检索结果-内蒙古大学图书馆

Learning Fine-Grained information with Capsule-Wise Attention for Salient Object Detection

IEEE Transactions on Multimedia 2023年 1-14页

作者： Zhao, Sanyuan Wen, Zongzheng Qi, Qi Lam, Kin-Man Shen, Jianbing School of Computer Science & Technology Beijing Institute of Technology China Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau Macau China

With the popularity of convolutional neural networks being used for salient object detection (SOD), the performance has been significantly improved. However, how to integrate crucial features for modeling salient objects needs further exploration. In this work, we propose an effective feature selection scheme to solve this task. Firstly, we provide a Simplified Atrous Spatial Pyramid Pooling (SASPP) module to lightweight the multi-scale features. Dealing with the SASSP features, we design a pixel-level local feature selection scheme named Multi-Scale Capsule-wise Attention (MSCA). It aggregates features from multi-scales by dynamic routing and helps the network to generate fine-grained prediction maps. In addition, we exploit holistic features by the Spatial-wise Attention and Channel-wise Attention (SA/CA) mechanisms, which adaptively extracts spatial or channel information. We also propose a Multi-crossed Layer Connections (MLC) structure in the upsampling stage, to fuse features from not only different levels but also different scales. The salient object prediction is performed in a coarse-to-fine manner. By conducting comprehensive experiments on five benchmark datasets, our method achieves the best performance when compared to existing state-of-the-art approaches. IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PROJECT-BASED APPROACH FOR electrical engineering EDUCATION AT ETH ZURICH 52

PROJECT-BASED APPROACH FOR ELECTRICAL ENGINEERING EDUCATION ...

引用

52nd Annual Conference of the European Society for engineering: Educating Responsible Engineers, SEFI 2024

作者： Magno, Michele Abou-Khalil, Victoria Schurgers, Curt Center for Project-Based Learning Department of Information Technology and Electrical Engineering ETH Zürich Zürich Switzerland Lausanne Switzerland Electrical and Computer Engineering Department UC San Diego CA United States

ISBN: (纸本)9782873520274

This practice paper introduces the project-based approach of the Center for Project-Based Learning within the department of information Technology and electrical engineering of ETH Zürich. This center's approach to education is built around a three-stage education model that includes projects early on in the students' educational journeys, gradually increasing their complexity in alignment with their growing level of experience. This approach ensures students develop both technical expertise and essential professional skills necessary for their engineering careers, scaffolding course work, small scale group projects and interdisciplinary flagship projects. The center is further enhanced by an evidence-based approach to continued improvement, using regular surveys, reflective journals, and research findings to refine course design and supervision. Students have reported high satisfaction levels with the courses, expressing that the projects aided their understanding of future aspirations and helped develop crucial soft skills, notably in collaboration, communication, and presentation. Projects focus on real-world applicability, ensuring students are well-prepared to tackle real-world challenges, with many focusing on contemporary problems in areas such as sustainability. © 2024 SEFI 2024 - 52nd Annual Conference of the European Society for engineering, Proceedings: Educating Responsible Engineers. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Understanding Cybercrime: A Study of Malware Analysis, Phishing Attacks, and Sentiment Trends 3

Understanding Cybercrime: A Study of Malware Analysis, Phish...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, electrical and Electronics, IITCEE 2025

作者： Kumaran, U. Sreeraag, G. Narendran, Advik Meena, V.P. Gupta, Sushil Kumar Appaji, Abhishek Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bangalore India National Institute of Technology Department of Electrical Engineering Jharkhand Jamshedpur831014 India Bms College of Engineering Department of Medical Electronics Engineering Bangalore India

ISBN: (纸本)9798331515911

With the rapid evolution of computer systems and technologies, individuals face an increasing threat of cybercrime. This research explores the changing landscape of cybercrime by focusing on three key areas: malware analysis, phishing attack analysis, and sentiment analysis. The study aims to identify malware strategies for evading detection and analyze the prevalence of spyware by examining diverse malware samples. Additionally, trend analysis highlights the rising complexity and frequency of phishing attacks, with a notable shift toward targeting reputable platforms. Sentiment analysis of media headlines surrounding data breaches uncovers a paradox: while concerns about cybersecurity remain, there is a growing confidence in the ability to manage cybersecurity crises. These findings provide insights into emerging threats and evolving public perceptions, offering a comprehensive understanding of the current cyber- crime landscape. © 2025 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Embedded Sensor Network for an Automated Radio Telescope 3

Design and Implementation of Embedded Sensor Network for an ...

