Our overarching goal is to make the Internet of Things smarter and safer by incorporating artificial intelligence—in particular, machine learning—into their IoT applications. The value of AI in IoT is its ability to quickly wring valuable knowledge from data. This enables to avoid unplanned downtime, increase operating efficiency, spawn new products and services, and enhance risk management.
Here are some themes and techniques that we currently work on:
The AI-enabled framework for IoT Edge Computing. We have developed an AI-enabled framework for edge devices able to jointly satisfy the Quality of Experience (QoE) criteria of IoT applications. To minimize the network cost of deploying the models to edge devices, we developed a lightweight deployment paradigm supporting cloud-compression and edge-decompression based on a user-desired compression ratio. More details……..
Deep learning-based Intrusion Detection Systems. Cyber security has become increasingly challenging due to the proliferation of the Internet of things (IoT), where a massive number of tiny, smart devices push trillion bytes of data to the Internet. However, IoT gateways provide very limited security features to detect such threats, especially the absence of intrusion detection methods powered by deep learning. Indeed, deep learning models require high computational power that exceeds the capacity of these gateways. Therefore, we aim at designing a DNN-based network intrusion detection system (NIDS) directly operated on local gateways to protect IoT devices within the network. It can accurately detect multiple cyber attacks in real-time with a small computational footprint due to a lightweight feature extraction mechanism and an efficient attack detection model powered by deep neural networks. More details……..
Leaf Disease Detection. There are many kinds of leaf diseases firmly harm crop yield. In a traditional way, leaf diseases were diagnosed intuitively by farmers that is inefficient and unreliable. Therefore, we aim at employing deep neural networks for identifying leaf diseases.More details……..
Towards AI-Based Traffic Counting System with Edge Computing. The recent years have witnessed a considerable rise in the number of vehicles, which has placed transportation infrastructure and traffic control under tremendous pressure. Yielding timely and accurate traffic flow information is essential in the development of traffic control strategies. Despite the continual advances and the wealth of literature available in intelligent transportation system (ITS), there is a lack of practical traffic counting system, which is readily deployable on edge devices. Therefore, we desire a low-cost and effective edge-based system integrating object detection models to perform vehicle detecting, tracking, and counting. More details……..
Anomaly Detection in Time Series Data. Anomalies are pervasive in time series data, such as sensor readings. Existing methods for anomaly detection cannot distinguish between anomalies that represent data errors, such as incorrect sensor readings, and notable events, such as the watering action in soil monitoring. In addition, the quality performance of such detection methods highly depends on the configuration parameters, which are dataset specific. More details……..
We’ve been active in several domains, including computer networks, network security, data cleaning, edge computing. Although these are important fields, in the mentioned list showing only works in the AI/machine learning and IoT domains, which has been attracting most of our attention lately.