检索结果-内蒙古大学图书馆

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

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

Deep neural network-based secure healthcare framework

引用

Neural Computing and Applications 2024年第28期36卷 17467-17482页

作者： Aldaej, Abdulaziz Ahanger, Tariq Ahamed Ullah, Imdad College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj11942 Saudi Arabia Management Information Systems Department CoBA Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia School of Computer Science Faculty of Engineering The University of Sydney SydneyNSW2006 Australia

Healthcare stands out as a critical domain profoundly impacted by Internet of Things (IoT) technology, generating vast data from sensing devices as IoT applications expand. Addressing security challenges is paramount for a successful IoT healthcare framework, with blockchain technology offering a decentralized structure for robust data protection and secure data exchange within multi-node IoT networks. The research introduces a secure IoT healthcare diagnostic model empowered by deep neural networks, emphasizing encryption, safe transactions, and healthcare diagnostics as key components. Notably, the model incorporates innovative techniques like the orthogonal particle swarm optimization algorithm for sharing medical images and a neighborhood indexing sequence method for hash value encryption. The development of an optimized deep neural network-based classification model for illnesses, validated through extensive trials, demonstrates superior performance metrics compared to existing decision-making techniques, with significant improvements in f-Measure (96.25%), sensitivity (93.26%), specificity (94.26%), and accuracy (93.26%). This study’s scientific contribution lies in its innovative approach to securing IoT-healthcare diagnosis models, validated performance enhancements using real-world datasets, and insightful recommendations for future research directions, fostering advancements in healthcare technology for enhanced patient care and system efficiency. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance of Machine Learning Models for Dynamic Resource Allocation in NFV 3

Evaluating the Performance of Machine Learning Models for Dy...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Gamal, Gameel Al-Shaikh, Marya Saeed, Mogeeb A. Hazza'a, Ahmed G. Alomary, Ahmed Alshehabi, Reem Taiz University Al-Saeed Faculty of Engineering & It Computer Network and Distributed Systems Dep Yemen

ISBN: (纸本)9798350305333

Network Function Virtualization (NFV) is an emerging architecture that leverages virtualization technology to decouple software from hardware. The management of virtual network functions (VNFs) poses a significant challenge in NFV, given the dynamic nature of the system. Resource allocation to VNFs must adjust to accommodate varying traffic loads, but this process can lead to substantial delays. To address this issue, resource estimation models can be applied to predict the resources required for each VNF and optimize dynamic resource allocation. Our study utilized machine learning (ML) techniques to train models using real data from VNFs, encompassing performance metrics and resource needs. The models, once trained, were successful in accurately forecasting the necessary resources for handling particular traffic loads concerning each VNF. The evaluation utilizing real-world data demonstrates the importance of selecting a good model for dynamic resource allocation by contrasting seventeen different ML algorithms with a common fixed allocation model. Using FRA in particular could lead to significant resource over-allocation, a high number of VNF instances, and needless high delay, all of which could lead to high prices and poor service quality. Although linear approximation performs admirably in the assessment, more potent techniques like KNN, SVR, or Boosting outperform it because they can more precisely forecast the actual VNF resource requirements. Overall, using ML to allocate resources dynamically can help cut down on resource waste while enhancing service quality. © 2023 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Robust In-Vehicle Diagnostic-Based Intrusion Detection System

Robust In-Vehicle Diagnostic-Based Intrusion Detection Syste...

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Shafee, Ahmed Awaad, Tasneem A. Moro, Ahmed Adams State University Department of Engineering and Computer Science AlamosaCO United States Ain Shams University Faculty of Engineering Department of Computer and Systems Engineering Cairo Egypt Siemens Eda Cairo Egypt Siemens Digital Industries Software Integrated Electrical Systems Segment Cairo Egypt

ISBN: (纸本)9798350364910

Cybersecurity has become a significant concern for automotive manufacturers as modern cars increasingly incorporate electronic components. Electronic Control Units (ECUs) have evolved to become the central control units for critical car functions such as engines and brakes, experiencing rapid technological advancements. However, this swift progression in ECU technology has also made them prime targets for cyber attacks. This vulnerability has spurred researchers to focus on securing ECUs. Numerous studies have proposed intrusion detection systems (IDS) to protect against attacks on ECUs in vehicles. Yet, these IDSs are not impenetrable;attackers can exploit them by launching evasion attacks, which can trigger numerous false positive alarms. Such false alarms can be disruptive and potentially hazardous for drivers. Additionally, attackers can evade IDSs from detecting malicious data that can cause harm to the vehicle. Accordingly, in this paper, we propose a novel training framework to train a robust in-vehicle IDS that can encounter evasion attacks. Our methodology is based on implementing two rounds of mimic learning technique for training Random Forest (RF) based IDS. RF has been chosen to incorporate the randomness of the RF architecture to enhance the robustness of the model. Additionally, in each round of the two rounds of the mimic learning technique, an RF model with a different architecture is chosen to improve the resilience of the model against evasion attacks without affecting its accuracy. Our Experimental results have shown the effectiveness of our framework against evasion attacks. © 2024 IEEE.

