Publications

TransNet: Minimally-Supervised Deep Transfer Learning for Dynamic Adaptation of Wearable Systems
Wearables are poised to transform health and wellness through automation of cost-effective, objective, and real-time health monitoring. However, machine learning models for these systems are designed based on labeled data collected, and feature representations engineered, in controlled environments. This approach has limited scalability of wearables because (i) collecting and labeling sufficiently large amounts of sensor data is a labor-intensive and expensive process; and (ii) wearables are deployed in highly dynamic environments of the end-users whose context undergoes consistent changes. We introduce TransNet, a deep learning framework that minimizes the costly process of data labeling, feature engineering, and algorithm retraining by constructing a scalable computational approach. TransNet learns general and reusable features in lower layers of the framework and quickly reconfigures the underlying models from a small number of labeled instances in a new domain, such as when the system is adopted by a new user or when a previously unseen event is to be added to event vocabulary of the system. Utilizing TransNet on four activity datasets, TransNet achieves an average accuracy of 88.1% in cross-subject learning scenarios using only one labeled instance for each activity class. This performance improves to an accuracy of 92.7% with five labeled instances.
TransNet: Minimally-Supervised Deep Transfer Learning for Dynamic Adaptation of Wearable Systems
Proximity-Based Active Learning for Eating Moment Recognition in WearableSystems
A Dynamic Programming Framework for DVFS-Based Energy-Efficiency in Multicore Systems
A Dynamic Programming Framework for DVFS-Based Energy-Efficiency in Multicore Systems
Share-n-Learn: A Framework for Sharing Activity Recognition Models in Wearable Systems with Context-Varying Sensors
Resource-Efficient Computing in Wearable Systems
Resource-Efficient Computing in Wearable Systems
Mindful Active Learning
LabelForest: Non-Parametric Semi-Supervised Learning for Activity Recognition
Human-in-the-Loop Learning for Personalized Diet Monitoring from Unstructured Mobile Data
Trading Off Power Consumption and Prediction Performance in Wearable Motion Sensors: An Optimal and Real-Time Approach
Toward visual field assessment using head-worn sensing devices
Speech2Health: A Mobile Framework for Monitoring Dietary Composition From Spoken Data
Diet and physical activity are known as important lifestyle factors in self-management and prevention of many chronic diseases. Mobile sensors such as accelerometers have been used to measure physical activity or detect eating time. In many intervention studies, however, stringent monitoring of overall dietary composition and energy intake is needed. Currently, such a monitoring relies on self-reported data by either entering text or taking an image that represents food intake. These approaches suffer from limitations such as low adherence in technology adoption and time sensitivity to the diet intake context. In order to address these limitations, we introduce development and validation of Speech2Health, a voice-based mobile nutrition monitoring system that devises speech processing, natural language processing (NLP), and text mining techniques in a unified platform to facilitate nutrition monitoring. After converting the spoken data to text, nutrition-specific data are identified within the text using an NLP-based approach that combines standard NLP with our introduced pattern mapping technique. We then develop a tiered matching algorithm to search the food name in our nutrition database and accurately compute calorie intake values. We evaluate Speech2Health using real data collected with 30 participants. Our experimental results show that Speech2Health achieves an accuracy of 92.2% in computing calorie intake. Furthermore, our user study demonstrates that Speech2Health achieves significantly higher scores on technology adoption metrics compared to text-based and image-based nutrition monitoring. Our research demonstrates that new sensor modalities such as voice can be used either standalone or as a complementary source of information to existing modalities to improve the accuracy and acceptability of mobile health technologies for dietary composition monitoring.
