Related references
Note: Only part of the references are listed.
Article
Automation & Control Systems
Zhihan Lv et al.
Summary: This article aims to optimize the fault diagnosis effect of manufacturing equipment and explore the application of digital twins technology in intelligent manufacturing. By adopting equipment failures in Poka Yoke technology, a fault identification and chopping algorithm based on active learning-deep neural network (AL-DNN) and domain adversarial neural networks (DANN) is designed. Additionally, a digital twins workshop management and control system is designed for intelligent manufacturing management. Experimental exploration shows that the accuracy of the AL-DNN algorithm is as high as 99.248% and the DANN algorithm can realize fault identification and diagnosis under different working conditions, with an accuracy improvement of up to 20.256% compared to other deep learning algorithms.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Li Zhong et al.
Summary: This article discusses the problem of handling unknown classes in unsupervised open set domain adaptation (UOSDA). A new upper bound risk function is proposed, and a solution is presented for the issue of open set difference in deep neural networks (DNNs). Source-domain risk and epsilon-open set difference are minimized through gradient descent, while distributional discrepancy is minimized using a novel adversarial training strategy. Experimental results show that the proposed method achieves state-of-the-art performance on multiple datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yu Lin et al.
Summary: The paper investigates the optimal caching scheme for D2D networks with multiple robot helpers, proposing the RHAC scheme to optimize system performance through moving robots to optimal positions. It introduces the PAPSO algorithm and mobility-aware optimization strategy for robot helpers. Results show significant performance improvements with the RHAC scheme and provide insights for introducing robot helpers into scenarios like smart factories.
COMPUTER COMMUNICATIONS
(2022)
Article
Engineering, Aerospace
Aibin Yan et al.
Summary: With the reduction of technology nodes, circuits become more susceptible to external perturbations. This article presents advanced circuit components and latch designs based on voters, which effectively mitigate soft errors and improve reliability.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2022)
Article
Engineering, Civil
Lina Yang et al.
Summary: This study focuses on improving data transmission efficiency in a dedicated transportation sensor network using network coding. The research builds the overall network structure and designs a time model and firefly algorithm. Experimental results show that the simulation results are consistent with the predicted results, and code images can be quickly and efficiently transmitted in the DTSN.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Jun Dou et al.
Summary: This study introduces a feature selection method that can address imbalanced class and incomplete data simultaneously, and its effectiveness and universal applicability are demonstrated through experiments.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Yangyang Tian et al.
Summary: An innovative hybrid deep learning mechanism is proposed in this research to accurately identify damages in power transmission lines, addressing challenges in efficient power facility provision. The model, consisting of convolution neural network and support vector machine, achieves a high recognition rate of 95.57% in identifying damaged power lines, offering potential solutions to improve transmission infrastructure reliability and safety.
Article
Engineering, Electrical & Electronic
Debottam Mukherjee et al.
Summary: With the advancement in smart grid technology, real-time monitoring of the grid has become crucial. This paper proposes a deep learning architecture that can detect the exact locations of data intrusions in real-time, catering to both structured and unstructured false data injection attacks. The architecture is model-free and emphasizes the consistency and co-occurrence dependency of potential attacks, making it a multilabel classifier.
ELECTRICAL ENGINEERING
(2022)
Article
Environmental Sciences
Jiawei Tian et al.
Summary: Smog pollution is a significant global problem requiring further research and prediction. This paper proposes a deep learning technology based on a Deep Belief-Back Propagation neural network to predict and prevent smog pollution using air pollution data in Sichuan. The results show that the prediction accuracy is higher with more hidden layers, and PM2.5 can be predicted more accurately than PM10 using this network.
Article
Engineering, Electrical & Electronic
Chao Mi et al.
Summary: The visual sensor network (VSN) is an integral part of automated container terminals, but it faces challenges such as redundant sensor numbers and limited computing resources. This paper proposes a solution that transforms the task scheduling process of the VSN terminal into a Markov Decision Process, using a Deep-Q Learning algorithm. The algorithm introduces an innovative return value function to achieve better convergence. Experimental results demonstrate that the proposed algorithm improves the recognition rate and enables a reduction in the number of visual sensors, optimizing the use of computing resources and reducing costs, which is crucial for port operation optimization.
IEEE SENSORS JOURNAL
(2022)
Article
Energy & Fuels
Liang Zhang et al.
Summary: This paper develops a charging safety early warning model for electric vehicles based on the Improved Grey Wolf Optimization algorithm to improve the timeliness and accuracy of charging safety early warning. The findings reveal that the proposed model can reliably recognize abnormal charging voltage and issue timely warnings.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Computer Science, Interdisciplinary Applications
Jiwen Li et al.
Summary: This paper provides a comprehensive review of DSS strategies for energy-efficient IoT applications in intelligent urban computing, including presenting a technical taxonomy of existing energy-efficient DSS models, recognizing significant research trends in energy-aware DSS strategies for intelligent urban computing in IoT, and conducting a technical and statistical analysis of reviewed studies and evaluation factors.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
Libang Guo et al.
Summary: This paper proposes a 5G-based centralized switch FCL framework and an optimal allocation method for flexible FCLs. By using the FD model, online FCL switching schemes are provided to meet the fast requirement of power system protection. Furthermore, a bi-level FCL allocation model is established, considering installation and expected switching costs, to determine the optimal FCL allocation strategy.
