Search scope:
排序: Display mode:
A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring Article
Chunhua Yang, Huiping Liang, Keke Huang, Yonggang Li, Weihua Gui
Engineering 2021, Volume 7, Issue 9, Pages 1262-1273 doi: 10.1016/j.eng.2020.08.028
Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge. However, most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution. In fact, due to the harsh environment of industrial systems, the
collected data from real industrial processes are always affected by many factors, such as the changeable operating environment, variation in the raw materials, and production indexes. These factors often cause the distributions of online monitoring data and historical training data to differ, which induces a model mismatch in the process-monitoring task. Thus, it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring. In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments, a robust transfer dictionary learning (RTDL) algorithm is proposed in this paper for industrial process monitoring. The RTDL is a synergy of representative learning and domain adaptive transfer learning. The proposed method regards historical training data and online testing data as the source domain and the target domain, respectively, in the transfer learning problem. Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework, which can reduce the distribution divergence between the source domain and target domain. In this way, a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment. Such a dictionary can effectively improve the performance of process monitoring and mode classification. Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.
Keywords: Process monitoring Multimode process Dictionary learning Transfer learning
Incentive-Aware Blockchain-Assisted Intelligent Edge Caching and Computation Offloading for IoT Article
Qian Wang, Siguang Chen, Meng Wu
Engineering 2023, Volume 31, Issue 12, Pages 127-138 doi: 10.1016/j.eng.2022.10.014
The rapid development of artificial intelligence has pushed the Internet of Things (IoT) into a new stage. Facing with the explosive growth of data and the higher quality of service required by users, edge computing and caching are regarded as promising solutions. However, the resources in edge nodes (ENs) are not inexhaustible. In this paper, we propose an incentive-aware blockchain-assisted intelligent edge caching and computation offloading scheme for IoT, which is dedicated to providing a secure and intelligent solution for collaborative ENs in resource optimization and controls. Specifically, we jointly optimize offloading and caching decisions as well as computing and communication resources allocation to minimize the total cost for tasks completion in the EN. Furthermore, a blockchain incentive and contribution co-aware federated deep reinforcement learning algorithm is designed to solve this optimization problem. In this algorithm, we construct an incentive-aware blockchain-assisted collaboration mechanism which operates during local training, with the aim to strengthen the willingness of ENs to participate in collaboration with security guarantee. Meanwhile, a contribution-based federated aggregation method is developed, in which the aggregation weights of EN gradients are based on their contributions, thereby improving the training effect. Finally, compared with other baseline schemes, the numerical results prove that our scheme has an efficient optimization utility of resources with significant advantages in total cost reduction and caching performance.
Keywords: Computation offloading Caching Incentive Blockchain Federated deep reinforcement learning
Ensemble-transfer-learning-based channel parameter prediction in asymmetric massive MIMO systems Research Article
Zunwen HE, Yue LI, Yan ZHANG, Wancheng ZHANG, Kaien ZHANG, Liu GUO, Haiming WANG
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 2, Pages 275-288 doi: 10.1631/FITEE.2200169
Keywords: Asymmetric massive multiple-input multiple-output (MIMO) system Channel model Ensemble learning Instance transfer Parameter prediction
Two-level hierarchical feature learning for image classification Article
Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE
Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 9, Pages 897-906 doi: 10.1631/FITEE.1500346
Keywords: Transfer learning Feature learning Deep convolutional neural network Hierarchical classification Spectral clustering
A software defect prediction method with metric compensation based on feature selection and transfer learning Research Article
Jinfu CHEN, Xiaoli WANG, Saihua CAI, Jiaping XU, Jingyi CHEN, Haibo CHEN,caisaih@ujs.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 5, Pages 715-731 doi: 10.1631/FITEE.2100468
Keywords: Defect prediction Feature selection Transfer learning Metric compensation
Cong Wang, Shuaining Xie, Kang Li, Chongyang Wang, Xudong Liu, Liang Zhao, Tsung-Yuan Tsai
Engineering 2021, Volume 7, Issue 6, Pages 881-888 doi: 10.1016/j.eng.2020.03.016
Deep-learning methods provide a promising approach for measuring in-vivo knee joint motion from fast registration of two-dimensional (2D) to three-dimensional (3D) data with a broad range of capture. However, if there are insufficient data for training, the data-driven approach will fail. We propose a feature-based transfer-learning method to extract features from fluoroscopic images. With three subjects and fewer than 100 pairs of real fluoroscopic images, we achieved a mean registration success rate of up to 40%. The proposed method provides a promising solution, using a learning-based registration method when only a limited number of real fluoroscopic images is available.
