检索结果-内蒙古大学图书馆

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Computationally efficient reductions between some statistical models 36

Computationally efficient reductions between some statistica...

引用

36th International Conference on Algorithmic Learning Theory, ALT 2025

作者： Lou, Mengqi Bresler, Guy Pananjady, Ashwin School of Industrial and Systems Engineering Georgia Tech United States Department of Electrical Engineering and Computer Science MIT United States Schools of Industrial and Systems Engineering and Electrical and Computer Engineering Georgia Tech United States

We study the problem of approximately transforming a sample from a source statistical model to a sample from a target statistical model without knowing the parameters of the source model, and construct several computationally efficient such reductions between canonical statistical experiments. In particular, we provide computationally efficient procedures that approximately reduce uniform, Erlang, and Laplace location models to general target families. We illustrate our methodology by establishing nonasymptotic reductions between some canonical high-dimensional problems, spanning mixtures of experts, phase retrieval, and signal denoising. Notably, the reductions are structure-preserving and can accommodate missing data. We also point to a possible application in transforming one differentially private mechanism to another. © 2025 M. Lou, G. Bresler & A. Pananjady.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

The TMAP Framework: Describing the Design Space of Technology-Mediated Audience Participation in Live Music

引用

IEEE Access 2025年 13卷 38593-38608页

作者： Hödl, Oliver Turchet, Luca University of Vienna Faculty of Computer Science Cooperative Systems Research Group Vienna1090 Austria University of Applied Sciences Upper Austria Department for Smart and Interconnected Living Hagenberg4232 Austria University of Trento Department of Information Engineering and Computer Science Trento38123 Italy

Technology-mediated audience participation (TMAP) offers a wide variety of ways to enhance the involvement of spectators during a music performance. Technological change has created rich new opportunities for such interactive performance experiences. Effective design of TMAP requires balancing knowledge from diverse human and technological perspectives and taking into account very different characteristics and requirements in live music performance. However, research in this distinctive area of interaction design is limited, and the provision of practical guidance for designers has been scarcely addressed thus far. To bridge this gap, we propose the TMAP Framework, which describes the design space of audience participation in a practice-oriented way to support design-related processes. This descriptive framework is grounded on existing literature from the last 25 years, and has been iteratively improved and peer reviewed with different experts. It was validated using actual TMAP performances not included in the framework development. The TMAP Framework contains 180 entities in a tree-like sorted structure on four levels. Alongside the contribution to knowledge of extensively describing the design space of TMAP in live music, with the validation of the framework, we demonstrate its completeness, stability and generalisability. In this regard, the framework may also serve as a common language between different perspectives and practitioners, thus addressing the highly interdisciplinary nature of the TMAP field. © 2013 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Topology, Size, and Shape Optimization in Civil engineering Structures: A Review

引用

computer Modeling in engineering & sciences 2025年第2期142卷 933-971页

作者： Ahmed Manguri Hogr Hassan Najmadeen Saeed Robert Jankowski Faculty of Civil and Environmental Engineering Gdansk University of TechnologyGdansk80-223Poland Department of Computer Science ModelingElectronics and Systems EngineeringUniversity of CalabriaCosenza87036Italy Civil Engineering Department University of RaparinRania46012Iraq Civil Engineering Department Tishk International UniversityErbil44001Iraq

The optimization of civil engineering structures is critical for enhancing structural performance and material efficiency in engineering *** optimization approaches seek to determine the optimal design,by considering material performance,cost,and structural *** design approaches aim to reduce the built environment’s energy use and carbon *** comprehensive review examines optimization techniques,including size,shape,topology,and multi-objective approaches,by integrating these *** trends and advancements that contribute to developing more efficient,cost-effective,and reliable structural designs were *** review also discusses emerging technologies,such as machine learning applications with different optimization *** of truss,frame,tensegrity,reinforced concrete,origami,pantographic,and adaptive structures are covered and *** techniques are explained,including metaheuristics,genetic algorithm,particle swarm,ant-colony,harmony search algorithm,and their applications with mentioned structure *** and non-linear structures,including geometric and material nonlinearity,are *** role of optimization in active structures,structural design,seismic design,form-finding,and structural control is taken into account,and the most recent techniques and advancements are mentioned.

