Akhil Mathur

Improving literacy in rural India: cellphone games in an after-school program

Literacy is one of the great challenges in the developing world. But universal education is an unattainable dream for those children who lack access to quality educational resources such as well-prepared teachers and schools. Worse, many of them do not attend school regularly due to their need to work for the family in the agricultural fields or households. This work commitment puts formal education far out of their reach. On the other hand, educational games on cellphones hold the promise of making learning more accessible and enjoyable. In our projects 4th year, we reached a stage where we could implement a semester-long pilot on cellphone-based learning. The pilot study took the form of an after-school program in a village in India. This paper reports on this summative learning assessment. While we found learning benefits across the board, it seemed that more of the gains accrued to those children who were better equipped to take advantage of this opportunity. We conclude with future directions for designing educational games that target less well-prepared children in developing regions.

Designing digital games for rural children: a study of traditional village games in India

Low educational levels hinder economic empowerment in developing countries. We make the case that educational games can impact children in the developing world. We report on exploratory studies with three communities in North and South India to show some problems with digital games that fail to match rural childrens understanding of games, to highlight that there is much for us to learn about designing games that are culturally meaningful to them. We describe 28 traditional village games that they play, based on our contextual interviews. We analyze the mechanics in these games and compare these mechanics against existing videogames to show what makes traditional games unique. Our analysis has helped us to interpret the playability issues that we observed in our exploratory studies, and informed the design of a new videogame that rural children found to be more intuitive and engaging.

Tiny habits in the giant enterprise: understanding the dynamics of a quantified workplace

We offer a reflection on the technology usage for workplace quantification through an in the wild study. Using a prototype Quantified Workplace system equipped with passive and participatory sensing modalities, we collected and visualized different workplace metrics (noise, color, air quality, self reported mood, and self reported activity) in two European offices of a research organization for a period of 4 months. Next we surveyed 70 employees to understand their engagement experience with the system. We then conducted semi-structured interviews with 20 employees in which they explained which workplace metrics are useful and why, how they engage with the system and what privacy concerns they have. Our findings suggest that sense of inclusion acts as the initial incentive for engagement which gradually translates into a habitual routine. We found that incorporation of an anonymous participatory sensing aspect into the system could lead to sustained user engagement. Compared to past studies we observed a shift in the privacy concerns, due to the trust and transparency of our prototype system. We conclude by providing a set of design principles for building future Quantified Workplace systems.

Engagement-aware computing: modelling user engagement from mobile contexts

In this paper, we examine the potential of using mobile context to model user engagement. Taking an experimental approach, we systematically explore the dynamics of user engagement with a smartphone through three different studies. Specifically, to understand the feasibility of detecting user engagement from mobile context, we first assess an EEG artifact with 10 users and observe a strong correlation between automatically detected engagement scores and users subjective perception of engagement. Grounded on this result, we model a set of application level features derived from smartphone usage of 10 users to detect engagement of a usage session using a Random Forest classifier. Finally, we apply this model to train a variety of contextual factors acquired from smartphone usage logs of 130 users to predict user engagement using an SVM classifier with a F1-Score of 0.82. Our experimental results highlight the potential of mobile contexts in designing engagement-aware applications and provide guidance to future explorations.

The myth of subtle notifications

Push notifications keep user informed and engaged with the events around the mobile applications. However not all the notifications are of the same importance level to the user. We explore how mobile notifications are regarded as increasing number of applications are adopting notification services. We logged notification management traces from 10 individuals for 15 days to understand how they perceived mobile notifications and their importance, accompanying our results with semi-structured interviews.

DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware

Wearable devices with built-in cameras present interesting opportunities for users to capture various aspects of their daily life and are potentially also useful in supporting users with low vision in their everyday tasks. However, state-of-the-art image wearables available in the market are limited to capturing images periodically and do not provide any real-time analysis of the data that might be useful for the wearers. In this paper, we present DeepEye - a match-box sized wearable camera that is capable of running multiple cloud-scale deep learn- ing models locally on the device, thereby enabling rich analysis of the captured images in near real-time without offloading them to the cloud. DeepEye is powered by a commodity wearable processor (Snapdragon 410) which ensures its wearable form factor. The software architecture for DeepEye addresses a key limitation with executing multiple deep learning models on constrained hardware, that is their limited runtime memory. We propose a novel inference software pipeline that targets the local execution of multiple deep vision models (specifically, CNNs) by interleaving the execution of computation-heavy convolutional layers with the loading of memory-heavy fully-connected layers. Beyond this core idea, the execution framework incorporates: a memory caching scheme and a selective use of model compression techniques that further minimizes memory bottlenecks. Through a series of experiments, we show that our execution framework outperforms the baseline approaches significantly in terms of inference latency, memory requirements and energy consumption.

