检索结果-内蒙古大学图书馆

Feature fusion-based hand gesture classification with time-domain descriptors and multi-level deep attention network

引用

Applied Soft Computing 2025年 178卷

作者： Ömer Faruk Alçin Deniz Korkmaz Hakan Acikgoz Department of Software Engineering Faculty of Engineering Inonu University Malatya 44210 Turkey Department of Electrical and Electronics Engineering Faculty of Engineering and Natural Sciences Malatya Turgut Ozal University Malatya 44210 Turkey Department of Software Engineering Faculty of Engineering Architecture and Design Kahramanmaras Istiklal University Kahramanmaras 46050 Turkey

In conventional human-robot interaction (HRI), it is difficult to provide adaptability by located systems in the human body. Surface Electromyography (sEMG) signals have the potential to meet adaptability in HRI by directly representing movements, and classifying hand gestures with sEMG can be an effective solution to meet the increasing needs of these applications. In this paper, a hybrid and multi-scale convolutional neural network (CNN) model is proposed to obtain an efficient sEMG-based classification approach of human hand gestures. The proposed method includes an effective feature extraction process, including spectral moments, sparseness, irregularity factor, Teager–Kaiser energy, Shannon entropy, Katz fractal dimension, and Higuchi’s fractal dimension, and waveform length. The obtained features are then converted to RGB images. The designed network is built on multi-scale convolutional blocks with residual learning and convolutional blocks, including the CBAM to improve the network performance by focusing on channel and spatial features. Furthermore, a pyramid non-pooling local block is utilized at the end of the network to learn more powerful features and their correlations. Five comprehensive publicly available datasets are evaluated in the experiments, and the obtained results are compared with the benchmark CNN models and network variations with different attention mechanisms. In the comparative evaluations, the CBAM achieves a classification accuracy between 84.62 % and 97.56 % while other attention mechanism results give accuracy values between 82.88 % and 97.17 %. The experiments show that the proposed method gives more accurate and robust classification performance compared with other variations and benchmark models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bubble dynamics and structural damage caused by underwater explosion

引用

International Journal of Mechanical Sciences 2025年 297-298卷

作者： Li, Hailong Zhang, Jingyuan Wang, Longkan Li, Bing Zhang, Zhifan Zhang, Guiyong Zong, Zhi State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Naval Architecture Engineering Dalian University of Technology Dalian116024 China China Ship Research and Development Academy Beijing100192 China 91439 Troops Liaoning Dalian116041 China Collaborative Innovation Center for Advanced Ship and Deep-Sea Exploration Shanghai200240 China Fuyao University of Science and Technology Fuzhou350100 China

In ocean engineering, curved structures are commonly used in various marine applications, including unmanned underwater vehicles (UUVs) and autonomous underwater vehicles (AUVs). However, the interaction between underwater explosions (UNDEX) and such elastic-plastic curved structures remains insufficiently understood, particularly regarding bubble dynamics and water jet loading near deformable boundaries. To address this gap, this study presents a combined experimental and numerical investigation of UNDEX near an elastic-plastic curved double-hull structure—a configuration that has received limited prior attention. Shockwave and bubble pulsation pressures were recorded using pressure sensors, and bubble motion and jet formation were captured via high-speed imaging. Numerical simulations using the coupled Eulerian-Lagrangian (CEL) method were performed to complement the experiments, covering 63 representative cases. Compared to shockwave loading alone, the combined action of shockwave, bubble, and water jet increased the outer hull deflection by 184 %, highlighting the critical role of multi-source interactions. Two key parameters—distance parameter (γ) and ring rib position (β)—were systematically varied to assess their influence on bubble behavior, jet dynamics, and structural damage. This study contributes new insights into the emergence of mutually deviating water jets and proposes a classification of six typical bubble shapes, four fundamental jet units, and five distinct jet types near elastic-plastic boundaries. These findings enhance the understanding of fluid-structure interaction (FSI) under multi-source loading and reveal the structural vulnerability associated with bubble pulsation and jet impact. The results underscore the importance of considering these coupled effects in the design and protection of marine structures exposed to underwater explosions. © 2025

