Hafiz Syed Muhammad Bilal

On curating multimodal sensory data for personalized health and wellness services

In recent years, the focus of healthcare and wellness technologies has shown a significant shift towards personal vital signs devices. The technology has evolved from smartphone-based wellness applications to fitness bands and smartwatches. The novelty of these devices is the accumulation of activity data as their users go about their daily life routine. However, these implementations are device specific and lack the ability to incorporate multimodal data sources. Data accumulated in their usage does not offer rich contextual information that is adequate for providing a holistic view of a user’s lifelog. As a result, making decisions and generating recommendations based on this data are single dimensional. In this paper, we present our Data Curation Framework (DCF) which is device independent and accumulates a user’s sensory data from multimodal data sources in real time. DCF curates the context of this accumulated data over the user’s lifelog. DCF provides rule-based anomaly detection over this context-rich lifelog in real time. To provide computation and persistence over the large volume of sensory data, DCF utilizes the distributed and ubiquitous environment of the cloud platform. DCF has been evaluated for its performance, correctness, ability to detect complex anomalies, and management support for a large volume of sensory data.

MRPack: multi-algorithm execution using compute-intensive approach in MapReduce

Large quantities of data have been generated from multiple sources at exponential rates in the last few years. These data are generated at high velocity as real time and streaming data in variety of formats. These characteristics give rise to challenges in its modeling, computation, and processing. Hadoop MapReduce (MR) is a well known data-intensive distributed processing framework using the distributed file system (DFS) for Big Data. Current implementations of MR only support execution of a single algorithm in the entire Hadoop cluster. In this paper, we propose MapReducePack (MRPack), a variation of MR that supports execution of a set of related algorithms in a single MR job. We exploit the computational capability of a cluster by increasing the compute-intensiveness of MapReduce while maintaining its data-intensive approach. It uses the available computing resources by dynamically managing the task assignment and intermediate data. Intermediate data from multiple algorithms are managed using multi-key and skew mitigation strategies. The performance study of the proposed system shows that it is time, I/O, and memory efficient compared to the default MapReduce. The proposed approach reduces the execution time by 200% with an approximate 50% decrease in I/O cost. Complexity and qualitative results analysis shows significant performance improvement.

SNS Based Predictive Model for Depression

Worldwide the Mental illness is a primary cause of disability. It affects millions of people each year and whom of few receives cure. We found that social networking sites (SNS) can be used as a screening tool for discovering an affective mental illness in individuals. SNS posting truly depicts user’s current behavior, thinking style, and mood. We consider a set of behavioral attributes concerning to socialization, socioeconomics, familial, marital status, feeling, language use, and references of antidepressant treatments. We take advantage of these behavioral attributes to envision a tool that can provide prior alerts to an individual based on their SNS data regarding Major Depression Disorder (MDD). We propose a method, to automatically classify individuals into displayer and non-displayer depression using ensemble learning techniquefrom theirFacebook profile. Our developed tool is used for MDD diagnosis of individuals in additional to questioner techniques such as Beck Depression Inventory (BDI) and CESD-R.

An interactive case-based flip learning tool for medical education

Legacy Case-Based Learning (CBL) medical educational systems aim to boost the learning and educational process but lacks the support of Systematized Nomenclature of Medicine (SNOMED) and flip learning concepts. Integrating these vocabularies can exploit the learning outcomes and build confidence in students while making decision to rehearsal in advance before attending the actual CBL. The scope of this research covers delivering of medical education in interactive and intelligent way, efficient knowledge sharing, promoting team work environments, and building a knowledge-base for future to support automated computerized feedback. To achieve these goals, we propose a tool called Interactive Case-Based Flip Learning Tool (ICBFLT) that covers formulation of CBL case summaries, getting standard computerized help from both SNOMED vocabulary and state of the art solutions, and finally getting feedback from concerned tutor. In order to evaluate the ICBFLT, a scenario from the School of Medicine, University of Tasmania, Australia has been considered. This is an ongoing work and this paper gives an overview of the ICBFLT architecture with some intermediate results. The evaluation shows that the system has satisfied its users in term of interaction upto 70%.

