检索结果-内蒙古大学图书馆

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Mahfuri, Mahmoud Ghwanmeh, Sameh Ali, Liaqat Al-Zoubi, Hani Q. International University For Science And Technology Computer And Information Technology Department Syria American University In The Emirates Department Of Computer Science United Arab Emirates College Of Engineering And Technology University Of Science And Technology Of Fujairah Fujairah United Arab Emirates College Of Engineering Mutah University Department Of Computer Engineering Jordan

ISBN: (纸本)9798350394962

This paper addresses the crucial goal of improving communication between the deaf and mute community and the broader public. We present the development of a sign language translator that effectively converts hand gestures into text, encompassing alphabets and digits, thereby facilitating comprehension of the conveyed messages. Our approach incorporates an intelligent hand gesture recognition system powered by Convolutional Neural Networks (CNNs) and utilizes a comprehensive dataset comprising 44 distinct gestures, including letters and numbers. The proposed model plays a pivotal role in preprocessing input images by employing a threshold mechanism to eliminate noise and enhance image smoothness. To ensure accuracy and continuity in the regions of interest, we implement a region filling technique. TensorFlow serves as the backend for our CNN-based Keras model, which undergoes rigorous training on the collected dataset. After the training phase, the model is rigorously tested to validate its performance. Upon successful testing, users can express their gestures, and the system displays the corresponding text representation while simultaneously converting it into speech. This groundbreaking work contributes significantly to bridging the communication gap and fostering inclusivity within our society. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Epileptic seizure detection in EEG signals via an enhanced hybrid CNN with an integrated attention mechanism

引用

Mathematical Biosciences and Engineering 2025年第1期22卷 73-105页

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao56000 Thailand Department of Applied Statistics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research Institute King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand

Epileptic seizures, a prevalent neurological condition, necessitate precise and prompt identification for optimal care. Nevertheless, the intricate characteristics of electroencephalography (EEG) signals, noise, and the want for real-time analysis require enhancement in the creation of dependable detection approaches. Despite advances in machine learning and deep learning, capturing the intricate spatial and temporal patterns in EEG data remains challenging. This study introduced a novel deep learning framework combining a convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU), and convolutional block attention module (CBAM). The CNN extracts spatial features, the BiGRU captures long-term temporal dependencies, and the CBAM emphasizes critical spatial and temporal regions, creating a hybrid architecture optimized for EEG pattern recognition. Evaluation of a public EEG dataset revealed superior performance compared to existing methods. The model achieved 99.00% accuracy in binary classification, 96.20% in three-class tasks, 92.00% in four-class scenarios, and 89.00% in five-class classification. High sensitivity (89.00–99.00%) and specificity (89.63–99.00%) across all tasks highlighted the model’s robust ability to identify diverse EEG patterns. This approach supports healthcare professionals in diagnosing epileptic seizures accurately and promptly, improving patient outcomes and quality of life. © 2025 American Institute of Mathematical sciences. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

An Extensive Analysis of Green Cloud Computing: Overview, Associated Challenges and Research Directions 3

An Extensive Analysis of Green Cloud Computing: Overview, As...

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Suratia, Nishi Thakkar, Priyansh Sheth, Kunal Ramoliya, Dipak Patel, Anand K. Department of Computer Science and Engineering Gujarat Changa India Dharmsinh Desai University Faculty of Technology Department of Information Technology India

ISBN: (纸本)9798350343632

Current questions and challenges for environmental shielding are introduced by Cloud Computing. Reliability, high performance, and scalability are application states that are offered by cloud computing technologies. The Cloud Computing revolution promises environmental protection, modern networking redesign, and economic and technological advantages. Huge data centers are needed for this facility and they are coupled with a system that increases energy consumption and enormous CO2 emissions. Since the prime concern is energy, the problem generates the need for Green Cloud Computing, which can boost the efficiency of energy and to lower down tracks of carbon and electronic waste. © 2023 IEEE.

关键词： Architecture Challenges Green Cloud Computing Green Initiatives Merits and Demerits

来源：评论

学校读者我要写书评

暂无评论

Hybrid Cryptosystem with Cramer-Shoup and Spritz Algorithms for Securing Digital Documents 8

Hybrid Cryptosystem with Cramer-Shoup and Spritz Algorithms ...

