检索结果-内蒙古大学图书馆

Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks

Physical Review Letters 2025年第1期134卷 017301-017301页

作者： Satoshi Sunada Tomoaki Niiyama Kazutaka Kanno Rin Nogami André Röhm Takato Awano Atsushi Uchida Faculty of Mechanical Engineering Institute of Science and Engineering Kanazawa University Kakuma-machi Kanazawa Ishikawa 920-1192 Japan Department of Information and Computer Sciences Saitama University 255 Shimo-Okubo Sakura-ku Saitama City Saitama 338-8570 Japan Department of Information Physics and Computing Graduate School of Information Science and Technology The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan

The rapidly increasing computational demands for artificial intelligence (AI) have spurred the exploration of computing principles beyond conventional digital computers. Physical neural networks (PNNs) offer efficient neuromorphic information processing by harnessing the innate computational power of physical processes; however, training their weight parameters is computationally expensive. We propose a training approach for substantially reducing this training cost. Our training approach merges an optimal control method for continuous-time dynamical systems with a biologically plausible training method—direct feedback alignment. In addition to the reduction of training time, this approach achieves robust processing even under measurement errors and noise without requiring detailed system information. The effectiveness was numerically and experimentally verified in an optoelectronic delay system. Our approach significantly extends the range of physical systems practically usable as PNNs.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

A Survey on Web Application Testing: A Decade of Evolution

arXiv

引用

arXiv 2024年

作者： Li, Tao Huang, Rubing Cui, Chenhui Towey, Dave Ma, Lei Li, Yuan-Fang Xia, Wen School of Computer Science and Engineering Macau University of Science and Technology Macau Taipa999078 China Macau University of Science and Technology Zhuhai MUST Science and Technology Research Institute Guangdong Province Zhuhai519099 China School of Computer Science University of Nottingham Ningbo China Zhejiang Ningbo999078 China School of Science University of Tokyo Tokyo113-0033 Japan Faculty of Information Technology Monash University MelbourneVIC Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen518055 China

As one of the most popular software applications, a web application is a program, accessible through the web, to dynamically generate content based on user interactions or contextual data, for example, online shopping platforms, social networking sites, and financial services. Web applications operate in diverse environments and leverage web technologies such as HTML, CSS, JavaScript, and Ajax, often incorporating features like asynchronous operations to enhance user experience. Due to the increasing user and popularity of web applications, approaches to their quality have become increasingly important. Web Application Testing (WAT) plays a vital role in ensuring web applications’ functionality, security, and reliability. Given the speed with which web technologies are evolving, WAT is especially important. Over the last decade, various WAT approaches have been developed. The diversity of approaches reflects the many aspects of web applications, such as dynamic content, asynchronous operations, and diverse user environments. This paper provides a comprehensive overview of the main achievements during the past decade: It examines the main steps involved in WAT, including test-case generation and execution, and evaluation and assessment. The currently available tools for WAT are also examined. The paper also discusses some open research challenges and potential future WAT work. © 2024, CC BY.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Ensemble-Stacking Machine Learning Model for Multi-Class Skin Diseases Identification

Ensemble-Stacking Machine Learning Model for Multi-Class Ski...

引用

International Conference on Biomedical Engineering (IBIOMED)

作者： Dennis Tandelon David Lawrence Christiono Nur Afny Catur Andryani Srie P. Gondokaryono July I. Rahardja Retno Danarti Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Doctor of Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia Indonesia Dermatovenereology Department Faculty of Medicine Indonesian Society of Dermatology & Venereology Padjadjaran University Indonesia Dermatovenereology Department Faculty of Medicine Indonesian Society of Dermatology & Venereology Gadjah Mada University

ISBN: (数字)9798350389265

ISBN: (纸本)9798350389272

Algorithm development on skin diseases identification with high cardinality classification is still very challenging. In addition, the high similarity appearance among diseases makes the computer vision approach meet high difficulties on providing clear distinct feature representation. In general, some literature shows that the performance of single machine learning or single deep learning techniques can be further improved when merged by ensemble mechanism. This approach has been applied on binary skin's cancer diseases diagnosis prediction and successfully improve the prediction ability. This paper elaborates the potential of ensemble machine learning approaches using stacking techniques on conducting feature extraction and classification model for identifying more general skin diseases based on dermoscopy images and mobile phone images. The proposed model combines three different CNN architectures, ResNet50, Xception, and VGG16 to extract features from the image then stacked as input for the model trained using five different algorithms, which are logistic regression, support vector machines, multi-layer perceptron, k-nearest neighbors, random forests and the combination of these algorithm in stacking classifier as the base estimators and final estimator. The simulation results present the proposed ensemble - stacking model succeeds to improve the identification ability in all utilized datasets. In addition, the proposed ensemble - stacking models show better recall which indicates good sensitivity on handling false negative. It is beneficial for medical application.

