检索结果-内蒙古大学图书馆

Frontiers of computer Science 2025年第4期19卷 43-57页

作者： Xiao MA Shen-Yi ZHAO Zhao-Heng YIN Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing UniversityNanjing 210023China Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720-1770USA

Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.

关键词： deep reinforcement learning exploration count-based method clustering K-means

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Class Imbalance-Aware Shoulder Implant Classification from X-Ray Images

引用

Journal of Bionic engineering 2024年第2期21卷 892-912页

作者： Marut Jindal Birmohan Singh Department of Computer Science and Engineering Sant Longowal Institute of Engineering and TechnologySangrur148106PunjabIndia

Total shoulder arthroplasty is a standard restorative procedure practiced by orthopedists to diagnose shoulder arthritis in which a prosthesis replaces the whole joint or a part of the *** is often challenging for doctors to identify the exact model and manufacturer of the prosthesis when it is *** paper proposes a transfer learning-based class imbalance-aware prosthesis detection method to detect the implant’s manufacturer automatically from shoulder X-ray *** framework of the method proposes a novel training approach and a new set of batch-normalization,dropout,and fully convolutional layers in the head *** employs cyclical learning rates and weighting-based loss calculation *** modifications aid in faster convergence,avoid local-minima stagnation,and remove the training bias caused by imbalanced *** proposed method is evaluated using seven well-known pre-trained models of VGGNet,ResNet,and DenseNet *** is performed on a shoulder implant benchmark dataset consisting of 597 shoulder X-ray *** proposed method improves the classification performance of all pre-trained models by 10–12%.The DenseNet-201-based variant has achieved the highest classification accuracy of 89.5%,which is 10%higher than existing ***,to validate and generalize the proposed method,the existing baseline dataset is supplemented to six classes,including samples of two more implant *** results have shown average accuracy of 86.7%for the extended dataset and show the preeminence of the proposed method.

关键词： Biomedical engineering Artificial intelligence Total shoulder arthroplasty Prosthesis identification Biomedical image classification

来源：评论

学校读者我要写书评

暂无评论

An electrical Impedance Imaging System Towards Edge Intelligence for Non-Destructive Testing of Concrete

引用

Tsinghua Science and technology 2024年第3期29卷 883-896页

作者： Abolfazl Roshanpanah Mahdi Abbasi Hani Attar Ayman Amer Mohammad R.Khosravi Ahmed A.Solyman Department of Electrical Engineering Islamic Azad UniversityScience and Research BranceTehran ***Iran Department of Computer Engineering Bu-Ali Sina UniversityHamedan ***Iran Department of Energy Engineering Zarqa UniversityZarqa 13110Jordan Department of Computer Engineering Persian Gulf UniversityBushehr ***Iran Department of Electrical and Electronics Engineering Faculty of Engineering and ArchitectureNişantaşıUniversityIstanbul 34398Turkey

In the construction industry,to prevent accidents,non-destructive tests are necessary and *** impedance tomography is a new technology in non-invasive imaging in which the image of the inner part of conductive bodies is reconstructed by the arrays of external electrodes that are connected on the periphery of the *** equipment is cheap,fast,and edge *** this imaging method,the image of electrical conductivity distribution(or its opposite;electrical impedance)of the internal parts of the target object is *** image reconstruction process is performed by injecting a precise electric current to the peripheral boundaries of the object,measuring the peripheral voltages induced from it and processing the collected *** an electrical impedance tomography system,the voltages measured in the peripheral boundaries have a non-linear equation with the electrical conductivity *** paper presents a cheap electrical Impedance Tomography(EIT)instrument for detecting impurities in the concrete.A voltage-controlled current source,a micro-controller,a set of multiplexers,a set of electrodes,and a personal computer constitute the structure of the *** conducted tests on concrete with impurities show that the designed EIT system can reveal impurities with a good accuracy in a reasonable time.