引用

3rd International Conference on Robotics, electrical and Signal Processing Techniques, ICREST 2023

作者： Meah, Kala Hake, Donald Babcock, David Bosse, Eric Nelson, Blake York College of Pennsylvania Department of Electrical and Computer Engineering and Computer Science YorkPA United States

ISBN: (纸本)9798350346435

This paper presents a real-time implementation of an embedded sensor network for an automated radio telescope. The sensor network consists of accelerometers, digital motor temperature sensors, azimuth and elevation encoders, ambient temperature and humidity sensors, and an over the air wireless updating system for the microcontroller. A super loop software architecture was used to collect sensor data and update the control room operation. A custom PCB was designed for the sensor that houses the microcontroller, a wireless communication module, and peripheral circuit components. A laboratory test setup was built to collect sensor data and emulate the actual system operation. The test results validated the sensor network and system operation. © 2023 IEEE.

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Machine Learning and Deep Learning in ECG Image Analysis for Cardiovascular Disease Diagnosis 5

Exploring the Potential of Machine Learning and Deep Learnin...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Sathiya Priya, S. Angel Jean Vincy, K. Bharathi, S. Gresa, P. Sasi Manivannan, D. Sathya, V. VelTech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai600062 India Srm Institute of Science and Technology Department of Computer Science & Engineering Vadapalani Chennai26 India Velammal Engineering College Department of Information Technology Surapet Chennai India

ISBN: (纸本)9798350379945

This research proposes a novel machine learning approach to detect cardiovascular diseases (CVDs) in electrocardiogram (ECG) images. The goal is to improve diagnostic accuracy and efficiency within the healthcare system. CVDs remain the leading cause of death globally, emphasizing the importance of early and accurate diagnosis for effective treatment. ECG signals provide valuable information for assessing cardiovascular health. The methodology utilizes advanced machine learning algorithms for classification. First, it pre-processes ECG signals to extract relevant features. The results demonstrate the machine learning model's potential as a significant diagnostic tool by showcasing its accuracy in detecting various cardiovascular illnesses from ECG images. Specifically, this research leveraged the power of machine learning to predict four major heart abnormalities: arrhythmias, myocardial infarction (heart attack), heart failure, and hypertrophic cardiomyopathy. This investigation explores how different machine learning methods perform when analyzing ECG images to identify cardiovascular diseases. The primary objective is to identify the algorithm that delivers the highest accuracy in classifying ECG images for CVD detection. Decision trees are best suited for working with data organized in tables, where each entry has specific numerical values or categories. Random forests, like decision trees, are primarily designed to handle data in a tabular format with features like numbers or categories. ECG image analysis necessitates techniques adept at recognizing intricate patterns within the pixels of an image. The ultimate goal is to identify the most effective machine learning approach for accurate CVD detection using ECG images, potentially leading to improved healthcare system efficiency and patient outcomes. In the proposed system the algorithm with the highest accuracy for CVD diagnosis using ECG image analysis is the Decision Tree, achieving 59.36% accuracy. © 2024

关键词： Cardiovascular diseases (CVD) Decision Tree(DT) Deep Learning Machine Learning Random Forest(RF) Support Vector Machine(SVM)

来源：评论

学校读者我要写书评

暂无评论

Robust Fuzzy controller design for respiratory systems 10

Robust Fuzzy controller design for respiratory systems

引用

10th International Conference on Control, Instrumentation and Automation, ICCIA 2024