DXTK: Enabling Resource-efficient Deep Learning on Mobile and Embedded Devices with the DeepX Toolkit

Deep learning is having a transformative effect on how sensor data are processed and interpreted. As a result, it is becoming increasingly feasible to build sensor-based computational models that are much more robust to real-world noise and complexity than previously possible. It is paramount that these innovations reach mobile and embedded devices that often rely on understanding and reacting to sensor data. However, deep models conventionally demand a level of system resources (e.g., memory and computation) that makes them problematic to run directly on constrained devices. In this work, we present the DeepX toolkit (DXTK); an open-source collection of software components for simplifying the execution of deep models on embedded and mobile platforms. DXTK contains a number of pre-trained low-resource deep models that users can quickly adopt and integrate for their particular application needs. Similarly, it offers a range of runtime options for executing deep models on devices ranging from Android platforms to Linux-based embedded platforms. But the heart of DXTK is a series of optimization techniques (viz. weight/sparse factorization, convolution separation, precision scaling, and parameter cleaning). These optimizers offer different methods for shaping the system resource needs and are compatible with a wide variety of different forms of deep neural networks. We hope that DXTK accelerates the study of resource-constrained deep learning in the community.

Quantified Workplace: Opportunities and Challenges

We present the design of a Quantified Workplace system which has been deployed in two European offices of a research organization since October 2014. So far, the system has collected more than 680,000 samples of various environment metrics in the workplace (e.g., noise, air quality, . . . ) and 57,340 data points on the indoor location of employees. In addition, the system has received 7504 participatory inputs from the users about their moods and physical activities in the workplace. We present the system and its different services, discuss our initial findings on the user engagement, and highlight the challenges of device heterogeneity, privacy and trust. We conclude by discussing potential applications of workplace quantification that can be developed using the data we are collecting.

Understanding the impact of personal feedback on face-to-face interactions in the workplace

Face-to-face interactions have proven to accelerate team and larger organisation success. Many past research has explored the benefits of quantifying face-to-face interactions for informed workplace management, however to date, little attention has been paid to understand how the feedback on interaction behaviour is perceived at a personal scale. In this paper, we offer a reflection on the automated feedback of personal interactions in a workplace through a longitudinal study. We designed and developed a mobile system that captured, modelled, quantified and visualised face-to-face interactions of 47 employees for 4 months in an industrial research lab in Europe. Then we conducted semi-structured interviews with 20 employees to understand their perception and experience with the system. Our findings suggest that the short-term feedback on personal face-to-face interactions was not perceived as an effective external cue to promote self-reflection and that employees desire long-term feedback annotated with actionable attributes. Our findings provide a set of implications for the designers of future workplace technology and also opens up avenues for future HCI research on promoting self-reflection among employees.

Exploring playback and recording of web-based audio media on low-end feature phones

Web-based audio information systems have the potential to bring the full promise of the Internet to the developing world. However, these systems run into a practical difficulty - insufficient support for playback and recording of web-based multimedia from feature phones. At the moment, feature phones constitute more than 90% of all phone shipments in emerging markets like India, and will continue to form a significant fraction (>50%) several years from now. In this paper we explore the practical challenges associated with audio playback and audio recording on feature phones. We present a systematic evaluation of the options to play and record audio media in a range of feature phones, and highlight problems stemming from a lack of memory, slow processor speeds and no support for progressive streaming downloads. In summary, the players in these phones are usually designed to handle audio files of short durations (a few minutes). Anything longer results in frequent breaks in playback (of up to 300msecs), and a very poor experience for the end-users. We investigate various solution approaches that may overcome these issues, and present an implementation and evaluation that achieves a seamless user experience on any audio stream.