关键词： non-destructive testing system concrete electrical impedance tomography

来源：评论

学校读者我要写书评

暂无评论

Design and Develop Function for Research Based Application of Intelligent Internet-of-Vehicles Model Based on Fog Computing

引用

computers, Materials & Continua 2024年第12期81卷 3805-3824页

作者： Abduladheem Fadhil Khudhur Ayca Kurnaz Türkben Sefer Kurnaz Department of Electrical and Computer Engineering Altinbas UniversityIstanbul34000Turkey

The fast growth in Internet-of-Vehicles(IoV)applications is rendering energy efficiency management of vehicular networks a highly important *** of the existing models are failing to handle the demand for energy conservation in large-scale heterogeneous *** on Large Energy-Aware Fog(LEAF)computing,this paper proposes a new model to overcome energy-inefficient vehicular networks by simulating large-scale network *** main inspiration for this work is the ever-growing demand for energy efficiency in IoV-most particularly with the volume of generated data and connected *** proposed LEAF model enables researchers to perform simulations of thousands of streaming applications over distributed and heterogeneous *** the possible reasons is that it provides a realistic simulation environment in which compute nodes can dynamically join and leave,while different kinds of networking protocols-wired and wireless-can also be *** novelty of this work is threefold:for the first time,the LEAF model integrates online decision-making algorithms for energy-aware task placement and routing strategies that leverage power usage traces with efficiency optimization in *** existing fog computing simulators,data flows and power consumption are modeled as parameterizable mathematical equations in LEAF to ensure scalability and ease of analysis across a wide range of devices and *** results of evaluation show that LEAF can cover up to 98.75%of the distance,with devices ranging between 1 and 1000,showing significant energy-saving potential through A wide-area network(WAN)usage *** findings indicate great promise for fog computing in the future-in particular,models like LEAF for planning energy-efficient IoV infrastructures.

关键词： Fog computing internet of vehicles LEAF segmentation distance power consumption cloud vehicle nodes wireless

来源：评论

学校读者我要写书评

暂无评论

DeepBio:A Deep CNN and Bi-LSTM Learning for Person Identification Using Ear Biometrics

引用

computer Modeling in engineering & Sciences 2024年第11期141卷 1623-1649页

作者： Anshul Mahajan Sunil K.Singla Department of Electrical and Instrumentation Engineering Thapar Institute of Engineering and TechnologyPatiala147004India

The identification of individuals through ear images is a prominent area of study in the biometric *** recognition systems have faced challenges during the COVID-19 pandemic due to mask-wearing,prompting the exploration of supplementary biometric measures such as ear *** research proposes a Deep Learning(DL)framework,termed DeepBio,using ear biometrics for human *** employs two DL models and five datasets,including IIT Delhi(IITD-I and IITD-II),annotated web images(AWI),mathematical analysis of images(AMI),and *** augmentation techniques such as flipping,translation,and Gaussian noise are applied to enhance model performance and mitigate *** extraction and human identification are conducted using a hybrid approach combining Convolutional Neural Networks(CNN)and Bidirectional Long Short-Term Memory(Bi-LSTM).The DeepBio framework achieves high recognition rates of 97.97%,99.37%,98.57%,94.5%,and 96.87%on the respective *** analysis with existing techniques demonstrates improvements of 0.41%,0.47%,12%,and 9.75%on IITD-II,AMI,AWE,and EARVN1 datasets,respectively.

关键词： Data augmentation convolutional neural network bidirectional long short-term memory deep learning ear biometrics

来源：评论

学校读者我要写书评

暂无评论

Classified VPN Network Traffic Flow Using Time Related to Artificial Neural Network

引用

computers, Materials & Continua 2024年第7期80卷 819-841页

作者： Saad Abdalla Agaili Mohamed Sefer Kurnaz Department of Electrical and Computer Engineering Altinbas UniversityIstanbul34000Turkey

VPNs are vital for safeguarding communication routes in the continually changing cybersecurity ***,increasing network attack complexity and variety require increasingly advanced algorithms to recognize and categorizeVPNnetwork *** present a novelVPNnetwork traffic flowclassificationmethod utilizing Artificial Neural Networks(ANN).This paper aims to provide a reliable system that can identify a virtual private network(VPN)traffic fromintrusion attempts,data exfiltration,and denial-of-service *** compile a broad dataset of labeled VPN traffic flows from various apps and usage ***,we create an ANN architecture that can handle encrypted communication and distinguish benign from dangerous *** effectively process and categorize encrypted packets,the neural network model has input,hidden,and output *** use advanced feature extraction approaches to improve the ANN’s classification accuracy by leveraging network traffic’s statistical and behavioral *** also use cutting-edge optimizationmethods to optimize network characteristics and *** suggested ANN-based categorization method is extensively tested and *** show the model effectively classifies VPN traffic *** also show that our ANN-based technique outperforms other approaches in precision,recall,and F1-score with 98.79%*** study improves VPN security and protects against new *** VPNtraffic flows effectively helps enterprises protect sensitive data,maintain network integrity,and respond quickly to security *** study advances network security and lays the groundwork for ANN-based cybersecurity solutions.

