Skip to Main Content
It looks like you're using Internet Explorer 11 or older. This website works best with modern browsers such as the latest versions of Chrome, Firefox, Safari, and Edge. If you continue with this browser, you may see unexpected results.
Project 1: Measuring the effects of daytime activity levels on sleep quality (led by Dr. Metsis)
Correlation Analysis-Based Classification of Human Activity Time Series
In this paper, we introduce two correlation analysis-based methods for classifying time series data generated by sensors. Our first method is a lightweight supervised approach utilizing principal component analysis to jointly segment data and classify each segment into a class corresponding to an event of interest. The second method relies on unsupervised canonical correlation analysis to segment time series by clustering together consecutive data points that belong to the same event.
Automated Detection of Sleep Disorder-Related Events from Polysomnographic Data
This work presents our effort in analyzing human bio signals collected during sleep studies, to automatically detect events related to sleep disorders. We experiment with real sleep data collected using standard Polysomnography (PSG), and we detect events of interest from EEG signals, by segmenting the signal, extracting descriptive features from each segment, and applying supervised learning for classification. Our preliminary experimental results show that the event detection goal can be successfully achieved, while our methods are general enough to be directly applied to sleep data collected using alternative, noninvasive sensors.
Project 2: Modeling Tools and Risk Assessment for Smart Infrastructure (led by Dr. Guirguis)
Pinball attacks against Dynamic Channel assignment in wireless networks
In this paper, we expose a class of stealthy attacks, which we coin pinball attacks, that exploit the adaptive nature of Dynamic Channel Assignment algorithms in wireless networks.
A Game-Theoretic Two-Stage Stochastic Programing Model to Protect CPS against Attacks
This paper presents two-stage stochastic programming models for equipping the CPS control loops with the proper check blocks to secure them. The formulation is based on a game theoretical approach to enable the defender to find an optimal randomized (i.e., mixed strategy) assignment of check blocks while abiding to the control-loop constraints. The models incorporate uncertainty in the number of signals to be checked/protected and capture various degrees of overhead in the operation of the check blocks.
Project 5: Content Synchronization in Device-to-Device Communication in Smart Cities (led by Dr. Chen)
Content synchronization using device-to-device communication in smart cities.
In this paper, we consider the challenging problem of synchronizing the content of a subset of nodes in D2D networks. We adopt the City Section mobility model to mimic node movement in a city area, and produce theoretical analysis to the properties of the model. Based on this model, we propose two content synchronization strategies called direct contact synchronization and relay-assisted synchronization
Survey on device-to-device communications: Challenges and design issues
This survey focuses on cooperative communications in D2D-assisted networks and addresses challenges which limit the performance of the cooperative D2D-assisted networks such as relay selection, power consumption and multi-casting. Moreover, design issues and approaches to overcome these limitations are explained.
Project 3: Computing with Words in Threat Detection Systems (led by Dr. Tamir)
Computing with Words — A Framework for Human-Computer Interaction
In this paper we explore the possibility of using computation with words (CWW) systems and CWW-based human-computer interface (HCI) and interaction to enable efficient computation and HCI.
Computing with Words in Maritime Piracy and Attack Detection Systems
In this paper, we propose to apply recent advances in deep learning to design and train algorithms to localize, identify, and track small maritime objects under varying conditions (e.g., a snowstorm, high glare, night), and in computing-with-words to identify threatening activities where lack of training data precludes the use of deep learning
Project 4: Vision-based Automated Vehicle Activity Alert System (led by Dr. Tesic)
ActEV18: Human Activity Detection Evaluation for Extended Videos
In this paper, we introduce the Activities in Extended Video (ActEV) challenge to facilitate development of video analytic technologies that can automatically detect target activities, and identify and track objects associated with each activity. To benchmark the performance of currently available algorithms, we initiated the ActEV’18 activity-level evaluation along with reference segmentation and leaderboard evaluations. In this paper, we present a summary of results and findings from these evaluations. Fifteen teams from academia and industry participated in the ActEV18 evaluations using 19 activities from the VIRAT V1 dataset.