检索结果-内蒙古大学图书馆

Deep Learning Algorithm for Person Re-Identification Based on Dual Network Architecture

computers, Materials & Continua 2025年第5期83卷 2889-2905页

作者： Meng Zhu Xingyue Wang Honge Ren Abeer Hakeem Linda Mohaisen College of Information Engineering Harbin UniversityHarbin150086China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin UniversityHarbin150086China College of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China Heilongjiang Forestry Intelligent Equipment Engineering Research Center Northeast Forestry UniversityHarbin150040China Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

Changing a person’s posture and low resolution are the key challenges for person re-identification(ReID)in various deep learning *** this paper,we introduce an innovative architecture using a dual attention network that includes an attentionmodule and a joint measurement module of spatial-temporal *** proposed approach can be classified into two main ***,the spatial attention feature map is formed by aggregating features in the spatial ***,the same operation is carried out on the channel dimension to formchannel attention ***,the receptive field size is adjusted adaptively tomitigate the changing person posture ***,we use a joint measurement method for the spatial-temporal information to fully harness the data,and it can also naturally integrate the information into the visual features of supervised ReID and hence overcome the low resolution *** experimental results indicate that our proposed algorithm markedly improves the accuracy in addressing changing human postures and low-resolution issues compared with contemporary leading *** proposed method shows superior outcomes on widely recognized benchmarks,which are the Market-1501,MSMT17,and DukeMTMC-reID ***,the proposed algorithmattains a Rank-1 accuracy of 97.4% and 94.9% mAP(mean Average Precision)on the Market-1501 ***,it achieves a 94.2% Rank-1 accuracy and 91.8% mAP on the DukeMTMC-reID dataset.

关键词： Person reidentification ReID computer vision self-attention spatial-temporal information

来源：评论

学校读者我要写书评

暂无评论

Intelligent Control Based in Neural-Fuzzy of Adaptive Backstepping for The Double Stator IPMSM Powered by a Five-Level NPC Inverter 13

Intelligent Control Based in Neural-Fuzzy of Adaptive Backst...

引用

13th IEEE International Conference and Expositions on Electric and Power engineering, EPEi 2024

作者： Benaissa, Rabie Mansouri, Smail Ouledali, Omar University of Adrar Faculty of Sciences and Technology Department of Electrical Engineering Laboratory for Sustainable Development and Computer Science 01000 Algeria University of Adrar Faculty of Sciences and Technology Department of Hydrocarbons and Renewable Energies Laboratory for Energy Environment and Information Systems 01000 Algeria

ISBN: (纸本)9798350356199

This article supplies a proposed approach Neuro Fuzzy Controller (NFC)-Adaptive Backstepping Controller (ABC)-Space Vector Modulation (SVM) for a five-level NPC inverter-Double Stator Interior Permanent Magnet Synchronous Motor (DSIPMSM). This paper's primary objective is to enhance DSIPMSM's performance by the use of strong control using the proposed approach. Given its benefits - including high torque density, high efficiency, high power density, and minimal maintenance - DSIPMSM, have recently been the focus of much research. Using the input-output linearization approach and Lyapunov stability theory, asymptotically stable trajectory-following dynamics are demonstrated using nonlinear adaptive backstepping control. The use of fuzzy logic and intelligence-based controllers are increasingly being used to enhance traditional control's performance and output. In addition, the fuzzy logic controller has a lot of flaws that are presently being fixed by the extremely effective NFC tool. The proposed method's worth was demonstrated by the simulation results in terms of durability, effective tracking dynamics, precision, and good disturbance rejection with little ripple. © 2024 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Bayes-Q-Learning Algorithm in Edge Computing for Waste Tracking

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 2425-2440页

作者： D.Palanikkumar R.Ramesh Kumar Mehedi Masud Mrim M.Alnfiai Mohamed Abouhawwash Department of Computer Science and Engineering Dr.NGP Institute of TechnologyCoimbatore641048India Department of Information Technology Sri Krishna College of TechnologyCoimbatore641042India Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif P.O.Box 11099Taif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