关键词： Support vector machines Sensitivity Biological system modeling Simulation Stacking Feature extraction Skin Classification algorithms Diseases Skin cancer

来源：评论

学校读者我要写书评

暂无评论

Exploration of Human Emotion Recognition in Speech Data Based on Convolutional Neural Network with Mel and Delta Scale Features

Exploration of Human Emotion Recognition in Speech Data Base...

引用

information technology Research and Innovation (ICITRI), International Conference on

作者： Dwi Krisnandi Hilman Ferdinandus Pardede Faculty of Information Technology Graduate School of Computer Science Universitas Nusa Mandiri Jakarta Indonesia Research Center for Artificial Intelligence and Cyber Security Bandung Indonesia

This exploration of human emotion recognition in voice data can provide information related to human emotions based on the intonation of a person's voice that describes that person's emotions. The selection of voice data to determine emotions compared to facial expressions is aimed at knowing the emotions of a person because, during this pandemic, most people wore masks so they could not see the person's facial expressions clearly. In this study, we explored emotion recognition using the Mel and Delta scales to obtain accuracy from the RAVDESS dataset used in this study using the 2-dimensional CNN algorithm used in this study. The predicted labels in this study are 4 labels per group: angry, sad, neutral, and happy. CNN has the ability to recognize and distinguish complex audio frequency alloys and shapes, such as emotional voices, which increases the accuracy of emotion recognition. The disadvantages of the CNN model are highly dependent on the features selected, and selecting the wrong features can reduce accuracy. In LR 0.01 we can see that the delta-delta-mfcc with an f1 score result of 57.95% and an accuracy score of 63.88% is the best value and in LR 0.001 we can see that the delta-delta-mfcc with an f1 score result of 56.65% and an accuracy score of 62.50% is the best value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Domains Personalized Local Differential Privacy Frequency Estimation Mechanism for Utility Optimization

SSRN

引用

SSRN 2024年

作者： Li, Yunfei Fu, Xiaodong Liu, Li Ding, Jiaman Peng, Wei Jia, Lianyin Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Graduate School Yunnan University of Finance and Economics Kunming650221 China Yunnan Provincial Key Laboratory of Computer Technology Application Kunming University of Science and Technology Kunming650500 China

Local Differential Privacy (LDP) has garnered considerable attention in recent years because it does not rely on trusted third parties and has low interactivity and high operational efficiency. However, current LDP frequency estimation mechanisms aggregate data using different privacy budgets within the same data domain, overlooking the aggregation requirements across different data domains. This limits the potential for enhancing the data utility under fixed privacy budgets and meeting user preferences in multiple data domains and privacy budgets. To address this issue, we define a Multi-Domains Personalized Local Differential Privacy (MDPLDP) model that allows users to freely choose data domains and privacy budgets according to their privacy preferences. Furthermore, based on the MDPLDP model, two new frequency estimation mechanisms are proposed: MDPLDP-Generalized Randomized Response and MDPLDP-basic Randomized Aggregatable Privacy-Preserving Ordinal Response. These mechanisms support cross-domains data aggregation and optimize data utility by adjusting the data domains and increasing privacy budgets. Theoretical analysis reveals that these new mechanisms have lower estimation errors than the traditional LDP mechanisms. Experiments on real and synthetic datasets demonstrate that the proposed mechanisms effectively reduce estimation errors and enhance the utility of data-frequency estimation. © 2024, The Authors. All rights reserved.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

The Smart Analysis of Performing Scalable Inference for Big Data Analytics

The Smart Analysis of Performing Scalable Inference for Big ...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Bhandarkar, Vishakha D. Rongali, Aruna Sri Shamout, Mohamed Dawood Pund, Sachin Nama, Gigih Forda Patil, Shrishailappa Yeshwantrao Chavan College of Engineering Applied Mathematics and Humanities India University of the Cumberlands Graduate Doctoral Information Technology Information Technology Emphasis/Information Technology United States College of Business Administration University of Sharjah Department of Management Sharjah United Arab Emirates Shri Ramdeobaba College of Engineering and Management Department of Industrial Engineering Maharashtra Nagpur India Doctoral Program of Environtmental Science University of Lampung Department of Informatics Bandar Lampung Indonesia Vishwakarma Institute of Technology Computer Engineering Pune India