作者： Hossein, Noor Alhuda Farahani, Shoorangiz Shams Shamsabad Barzamini, Mehrshad Dorrimoghaddam, Farahnaz Arabian, Mohammad Barzamini, Roohollah Islamic Azad University Science and Research Branch Department of Electrical Engineering Tehran Iran Islamic Azad University Islamshahr Branch Department of Electrical Engineering Islamshahr Iran Sharif University of Technology Department of Computer Engineering Tehran Iran Department of Electrical Engineering Mashhad Iran Islamic Azad University Tehran Central Branch Department of Electrical Engineering Tehran Iran City University of London Department of Engineering London United Kingdom

ISBN: (纸本)9798331509972

A respiratory system combines a blower-hose-patient setup with a single lung system featuring nonlinear lung compliance. This paper explores the optimal design of resilient fuzzy control for such systems by integrating a fuzzy algorithm with a sliding mode control approach. The robust fuzzy controller, as proposed, effectively handles the system's dynamics and remains stable amidst nonlinear changes. It ensures airway flow and maintains peak pressure below critical levels despite uncertainties like hose leakage and varying respiratory effort. The findings show superior performance in reaction time, overshoot, and tracking errors compared to traditional methods. The control mechanism's parameters rise time, peak value, heave, and settlement values are independently computed, revealing an over 18% improvement in rise time and a more than 44% reduction in settling time. Simulations indicate the robust fuzzy controller outperforms the PID controller, demonstrating its efficacy for respiratory system control. © 2024 IEEE.

关键词： Hose

来源：评论

学校读者我要写书评

暂无评论

Automotive revolution and carbon neutrality

引用

Frontiers in Energy 2023年第6期17卷 693-703页

作者： C.C.CHAN Wei HAN Hanlei TIAN Yanbing LIU Tianlu MA C.Q.JIANG Department of Electrical and Electronic Engineering The University of Hong KongHong KongChina Sustainable Energy and Environment Thrust Hong Kong University of Science and Technology(Guangzhou)Guangzhou 511453China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologyHong KongChina Department of Electrical Engineering City University of Hong KongHong KongChina HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen 518048China

The automotive industry is in the midst of a groundbreaking revolution,driven by the imperative to achieve intelligent driving and carbon neutrality.A crucial aspect of this transformation is the transition to electric vehicles(EVs),which necessitates widespread changes throughout the entire automotive *** paper examines the challenges and opportunities of this transition,including automotive electrification,intelligence-connected transportation system,and the potential for new technologies such as hydrogen fuel ***,it discusses the key technologies and progress of the hydrogen energy industry chain in the upstream hydrogen production,midstream hydrogen storage and transportation,downstream hydrogen station construction and hydrogen fuel cells in ***,it proposes the directions for future layout,providing guidance for future development.

关键词： automotive revolution electric vehicles(EVs) hydrogen energy fuel cell

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Cryptographic Algorithm for IoT Devices based on Hybrid Architecture 3

A Lightweight Cryptographic Algorithm for IoT Devices based ...

引用

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Toma, Nadiatul Islam Kashem, Mohammod Abul Rana, Sohel Dhaka University of Engineering & Technology Department of Computer Science and Engineering Gazipur1707 Bangladesh Dhaka University of Engineering & Technology Institute of Information & Communication Technology Gazipur1707 Bangladesh

ISBN: (纸本)9798350388282

This paper introduces a new lightweight cryptographic algorithm with a hybrid architecture that is specifically designed for securing Internet of Things (IoT) devices. The hybrid architecture uses a unique combination of one-hot encoding (OHE) and substitution-permutation network (SPN) structures to encrypt data in a computationally and memory-efficient manner. The OHE technique is a method for representing categorical variables with a binary vector that provides confusion properties in the ciphertext. The SPN networks perform both linear and nonlinear operations to enhance the avalanche effect in generated round keys and encrypted ciphertext. The memory usage and execution cycle of the proposed cipher have been evaluated using the benchmark tool 'Evaluation of Lightweight Cryptography Algorithms' (FELICS). MATLAB is also utilized to test the key sensitivity of several encrypted and decrypted images using histograms and correlation graphs. The results show that the cipher provides a high level of security while being suitable for use on resource-constrained IoT devices. Hence, the proposed cipher can be a security solution for various IoT applications, such as smart homes, healthcare, and industrial automation. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Cost-Effective Autonomous Beach Cleaning Rover Using Deep Learning 1