关键词： Marine applications

来源：评论

学校读者我要写书评

暂无评论

Joint high-resolution feature learning and vessel-shape aware convolutions for efficient vessel segmentation

引用

Computers in Biology and Medicine 2025年 191卷 109982-109982页

作者： Zhang, Xiang Zhu, Qiang Hu, Tao Guo, Song Bian, Genqing Dong, Wei Hong, Rao Lin, Xia Ling Wu, Peng Zhou, Meili Yan, Qingsen Mohi-ud-din, Ghulam Ai, Chen Li, Zhou College of Information and Control Engineering Xi'an University of Architecture and Technology Xi'an China Shaanxi Provincial Key Lab of Bigdata of Energy and Intelligence Processing School of Physics and Electronic Information Yanan University Yanan China School of Computer Science and Engineering Northwestern Polytechnical University Xi'an China School of Software Nanchang University Nanchang China School of Cyber Security Zhejiang University Hangzhou China Department of Basic Education and Research Jiangxi Police College Nanchang China Northwestern Polytechnical University China

Clear imagery of retinal vessels is one of the critical shreds of evidence in specific disease diagnosis and evaluation, including sophisticated hierarchical topology and plentiful-and-intensive capillaries. In this work, we propose a new topology- and shape-aware model named Multi-branch Vessel-shaped Convolution Network (MVCN) to adaptively learn high-resolution representations from retinal vessel imagery and thereby capture high-quality topology and shape information thereon. Two steps are involved in our pipeline. The former step is proposed as Multiple High-resolution Ensemble Module (MHEM) to enhance high-resolution characteristics of retinal vessel imagery via fusing scale-invariant hierarchical topology thereof. The latter is a novel vessel-shaped convolution that captures the retinal vessel topology to emerge from unrelated fundus structures. Moreover, our MVCN of separating such topology from the fundus is a dynamical multiple sub-label generation via using epistemic uncertainty, instead of manually separating raw labels to distinguish definitive and uncertain vessels. Compared to other existing methods, our method achieves the most advanced AUC values of 98.31%, 98.80%, 98.83%, and 98.65%, and the most advanced ACC of 95.83%, 96.82%, 97.09%,and 96.66% in DRIVE, CHASE_DB1, STARE, and HRF datasets. We also employ correctness, completeness, and quality metrics to evaluate skeletal similarity. Our method's evaluation metrics have doubled compared to previous methods, thereby demonstrating the effectiveness thereof. © 2025 Elsevier Ltd

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

AccessAnalysis - A tool for measuring the appropriateness of access modifiers in Java systems

AccessAnalysis - A tool for measuring the appropriateness of...

引用

2012 IEEE 12th International Working Conference on Source Code Analysis and Manipulation, SCAM 2012

作者： Zoller, Christian Schmolitzky, Axel Software Engineering and Software Architecture Department of Informatics University of Hamburg Hamburg Germany

ISBN: (纸本)9780769547831

Access modifiers allow Java developers to define package and class interfaces tailored for different groups of clients. According to the principles of information hiding and encapsulation, the accessibility of types, methods, and fields should be as restrictive as possible. However, in programming practice, the potential of the given possibilities seems not always be fully exploited. Access Analysis is a plug-in for the Eclipse IDE that measures the usage of access modifiers for types and methods in Java. It calculates two metrics, Inappropriate Generosity with Accessibility of Types (IGAT) and Inappropriate Generosity with Accessibility of Methods (IGAM), which represent the degree of deviation between actual and necessary access modifiers. As an approximation for the necessary access modifier, we introduce the notion of minimal access modifiers. The minimal access modifier is the most restrictive access modifier that allows all existing references to a type or method in the entire source code of a system. Access Analysis determines minimal access modifiers by static source code analysis using the build-in Java DOM/AST API of Eclipse. © 2012 IEEE.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

PARALLEL SUPERCOMPUTER architectureS AND THEIR PROGRAMMING-MODELS

引用

PARALLEL COMPUTING 1994年第10-11期20卷 1443-1470页

作者： GILOI, WK GMD Research Institute for Computer Architecture and Software Engineering (FIRST) Rudower Chaussee 5 12489 Berlin Germany

