检索结果-内蒙古大学图书馆

8th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2024

作者： Salian, Supriya Preethi Salian, K. D'Souza, Ria Monterio, Rencita Fernandes, Rinette Veronica Almeida, Riya D. St. Joseph Engineering College Vamanjoor Dept. of Computer Science and Engineering Mangaluru India Dept. of Information Science and Engineering Udupi India

ISBN: (纸本)9798350350593

Recognition of human activities has drawn a lot of interest lately in the field of computer vision and machine learning. Group activity recognition is a significant subcategory in which several people participate in a common activity. The primary obstacle in these tasks is learning the relationships between individuals in a scene and understanding their evolution over time. The suggested study offers a new taxonomy to classify state-of-the-art (SOTA) group activity recognition approaches and subcategorizes the current literature. It also critically analyzes these techniques. To understand scenes involving multiple people, models must describe individual actions in context and infer collective activities. Accurately capturing relationships between actors and performing relational reasoning is crucial for comprehending group activities. However, modelling these relationships is challenging due to the limited availability of interaction information, relying only on individual action labels and collective activity labels. Inferring relationships from other aspects is thus essential. Group activity recognition has garnered increased research attention recently due to its importance in video understanding. The difficulties lie not only in recognizing individual actions but also in exploring scene information and collaborative relations among people. This research addresses these challenges by providing a comprehensive review of existing techniques, offering a structured approach to categorize them, and highlighting the importance of relational reasoning in understanding group activities. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Pediatric Appendicitis Diagnosis: Harnessing CNN and Hybrid Models with Ultrasound Imaging

Advancing Pediatric Appendicitis Diagnosis: Harnessing CNN a...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Kulkarni, Supritha Sharma, Sanchit Manavi, J. Vachana, U. Bhargavi, M.S. Bangalore Institute of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331508685

Pediatric appendicitis, an acute inflammatory disease, arises from the obstruction of the appendix, often due to inflammation or a fecalith. This common abdominal emergency in children presents diagnostic challenges due to its varied clinical manifestations, which can lead to misdiagnosis or higher perforation rates stemming from atypical symptoms. This research investigates the use of deep learning, more especially Convolutional Neural Networks (CNNs), by utilizing ultrasonic imaging data, which is less expensive, non-invasive, and quicker than the other approaches now in use. Several variants are evaluated including a basic CNN and more advanced hybrid models such as CNN-Support Vector Regression, CNN-Transformer, and Hierarchical Deep CNN, to identify the most optimal model to significantly enhance diagnostic accuracy, for young patients facing this condition. The study's main goal is to develop a highly accurate and dependable diagnostic tool for evaluating the severity of pediatric appendicitis by differentiating between simple and complex cases and identifying whether surgery is required to inform treatment plans. Various challenges that need to be tackled are managing significant dataset imbalances, enhancing interpretability and transparency for real-world clinical settings, and ensuring the robustness and adaptability of all these models across various healthcare environments. © 2025 IEEE.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Feature Selection for Detecting LOIC-based DDoS Attack

An Implementation of Feature Selection for Detecting LOIC-ba...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Cai, Yi-Xian Chen, Shih-Chieh Wang, Chih-Chiang National Kaohsiung University of Science and Technology Dept. of Computer Science and Information Engineering Kaohsiung Taiwan

ISBN: (纸本)9798350324174

Machine learning method is efficient and effective in detecting DDoS attacks, but it all begins from identifying and selecting their important features. This paper presents an implementation of feature selection for DDoS detection based on Random Forest method. In our implementation, we use a LOIC software flood DDoS requests to a target computer, then control the target to extract the features from the captured IP packets, and finally calculate their Gini feature importance and ranking for subsequent feature selection. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Smart Vehicle Procurement System using Blockchain technology 3

Smart Vehicle Procurement System using Blockchain Technology

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Kumar, Boddu Manoj Rajeswari, G. Duraipandian, Kavitha David, Shiela Dept. of Computer Science and Engineering with specialization in Blockchain Technology Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai600119 India

ISBN: (纸本)9798331527549

Blockchain technology has become more widespread in our lives revolutionizing various industries through improved security, transparency, and operational efficiency. Its decentralized ledger system is particularly effective in areas like finance and supply chain management ensuring data integrity and reducing the need for middlemen. This study explores how blockchain technology is used in the process of buying vehicles highlighting its benefits compared to methods. Traditional vehicle purchases involve a network of dealers, banks and regulators leading to inefficiencies, higher costs and potential fraud. The usual process involves steps like financing checking vehicle history and changing ownership. Each requiring extensive paperwork and third-party intervention. In contrast using blockchain for vehicle purchases can simplify things through contracts that automate tasks like verifying history securely transferring ownership instantly settling payments. The unchangeable nature of records ensures that all transaction data remains secure against tampering fostering trust between buyers and sellers. Furthermore, blockchain can cut costs significantly by removing the need for middlemen such, as escrow services and title companies while reducing burdens. The advanced security elements built into technology help reduce the chances of fraudulent actions like altering odometer readings or selling stolen cars. This study showcases a comparison illustrating how blockchain can simplify the process of buying vehicles offering an economical and secure experience. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Analysis of Neural Machine Translation for English to Hindi using Long Short-Term Memory Model and Transformer Model 4