引用

6th International Conference on information Systems and Management science, ISMS 2023

作者： Girish, S. Harikrishnan, S. Nair, Rahul H. Sreerajan, Midhun Sathyan, Soumya Pandi, V. Ravikumar Valsan, Vipina Suresh, Kavya Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9783031664106

ISBN: (纸本)9783031664090

This work aims to transform beach garbage management by developing an autonomous rover that utilizes deep learning and computer vision. The main goal is to enable the rover to traverse coastal environments on its own while using its sophisticated onboard camera to identify various waste products. The rover will identify different sorts of rubbish by employing the YOLO algorithm that uses the Bounding Box Regression technique to improve waste management tactics. The work involves hardware design, neural network training, real-time computer vision integration, and extensive field testing. The hardware components of the rover are carefully engineered through iterative development, guaranteeing smooth mobility and efficient data collection. By incorporating real-time computer vision techniques, the rover will be able to evaluate visual data and make decisions that will help identify waste. In order to verify the project’s effectiveness in tackling beach pollution field testing is carried out to confirm the rover’s accuracy in navigation and waste detection. An autonomous rover that embodies technical innovation for long-term, environmentally sustainable preservation is successfully developed. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

XEMLPD: an explainable ensemble machine learning approach for Parkinson disease diagnosis with optimized features

引用

International Journal of Speech Technology 2024年第4期27卷 1055-1083页

作者： Khanom, Fahmida Biswas, Shuvo Uddin, Mohammad Shorif Mostafiz, Rafid Department of Mathematics American International University – Bangladesh 408/1 Kuratoli Dhaka Khilkhet1229 Bangladesh Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Santosh Bangladesh Department of Computer Science and Engineering Jahangirnagar University Savar Bangladesh Institute of Information Technology Noakhali Science and Technology University Noakhali Bangladesh

Parkinson's disease (PD) is a progressive neurological disorder that gradually worsens over time, making early diagnosis difficult. Traditionally, diagnosis relies on a neurologist's detailed assessment of the patient's medical history and multiple scans. Recently, artificial intelligence (AI)-based computer-aided diagnosis (CAD) systems have demonstrated superior performance by capturing complex, nonlinear patterns in clinical data. However, the opaque nature of many AI models, often referred to as "black box" systems, has raised concerns about their transparency, resulting in hesitation among clinicians to trust their outputs. To address this challenge, we propose an explainable ensemble machine learning framework, XEMLPD, designed to provide both global and local interpretability in PD diagnosis while maintaining high predictive accuracy. Our study utilized two clinical datasets, carefully curated and optimized through a two-step data preprocessing technique that handled outliers and ensured data balance, thereby reducing bias. Several ensemble machine learning (EML) models—boosting, bagging, stacking, and voting—were evaluated, with optimized features selected using techniques such as SelectedKBest, mRMR, PCA, and LDA. Among these, the stacking model combined with LDA feature optimization consistently delivered the highest accuracy. To ensure transparency, we integrated explainable AI methods—SHapley Adaptive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME)—into the stacking model. These methods were applied post-evaluation, ensuring that each prediction is accompanied by a detailed explanation. By offering both global and local interpretability, the XEMLPD framework provides clear insights into the decision-making process of the model. This transparency aids clinicians in developing better treatment strategies and enhances the overall prognosis for PD patients. Additionally, our framework serves as a valuable tool for clinical data

关键词： CAD systems Ensemble machine learning Explainable AI Feature optimization Parkinson's disease

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：