关键词： Robustness (control systems)

来源：评论

学校读者我要写书评

暂无评论

Optimizing Random Forest Classifier for Detection of Alzheimer's Using OASIS

Optimizing Random Forest Classifier for Detection of Alzheim...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Sanjana Reddy, Karri Sai Reddy C, Kishor Kumar Doss, Srinath Lippert, Kari Stanley College of Engineering and Technology for Women Dept. of Computer Science and Engineering Hyderabad India Botho University Faculty of Engineering and Technology Botswana University of South Alabama Dept. of Systems Engineering Alabama United States

ISBN: (纸本)9798331540821

Alzheimer's disease (AD) is a progressive brain disorder impacting behavior, memory, and cognition, with over a million cases reported annually in India. The risk significantly increases beyond age 65. Early diagnosis and treatment can result in better recovery. We propose a predictive model using the Random Forest algorithm and the OASIS dataset for early AD diagnosis, leveraging MRI data, clinical notes, genetic markers, and cognitive test results. Our model was evaluated against several others, including Decision Tree, AdaBoost, SVM, and Logistic Regression. With a 97.3% accuracy and a 2.7% error rate, our Random Forest Classifier o utperformed t he others, demonstrating superior predictive power for early AD diagnosis and potentially improving patient care. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Improving VANET Localization Performance with Data Verification: Challenges and Solutions

Improving VANET Localization Performance with Data Verificat...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Ahmed, Amjed Abbas Kadhim, Aqeel Kamil Najim, Ali Hamza Ali Alheeti, Khattab M. Mohd Satar, Nurhizam Safie Abdallah Hashim, Aisa Hassan Universiti Kebangsaan Malaysia Center for Cyber Security Faculty of Information Science and Technology Bangi Malaysia Department of Computer Techniques Engineering Baghdad Iraq Department of Computer Technical Engineering Baghdad Iraq Department of Computer Technical Engineering Al-Diwaniyah Iraq College of Computer and Information Technology Computer Networking Systems Department University of Anbar Anbar Iraq Center for Cyber Security Faculty of Information Science and Technology Bangi43600 Malaysia International Islamic University Malaysia Faculty of Engineering Department of Electrical and Computer Engineering Selangor Malaysia

ISBN: (纸本)9798350369106

In VANETs, the important and effective applications of vehicle localization include safety and communication applications. Thus, it is difficult to get very accurate localization in the dynamic and often very fluctuating environment of VANET. This research responds to this challenge with a keen thrust on improving vehicle localization using the Mobility Data Verification process. The primary goal of this work is to achieve high accuracy of vehicle positioning within VANET by checking the coherence of mobility data of moving vehicles. Hence, we present a concept that builds upon Mobility Data Verification to provide real-time location details from vehicles. Both GPS and onboard sensors feed this method, which uses a multi-level verification to flag out or eliminate the errors of deliberately spoofed data points. We use simulations to evaluate and validate the effectiveness of the proposed verification approach. As the proposed system, our previously developed and fine-tuned weighted localization (OWL) strategy does so. The performance evaluation results suggest that our proposed solution is feasible to distinguish automobiles that are not trustworthy and improve the performance of the localization algorithm. © 2024 IEEE.

关键词： Vane pumps

来源：评论

学校读者我要写书评

暂无评论

Smart Water-Powered Renewable Energy System with IoT Integration

Smart Water-Powered Renewable Energy System with IoT Integra...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Ahmed, Amjed Abbas Najim, Ali Hamza Ibraheem, Ahmed Salman Ali Alheeti, Khattab M. Mohd Satar, Nurhizam Safie Abdallah Hashim, Aisha Hassan Universiti Kebangsaan Malaysia Center for Cyber Security Faculty of Information Science and Technology Bangi Malaysia Department of Computer Techniques Engineering Baghdad Iraq Department of Computer Technical Engineering Al-Diwaniyah Iraq Department of Computer Technical Engineering Baghdad Iraq College of Computer and Information Technology Computer Networking Systems Department University of Anbar Anbar Iraq Center for Cyber Security Faculty of Information Science and Technology Bangi43600 Malaysia International Islamic University Malaysia Faculty of Engineering Department of Electrical and Computer Engineering Selangor Malaysia