Analysis of Neural Machine Translation for English to Hindi ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Naveen, Rashmi Kumar, Archana Praveen Dept. of Information Science and Engineering India Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science & Engineering Manipal India

ISBN: (纸本)9798331540364

By providing enhanced accuracy and fluency compared to traditional approaches, Neural Machine Translation (NMT) has transformed the area of machine translation. In this research paper, the specific task of translating English to Hindi using NMT techniques is discussed. Creation and assessment of NMT systems developed for this language pair, considering the linguistic complexities and cultural aspects inherent in English and Hindi is examined. Leveraging large-scale parallel corpora and advanced neural network architectures, this work proposes novel approaches to improve translation quality and efficiency. Experimental results evaluated using standard metrics such as BLEU score, shows the efficacy of the proposed NMT models in accurately capturing the semantics and preserving the naturalness of the translated text. Additionally, this study discusses the implications of findings for cross-language communication and access to information, particularly in the context of the growing importance of Hindi in a globalized digital domain. Overall, this research contributes to develop neural machine translation for English to Hindi to a higher level and highlights the potential of NMT in facilitating multilingual communication and knowledge dissemination. © 2024 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Human Activity Recognition for Precision in Yoga Practice Analysis 8

Optimizing Human Activity Recognition for Precision in Yoga ...

引用

8th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2024

作者： Salian, Supriya Preethi Salian, K. Rodrigues, Maria Viola Ritesh Muhammed Elham, P.N. Mannan, Mohammed Abdul St. Joseph Engineering College Vamanjoor Dept. of Computer Science and Engineering Mangaluru India Dept. of Information Science and Engineering Udupi India

ISBN: (纸本)9798350350593

The proposed system on enhancing human activity recognition in yoga presents an innovative solution using advanced technologies to accurately and quickly analyze data of yoga poses. Through meticulous data collection and preprocessing, including noise removal, normalization, and handling missing data, the system ensures a clean and standardized dataset. Pose estimation algorithms contribute to accurately mapping the body's posture, extracting essential features like joint angles and body orientation. The features form the basis for a powerful machine learning model, trained on a labelled dataset and employing neural networks, enabling the system to recognize yoga poses with remarkable precision. The study embraces an iterative enhancement process, continuously refining the model based on feedback and performance metrics, ensuring ongoing improvements in accuracy. Ultimately, the proposed system represents a cutting-edge solution for advancing human activity recognition in yoga, providing practitioners with real- time feedback and guidance, fostering improved techniques, and enhancing the overall yoga experience. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Zero-Trust Architecture for Smart City Healthcare Systems 2

Zero-Trust Architecture for Smart City Healthcare Systems

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Alsofyani, Shahd Ishaque, Mohammad Nofal, Mostafa Jedah International College Dept. of Computer Science and Information Technology Jeddah Saudi Arabia

ISBN: (纸本)9798331506995

This paper introduces a tailored Zero-Trust Architecture (ZTA) for healthcare systems in smart cities, addressing the security challenges posed by interconnected infrastructures. The model enforces continuous access validation through micro-segmentation, identity and access management (IAM) with multi-factor authentication (MFA), and device trust verification, significantly reducing vulnerabilities. AI-powered real-time monitoring and anomaly detection enhance the system's ability to identify and mitigate advanced persistent threats (APTs) and insider risks. Secure communication protocols, end-to-end encryption, and audit logging ensure data protection, regulatory compliance, and forensic capabilities. The proposed ZTA provides a scalable, future-proof solution that strengthens patient data security and safeguards healthcare infrastructure against evolving cyber threats in smart cities. © 2025 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction Utilizing Machine Learning and Feature Selection with Clonal Selection Algorithm 5