The paper presents a taxonomy of the existing forms of parallel computer architectures, based on the characteristics of the hardware architecture and the abstract machine layered upon it. The abstract machine reflects the programming models provided. The main classes of hardware architectures are: physically shared memory systems and distributed memory systems. Distributed memory systems may be remote memory access architectures or message passing architectures. The major forms of abstract machine architecture are: message passing systems and logically shared memory architectures. Three solutions for logically shared memory architectures are known (1) distributed shared memory architectures, (2) multi-threaded architectures, and (3) virtual shared memory architectures. All three types are discussed in detail under the aspects of performance, programmability, and scalability, and their corresponding programming paradigms are characterized. The implications of the three concepts on node architecture and the requirements of latency minimization or latency hiding are discussed and illustrated by examples taken from pioneering realizations of the three kinds of architecture such as DASH, *T, and MANNA.

关键词： MASSIVELY PARALLEL DISTRIBUTED MEMORY architectureS SHARED-MEMORY AND MESSAGE-PASSING PROGRAMMING MODELS DISTRIBUTED SHARED MEMORY architectureS VIRTUAL SHARED MEMORY architectureS DATA CONSISTENCY AND SYNCHRONIZATION PARALLELIZATION TOOLS, PARALLELIZING COMPILERS MORE ABSTRACT PROGRAMMING MODELS

来源：评论

学校读者我要写书评

暂无评论

Understanding and addressing the essential costs of evolving systems

引用

BELL LABS TECHNICAL JOURNAL 2000年第2期5卷 44-54页

作者： Davison, JW Mancl, DM Opdyke, WF AMPS/PCS Software Engineering Department Lucent Technologies/Bell Labs Naperville Illinois Software Development Environment Group Software Process and Test Technology Department Bell Labs Murray Hill New Jersey Intelligent Network Architecture and Internet Software Department Lucent Technologies/Bell Labs Naperville Illinois

A major attribute of telecommunications software systems is change. For evolving telecom systems, significant expertise is needed to effectively handle and capitalize on these changes. This paper discusses some of the key dimensions of change that occur during telecom systems software development, the areas of expertise that software developers apply in managing these changes, and some of the means by which high-performing project members have overcome the learning curves associated with these systems. We base our results on data gathered from several Bell Labs multiyear development projects and interviews with experienced staff.

关键词： software engineering

来源：评论

学校读者我要写书评

暂无评论

Criminal emotion detection framework using convolutional neural network for public safety

引用

Scientific Reports 2025年第1期15卷 1-18页

作者： Raval, Jay Jadav, Nilesh Kumar Tanwar, Sudeep Pau, Giovanni Alqahtani, Fayez Tolba, Amr Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad 382481 India Department of Computer Engineering - AI ML & DS Marwadi University Rajkot 360003 India Faculty of Engineering and Architecture Kore University of Enna Enna 94100 Italy Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh 12372 Saudi Arabia Computer Science Department Community College King Saud University Riyadh 11437 Saudi Arabia

In the era of rapid societal modernization, the issue of crime stands as an intrinsic facet, demanding our attention and consideration. As our communities evolve and adopt technological advancements, the dynamic landscape of criminal activities becomes an essential aspect that requires careful examination and proactive approaches for public safety application. In this paper, we proposed a collaborative approach to detect crime patterns and criminal emotions with the aim of enhancing judiciary decision-making. For the same, we utilized two standard datasets - a crime dataset comprised of different features of crime. Further, the emotion dataset has 135 classes of emotion that help the AI model to efficiently find criminal emotions. We adopted a convolutional neural network (CNN) to get first trained on crime datasets to bifurcate crime and non-crime images. Once the crime is detected, criminal faces are extracted using the region of interest and stored in a directory. Different CNN architectures, such as LeNet-5, VGGNet, RestNet-50, and basic CNN, are used to detect different emotions of the face. The trained CNN models are used to detect criminal emotion and enhance judiciary decision-making. The proposed framework is evaluated with different evaluation metrics, such as training accuracy, loss, optimizer performance, precision-recall curve, model complexity, training time, and inference time. In crime detection, the CNN model achieves a remarkable accuracy of 92.45% and in criminal emotion detection, LeNet-5 outperforms other CNN architectures by offering an accuracy of 98.6%. © The Author(s) 2025.

