no code implementations • 13 Mar 2024 • Anik Mallik, Dawei Chen, Kyungtae Han, Jiang Xie, Zhu Han
With an increase in AoI, incremental service aggregation issues are observed with out-of-sequence information updates, which hampers the performance of low-latency applications in CAVs.
no code implementations • 30 Nov 2023 • Xiaolong Tu, Anik Mallik, Haoxin Wang, Jiang Xie
We anticipate that DeepEn2023 will improve transparency in sustainability in on-device deep learning across a range of edge AI systems and applications.
no code implementations • 19 Oct 2023 • Xiaolong Tu, Anik Mallik, Dawei Chen, Kyungtae Han, Onur Altintas, Haoxin Wang, Jiang Xie
In this paper, we conduct a threefold study, including energy measurement, prediction, and efficiency scoring, with an objective to foster transparency in power and energy consumption within deep learning across various edge devices.
no code implementations • 13 Sep 2023 • Jiang Xie, Shuhao Li, Yongzheng Zhanga, Peishuai Sun, Hongbo Xu
Then, many attack detection methods based on these datasets are proposed.
no code implementations • 31 Aug 2023 • Xiang Li, Juncheng Guo, Qige Song, Jiang Xie, Yafei Sang, Shuyuan Zhao, Yongzheng Zhang
Despite some existing learning-based ETC methods showing promising results, three-fold limitations still remain in real-world network environments, 1) label bias caused by traffic class imbalance, 2) traffic homogeneity caused by component sharing, and 3) training with reliance on sufficient labeled traffic.
no code implementations • 7 Mar 2023 • Jiang Xie, Qiao Deng, Shuyin Xia, Yangzhou Zhao, Guoyin Wang, Xinbo Gao
In recent years, the problem of fuzzy clustering has been widely concerned.
no code implementations • 2 Mar 2023 • Jiang Xie, Shuyin Xia, Guoyin Wang, Xinbo Gao
We construct coarsegrained granular-balls, and then use granular-balls and MST to implement the clustering method based on "large-scale priority", which can greatly avoid the influence of outliers and accelerate the construction process of MST.
no code implementations • 2 Mar 2023 • Anik Mallik, Haoxin Wang, Jiang Xie, Dawei Chen, Kyungtae Han
Predicting the energy consumption of these models, along with their different applications, such as vision and non-vision, requires a thorough investigation of their behavior using various processing sources.
no code implementations • 30 Dec 2022 • Jiang Xie, Pengfei Zhao, Shuyin Xia, Guoyin Wang, Dongdong Cheng
It is crucial to evaluate the quality and determine the optimal number of clusters in cluster analysis.
no code implementations • 29 May 2022 • Shuyin Xia, Jiang Xie, Guoyin Wang
Existing clustering methods are based on a single granularity of information, such as the distance and density of each data.
no code implementations • 27 May 2022 • Haoxin Wang, BaekGyu Kim, Jiang Xie, Zhu Han
In this paper, we design an edge-based energy-aware MAR system that enables MAR devices to dynamically change their configurations, such as CPU frequency, computation model size, and image offloading frequency based on user preferences, camera sampling rates, and available radio resources.
no code implementations • 26 Nov 2020 • Haoxin Wang, BaekGyu Kim, Jiang Xie, Zhu Han
In order to accurately measure the energy consumption on the smartphone and obtain the breakdown of energy consumed by each phase of the object detection processing pipeline, we propose a new measurement strategy.
no code implementations • 26 Sep 2020 • Haoxin Wang, Tingting Liu, BaekGyu Kim, Chung-Wei Lin, Shinichi Shiraishi, Jiang Xie, Zhu Han
These requirements ask for a well-designed computing architecture to support the Quality-of-Service (QoS) of CV applications.
Networking and Internet Architecture