Cardiovascular Disease Prediction Utilizing Machine Learning...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Rahman, Wahidur Aneek, Riasaad Haque Moinuddin, Md. Sakib, Md. Shadman Iqbal, Md. Sadiq Rahman, Mohammad Motiur Uttara University Dept. of Computer Science and Engineering Uttara Dhaka Bangladesh Z.H. Sikder University of Science and Technology Dept. of Computer Science and Engineering Bhedarganj Shariatpur Bangladesh University of Information Technology and Sciences Dept. of Computer Science and Engineering Dhaka Bangladesh Bangladesh University Dept. of Computer Science and Engineering Adabor Bangladesh Mawlana Bhashani Science and Technology University Dept. of Computer Science and Engineering Tangail Bangladesh

ISBN: (纸本)9798350394290

A substantial and rising number of patients suffer from cardiovascular diseases, including heart attacks, heart failure, and other related illnesses. This case surge places increasing pressure on healthcare professionals and administrators while patients grapple with growing medical costs. To address these challenges, an automated system is necessary within the healthcare sector. In this paper, we present a cardiovascular health monitoring system that incorporates Machine Learning techniques. The study employed feature selection techniques on a secondary dataset. The study has used a nature-inspired technique, namely the Clonal Selection Algorithm (CSA) and Maximum Relevance Minimum Redundancy (mRMR) technique, to identify the most prominent feature in the detection of cardio-vascular illness. This approach was combined with a collection of Machine Learning classifiers. A group of experimental data has been listed to assess the suggested model's effectiveness. The research findings indicated a maximum accuracy rate of 100% when employing the proposed algorithms and orientations. The study also discusses the performance analysis for CSA and mRMR using a set of performance evaluation matrices. Based on the obtained results, it can be inferred that the suggested model will likely exhibit a high level of effectiveness in identifying cardiovascular diseases. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Improving Liver Disease Diagnosis Through Generative Adversarial Network Driven Synthetic Tabular Data

Improving Liver Disease Diagnosis Through Generative Adversa...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Mahendran, S. Venkatasekhar, D. Shanmugasundaram, G. Annamalai University Department of Information Technology Chidambaram India Chennai Institute of Technology Dept. of Computer Science & Engineering Chennai India

ISBN: (数字)9798331540821

ISBN: (纸本)9798331540821

Liver ailments pose a significant worldwide health concern, with their extensive effects and severe repercussions highlighting the pressing necessity for precise diagnosis. Diagnosing hepatic disorders is frequently intricate and expensive. This work presents a Generative Adversarial Network (GAN) based methodology for producing synthetic tabular data to enhance early prediction of liver ailments, employing a dataset of Indian liver patients. The contribution of the work is the introduction of innovative architecture that integrates Stacked Ensemble Model with advanced preprocessing techniques and the use of Generative Adversarial Networks for data augmentation not extensively explored in current data-driven machine learning approaches for liver ailments prediction. The Stacked Ensemble Model has two tiers: the base-level and the meta-level. The base-level learning component trains various base learners, including Gradient Boosting, Ride classifier, Multi-layer Perceptron, and LightGBM on the input dataset. A strong prediction model is then constructed by combining and feeding the outputs of these several classifiers into a Random Forest classifier, which is the meta-learner. The results show that the model performs much better when synthetic data generated by GANs is included, obtaining an overall accuracy of 95%. This approach aims to greatly improve the prediction of liver ailments, hence enabling quick intervention and more effective treatment. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Gauging Deep Learning Archetypal Effectiveness in Haematological Reclamation

引用

SN computer science 2024年第7期5卷 963页

作者： Pradeep kumar, B.P. Ravikumar, J. Dept. of Computer Science and Design Atria Institute of Technology VTU Karnataka Bangalore India Dept. of Computer Science and Engineering Atria Institute of Technology VTU Karnataka Bangalore India

This paper project an system for reclamation of medical images in an effective way for the extraction and retrieving of data from large archives is critical. This study aims to improve haematological image reclamation by combining visual-based image reclamation (VBIR) approaches with the GLCM algorithm, specifically for characteristics related to the prostate gland. While previous research has focused on computer-aided methods for Gleason grading, our technique focuses on early-stage feature reclamation across 14 paired glands. The experimental findings, including Bicubic Interpolation The resolution Enrichment with a standard deviation of 12.37, kurtosis of 122.83, and skewness of 2.92, demonstrate improved reclamation performance. Our suggested methodology uses a handmade learning approach that includes critical components such as GLCM contrast and correlation. This extensive feature extraction step includes descriptors for morphology, texture, fractals, and contextual information, which are then subjected to in-dept. statistical analysis to identify significant features. Using an RNN, our technique improves performance somewhat but significantly when compared to alternatives, with time required for execution offering insights into the intricate interaction of stages and the effect of sample variability. These findings not only encourage more research, but also help to advance standard reviews in haematological analysis of images. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Gland reclamation Gray-level co-occurrence matrix (GLCM) Haematological Haematological image Prostate gland

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：