Keywords: 2D–3D registration Machine learning Domain adaption Point correspondence
Feng Wenxing,Yang Lizhong,Fang Tingyong,Huang Rui,Fan Weicheng
Strategic Study of CAE 2005, Volume 7, Issue 1, Pages 81-85
The various materials as fuel are burnt in an experimental device of Room-Corridor structure, the mass loss rate of which, and the relationship of the mass loss rate with the smoke transportation velocity and CO concentration at a distant location are studied in detail in this paper. It describes the characteristics of mass loss rate of various materials and indicates that the smoke transportation velocity is a linear function of mass loss rate, and is sensitive to the variation of the mass loss rate. It takes a relatively long time for the peak of the toxic species concentration to transport to the distant location.
Keywords: fire mass loss rate distant location transportation velocity smoke toxicity
The Stable Movement of Salty Water Soil and Pattern Researchof Removing the Salt
Zhou Heping,Peng Lixin,Xu Xiaobo
Strategic Study of CAE 2007, Volume 9, Issue 11, Pages 120-126
Through the research of the water-salt movement under different ground condition for the water saving irrigation in dry area, it has been found that there is the symptom of redistribution of water and salt in certain area:when the evolvement of water and salt movement occurs in vertical and horizontal direction, there is also the important symptom of sideward movement and has certain domino effect. This paper analyses the technology for treatment of the salt soil at home and abroad, and discusses the new mode of salt drainage under both the condition of water-salt directional movement and the condition of salt movement to the earth's surface. The study has the practical meaning for research and discussion on the new method of salt soil amending in dry agricultural area in China.
Keywords: water-salt directional movement new mode of salt dranage research and discussion
Texture branch network for chronic kidney disease screening based on ultrasound images Research Articles
Peng-yi Hao, Zhen-yu Xu, Shu-yuan Tian, Fu-li Wu, Wei Chen, Jian Wu, Xiao-nan Luo,fuliwu@zjut.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 8, Pages 1119-1266 doi: 10.1631/FITEE.1900210
Keywords: 慢性肾脏病;超声;纹理分支网络;迁移学习
Tian Zhaoyang, Jia Yonggang, Zhu Chaoqi, Lu Longyu, Guo Xu, Feng Xuezhi, Wang Hui, Wang Hongwei, He Manchao, Peng Jianbing
Strategic Study of CAE 2023, Volume 25, Issue 3, Pages 131-140 doi: 10.15302/J-SSCAE-2023.03.012
Seabed fluid migration is a critical process that involves the transport and movement of liquids, gases, and seawater within and outside the seabed, which has significant impacts on the genesis, development, and evolution of seabed geological disasters. Notably, typical disasters such as submarine landslides in the sea area of China demonstrate a strong relevance with seabed fluid migration phenomena. In this paper, we analyze the distribution characteristics of typical fluid migration system types and geological disaster causes taking the northern South China Sea as an example, and we summarize the observation and investigation methods of seabed fluid migration. Furthermore, we propose the primary issues and content that must be addressed in the study of disasters induced by seabed fluid migration and their prevention and control. Specifically, we suggest that research should focus on the three phases, namely disaster genesis induced by deep high-pressure fluid migration, disaster development caused by gas hydrate decomposition and fluid migration, and disaster triggering resulting from ocean water movement. Based on breakthroughs in technological bottlenecks such as multi-system integration, multi-scale cooperation, and multi-dimensional information processing in deep-sea exploration, we must conduct in-depth research on the evolution mechanisms of seabed disaster genesis, development, and triggering under the influence of seabed fluid migration. Additionally, we must develop theoretical methods for seabed disaster risk prevention and control under the coupled effects of seabed fluid migration, geological environment, and human activities.
