paper reports on a generic sequential thinning algorithm to thin both Bangla and E... more Abstract: This paper reports on a generic sequential thinning algorithm to thin both Bangla and English characters and numerals. In this algorithm the thinned image is obtained by making the whole image uniform at first and then thinning it by deleting the unnecessary ...
Uploads
Papers by Moushumi Sharmin