Model-based adaptive user interface based on context and user experience evaluation

Personalized services have greater impact on user experience to effect the level of user satisfaction. Many approaches provide personalized services in the form of an adaptive user interface. The focus of these approaches is limited to specific domains rather than a generalized approach applicable to every domain. In this paper, we proposed a domain and device-independent model-based adaptive user interfacing methodology. Unlike state-of-the-art approaches, the proposed methodology is dependent on the evaluation of user context and user experience (UX). The proposed methodology is implemented as an adaptive UI/UX authoring (A-UI/UX-A) tool; a system capable of adapting user interface based on the utilization of contextual factors, such as user disabilities, environmental factors (e.g. light level, noise level, and location) and device use, at runtime using the adaptation rules devised for rendering the adapted interface. To validate effectiveness of the proposed A-UI/UX-A tool and methodology, user-centric and statistical evaluation methods are used. The results show that the proposed methodology outperforms the existing approaches in adapting user interfaces by utilizing the users context and experience.

LogMap-P: On matching ontologies in parallel

An enormous amount of research have been published related to ontology matching. The core motivation behind these researches aim to develop matching techniques that result in highly accurate ontology matching systems. However the performance (in terms of execution time) of these matching techniques is predominantly unexplored and is equally important. Among the well established research implementations, LogMap an open source system, is considered as state-of-the-art in ontology matching due to its accuracy. This paper presents LogMap-P, an enhanced version of LogMap with motivation to boost performance while preserving the accuracy of the matching techniques.

Context-Based Lifelog Monitoring for Just-in-Time Wellness Intervention.

These days adoption of healthy behavior can be quantified through Ubiquitous computing and smart gadgets. This digital technology has revolutionized the self-quantification to monitor activities for improving lifestyle. Context based lifelog monitoring is among the processes of tracking individual’s lifestyle in an effective manner. We have proposed a methodology for context-based monitoring of an individual’s prolonged sedentary physical activity and unhealthy dietary behavior in the domain of wellness and give just-in-time intervention to adapt healthy behavior. It detects multiple unhealthy activities of its users and verifies the context for intervention generation. The results depict that the average response of the context-based just-in-time interventions is about 75%.

A Multimodal Deep Log-Based User Experience (UX) Platform for UX Evaluation

The user experience (UX) is an emerging field in user research and design, and the development of UX evaluation methods presents a challenge for both researchers and practitioners. Different UX evaluation methods have been developed to extract accurate UX data. Among UX evaluation methods, the mixed-method approach of triangulation has gained importance. It provides more accurate and precise information about the user while interacting with the product. However, this approach requires skilled UX researchers and developers to integrate multiple devices, synchronize them, analyze the data, and ultimately produce an informed decision. In this paper, a method and system for measuring the overall UX over time using a triangulation method are proposed. The proposed platform incorporates observational and physiological measurements in addition to traditional ones. The platform reduces the subjective bias and validates the user’s perceptions, which are measured by different sensors through objectification of the subjective nature of the user in the UX assessment. The platform additionally offers plug-and-play support for different devices and powerful analytics for obtaining insight on the UX in terms of multiple participants.

Unhealthy Dietary Behavior Based User Life-Log Monitoring for Wellness Services

Unhealthy behavior, constitutes of unhealthy diet, smoking, physical inactivity and alcohol intake, increases the risk of chronic diseases and premature mortality. These unhealthy behaviors can be avoided by little intention and guidance. Diet is an influential factor of healthcare. Healthy and balanced diet selection is related to the better life expectancy and decreases the chances of chronic diseases. The Ubiquitous computing revolutionized the wellness domain towards user centric preference based health management. In this study we proposed a method for monitoring and indication of users’ unhealthy nutrition consumption. We evaluated 3 different timings of indication to user for induction of healthy dietary pattern. The “location and time based indication” depicts very promising result of 78% in the adoption of healthy diet pattern and has positive impact on the intake of fat nutrient in diet.