Keywords: seabed fluid migration marine geologic hazards risk prevention and control northern South China Sea
Federated unsupervised representation learning Research Article
Fengda ZHANG, Kun KUANG, Long CHEN, Zhaoyang YOU, Tao SHEN, Jun XIAO, Yin ZHANG, Chao WU, Fei WU, Yueting ZHUANG, Xiaolin LI,fdzhang@zju.edu.cn,kunkuang@zju.edu.cn
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 8, Pages 1181-1193 doi: 10.1631/FITEE.2200268
Keywords: Federated learning Unsupervised learning Representation learning Contrastive learning
Driftor: mitigating cloud-based side-channel attacks by switching and migrating multi-executor virtual machines Regular Papers
Chao YANG, Yun-fei GUO, Hong-chao HU, Ya-wen WANG, Qing TONG, Ling-shu LI
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 5, Pages 731-748 doi: 10.1631/FITEE.1800526
Co-residency of different tenants’ virtual machines (VMs) in cloud provides a good chance for side-channel attacks, which results in information leakage. However, most of current defense suffers from the generality or compatibility problem, thus failing in immediate real-world deployment. VM migration, an inherit mechanism of cloud systems, envisions a promising countermeasure, which limits co-residency by moving VMs between servers. Therefore, we first set up a unified practical adversary model, where the attacker focuses on effective side channels. Then we propose Driftor, a new cloud system that contains VMs of a multi-executor structure where only one executor is active to provide service through a proxy, thus reducing possible information leakage. Active state is periodically switched between executors to simulate defensive effect of VM migration. To enhance the defense, real VM migration is enabled at the same time. Instead of solving the migration satisfiability problem with intractable CIRCUIT-SAT, a greedy-like heuristic algorithm is proposed to search for a viable solution by gradually expanding an initial has-to-migrate set of VMs. Experimental results show that Driftor can not only defend against practical fast side-channel attack, but also bring about reasonable impacts on real-world cloud applications.
Keywords: Cloud computing Side-channel attack Information leakage Multi-executor structure Virtual machine switch Virtual machine migration
Learning to select pseudo labels: a semi-supervised method for named entity recognition Research Articles
Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 6, Pages 809-962 doi: 10.1631/FITEE.1800743
Keywords: 命名实体识别;无标注数据;深度学习;半监督学习方法
New directions for artificial intelligence: human, machine, biological, and quantum intelligence Comment
Li WEIGANG,Liriam Michi ENAMOTO,Denise Leyi LI,Geraldo Pereira ROCHA FILHO
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 6, Pages 984-990 doi: 10.1631/FITEE.2100227
This comment reviews the “once learning” mechanism (OLM) that was proposed byWeigang (1998), the subsequent success of “one-shot learning” in object categories (Li FF et al., 2003), and “you only look once” (YOLO) in objective detection (Redmon et al., 2016). Upon analyzing the current state of research in artificial intelligence (AI), we propose to divide AI into the following basic theory categories: artificial human intelligence (AHI), artificial machine intelligence (AMI), artificial biological intelligence (ABI), and artificial quantum intelligence (AQI). These can also be considered as the main directions of research and development (R&D) within AI, and distinguished by the following classification standards and methods: (1) human-, machine-, biological-, and quantum-oriented AI R&D; (2) information input processed by dimensionality increase or reduction; (3) the use of one/a few or a large number of samples for knowledge learning.