The major environmental hazard in this pandemic is the unhygienic dis-posal of medical *** wastage is not properly managed it will become a hazard to the environment and *** medical wastage is a major issue in the city,municipalities in the aspects of the environment,and *** efﬁcient supply chain with edge computing technology is used in managing medical *** supply chain operations include processing of waste collec-tion,transportation,and disposal of *** research works have been applied to improve the management of *** main issues in the existing techniques are ineffective and expensive and centralized edge computing which leads to failure in providing security,trustworthiness,and *** over-come these issues,in this paper we implement an efﬁcient Naive Bayes classiﬁer algorithm and Q-Learning algorithm in decentralized edge computing technology with a binary bat optimization algorithm(NBQ-BBOA).This proposed work is used to track,detect,and manage medical *** minimize the transferring cost of medical wastage from various nodes,the Q-Learning algorithm is *** accuracy obtained for the Naïve Bayes algorithm is 88%,the Q-Learning algo-rithm is 82%and NBQ-BBOA is 98%.The error rate of Root Mean Square Error(RMSE)and Mean Error(MAE)for the proposed work NBQ-BBOA are 0.012 and 0.045.

关键词： Binary bat algorithm naïve bayes supply chain edge medical wastage

来源：评论

学校读者我要写书评

暂无评论

Epileptic seizure detection in EEG signals via an enhanced hybrid CNN with an integrated attention mechanism

引用

Mathematical Biosciences and engineering 2025年第1期22卷 73-105页

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao56000 Thailand Department of Applied Statistics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research Institute King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand

Epileptic seizures, a prevalent neurological condition, necessitate precise and prompt identification for optimal care. Nevertheless, the intricate characteristics of electroencephalography (EEG) signals, noise, and the want for real-time analysis require enhancement in the creation of dependable detection approaches. Despite advances in machine learning and deep learning, capturing the intricate spatial and temporal patterns in EEG data remains challenging. This study introduced a novel deep learning framework combining a convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU), and convolutional block attention module (CBAM). The CNN extracts spatial features, the BiGRU captures long-term temporal dependencies, and the CBAM emphasizes critical spatial and temporal regions, creating a hybrid architecture optimized for EEG pattern recognition. Evaluation of a public EEG dataset revealed superior performance compared to existing methods. The model achieved 99.00% accuracy in binary classification, 96.20% in three-class tasks, 92.00% in four-class scenarios, and 89.00% in five-class classification. High sensitivity (89.00–99.00%) and specificity (89.63–99.00%) across all tasks highlighted the model’s robust ability to identify diverse EEG patterns. This approach supports healthcare professionals in diagnosing epileptic seizures accurately and promptly, improving patient outcomes and quality of life. © 2025 American Institute of Mathematical Sciences. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Exploring Students' Attitudes Towards Robotics technology in STEM Education: A Machine Learning-Based Prediction Analysis 4

Exploring Students' Attitudes Towards Robotics Technology in...

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： El Aziz, Mahmoud I. Abd Elshewey, Ahmed M. Tarek, Zahraa El-Kenawy, El-Sayed M. Ghazy, Ahmed M. Bhatnagar, Roheet Shams, Mahmoud Y. Kafrelsheikh University Faculty of Education Department of Curriculum Instruction and Educational Technology Kafrelsheikh33511 Egypt Suez University Faculty of Computers and Information Computer Science Department Suez Egypt Mansoura University Faculty of Computers and Information Computer Science Department Mansoura35561 Egypt Delta Higher Institute of Engineering and Technology Dept. of Communications and Electronics Mansoura35111 Egypt Manipal University Department of Computer Science and Engineering Rajasthan Jaipur India Kafrelsheiku University Faculty of Artificial Intelligence Dept. of Machine Learning 33516 Egypt