Personalized Human Activity Recognition Using Convolutional Neural Networks
New Technologies in Geriatric Oncology Care
Digital Health for Geriatric Oncology
Design Space Exploration for Hardware Acceleration of Machine Learning Applications in MapReduce
Autonomous Training of Activity Recognition Algorithms in Mobile Sensors: A Transfer Learning Approach in Context-Invariant Views
Wearable technologies play a central role in human-centered Internet-of-Things applications. Wearables leverage machine learning algorithms to detect events of interest such as physical activities and medical complications. A major obstacle in large-scale utilization of current wearables is that their computational algorithms need to be re-built from scratch upon any changes in the configuration. Retraining of these algorithms requires significant amount of labeled training data, a process that is labor-intensive and time-consuming. We propose an approach for automatic retraining of the machine learning algorithms in real-time without need for any labeled training data. We measure the inherent correlation between observations made by an old sensor view for which trained algorithms exist and the new sensor view for which an algorithm needs to be developed. Our multi-view learning approach can be used in both online and batch modes. By applying the autonomous multi-view learning in the batch mode, we achieve an accuracy of 83.7 percent in activity recognition which is an improvement of 9.3 percent due to the automatic labeling of the data in the new sensor node. In addition to gain the less computation advantage of incremental training, the online learning algorithm results in an accuracy of 82.2 percent in activity recognition.
Architectural considerations for FPGA acceleration of machine learning applications in MapReduce
A Dynamic Programming Technique for Energy-Efficient Multicore Systems
Synchronous dynamic view learning: a framework for autonomous training of activity recognition models using wearable sensors
Personalization without user interruption: boosting activity recognition in new subjects using unlabeled data
Mobile sensing to improve medication adherence: demo abstract
Learn-on-the-go: Autonomous cross-subject context learning for internet-of-things applications
Head-mounted sensors and wearable computing for automatic tunnel vision assessment
Context-Aware System Design for Remote Health Monitoring: An Application to Continuous Edema Assessment
Designing remote health monitoring systems requires a multi-faceted perspective that takes into account requirements and contexts imposed by the medical application, technology, and end-user. We study such a design perspective in the context of remote and real-time edema monitoring. Edema (accumulation of fluid in certain soft-tissues) is regarded as one of the most important symptoms for systematic diseases such as heart failure. Monitoring edema allows patients and caregivers to understand the state of sickness and effectiveness of the treatments. This article proposes a novel low-power context-aware and real-time wearable platform capable of continuous assessment of ankle edema in remote settings. Our system keeps track of changes in subject’s ankle circumference as well as current body posture. An examination of our system with 15 subjects demonstrates the effectiveness and reliability of the proposed force-sensitive-resistor-based edema sensor (with an R2 of 0.87 for our regression model and intra-class correlation of 0.97) as well as an over 96 percent accuracy in activity monitoring that provide the means to perform reliable data validation on ankle circumference measurements in a continuous manner. Furthermore, we devise a novel derivative-free power optimization approach to maximize the battery lifetime resulting in improvement in battery lifetime by a factor of 2.13.