ISBN: (纸本)9798350357769

This paper examines the reproducibility of massive information analytics under particular factors. The paper proposes the 'performing Scalable Inference' technique to cope with scalability troubles and to exploit current big statistics platforms for efficient computing and statistics garage of the statistics. In particular, the paper describes how to perform leak-free, parallelizable visible analytics over massive datasets using present extensive records analytics frameworks such as Apache Flink. This method presents an automated manner to execute analytics that preserves reproducibility and the ability to make adjustments without re-running the entire technique. The paper also demonstrates how these analytics may help several real-world use instances, explore affected person cohorts for studies, and develop stratified patient cohorts for hospital therapy. In the end, the paper observes how the proposed method may be exercised within the real world. Actively scalable inference for massive information analytics is pivotal in optimizing decision-making and allocation of assets. Typically, such inferences are made based on information accumulated from numerous sources, databases, unstructured data, and different digital sources. So one can ensure scalability, a complete cloud-primarily based platform has to be hired. This solution will permit the ***, deploying the essential records series and evaluation algorithms are prime here. It could permit the platform to recognize the styles inside the statistics and discover any ability correlations or traits. Additionally, predictive analytics and system mastering strategies may be incorporated to provide insights into the results of the information. In the long run, by leveraging those techniques, the platform can draw efficient inferences and appropriately compare situations in an agile and green way.. © 2023 IEEE.

关键词： adjustments an a lytics automated preserves statistics

来源：评论

学校读者我要写书评

暂无评论

Taxonomy of rough set approaches for rule generation

Taxonomy of rough set approaches for rule generation

引用

International Conference on Engineering and Emerging Technologies (ICEET)

作者： Murni Marbun Opim Salim Sitompul Erna Budhiarti Nababan Poltak Sihombing Graduate Program of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

ISBN: (纸本)9781665427159

The rough set method is one of the well-known methods for classifying an object. The rough set method has been used since Pawlak discovered it in 1982. The rough set method can analyze data related to redundant attribute reduction, find the most significant attributes and make decision rules. This article presents a taxonomy of rough set approaches for generating rules. The rough set method in generating rules has been successfully applied in various fields, such as classification, decision analysis of medical data, manufacturing processes, machine operations, predictive data, evaluation of television sets, iris fisher data, trading stock indexes, information systems, learning database systems, scientific diagnostics, force protection, KANSEI Engineering, prediction, customization provider strategy, force stabilizer system, scientific data and vehicle traffic. Several researchers since 2000 have combined the rough set method with other methods or algorithms to get fewer rules and not reduce classification accuracy. The results of combining these methods have been shown to improve the performance of the rough set method.

关键词： TV Manufacturing processes Taxonomy Force Rough sets Prediction algorithms Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Improving Brain MRI Image Segmentation Quality: A Hybrid Technique for Intensity Inhomogeneity Correction 34

Improving Brain MRI Image Segmentation Quality: A Hybrid Tec...

引用

34th Conference of Open Innovations Association FRUCT, FRUCT 2023

作者： Aziz, Samah Abdel Hawbani, Ammar Wang, Xingfu Abdelhamid, Talaat Maolood, Ismail Y. Alsamhi, Saeed Ismail, A.S. School of Computer Science and Technology University of Science and Technology of China Hefei23002 China Zagazig University Zagazig44519 Egypt Menoufia University Faculty of Electronic Engineering Menoufia Egypt -System Information Ministry of Higher Education and Scientific Research Kurdistan Region Erbil Iraq National University of Ireland Insight Centre for Data Analytics Galway Ireland

ISBN: (纸本)9789526524603

Intensity inhomogeneity is a significant issue in magnetic resonance imaging (MRI), where the presence of bias field causes distortions in pixel values, resulting in inconsistent and erroneous intensities across the image. This artifact not only hampers accurate diagnosis by radiologists but also negatively impacts the performance of computer-aided diagnosis algorithms, particularly in tasks like segmentation. In our proposed approach, we use a hybrid technique called KIFCM, which integrates K-means and Fuzzy C-means to enhance brain tumor segmentation. K-means provides computational efficiency, while Fuzzy C-means improves accuracy by detecting missed tumor cells. We employ a bias correction method based on the level set framework, removing noise with a median filter and applying the hybrid KIFCM technique for optimal segmentation. Our method effectively addresses intensity variation challenges, ensuring precise brain tumor region segmentation. We compare our results with DFCM and MFFLs, and the comparison shows the efficiency of our proposed method by highlighting the superior quality and accuracy of 81% achieved, requiring less computational time. Consequently, our results demonstrate KIFCM's potential to boost both accuracy and speed in MRI-based brain tumor detection through computer-aided diagnosis. © 2023 FRUCT Oy.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Studying Cardiac Electrophysiology via EPSSIM