关键词： VPN network traffic flow ANN classification intrusion detection data exfiltration encrypted traffic feature extraction network security

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Hybrid Model Based on CNN and BiLSTM for Identifying Individuals via Handwriting Analysis

引用

computer Modeling in engineering & Sciences 2024年第8期140卷 1689-1710页

作者： Md.Abdur Rahim Fahmid Al Farid Abu Saleh Musa Miah Arpa Kar Puza Md.Nur Alam Md.Najmul Hossain Sarina Mansor Hezerul Abdul Karim Department of Computer Science and Engineering Pabna University of Science and TechnologyPabna6600Bangladesh Faculty of Engineering Multimedia UniversityCyberjaya63100Malaysia Department of Computer Science and Engineering Bangladesh Army University of Science and TechnologySaidpur5311Bangladesh Department of Mathematics Pabna University of Science and TechnologyPabna6600Bangladesh Department of Electrical Electronic and Communication EngineeringPabnaUniversity of Science and TechnologyPabna6600Bangladesh Department of Electrical and Communication Engineering Pabna University of Science and TechnologyPabna6600Bangladesh

Handwriting is a unique and significant human feature that distinguishes them from one *** are many researchers have endeavored to develop writing recognition systems utilizing specific signatures or symbols for person identification through ***,such systems are susceptible to forgery,posing security *** response to these challenges,we propose an innovative hybrid technique for individual identification based on independent handwriting,eliminating the reliance on specific signatures or *** response to these challenges,we propose an innovative hybrid technique for individual identification based on independent handwriting,eliminating the reliance on specific signatures or *** innovative method is intricately designed,encompassing five distinct phases:data collection,preprocessing,feature extraction,significant feature selection,and *** key advancement lies in the creation of a novel dataset specifically tailored for Bengali handwriting(BHW),setting the foundation for our comprehensive ***-preprocessing,we embarked on an exhaustive feature extraction process,encompassing integration with kinematic,statistical,spatial,and composite *** meticulous amalgamation resulted in a robust set of 91 *** enhance the efficiency of our system,we employed an analysis of variance(ANOVA)F test and mutual information scores approach,meticulously selecting the most pertinent *** the identification phase,we harnessed the power of cutting-edge deep learning models,notably the Convolutional Neural Network(CNN)and Bidirectional Long Short-Term Memory(BiLSTM).These models underwent rigorous training and testing to accurately discern individuals based on their handwriting ***,our methodology introduces a groundbreaking hybrid model that synergizes CNN and BiLSTM,capitalizing on fine motor features for enhanced individual ***,our experimental results unde

关键词： Bengali handwriting(BHW) person identification convolutional neural network(CNN) BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Patient-independent epileptic seizure detection using weighted visibility graph features and wavelet decomposition

引用

Multimedia Tools and Applications 2025年第6期84卷 3197-3221页

作者： Mohammadpoory, Zeynab Nasrolahzadeh, Mahda Amiri, Sekineh Asadi Department of Biomedical Engineering Shahrood University of Technology Shahrood Iran Department of Electrical Engineering University of Torbat Heydarieh Torbat Heydarieh Iran Department of Computer Engineering University of Mazandaran Babolsar Iran

Epileptic seizure detection has been a complex task due to the chaos and non-stationariness observed in the electroencephalogram (EEG) signals. Most existing EEG-based seizure detection algorithms are patient-dependent and train a detection model for each patient. This study investigates the patient-independent detection of seizure events using the big dataset CHB-MIT Scalp EEG. This paper proposes a new method based on weighted visibility graph (WVG) features to identify seizures from EEG signals. EEG signals from 22 channels and delta, theta, alpha, beta, and gamma sub-bands of EEGs are mapped into the WVG, and then WVG features are calculated from these WVGs. Then more informative features were selected using a combination of some feature selection methods and were given to five classifiers to investigate the performance of these features to classify the brain signals into seizure free (interictal) and during a seizure (ictal) groups. After that, the post-processing step was used to promote the performance of the method and also detect the seizure onset and offset times detection. The proposed method could detect 163 seizures out of 184, considering patient-independent situations for training classifiers and it could obtain an accuracy, sensitivity, and specificity of 94.02%, 92.31%, and 94.12% respectively. It also could obtain an FDR equal to 0.12/h and an ADL of 5.11 Seconds. Then, the proposed method has promising results in detection of seizures and it may use in online seizure detection applications such as closed-loop therapies. This study proposed extracting some WVG-based features from the signal and its sub-band with a feature selection scheme combining some feature selection methods and using some classifiers. Then a post-processing proposed to process the classifiers output and promote the performance of the proposed method. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Theoretical connection from the dielectric constant of films to the capacitance of capacitors under high temperature