ISBN: (纸本)9798350387063

The aim of this paper is to predict the extent to which students will accept robotics technology in future teaching plans. The study involves students engaging in a two-week project-based learning program on robotics technology, after which they will decide whether it is suitable for them. To achieve this, the paper uses several prediction algorithms based on Machine Learning (ML), including Linear Regression (LR), Ridge Regression (RR), Elastic Net (EN) regression, and K-Nearest Neighbor (KNN) models. The sample group consists of 35 students from STEM high schools in Egypt. The research findings indicate that the students have gained confidence and satisfaction in robotics technology and believe it will have significant value in the future. The prediction results obtained from the ML regression models support these findings. The dataset used in the study includes seven input features and one target output representing the total prediction values of accepting and rejecting robotics technology in STEM schools. The regression models LR, RR, EN, and KNN achieve determination coefficients (R2) of 99.99%, 98.80%,99.20%, and 85.60%, respectively. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Applying Machine Learning Techniques to Increase Real-Time Data Analysis Accuracy 1

Applying Machine Learning Techniques to Increase Real-Time D...

引用

1st IEEE International Conference on Emerging Research in Computational Science, ICERCS 2023

作者： Naval, Preeti Mahesh, T.R. Kumar, Ajay Dhingra, Lovish Janakiraman, V. Banchhor, Chitrakant O. Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350359756

facts analysis examines, transforms, and models record sets to uncover valuable data and help make higher selections. Machine mastering techniques allow computer systems to automatically learn from records to make predictions primarily based on previously discovered patterns. By using these strategies, businesses can grow actual-time records analysis accuracy and see tendencies faster, allowing them to promptly respond to adjustments inside the surroundings. This paper will speak about using system studying techniques for actual-time statistics evaluation and the benefits of using such strategies. Mainly, techniques that include supervised studying, unsupervised learning, and deep studying will be discussed. Moreover, use instances in which system mastering may be applied, including economic fraud detection software programs, digital advertising and marketing, and predictive preservation, will be explored. Eventually, the outcomes of using system mastering strategies for data analysis, including statistics privateness and safety issues, can be mentioned. © 2023 IEEE.

关键词： Marketing

来源：评论

学校读者我要写书评

暂无评论

Statistical Investigation of Scientific Journals Impact Factors in Relation to Benford's Law 6

Statistical Investigation of Scientific Journals Impact Fact...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Sorour, Marwa A. Marey, Yassmine A. Halim, Islam Tharwat Abdel Kasem, Mohamed Mahran School of Information Technology and Computer Science Nile University Giza Egypt Nile University Giza Egypt Alexandria University Faculty of Engineering Egypt School of Engineering and Applied Science Nile University Giza Egypt

ISBN: (纸本)9798350378511

Benford's law (BL) has been used as a tool for the detection of possible data manipulation in datasets. The statistics of the first digit(s) of the observed values are compared to a set of expected values given by BL, and violations signal possible data anomalies. Though this method is first used for economical purposes, it has been recently used in bibliometric statistical analyses. The method provides alert that records may have certain unusual trends. In the present work, we investigate the impact factor statistics for 24 years starting from 1997 up to 2021, for open access and subscribed journals. We study conformity to BL using the basic first digit(s) violation test and the mantissa arc test, besides using the relative size factor test. Results show that open access journals adhere to Benford's Law more closely than subscribed journals. © 2024 IEEE.

关键词： Open access

来源：评论

学校读者我要写书评

暂无评论

Clustering the Academician Knowledge Qualification: K-Means for Performance Measurement Analysis 22

Clustering the Academician Knowledge Qualification: K-Means ...

引用

22nd IEEE Student Conference on Research and Development, SCOReD 2024

作者： Yanti, Novi Defit, Sarjon Okfalisa Universitas Islam Negeri Sultan Syarif Kasim Riau Department of Informatics Engineering Faculty of Science and Technology Riau Pekanbaru Indonesia Universitas Putra Indonesia YPTK Padang Department of Information Technology Faculty of Computer Science Sumatera Barat Padang Indonesia