关键词： Structural optimization topology optimization size optimization shape optimization multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Psychological Impact of Internet Blackouts: A Case Study With Machine Learning-Based Stress Analysis

引用

IEEE Access 2025年 13卷 83505-83527页

作者： Islam, Mohammad Ariful Islam, Tahidul Hossain, Gahangir Mofazzal Hossain, M. The University of Melbourne Department of Computing and Information Systems MelbourneVIC3010 Australia Bangladesh University of Engineering and Technology Department of Computer Science and Engineering Dhaka1000 Bangladesh University of North Texas Department of Data Science DentonTX76205 United States Southeast University Department of Electrical and Electronic Engineering Dhaka1208 Bangladesh

Access to the internet has become a vital part of modern life, especially for communication and essential services. However, during politically sensitive times, internet blackouts can disrupt daily routines, leading to significant psychological impacts. This study explores the mental health effects of the internet shutdown imposed during the Bangladesh Quota Movement in July 2024, when the government cut off access to control information flow. The blackout hindered communication, financial transactions, and critical services, amplifying stress, feelings of isolation, and emotional distress. A survey of 2,085 participants was conducted to assess the behavioral, emotional, and psychological consequences, particularly in academic, work, and social settings. Stress levels among respondents varied from minimal to extreme, reflecting widespread mental distress. To classify these stress levels, machine learning models;Decision Tree (DT), Random Forest (RF), Bernoulli Naive Bayes (BNB), Logistic Regression (LR), eXtreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM) were applied. The SVM model outperformed others, achieving high precision (99.33%), recall (99.00%), F1-score (99.33%), and accuracy (99.49%). This study underscores the urgent need for mental health support during such crises, particularly in low- and middle-income countries like Bangladesh, where mental health care is often neglected. These findings are aligned with Sustainable Development Goal (SDG 3), "Good Health and Well-Being," stressing the importance of mental health interventions in fostering resilience, well-being, and social stability during crises. © 2013 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Mango Disease Detection Using Fused Vision Transformer with ConvNeXt Architecture

引用

computers, Materials & Continua 2025年第4期83卷 1023-1039页

作者： Faten S.Alamri Tariq Sadad Ahmed S.Almasoud Raja Atif Aurangzeb Amjad Khan Department of Mathematical Sciences College of SciencePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science University of Engineering&TechnologyMardan23200Pakistan AIDA Lab Department of Information SystemsCollege of Computer&Information SciencesPrince Sultan UniversityRiyadh12435Saudi Arabia Department of Computer Science International Islamic UniversityIslamabad44000Pakistan

Mango farming significantly contributes to the economy,particularly in developing ***,mango trees are susceptible to various diseases caused by fungi,viruses,and bacteria,and diagnosing these diseases at an early stage is crucial to prevent their spread,which can lead to substantial *** development of deep learning models for detecting crop diseases is an active area of research in smart *** study focuses on mango plant diseases and employs the ConvNeXt and Vision Transformer(ViT)*** datasets were *** first,MangoLeafBD,contains data for mango leaf diseases such as anthracnose,bacterial canker,gall midge,and powdery *** second,SenMangoFruitDDS,includes data for mango fruit diseases such as Alternaria,Anthracnose,Black Mould Rot,Healthy,and Stem and *** datasets were obtained from publicly available *** proposed model achieved an accuracy of 99.87%on the MangoLeafBD dataset and 98.40%on the MangoFruitDDS *** results demonstrate that ConvNeXt and ViT models can effectively diagnose mango diseases,enabling farmers to identify these conditions more *** system contributes to increased mango production and minimizes economic losses by reducing the time and effort needed for manual ***,the proposed system is integrated into a mobile application that utilizes the model as a backend to detect mango diseases instantly.

关键词： ConvNeXt model fusion mango disease smart agriculture vision transformer

来源：评论

学校读者我要写书评

暂无评论

Empirical techniques for effort estimation in designing effective ML models

引用

International Journal of computers and Applications 2025年第2期47卷 226-234页

作者： Padmanabha Reddy, Y.C.A. Kosuru, Sai Sathwik Sirisalla, Nageswara Rao Vivekananda, G.N. Perala, Venkata Akanksha Department of Artificial Intelligence and Machine Learning Chaitanya Bharati Institute of Technology Telangana Hyderabad India Department of CSE B V Raju Institute of Technology Telangana Narsapur India Department of Computer Science and Engineering K.S.R.M. College of Engineering AP Kadapa India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