引用

High Voltage 2023年第4期8卷 707-716页

作者： Yongxin Zhang Qikun Feng Shaolong Zhong Jiayao Pei Fangyi Chen Lei Huang Zhe Yang Zhimin Dang Department of Electrical Engineering Tsinghua UniversityBeijingChina Department of Electrical and Computer Engineering Carnegie Mellon UniversityPittsburghPennsylvaniaUSA Department of Energy Technology Aalborg UniversityAalborgDenmark

In the process of coping with energy and environmental protection issues,technologies such as energy materials,energy devices,and energy systems have made great *** excellent performance,film capacitors play an increasingly important role in energyrelated *** the increase of application scenarios and the continuous development of film material technology,it is urgent to establish a better theoretical connection from films to ***,the main components of the capacitor including the film and the positional relationships among them are ***,from the two perspectives of indirect calculation according to the volume and the direct calculation according to the winding process,the equation between the dielectric constant of films and the corresponding capacitance of capacitors is ***,the measurement data and error analysis results of the built test platform prove the accuracy and great potential of the proposed calculation *** addition,error sources,including film thickness uniformity,are ***,the challenges faced by the proposed calculation methods and the paths that can be referenced for future research are summarised and discussed.

关键词： film dielectric capacitance

来源：评论

学校读者我要写书评

暂无评论

Efficient power conversion with four switch soft-switching boost integrated half-bridge dual-output series resonant converter

引用

Journal of engineering and Applied Science 2024年第1期71卷 173页

作者： Kumar, Parveen Patthi, Sridhar Prakhya, Rajesh Kumar Rao, J. V. G. Rama Rayudu, K. Department of Electrical Engineering Model Institute of Engineering and Technology Jammu181122 India Department of Electrical Engineering Institute of Aeronautical Engineering Hyderabad500043 India Department of Electrical Engineering CVR College of Engineering Ibrahimpatnam501510 India Department of Electrical Engineering BVC Institute of Technology and Science Amalapuram533221 India Department of Electrical and Electronics Engineering B.V. Raju Institute of Technology Medak534202 India

Soft switching reduces voltage and current stress during transitions, smoothing and quieting operations and reducing electromagnetic interference while also increasing efficiency and equipment lifespan. Circuit design, component selection, and switching frequency optimization affect power electronics soft switching. This paper proposes boost integrated half-bridge dual-output series resonant (BIHBDOSR) converter, a novel converter design and control method to increase series resonant converter performance by reducing storage element size, switch count, and switching losses. This methodology relies on soft-switching technologies like zero-voltage switching (ZVS) and zero-current switching (ZCS). These methods use class-D, class-E, series, parallel, and series–parallel resonant converter circuits to increase efficiency and minimize component stress. The proposed converter is ideal for constant voltage, constant power, and current-controlled loads with the output voltage being regulated by a closed-loop PI controller. The output voltages for two loads in the simulation depart from reference values. V01 changes from 14 to 20 V and V02 from 18 to 15 V at 300 ms owing to switching variances. The proposed converter utilizes gate driver circuits, resonant tank circuit, current sensor, FPGA board for closed-loop control, and current sensor for stability, ensuring converter stability. The proposed converter closed-loop control method modifies PWM signals to regulate both loads independently and ensure steady output voltage. Additionally, to validate the effectiveness of proposed converter, a 50-W driver circuit is designed, delivering two independent outputs of 20 W and 30 W. Frequency modulation (FM) and duty cycle control methods are employed to obtain the desired outputs. © The Author(s) 2024.

关键词： Pulse width modulation

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：