Lakmal Meegahapola

Emma Bouton--Bessac, Lakmal Meegahapola, Daniel Gatica-Perez

Human Activity Recognition (HAR) enables context-aware user experiences where mobile apps can alter content and interactions depending on user activities. Hence, smartphones have become valuable for HAR as they allow large, and diversified data collection. Although previous work in HAR managed to detect simple activities (i.e., sitting, walking, running) with good accuracy using inertial sensors (i.e., accelerometer), the recognition of complex daily activities remains an open problem, specially in remote work/study settings when people are more sedentary. Moreover, understanding the everyday activities of a person can support the creation of applications that aim to support their well-being. This paper investigates the recognition of complex activities exclusively using smartphone accelerometer data. We used a large smartphone sensing dataset collected from over 600 users in five countries during the pandemic and showed that deep learning-based, binary classification of eight complex activities (sleeping, eating, watching videos, online communication, attending a lecture, sports, shopping, studying) can be achieved with AUROC scores up to 0.76 with partially personalized models. This shows encouraging signs toward assessing complex activities only using phone accelerometer data in the post-pandemic world.

Lakmal Meegahapola, Hamza Hassoune, Daniel Gatica-Perez

Over the years, multimodal mobile sensing has been used extensively for inferences regarding health and well being, behavior, and context. However, a significant challenge hindering the widespread deployment of such models in real world scenarios is the issue of distribution shift. This is the phenomenon where the distribution of data in the training set differs from the distribution of data in the real world, the deployment environment. While extensively explored in computer vision and natural language processing, and while prior research in mobile sensing briefly addresses this concern, current work primarily focuses on models dealing with a single modality of data, such as audio or accelerometer readings, and consequently, there is little research on unsupervised domain adaptation when dealing with multimodal sensor data. To address this gap, we did extensive experiments with domain adversarial neural networks (DANN) showing that they can effectively handle distribution shifts in multimodal sensor data. Moreover, we proposed a novel improvement over DANN, called M3BAT, unsupervised domain adaptation for multimodal mobile sensing with multi-branch adversarial training, to account for the multimodality of sensor data during domain adaptation with multiple branches. Through extensive experiments conducted on two multimodal mobile sensing datasets, three inference tasks, and 14 source-target domain pairs, including both regression and classification, we demonstrate that our approach performs effectively on unseen domains. Compared to directly deploying a model trained in the source domain to the target domain, the model shows performance increases up to 12% AUC (area under the receiver operating characteristics curves) on classification tasks, and up to 0.13 MAE (mean absolute error) on regression tasks.

Laura Schelenz, Ivano Bison, Matteo Busso et al.

Diversity-aware platform design is a paradigm that responds to the ethical challenges of existing social media platforms. Available platforms have been criticized for minimizing users' autonomy, marginalizing minorities, and exploiting users' data for profit maximization. This paper presents a design solution that centers the well-being of users. It presents the theory and practice of designing a diversity-aware platform for social relations. In this approach, the diversity of users is leveraged in a way that allows like-minded individuals to pursue similar interests or diverse individuals to complement each other in a complex activity. The end users of the envisioned platform are students, who participate in the design process. Diversity-aware platform design involves numerous steps, of which two are highlighted in this paper: 1) defining a framework and operationalizing the "diversity" of students, 2) collecting "diversity" data to build diversity-aware algorithms. The paper further reflects on the ethical challenges encountered during the design of a diversity-aware platform.

Lakmal Meegahapola, Florian Labhart, Thanh-Trung Phan et al.

According to prior work, the type of relationship between the person consuming alcohol and others in the surrounding (friends, family, spouse, etc.), and the number of those people (alone, with one person, with a group, etc.) are related to many aspects of alcohol consumption, such as the drinking amount, location, motives, and mood. Even though the social context is recognized as an important aspect that influences the drinking behavior of young adults in alcohol research, relatively little work has been conducted in smartphone sensing research on this topic. In this study, we analyze the weekend nightlife drinking behavior of 241 young adults in Switzerland, using a dataset consisting of self-reports and passive smartphone sensing data over a period of three months. Using multiple statistical analyses, we show that features from modalities such as accelerometer, location, application usage, bluetooth, and proximity could be informative about different social contexts of drinking. We define and evaluate seven social context inference tasks using smartphone sensing data, obtaining accuracies of the range 75%-86% in four two-class and three three-class inferences. Further, we discuss the possibility of identifying the sex composition of a group of friends using smartphone sensor data with accuracies over 70%. The results are encouraging towards (a) supporting future interventions on alcohol consumption that incorporate users' social context more meaningfully, and (b) reducing the need for user self-reports when creating drink logs.