Keywords: 人工智能;机器学习;一次性学习;一瞥学习;量子计算
Engineering philosophical thinking of the old mining area transformation development
Jin Zhixin
Strategic Study of CAE 2014, Volume 16, Issue 10, Pages 64-70
The transformation development of the old mining area is a complex system engineering, it needs to command the overall situation by standing on the height of system engineering and needs to follow the harmonization in engineering, nature, science, technology, industry, economy and society. Engineering innovation is the main part of the technology innovations, it pushes the development of scientific, technical, industrial, economic and social, also the engineering innovation is relied on scientific and technological progress. Ecological protection is the premise of engineering development, and the ecological engineering construction is promoted by economic development. The protecting and mining of rare coking coal resources is a unity of oppisites. The companies of producting coking coal must pursue both immediate and long-term interests, especially the old mining, so the company should resolve the conflict between the scarcity of resources and the growth of demands by implementing limited exploitation, increasing resource recovery and efficiently recycling of coking coal resources to build the big-vertical-deep industry group. The conflict between frequent accidents and high input of existing security control promotes the development of security theory and technology, the transformation of security theory and technology from system security to structural security is a inevitable process of development.
Keywords: engineering philosophical asymmetric development green migration big-vertical-deep industry group protective mining security structure theory
Title Author Date Type Operation
A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring
Chunhua Yang, Huiping Liang, Keke Huang, Yonggang Li, Weihua Gui
Journal Article
Incentive-Aware Blockchain-Assisted Intelligent Edge Caching and Computation Offloading for IoT
Qian Wang, Siguang Chen, Meng Wu
Journal Article
Ensemble-transfer-learning-based channel parameter prediction in asymmetric massive MIMO systems
Zunwen HE, Yue LI, Yan ZHANG, Wancheng ZHANG, Kaien ZHANG, Liu GUO, Haiming WANG
Journal Article
Two-level hierarchical feature learning for image classification
Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE
Journal Article
A software defect prediction method with metric compensation based on feature selection and transfer learning
Jinfu CHEN, Xiaoli WANG, Saihua CAI, Jiaping XU, Jingyi CHEN, Haibo CHEN,caisaih@ujs.edu.cn
Journal Article
Multi-View Point-Based Registration for Native Knee Kinematics Measurement with Feature Transfer Learning
Cong Wang, Shuaining Xie, Kang Li, Chongyang Wang, Xudong Liu, Liang Zhao, Tsung-Yuan Tsai
Journal Article
Experimental Study on Relationship Between Mass Loss Rate and Smoke Transportation to the Distant Location in Fires
Feng Wenxing,Yang Lizhong,Fang Tingyong,Huang Rui,Fan Weicheng
Journal Article
The Stable Movement of Salty Water Soil and Pattern Researchof Removing the Salt
Zhou Heping,Peng Lixin,Xu Xiaobo
Journal Article
Texture branch network for chronic kidney disease screening based on ultrasound images
Peng-yi Hao, Zhen-yu Xu, Shu-yuan Tian, Fu-li Wu, Wei Chen, Jian Wu, Xiao-nan Luo,fuliwu@zjut.edu.cn
Journal Article
Research Progress and Prospects of Geohazard Mechanism and Risk Prevention Related to Seabed Fluid Migration
Tian Zhaoyang, Jia Yonggang, Zhu Chaoqi, Lu Longyu, Guo Xu, Feng Xuezhi, Wang Hui, Wang Hongwei, He Manchao, Peng Jianbing
Journal Article
Federated unsupervised representation learning
Fengda ZHANG, Kun KUANG, Long CHEN, Zhaoyang YOU, Tao SHEN, Jun XIAO, Yin ZHANG, Chao WU, Fei WU, Yueting ZHUANG, Xiaolin LI,fdzhang@zju.edu.cn,kunkuang@zju.edu.cn
Journal Article
Driftor: mitigating cloud-based side-channel attacks by switching and migrating multi-executor virtual machines
Chao YANG, Yun-fei GUO, Hong-chao HU, Ya-wen WANG, Qing TONG, Ling-shu LI
Journal Article
Learning to select pseudo labels: a semi-supervised method for named entity recognition
Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn
Journal Article
New directions for artificial intelligence: human, machine, biological, and quantum intelligence
Li WEIGANG,Liriam Michi ENAMOTO,Denise Leyi LI,Geraldo Pereira ROCHA FILHO
Journal Article