引用

8th International Conference on Electrical, Telecommunication and computer Engineering, ELTICOM 2024

作者： Hulu, Delisman Lydia, Maya Silvi Budiman, Mohammad Andri Universitas Sumatera Utara Master of Informatics Program Faculty of Computer Science and Information Technology Medan Indonesia

ISBN: (纸本)9798331531249

Symmetric algorithms offer speed but have weaknesses in key distribution, while asymmetric algorithms are secure but less efficient for encrypting and decrypting large text messages. This research aims to secure data and digital documents through the implementation of a hybrid cryptosystem that combines the Cramer-Shoup algorithm and Spritz. This research also analyzes and evaluates the effectiveness and speed of encryption and decryption, as well as the efficiency of the system in protecting various types of data, including docx and pdf document files. The methodology of this research includes a literature review, analysis of the encryption-decryption process, and performance testing of the system using the Python programming language. The speed test results show that this hybrid cryptosystem provides fast encryption-decryption times, with an encryption time of 0.002607 milliseconds for 400 characters and a decryption time of 0.001537 milliseconds, while for digital documents of the pdf file type, the encryption time is 0.424478 milliseconds and the decryption time is 0.404343 milliseconds. In addition, the use of the SHA-3 hash function has proven effective in maintaining data integrity. In conclusion, this hybrid cryptosystem offers an efficient and secure solution for protecting various types of digital data, including text and documents. © 2024 IEEE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

Blockchain technology and Artificial Intelligence based Integrated Framework for Sustainable Supply Chain Management system 18

Blockchain Technology and Artificial Intelligence based Inte...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Dar, Arshad Ahmad Reegu, Faheem Ahmad Ahmed, Sarfaraz Hussain, Gousiya Jazan University College of Computer Science and Information Technology Jazan Saudi Arabia Mewar University Department of Computer Science Chittorgarh India

ISBN: (纸本)9789380544519

The supply chain has become increasingly complex, making it challenging to verify sustainable practices. Blockchain has been viewed as a viable option to improve numerous aspects of sustainable supply chain management (SSCM) in response to increased customer demand for product traceability and proof of origin. This technology was initially developed as a secure distributed ledger for the bitcoin market, but it has since been adopted by several businesses, including the food, healthcare, and logistics sectors. This research seeks to propose a framework for more open, transparent supply chain operations using blockchain and artificial intelligence (AI) technologies. Two research topics will be addressed in relation to the main advantages and challenges in the market for consumer goods: This proposal will employ a qualitative methodology to investigate how blockchain and AI might result in more transparent supply chains from a social and environmental perspective. By considering the integration of blockchain and AI from many perspectives, triangulation will be achieved in order to promote transparency and traceability. We will suggest a single framework that assembles the necessary data pieces that must be maintained digitally in order to enhance sustainability in supply chains management systems utilizing Artificial Intelligence and Blockchain technology (BCT). © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Blockchain Consumer products Sustainability Traceability Transparency

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Clustering-based Self-Labeling for Multimodal Data Classification 24

Cross-Modality Clustering-based Self-Labeling for Multimodal...

引用

24th IEEE International Conference on Data Mining Workshops, ICDMW 2024

作者： Zyblewski, Pawel Minku, Leandro L. Wroclaw University of Science and Technology Faculty of Information and Communication Technology Wroclaw Poland University of Birmingham School of Computer Science Birmingham United Kingdom

ISBN: (纸本)9798331530631

Technological advances facilitate the ability to acquire multimodal data, posing a challenge for recognition systems while also providing an opportunity to use the heterogeneous nature of the information to increase the generalization capability of models. An often overlooked issue is the cost of the labeling process, which is typically high due to the need for a significant investment in time and money associated with human experts. Existing semi-supervised learning methods often focus on operating in the feature space created by the fusion of available modalities, neglecting the potential for cross-utilizing complementary information available in each modality. To address this problem, we propose Cross-Modality Clustering-based Self-Labeling (CMCSL). Based on a small set of pre-labeled data, CMCSL groups instances belonging to each modality in the deep feature space and then propagates known labels within the resulting clusters. Next, information about the instances' class membership in each modality is exchanged based on the Euclidean distance to ensure more accurate labeling. Experimental evaluation conducted on 20 datasets derived from the MM-IMDb dataset indicates that cross-propagation of labels between modalities - especially when the number of pre-labeled instances is small - can allow for more reliable labeling and thus increase the classification performance in each modality. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection from CCTV Camera Feed 10

Anomaly Detection from CCTV Camera Feed

引用

10th IEEE International Symposium on Smart Electronic systems, iSES 2024

作者： Aakash Chauhan, Lakshay Sharma, Shubham Deb, Sujay Indraprastha Institute of Information Technology Delhi Computer Science & Engineering Department Delhi India

ISBN: (纸本)9798331533229

The paper presents a novel approach for detecting anomalies like arson, explosion, vandalism, etc in public spaces using CCTV camera feeds. We propose a deep learning-based system that analyzes video streams to identify unusual events or behaviours that deviate from normal patterns. Our method combines Convolutional Neural Networks (CNNs) and Spiking Neural Networks (SNNs) for feature extraction with Long Short-Term Memory (LSTM) networks to model temporal dependencies in the video sequences. The system is trained on the UCF Crime Dataset to learn normal activity patterns and can flag potential anomalies in emulated real-time situations. To enhance accuracy, we incorporate additional computer vision technique, like optical flow, with CNN/SNN and LSTM to get various combinations of models (OF-CNN, OF-CNNLSTM, OF-SNN, OF-SNNLSTM, CNNLSTM) for improved anomaly detection. The proposed system has potential applications in enhancing public safety and security monitoring in urban environments. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fruit Quality Monitoring system using CNN 1