Studying Cardiac Electrophysiology via EPSSIM

引用

International Joint Conference on computer science and Software Engineering (JCSSE)

作者： Sujitra Katekarn Noppadon Sisuk Teonchit Nuamchit Kanjana Jittiporn Janjira Payakpate Department of Cardio-thoracic Technology Faculty of Allied Health Sciences Naresuan University Phitsanulok Thailand Program in Computer Engineering Faculty of Industrial Technology Phibunsongkhram Rajabhat University Phitsanulok Thailand Department of Computer Science and Information Technology Faculty of Sciences Naresuan University Phitsanulok Thailand

For Cardio-thoracic technology education program, the focus is on teaching pathophysiology, as well as the interpretation of electrocardiograms (ECG), through case studies. The curriculum includes instruction on treatment options and the use of electrophysiology studies (EP studies) for tachycardia and cardiac ablation. A portion of e-learning resources for ECGs and EP studies are delivered via web-based platforms. However, to date, there have been no e-learning platforms that combine instruction on pathological ECGs, EP study, cardiac ablation, or simulations of EP which would provide a more comprehensive learning experience for students. Therefore, the purpose of this study was to create the electrophysiology study simulator program (EPSSIM), which serves as an e-learning platform for EP studies and ECG. The development started with gathering information about ECG from the medical records of patients at a public hospital. MATLAB was used to generate synthetic heart signals. Microsoft Visual Studio 2019 was used to construct the EPSSIM program. A total of 47 cardio-thoracic technology students who used the program completed a pre-test and post-test and questionnaires. The effectiveness and satisfaction of the EPSSIM program were evaluated. The results showed that participants' scores improved, but the improvement was restricted due to the short time that the students were able to use the system. The participants who completed the satisfaction survey generally indicated satisfaction with the effectiveness of EPSSIM. Overall, the use of the application was beneficial and the application could be successfully used in future to enhance users knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extremely Weak Feedback Method for Controlling Chaotic Resonance

Extremely Weak Feedback Method for Controlling Chaotic Reson...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Takahiro Iinuma Yudai Ebato Sou Nobukawa Anh Tu Tran Nobuhiko Wagatsuma Keiichiro Inagaki Hirotaka Doho Teruya Yamanishi Haruhiko Nishimura Graduate School of Information and Computer Science’ Chiba Institute of Technology Chiba Japan Department of Computer Science Chiba Institute of Technology Chiha Japan Department of Information Science Faculty of Science Toho University Chiba Japan Department of Artificial Intelligence and Robotics Chubu University Aichi Japan Faculty of Education Teacher Training Division Kouchi University Kochi Japan Faculty of Data Science Osaka Seikei University Osaka Japan Faculty of Informatics Yamato University Osaka Japan

Chaotic resonance, resembling stochastic resonance, is induced by internal fluctuations (i.e., chaos). This phenomenon has been observed in numerous systems. The most representative form of chaotic resonance is the synchronization with respect to weak applied signals under chaos-chaos intermittency, where a chaotic orbit moves among multiple attractors. Chaotic resonance exhibits higher sensitivity than stochastic resonance, but its engineering applications are limited by concerns such as the requirement to adjust the state of chaos by internal system parameters to induce chaotic resonance rather than the external noise strength. However, achieving this adjustment is challenging, especially in biological systems. Therefore, to handle this limitation, we proposed a novel double-Gaussian-filtered reduced region of orbit (RRO) method (called the DG-RRO method) for obtaining perturbed feedback signals lower than the conventional RRO method. This DG-RRO feedback signal is determined by the inverse sign of the map function and double-Gaussian filters around the local maximum/minimum values of the map. Because of its fine local specification, the DG-RRO feedback signal induces a chaotic resonance by one-third the feedback strength of the conventional signal. This method may pave the way for using chaotic resonance in engineering applications.

关键词：

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：