ISBN: (纸本)9798350369106

An advanced hybrid renewable energy collecting and storage system prototype that utilizes water flow as its primary power source. Additionally, the system incorporates an energy monitoring system based on the Internet of Things (IoT) technology. The device effectively harnesses energy from the movement of water, storing it for future use in low-voltage applications. It demonstrates a maximum daily energy capture capacity of about 100Wh. The energy monitoring system, based on the Internet of Things (IoT), enables the real-time and remote monitoring of energy harvesting and usage. We thoroughly assessed the energy harvesting component across different situations to identify the crucial parameters that impact energy output. The results of our study demonstrate that several elements, including the spatial separation 'between the energy harvester and the water source, Water flow' speed, sensor orientation, and sensor density, all play significant roles in determining the quantity of energy collected. This research shows that it is possible to integrate IoT technology with hydropower renewable energy systems. It provides significant perspectives on enhancing energy extraction efficiency in practical scenarios. © 2024 IEEE.

关键词： harvesting renewable energy IoT storage energy water flow energy

来源：评论

学校读者我要写书评

暂无评论

Extracting Motion Patterns of Greeting Gestures Using GNG with Spiking Neuron Model 13

Extracting Motion Patterns of Greeting Gestures Using GNG wi...

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Obo, Takenori Wibowo, Angga Wahyu Sato-Shimokawara, Eri Shibata, Hiroki Ho, Yihsin Kobayashi, Ichiro Tokyo Metropolitan University Department of Mechanical Systems Engineering Tokyo Japan Tokyo Metropolitan University Department of Computer Science Tokyo Japan Takushoku University Department of Electronics and Computer Systems Tokyo Japan Takushoku University Faculty of Engineering Tokyo Japan

ISBN: (纸本)9798350373332

This study focuses on behavior patterns, which are characteristic actions common to groups or communities, to promote intercultural understanding. Understanding greeting gestures is crucial for comprehending social relationships, but these vary across cultures and regions. Recent advancements in sensing technology and artificial intelligence, such as RGB-D cameras and markerless motion capture systems, have made it easier to capture motion data in diverse formats. Therefore, it is important to extract relevant motion patterns and apply appropriate structuring for effective long-term archiving. We propose a method for extracting motion patterns using a Growing Neural Gas (GNG) algorithm with a Spiking Neuron Model. Additionally, this paper presents an experimental example of extracting a gesture pattern in Indonesian style. © 2024 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

A Hybrid Model for Reliability Aware and Energy-Efficiency in Multicore systems

引用

computers, Materials & Continua 2022年第3期70卷 4447-4466页

作者： Samar Nour Sameh A.Salem Shahira M.Habashy Department of Computer and Systems Engineering Faculty of EngineeringHelwan UniversityCairo11792Egypt Egyptian Computer Emergency Readiness Team(EG-CERT) National Telecom Regulatory Authority(NTRA)Cairo12577Egypt

Recently,Multicore systems use Dynamic Voltage/Frequency Scaling(DV/FS)technology to allow the cores to operate with various voltage and/or frequencies than other cores to save power and enhance the *** this paper,an effective and reliable hybridmodel to reduce the energy and makespan in multicore systems is *** proposed hybrid model enhances and integrates the greedy approach with dynamic programming to achieve optimal Voltage/Frequency(Vmin/F)***,the allocation process is applied based on the *** hybrid model consists of three *** first stage gets the optimum safe voltage while the second stage sets the level of energy efficiency,and finally,the third is the allocation *** results on various benchmarks show that the proposed model can generate optimal solutions to save energy while minimizing the makespan *** with other competitive algorithms show that the proposed model provides on average 48%improvements in energy-saving and achieves an 18%reduction in computation time while ensuring a high degree of system reliability.

关键词： Energy-efficiency safe voltage multicore processors core utilization dynamic voltage/frequency scaling makespan

来源：评论

学校读者我要写书评

暂无评论

Metaheuristics for Financial Investment Strategies: Applications Survey

Metaheuristics for Financial Investment Strategies: Applicat...

引用

2023 International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Bousbaa, Zineb Bencharef, Omar Cady Ayyad University Computer and Systems Engineering Laboratory Faculty of Sciences and Technology Computer Science Department Marrakesh Morocco

ISBN: (纸本)9798350322972

Machine learning has been widely used as part of financial markets investment strategies, whether for forecasting the financial assets exchange rate, managing market volatility, or solving different classification problems that help with decision-making. Building an investment strategy using a scientific approach requires a massive amount of data, good computational power, and some expertise in the finance industry. Machine learning applications to the financial field, such as price exchange rate prediction, market pattern recognition, or other trading strategy tasks, are considered optimization problems. As they require an efficient algorithm dedicated to finding a global optimum, they can be solved using metaheuristics. In this survey, we study how metaheuristic optimization techniques contribute to building a robust learning model dedicated to financial investment strategy applications. © 2023 IEEE.

关键词： Financial markets

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：