Skip to Main Content

Research Experience for Undergraduates in Computer Science: Project Support REU-CS

Project 1: • Time-Critical Edge Applications in Autonomous Vehicles (Dr. Kecheng Yang)

Edge Computing Resource Allocation Orchestration System for Autonomous Vehicles

Edge computing is the key to building 5G Networks and Future 2030 Networks. Edge computing extends the cloud computing paradigm by placing resources close to the network edges to cope with the upcoming growth of connected devices. Future applications: health monitoring and predictive services within the framework of the Smart City, Internet of things (IoT), vehicular ad hoc network, autonomous vehicles present a new set of strict requirements, such as low latency. In this paper, we develop a set of methods for managing and orchestrating new intelligent services in a new network and computing infrastructure. In addition, we consider a new prototype using an orchestration system for managing the autonomous vehicles’ resources in comparison with the existing approaches to the design of high-load networks. This orchestration platform is based on independent Docker containers that running the orchestration system. The main goal of our proposed system is to build an efficient network architecture with a minimum delay to process the information based on neural networks. Finally, simulation results proved that the proposed system can significantly not only reduce the overall network load but also increase the quality of the transmitted stream across the network in comparison with traditional network architectures.


Project 4: • Cognitive-Neuroscience Inspired Reinforcement Learning for Cyber Physical System (Dr. Heena Rathore)

An Overview of Deep Reinforcement Learning

As a new machine learning method, deep reinforcement learning has made important progress in various fields of people's production and life since it was proposed. However, there are still many difficulties in function design and other aspects. Therefore, further research on deep reinforcement learning is of great significance for promoting the progress of the whole science and society. Based on the basic theory of deep learning, this paper introduces the basic theory, research method, main network model and successful application in various fields of deep reinforcement learning.

Project 2: • Wearable Sensing System for Personalized Fall Detection at the Edge (Dr. Anne H.H. Ngu)

Fuzzy Logic Web Services for Real-Time Fall Detection Using Wearable Accelerometer and Gyroscope Sensors

The fall of the elderly population is a significant source of serious illness. Various wearable fall warning devices have been created recently to ensure older people's health. However, most of these devices are dependent on local data processing. This paper presents a new algorithm used in wearable sensors to track a real-time fall effectively and focuses on fall detection via fuzzy-as-a-service based on IEEE 1855-2016, Java fuzzy markup language and service-oriented architecture. Fuzzy logic systems (FLSs) have revealed their capability in ambient intelligence (AmI) applications. However, FLS deployment requires committed and quasi-scalable hardware/software systems. Sharing FLSs capability as web services allows flexibility, transparency, load balancing, efficient allocation of resources and ultimately cost-effectiveness. In this study, wearable sensors (i.e., accelerometer and gyroscope) that stimulate human activity monitoring using a rule-dependent FLS are demonstrated. Research findings exhibit that the proposed algorithm could easily differentiate between fall and non-fall occurrences with an accuracy, sensitivity and specificity of 90%, 88.89% and 91.67%, respectively.

Project 5: • Data Science in Healthcare and Medical Research (Dr. Lu Wang)

Project 3: • DLP: Dynamic and Lightweight Protection towards the Security of IoT Devices (Dr. Tao Hou)

Security and Privacy Requirements for the Internet of Things

The design and development process for internet of things (IoT) applications is more complicated than that for desktop, mobile, or web applications. First, IoT applications require both software and hardware to work together across many different types of nodes with different capabilities under different conditions. Second, IoT application development involves different types of software engineers such as desktop, web, embedded, and mobile to work together. Furthermore, non-software engineering personnel such as business analysts are also involved in the design process. In addition to the complexity of having multiple software engineering specialists cooperating to merge different hardware and software components together, the development process requires different software and hardware stacks to be integrated together (e.g., different stacks from different companies such as Microsoft Azure and IBM Bluemix). Due to the above complexities, non-functional requirements (such as security and privacy, which are highly important in the context of the IoT) tend to be ignored or treated as though they are less important in the IoT application development process. This article reviews techniques, methods, and tools to support security and privacy requirements in existing non-IoT application designs, enabling their use and integration into IoT applications. This article primarily focuses on design notations, models, and languages that facilitate capturing non-functional requirements (i.e., security and privacy). Our goal is not only to analyse, compare, and consolidate the empirical research but also to appreciate their findings and discuss their applicability for the IoT.