Fruit Quality Monitoring System using CNN

引用

1st International Conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Ravikumar, B.N. Vidya, M.S. Gowda, Naveen Chandra NarendraBabu, C.R. Veena, H.N. Ramani, D. Roja Bms Institute of Technology and Management Department of Information Science and Engineering Bengaluru India Bms Institute of Technology and Management Department of Computer Science and Engineering Bengaluru India School of Computer Science and Engineering Reva University Bengaluru India Sjb Institute of Technology Department of Computer Science and Engineering Bengaluru India New Horizon College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331529246

The grading of fruits relies on inspections, experiences, and observations, with a proposed system integrating machine learning techniques to assess fruit freshness. By analyzing 2D fruit portrayals based on shape and color, limitations arise as different fruits may share similar color, size, and shape values. To enhance accuracy, the system combines size, shape, and color analysis with Convolutional Neural Network (CNN) technology. Upon capturing the fruit image, properties like size, shape, and color are extracted, followed by CNN training and testing processes. The proposed work have implements UNet and En-UNet chosen over other architectures like ResNet or MobileNet for segmentation. This innovative approach utilizes CNN to extract comprehensive features, yielding promising results in fruit freshness detection with accuracy of 99% and loss rate of 0.0123. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Development of Extraction Technique for Diagnosing Kidney Abnormalities by Using Ultrasound Images 8

Development of Extraction Technique for Diagnosing Kidney Ab...

引用

8th International Conference on information technology, information systems and Electrical Engineering, ICITISEE 2024

作者： Zain, Ruri Hartika Sumijan Defit, Sarjon Universitas Putra Indonesia Yptk Faculty of Computer Science Dept. Information Technology Padang Indonesia

ISBN: (纸本)9798350368970

Kidney disease is a health problem consisting of kidney failure, where it is caused by a complication of decreased kidney function. To prevent serious complications, kidney disorders must be diagnosed quickly and automatically. The aim of this study was to develop an extraction method to diagnose kidney abnormalities in ultrasound images from 102 patients. Researchers proposed the development of an extraction technique by using a combination of the Grey Level Co-Occurrence Matrix (GLCM), Scale Invariant Feature Transform (SIFT) method and the Canny method. The statistical-based GLCM feature extraction method used a pixel value matrix that had a certain score and forms the angle of the kidney image pattern. The research shows that the SIFT algorithm is effective for object recognition and it is robust to changes in rotation and scaling of kidney images. Canny is also known as optimal edge detection, localizing edge points and providing only one response for one edge of the image. Based on the tests, it is found that the process of detecting kidney abnormalities quickly and accurately. it increases the efficiency of the medical role in decision making. This automatic system analyses and identifies kidneys based on existing abnormalities with maximum accuracy such as cysts, kidney stones, cancer and tumours as abnormalities in the kidneys. In addition, the automated kidney diagnosis system will help radiologists and nephrologists in reducing inadequate nephrology problems and discrepancies. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Implementation of CNN-LSTM Integration for Advancing Human-computer Dialogue through Precise Sign Language Gesture Interpretation 5

Implementation of CNN-LSTM Integration for Advancing Human-C...

引用

5th IEEE International Conference on Recent Trends in computer science and technology, ICRTCST 2024

作者： Duraisamy, Premkumar Abinaya Srijanani, A. Duraisamy, M. Amrit Candida, M. Dinesh Babu, P. Karthik, S. KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Government Arts and Science College Department of Computer Science Tirupattur635901 India Hindusthan College of Engineering & Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798350351378

Sign gestures play a crucial role in communication for the deaf community, emphasizing the need for effective translation systems. Hand gestures convey thoughts more rapidly than other actions, making them essential for those who are deaf-mute. The primary goal is to design an assistive device that seamlessly translates a variety of sign signals into understandable text and vocalized output for individuals with speech difficulties. The proposed method involves creating a robust dataset with diverse hand gestures, employing image recognition preprocessing techniques, and implementing a CNN-LSTM model. This comprehensive framework combines computer vision, natural language processing, and speech synthesis for gesture recognition, text generation, and speech synthesis. Through extensive experimentation and model optimization, the system achieves a remarkable 94.5% accuracy in identifying and translating hand gestures into coherent text. Case tests with letters, numbers, and typical gestures demonstrate an average accuracy of 95%, showcasing the system's versatility and durability. © 2024 IEEE.

关键词： Long short-term memory

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：