IEEE TRANSACTIONS ON POWER DELIVERY
(2021)
Article
Computer Science, Artificial Intelligence
Zhuoqun Xia et al.
Summary: This paper proposes a confidence-aware collaborative detection mechanism for false data attacks, including trust-based compromised PMU identification and voting-based detection method based on physical rules, which can improve the detection rate of false data attacks and reduce the computational cost at the control center.
Review
Pharmacology & Pharmacy
Wing-Fu Lai et al.
Summary: Graphene, with its excellent properties, has been widely studied for biomedical applications. To enhance practical use, future research needs to examine the toxicity in more detail and establish guidelines for standardized experimental conditions to evaluate the performance of graphene-based materials.
ASIAN JOURNAL OF PHARMACEUTICAL SCIENCES
(2021)
Article
Engineering, Mechanical
Zhongjie Li et al.
Summary: The study focuses on how abrupt magnetic flux density changes influence the electric outputs of electromagnetic energy harvesters. It is found that the cubic-magnet array configuration yields the best performance in terms of output voltage, power density, and charging rates, demonstrating the importance of magnet volume in optimizing the harvester's performance.
INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES
(2021)
Article
Engineering, Electrical & Electronic
Hai Zhou et al.
Summary: This study investigates the transient magnetoelectric response of the symmetric TerfenolD/PZT/Terfenol-D laminate structure under different transient current driving, revealing damping oscillation phenomena. The results suggest that the ME composite is an ideal lightning current sensing device.
SENSORS AND ACTUATORS A-PHYSICAL
(2021)
Article
Computer Science, Artificial Intelligence
Bin Cao et al.
Summary: In order to address the growing problem of traffic pollution caused by the rapid increase in motor vehicles, a many-objective optimization model of multi-depot heterogeneous vehicle CARP is constructed in this study. Through the use of a memetic algorithm based on Two_Arch2, the model is effectively optimized and the pollution problem is successfully solved.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Software Engineering
Hanxin Chen et al.
Summary: A fault diagnosis model for nonstationary mechanical system is proposed with an algorithm utilizing an improved particle filter and Back Propagation. The method is able to reduce noise in experimental vibration signals to effectively locate impeller faults in a centrifugal pump for integrity assessment.
JOURNAL OF WEB ENGINEERING
(2021)
Article
Chemistry, Analytical
Rabeea Jaffari et al.
Summary: This study proposes a generalized focal loss function based on the Matthews correlation coefficient or the Phi coefficient to address the class imbalance problem in power line segmentation using a generic deep segmentation architecture. Evaluation on two power line datasets shows that the proposed loss function outperforms the popular BBCE loss in dice scores, precision, and false detection rate values. Additionally, the ACU-Net model improves upon the baseline U-Net for evaluation parameters in the range of 1-10% for both datasets, achieving an optimal trade-off without any additional complexity.
Article
Computer Science, Information Systems
Zhenyong Zhang et al.
Summary: This article introduces a new type of data integrity attack (DIA) - zero-parameter-information DIA (ZDIA), where attackers can execute stealthy data tampering attacks on smart grids without any branch parameter information. The paper also proposes two countermeasures to address the topology vulnerability exploited by ZDIA, as well as a branch perturbation strategy to defend against general DIAs.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Zhihan Lv et al.
Summary: The study introduces the CSWC-SVM algorithm and demonstrates its effectiveness in responding to attacks on industrial control systems in a virtual reality environment, providing practical significance for application.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Chao Guo et al.
Summary: This paper develops a fragile model to evaluate nodal SCF probability and presents a response framework for extreme weather events, optimizing measures to ensure system transient stability.
IEEE TRANSACTIONS ON POWER DELIVERY
(2021)
Article
Computer Science, Artificial Intelligence
Wujie Zhou et al.
Summary: Combining a gated attention mechanism and linear fusion method in a dual-stream interactive recursive feature-reshaping network (IRFR-Net) has shown significant advantages in salient object detection, outperforming 11 state-of-the-art RGB-D approaches in various evaluation indicators, as demonstrated through comprehensive experiments.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Information Systems
Jingbao Hou et al.
Summary: A novel rolling bearing fault diagnosis method based on adaptive feature selection and clustering is proposed in this research. The results show that good fault diagnosis results can be obtained whether the characteristic number parameters are set based on engineering experience or adaptive feature selection. Comparative experiments indicate that the fault diagnosis effect of the method based on adaptive parameter setting is better, demonstrating the feasibility and effectiveness of the proposed adaptive parameter fault diagnosis method for rolling bearing fault diagnosis.
Article
Automation & Control Systems
Tianju Sui et al.
Article
Engineering, Electrical & Electronic
Gautham Prasad et al.
IEEE COMMUNICATIONS MAGAZINE
(2020)
Article
Computer Science, Artificial Intelligence
Alireza Souri et al.
Article
Computer Science, Information Systems
Chenlei Lv et al.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Zhiyong Dai et al.
APPLIED INTELLIGENCE
(2020)
Article
Computer Science, Hardware & Architecture
Aibin Yan et al.
IEEE TRANSACTIONS ON RELIABILITY
(2019)
Article
Environmental Sciences
Heng Zhang et al.
Article
Chemistry, Analytical
Xuezhi Xiang et al.
Article
Telecommunications
Guiyang Luo et al.
CHINA COMMUNICATIONS
(2018)