Machine Learning Research often involves the use of diverse libraries, modules, and pseudocodes for data processing, cleaning, filtering, pattern recognition, and computer intelligence. Quantization of Effort Required for the above cumulative processes is rarely discussed in the existing works and The time to reach the desired level of the model's functionality is essential to gauge the environment training for the model training and pre-deployment testing. In this study, we empirically defined the manual-cum-computational effort required for the model development in terms of 2-time factors: time-to-live (time until 1st code modification) and time-for-modification (time between 2 codebase changes) taken together in a mathematical model to compute Effort Factor(quantitative measure of determining effort needed to design ML algorithms). The study is novel in terms of how the effort required to create ML models is calculated with a particular focus on the manual effort direction. The results and the findings obtained can be used for determining the total time needed to synthesize ML models and frameworks in terms of code change cycles and implementation strategies marking a 25% performance increase in the current method above the Standard Pipeline. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pipeline codes

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Can i Get There? Negotiated User-to-User Teleportations in Social VR

引用

IEEE Transactions on Visualization and computer Graphics 2025年第5期31卷 2320-2330页

作者： Wang, Miao Shu, Wen-Tong Li, Yi-Jun Li, Wanwan School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Zhongguancun Laboratory Beijing100094 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Tandy School of Computer Science University of Tulsa Tulsa United States

The growing adoption of social virtual reality (VR) platforms underscores the importance of safeguarding personal VR space to maintain user privacy and security. Teleportation, a prevalent instantaneous locomotion method in VR, facilitates user engagement but can also inadvertently intrude upon personal VR space, thereby raising privacy concerns. This paper introduces three innovative negotiated teleportation techniques designed to secure user-to-user teleportation and protect personal space privacy, all under a unified small-group development framework. We have designed and evaluated three types of negotiated teleportation techniques: Sector technique for directional control, Distance technique for minimum social distance control, and Area technique for defining circular permissible teleportation areas. These techniques foster a collaborative approach to selecting teleportation points that respect personal space. To evaluate the efficacy of these techniques, we conducted a user study with 20 participants who performed social tasks within a virtual campus environment. The findings demonstrate that our techniques significantly enhance privacy protection and alleviate anxiety associated with unwanted proximity in social VR. © 1995-2012 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

MediGuide AI using Machine Learning 2

MediGuide AI using Machine Learning

引用

2nd International Conference on Machine Learning and Autonomous systems, ICMLAS 2025

作者： Pooja, R. Elugubanti, Nikitha Mary Shiba, C. Kalai priya, V. Sasirekha, K. Sabapathy, S Rathana R.M.K Engineering College Computer Science and Business Systems Tiruvallur District Kavaraipettai India R.M.K Engineering College Department Of Computer Science and Business Systems Kavaraipettai India R.M.K College of Engineering and Technology Department Of Computer Science and Engineering Tiruvallur District Puduvoyal India R.M.D Engineering College Department Of Computer Science and Business Systems Kavaraipettai India Dhaanish Ahmed College of Engineering Department Of Computer Science and Engineering Vanchuvanchery Chennai India

ISBN: (纸本)9798331505745

Providing diverse patient groups with their specific medication requirements, using a wide range of drugs, poses meaningful challenges for prescribing. Standardized approaches often lead to large waste, many side effects and suboptimal outcomes. Therefore, we need improved, more personalized healthcare. MediGuide AI's drug recommendation system is powered by machine learning and it offers a thorough solution. Optimized data pre-processing and analysis, leading to the desired outcome, is achieved using advanced machine learning algorithms like Naive Bayes, TF-IDF and the Natural Language Toolkit. Highly personalized prescriptions are generated using thorough patient data, including demographics and meaningful clinical factors to achieve substantially better accuracy. Important enhancements include dual recommendation outputs, which provide many drug recommendations alongside a large number of alternative Ayurvedic treatments presented side by side for effortless comparison. An advanced personalized dosage calculation module precisely determines drug dosages using advanced regression models based on age, weight and metabolism. This system helps patients track and record their medications and it also suggests several nearby Ayurvedic shops based on their location. MediGuide AI employs exceptionally powerful algorithms and its advanced tools deliver remarkably precise and exceptionally user-friendly healthcare solutions. Current systems make use of rule-based methods that cannot learn from new data, whereas MediGuide AI leverages a hybrid Naïve Bayes and PassiveAggressiveClassifier model for higher accuracy and real-time adaptability. It also includes Ayurvedic options to ensure personalized healthcare experience. © 2025 IEEE.

关键词： Drug dosage

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：