Lakmal Meegahapola, Daniel Gatica-Perez

Over the years, mobile phones have become versatile devices with a multitude of capabilities due to the plethora of embedded sensors that enable them to capture rich data unobtrusively. In a world where people are more conscious regarding their health and well-being, the pervasiveness of smartphones has enabled researchers to build apps that assist people to live healthier lifestyles, and to diagnose and monitor various health conditions. Motivated by the high smartphone coverage among young adults and the unique issues they face, in this review paper, we focus on studies that have used smartphone sensing for the well-being of young adults. We analyze existing work in the domain from two perspectives, namely Data Perspective and System Perspective. For both these perspectives, we propose taxonomies motivated from human science literature, which enable to identify important study areas. Furthermore, we emphasize the importance of diversity-awareness in smartphone sensing, and provide insights and future directions for researchers in ubiquitous and mobile computing, and especially to new researchers who want to understand the basics of smartphone sensing research targeting the well-being of young adults.

Darshana Rathnayake, Ashen de Silva, Dasun Puwakdandawa et al.

Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate comprehension of such multimodal instructions (MMI), on resource-constrained wearable devices, remains an open challenge, especially as the state-of-the-art comprehension techniques for each individual modality increasingly utilize complex Deep Neural Network models. We demonstrate the possibility of overcoming the core limitation of latency--vs.--accuracy tradeoff by exploiting cross-modal dependencies -- i.e., by compensating for the inferior performance of one model with an increased accuracy of more complex model of a different modality. We present a sensor fusion architecture that performs MMI comprehension in a quasi-synchronous fashion, by fusing visual, speech and gestural input. The architecture is reconfigurable and supports dynamic modification of the complexity of the data processing pipeline for each individual modality in response to contextual changes. Using a representative "classroom" context and a set of four common interaction primitives, we then demonstrate how the choices between low and high complexity models for each individual modality are coupled. In particular, we show that (a) a judicious combination of low and high complexity models across modalities can offer a dramatic 3-fold decrease in comprehension latency together with an increase 10-15% in accuracy, and (b) the right collective choice of models is context dependent, with the performance of some model combinations being significantly more sensitive to changes in scene context or choice of interaction.

Lakmal Meegahapola, Vengateswaran Subramaniam, Lance Kaplan et al.

In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We show that the combined neural activations of such a hidden layer have class-specific distributional properties, and then define multiple statistical measures to compute how far a test sample's activations deviate from such distributions. Using a variety of benchmark datasets (including MNIST, CIFAR10, Fashion-MNIST & notMNIST), we show how such PAD-based measures can be used, independent of any training technique, to (a) derive fine-grained uncertainty estimates for inferences; (b) provide inferencing accuracy competitive with alternatives that require execution of the full pipeline, and (c) reliably isolate out-of-distribution test samples.

Madhawa Vidanapathirana, Lakmal Meegahapola, Indika Perera

360 degrees surround photography or photospheres have taken the world by storm as the new media for content creation providing viewers rich, immersive experience compared to conventional photography. With the emergence of Virtual Reality as a mainstream trend, the 360 degrees photography is increasingly important to offer a practical approach to the general public to capture virtual reality ready content from their mobile phones without explicit tool support or knowledge. Even though the amount of 360-degree surround content being uploaded to the Internet continues to grow, there is no proper way to index them or to process them for further information. This is because of the difficulty in image processing the photospheres due to the distorted nature of objects embedded. This challenge lies in the way 360-degree panoramic photospheres are saved. This paper presents a unique, and innovative technique named Photosphere to Cognition Engine (P2CE), which allows cognitive analysis on 360-degree surround photos using existing image cognitive analysis algorithms and APIs designed for conventional photos. We have optimized the system using a wide variety of indoor and outdoor samples and extensive evaluation approaches. On average, P2CE provides up-to 100% growth in accuracy on image cognitive analysis of Photospheres over direct use of conventional non-photosphere based Image Cognition Systems.

Vijini Mallawaarachchi, Lakmal Meegahapola, Roshan Alwis et al.

Majority of the currently available webpages are dynamic in nature and are changing frequently. New content gets added to webpages and existing content gets updated or deleted. Hence, people find it useful to be alert for changes in webpages which contain information valuable to them. In the current context, keeping track of these webpages and getting alerts about different changes have become significantly challenging. Change Detection and Notification (CDN) systems were introduced to automate this monitoring process and notify users when changes occur in webpages. This survey classifies and analyzes different aspects of CDN systems and different techniques used for each aspect. Furthermore, the survey highlights the current challenges and areas of improvement present within the field of research.