A beverage intake tracking system based on machine learning algorithms, and ultrasonic and color sensors: poster abstract
A beverage intake tracking system based on machine learning algorithms, and ultrasonic and color sensors: poster abstract
Wearable sensors for gait pattern examination in glaucoma patients
Transfer learning algorithms for autonomous reconfiguration of wearable systems
SmartSock: A wearable platform for context-aware assessment of ankle edema
S2NI: A mobile platform for nutrition monitoring from spoken data
Autonomous sensor-context learning in dynamic human-centered internet-of-things environments
An Energy-Efficient Computational Model for Uncertainty Management in Dynamically Changing Networked Wearables
An asynchronous multi-view learning approach for activity recognition using wearables
A Hardware-Assisted Energy-Efficient Processing Model for Activity Recognition Using Wearables
Toward robust and platform-agnostic gait analysis
Smart-Cuff: A wearable bio-sensing platform with activity-sensitive information quality assessment for monitoring ankle edema
Power-Aware Computing in Wearable Sensor Networks: An Optimal Feature Selection
Wearable sensory devices are becoming the enabling technology for many applications in healthcare and well-being, where computational elements are tightly coupled with the human body to monitor specific events about their subjects. Classification algorithms are the most commonly used machine learning modules that detect events of interest in these systems. The use of accurate and resource-efficient classification algorithms is of key importance because wearable nodes operate on limited resources on one hand and intend to recognize critical events (e.g., falls) on the other hand. These algorithms are used to map statistical features extracted from physiological signals onto different states such as health status of a patient or type of activity performed by a subject. Conventionally selected features may lead to rapid battery depletion, mainly due to the absence of computing complexity criterion while selecting prominent features. In this paper, we introduce the notion of power-aware feature selection, which aims at minimizing energy consumption of the data processing for classification applications such as action recognition. Our approach takes into consideration the energy cost of individual features that are calculated in real-time. A graph model is introduced to represent correlation and computing complexity of the features. The problem is formulated using integer programming and a greedy approximation is presented to select the features in a power-efficient manner. Experimental results on thirty channels of activity data collected from real subjects demonstrate that our approach can significantly reduce energy consumption of the computing module, resulting in more than 30 percent energy savings while achieving 96.7 percent classification accuracy.
Investigation of gait characteristics in glaucoma patients with a shoe-integrated sensing system
Toward seamless wearable sensing: Automatic on-body sensor localization for physical activity monitoring
SmartHealthSys 2014: ACM ubicomp international workshop on smart health systems and applications
Patient-centric on-body sensor localization in smart health systems
Cost-sensitive feature selection for on-body sensor localization
Ultra low-power signal processing in wearable monitoring systems: A tiered screening architecture with optimal bit resolution
Multimodal energy expenditure calculation for pervasive health: A data fusion model using wearable sensors
Context-aware signal processing in medical embedded systems: A dynamic feature selection approach
Generalized precursor pattern discovery for biomedical signals
Energy-efficient signal processing in wearable embedded systems: an optimal feature selection approach
Dynamic self-adaptive remote health monitoring system for diabetics
Automatic Segmentation and Recognition in Body Sensor Networks Using a Hidden Markov Model
A Mining Technique Using n-Grams and Motion Transcripts for Body Sensor Network Data Repository
Ultra Low Power Granular Decision Making Using Cross Correlation: Optimizing Bit Resolution for Template Matching
An Ultra Low Power Granular Decision Making Using Cross Correlation: Minimizing Signal Segments for Template Matching
A wireless communication selection approach to minimize energy-per-bit for wearable computing applications
Toward power optimization for communication failure recovery in Body Sensor Networks
Structural action recognition in body sensor networks: distributed classification based on string matching
Data Aggregation in Body Sensor Networks: A Power Optimization Technique for Collaborative Signal Processing
Collaborative signal processing for action recognition in body sensor networks: a distributed classification algorithm using motion transcripts
Burst communication by means of buffer allocation in body sensor networks: Exploiting signal processing to reduce the number of transmissions
Body sensor networks for baseball swing training: Coordination analysis of human movements using motion transcripts
Applications of sensing platforms with wearable computers
A greedy buffer allocation algorithm for power-aware communication in body sensor networks
A body sensor network with electromyogram and inertial sensors: multimodal interpretation of muscular activities
Wearable coach for sport training: A quantitative model to evaluate wrist-rotation in golf
Sport training using body sensor networks: a statistical approach to measure wrist rotation for golf swing
Report from HotMobile 2009
Energy-Efficient Information-Driven Coverage for Physical Movement Monitoring in Body Sensor Networks
Distributed Continuous Action Recognition Using a Hidden Markov Model in Body Sensor Networks
An automatic segmentation technique in body sensor networks based on signal energy
Locomotion Monitoring Using Body Sensor Networks
Action coverage formulation for power optimization in body sensor networks
A phonological expression for physical movement monitoring in body sensor networks
Modified Pseudo LRU Replacement Algorithm