A5019159365- Cloud Computing and Resource Management
- IoT and Edge/Fog Computing
- Parallel Computing and Optimization Techniques
- Advanced Data Storage Technologies
- Distributed and Parallel Computing Systems
- Caching and Content Delivery
- Software-Defined Networks and 5G
- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
- Blockchain Technology Applications and Security
- Age of Information Optimization
- Robotics and Automated Systems
- Software System Performance and Reliability
- Interconnection Networks and Systems
- Infrared Target Detection Methodologies
- Advanced Memory and Neural Computing
- Semiconductor materials and devices
- Opportunistic and Delay-Tolerant Networks
- Vascular Malformations and Hemangiomas
- COVID-19 diagnosis using AI
- Gastrointestinal disorders and treatments
- Machine Learning and Data Classification
- Cloud Data Security Solutions
- Network Packet Processing and Optimization
- Neural Networks and Applications
Chung-Ang University
2018-2024
Chung Cheong University
2024
University of St Andrews
2024
Electronics and Telecommunications Research Institute
2024
Queen's University Belfast
2016-2021
University of Cambridge
2021
Korea University
2008-2016
Hanyang University Guri Hospital
2005
Listening to music is a crucial tool for relieving stress and promoting relaxation. However, the limited options available stress-relief do not cater individual preferences, compromising its effectiveness. Traditional methods of curating rely heavily on measuring biological responses, which time-consuming, expensive, requires specialized measurement devices. In this paper, deep learning approach solve problem introduced that explicitly uses convolutional neural networks provides more...
This article argues that low latency, high bandwidth, device proliferation, sustainable digital infrastructure, and data privacy sovereignty continue to motivate the need for edge computing research even though its initial concepts were formulated more than a decade ago.
Given the energy constraints in autonomous mobile agents (AMAs), such as unmanned vehicles, spiking neural networks (SNNs) are increasingly favored a more efficient alternative to traditional artificial networks. AMAs employ multi-object detection (MOD) from multiple cameras identify nearby objects while ensuring two essential objectives, (R1) timing guarantee and (R2) high accuracy for safety. In this paper, we propose RT-SNN, first system design, aiming at achieving R1 R2 SNN-based MOD...
Increasingly high performance computing (HPC) application developers are opting to use cloud resources due higher availability. Virtualized GPUs would be an obvious and attractive option for HPC using hosting services. Unfortunately, existing GPU virtualization software is not ready address fairness, utilization, limitations associated with consolidating mixed workloads. This paper presents FairGV, a radically redesigned system that achieves system-wide weighted fair sharing strong isolation...
Fog computing is a new paradigm that employs computation and network resources at the edge of to build small clouds, which perform as data centers. In fog computing, lightweight virtualization (e.g., containers) has been widely used achieve low overhead for performance-limited devices such WiFi access points (APs) set-top boxes. Unfortunately, containers have weakness in control bandwidth outbound traffic, poses challenge computing. Existing solutions fail desirable control, causes...
The cloud has become integral to most Internet-based applications and user gadgets. This article provides a brief history of the presents researcher's view prospects for innovating at infrastructure, middleware, delivery levels already crowded computing stack.
Defects or cracks in roads, building walls, floors, and product surfaces can degrade the completeness of become an impediment to quality control. Machine learning be a solution for detecting defects effectively without human experts; however, low-power computing device cannot afford that. In this paper, we suggest crack detection system accelerated by edge computing. Our consists two: Rsef Rsef-Edge. is real-time segmentation method based on effective feature extraction that perform image...
Mobile phones have evolved into complex systems as they more and new applications built-in. As a result, are less reliable secure than before. Virtual Machine Monitors (VMM) or hypervisors been introduced to help the reliability security of mobile but existing research does not completely address three issues critical phones: real-time support, resource limitation, power efficiency. In this paper we propose building VMM called MobiVMM for deal with these issues. enables support using...
Service level agreements (SLAs) for storage performance in virtualized systems are difficult to guarantee, because different consolidated virtual machines have their own requirements. Moreover, hard disk drives (HDDs) being replaced by solid-state (SSDs). SSDs higher throughput and lower latency than HDDs; however, they pose new challenges terms of SLAs. In this paper, we determine that existing I/O schedulers working with fail guarantee SLAs among virtualmachines, do not effectively utilize...
Industrial Internet of Things (IIoT) applications can benefit from leveraging edge computing.For example, relying on deep neural network (DNN) models be sliced and distributed across the IIoT device for decreasing latency inference.However, low performance between devices is often a bottleneck.In this study, we propose ScissionLite, holistic framework accelerating DNN inference using lightweight data compression.For compression method, implement new down/upsampling performance-limited...
This position paper presents a novel heterogeneous CPU-GPU multi-level cloud acceleration focusing on applications running embedded systems found low-power devices. A runtime system performs energy and performance estimations in order to automatically select local CPU-based GPU-based tasks that should be seamlessly executed more powerful remote devices or infrastructures. Moreover, it proposes, for the first time, secure unified model where almost any device infrastructure can operate as an...
In this paper, we analyze the performance impact of JobTracker failure in Hadoop. A is a serious problem that affects overall job processing performance. We describe cause and system behaviors because failed On basis analysis, build completion time model reflects effects. Our based on stochastic process with node crash probability. With our model, run simulation very credible data available from USENIX called computer repository have been collected for past 9 years. The results show severe...
Virtualization has recently been applied to consumer electronic (CE) devices such as smart TVs and smartphones. In these virtualized CE devices, memory is a valuable resource, because the virtual machines (VMs) on must share same physical memory. However, usually partitioned allocated each VM. This partitioning technique may result in shortages, which can seriously degrade application performance. paper proposes new swap mechanism for with flash proposed reduces consumption by compressing...
Deep learning is pervasive in our daily life, including self-driving cars, virtual assistants, social network services, healthcare face recognition, etc. However, deep neural networks demand substantial compute resources during training and inference. The machine community has mainly focused on model-level optimizations such as architectural compression of models, while the system implementation-level optimization. In between, various arithmetic-level optimization techniques have been...