关键词： Artificial intelligence Convolutional neural networks Deep learning Face emotion detection Public safety

来源：评论

学校读者我要写书评

暂无评论

Dependencies, traceability and consistency in software architecture: Towards a view-based perspective 11

Dependencies, traceability and consistency in software archi...

引用

5th European Conference on software architecture, ECSA 2011 - Workshop on Traceability, Dependencies and software architecture, TDSA 2011, 1st International Workshop on software architecture Variability, SAVA 2011

作者： Galster, Matthias Software Engineering and Architecture Group University of Groningen Netherlands

ISBN: (纸本)9781450306188

Managing dependencies between software development artifacts helps achieve traceability and consistency in software-intensive systems. Traceability supports the alignment between different stakeholder concerns, development artifacts, and various products of the software development process. Consistency ensures that different software development artifacts are used in different parts of a software-intensive system (or in the description of this system), without causing contradictions between the different parts of the system (or its description). In this position paper we explore how software architecture viewpoints and views can help represent dependencies and facilitate traceability and consistency in software architecture. Here, correspondences, which are parts of viewpoint definitions, express consistency, traceability, dependencies, obligations, etc. in the architecture. We provide examples of viewpoints and their mechanisms to support the description of dependencies. Furthermore, based on our experience we discuss challenges that occur when ensuring traceability, consistency, and managing dependencies between software development artifacts, with an emphasis on software architecture elements. Copyright © 2011 ACM.

关键词： software architecture

来源：评论

学校读者我要写书评

暂无评论

Who will rob you on the digital highway?

引用

COMMUNICATIONS OF THE ACM 2004年第5期47卷 56-60页

作者： Slewe, T Hoogenboom, M Managing consultant specializing in security and architecture Capgemini The Netherlands. Principal consultant specializing in connecting architecture studies to software engineering projects Capgemini The Netherlands

In the not-so-distant past, bandits and highwaymen frequently roamed themajor transportation routes robbing travelers and the pony express of gold, money, and otherprecious assets. In the current digital age, except for few retail transactions where paper money orcoins are used, money and money flows are represented by information about financial assets owned,owed, or transferred to another party. When information is no longer isolated, surrounded by thickwalls, or guarded by armed security personnel, and never locked in a safe, it seems an almostimpossible task to provide security for money.

关键词： Financial services industry Internet banking Banking industry Communication & technology Electronic commerce Data protection Internet industry

来源：评论

学校读者我要写书评

暂无评论

Enhancement effect of casing on underwater explosion shock wave and bubble

引用

Applied Ocean Research 2025年 158卷

作者： Zhang, Zhifan Zhang, Jingyuan Li, Hailong Liu, Gangwei Wang, Longkan Zhang, Guiyong State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Naval Architecture Engineering Dalian University of Technology Dalian116024 China Naval University of Engineering Wuhan430030 China Xi'an Modern Chemistry Research Institute Xi'an710065 China Collaborative Innovation Center for Advanced Ship and Deep-Sea Exploration Shanghai200240 China China Ship Research and Development Academy Beijing100192 China

The casing is a critical design factor for underwater weapons, significantly influencing the energy output of underwater explosion (UNDEX) charges. In this study, a numerical model for cased charge UNDEX was developed using the coupled Eulerian-Lagrangian (CEL) method. To optimize the shock wave and bubble energy outputs, the effects of the thickness ratio n and casing material on load characteristics were systematically investigated, and optimal parameters were derived. First, the enhancement effects of the thickness ratio n on shock wave and bubble loads were examined at varying distance parameters δ. Subsequently, the influence of n on the spatial distribution of shock wave and bubble loads was analyzed using a two-way analysis of variance (ANOVA) model. Four typical underwater weapon casing materials - Ti6%Al4%V, Cu-OFHC, Al 6061-T6, Q235 - were selected. Their impacts on key parameters, including peak shock wave overpressure, bubble radius, bubble period, bubble shape, and pulsation pressure, were thoroughly evaluated. This study aims to elucidate the spatial and temporal evolution laws of shock wave and bubble loads for different types of cased charges, providing insights into the design and optimization of underwater weapons. © 2025

关键词： Ternary alloys

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

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

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：