ISBN: (纸本)9798331510077

The assessment of an academic's performance is not solely based on the tangible results achieved. Nonetheless, the formation aspect of the Knowledge Management (KM) process, which arises in the pursuit of outcomes, must be acknowledged. This emphasizes the significance of KM process development for academics in achieving their essential responsibilities including teaching and learning, research and publishing, and community service. Consequently, it is essential to develop a KM model for assessing the accomplishments of academics in higher education. An evaluation of academic performance in higher education was conducted to identify the success factors of knowledge management, by considering five key elements viz, knowledge creation, knowledge acquisition, knowledge storage, knowledge sharing, and knowledge application. Accordingly, sixty-five sub-variables were identified as success model factors for evaluating academic knowledge management performance. A K-Means clustering method was utilized to assess the KM qualifications of academics at an Islamic public institution in Indonesia (University X) as the primary study. Herein, a 5-point Likert scale questionnaire was administered to 500 academics and subsequently categorized into three performance levels such as low, medium, and high performance. As a result, 140 academicians were categorized as low KM performance, 139 were clustered as medium qualification, and 221 academicians were positioned in high performance. Furthermore, a recommendation analysis is presented to elucidate the accomplishments of academic credentials for each cluster and propose corrective actions for enhancement. Therefore, the scholars at University X might enhance their knowledge management practices to get a superior quality university. © 2024 IEEE.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

Smart Aero Generator Monitoring System using IoT 2

Smart Aero Generator Monitoring System using IoT

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Sathyamoorthy, Malathy Vanitha, C.N. Dhanaraj, Rajesh Kumar Mon, Feslin Anish Rai, Priti Kpr Institute of Engineering and Technology Department of Information Technology Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Erode India Pune India University of Technology and Applied Sciences Faculty in Department of Information Technology Ibri Oman Gl Bajaj Institute of Management Greater Noida India

ISBN: (纸本)9798350325799

Wind turbine plays a major role in energy production. From small wind turbines to ocean wind turbines, wind turbine industry introduces the latest version with bigger flexible blades, high towers, good efficiency and low-cost repairs. Small wind turbines malfunctioning will lead to a reduction in total energy. Faults like increasing in temperature may lead to fire accidents. The excessive vibration of the turbines may cause the turbine to sustain damage. The current shock will be passed to the people from the turbine if they try to contact it. IoT sensors can help us to overcome these obstacles. The proposed system will monitor the temperature, measures the speed, smoke and motion near the windmills. If the temperature exceeds the threshold then an alert will be generated and also water will be splashed in order to overcome the fire accident. If the speed of the wind is more than the threshold then the windmill be turned off to avoid damage in the turbines. Also, if an unnecessary movement is detected after a particular distance then the gate will be closed in the proposed system. It also measures the smoke for the gases released and generates an alert to avoid further damage to human lives and the windmill. The experimental results prove that the proposed system will improve the security of the windmill and also reduces the damage that occurs in the environment. The alert will be generated within 15s of an incident which proves that this is an efficient system when compared to the existing ones. © 2023 IEEE.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Preventive and proactive planning of PaaS maintenance service teams

引用

IFAC-PapersOnLine 2024年第19期58卷 778-783页

作者： Eryk Szwarc Grzegorz Bocewicz Arkadiusz Gola Robert Wójcik Zbigniew Banaszak Faculty of Electronics and Computer Science Koszalin University of Technology Poland Department of Production Computerisation and Robotisation Faculty of Mechanical Engineering Lublin University of Technology Poland Department of Computer Engineering Faculty of Information and Communication Technology Wrocław University of Science and Technology Poland

This paper employing the Product-as-a-Service (PaaS) paradigm provides a model integrating preventive and proactive management strategies to maintain the required service level availability in MultiFunction Device (MFD) offerings. The problems of resource allocation and servicing problems implied by these strategies focus on planning leasing offers that meet an acceptable failure risk level and routing service teams participating in maintenance missions. The aim is to allocate services that provide balanced risk to suppliers and renters, reduce delays, and prioritize urgent cases by routing a fleet of technical vehicles responsible for delivering and receiving service teams without the constraint of requiring the exact vehicle for both operations. The conducted computer experiments demonstrated the effectiveness of the adopted reference model, allowing for increasing PaaS availability and minimizing service costs.

关键词： Product-as-a-Service preventive proactive planning vehicle routing resource allocation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：