检索结果-内蒙古大学图书馆

Light gradient boosting machine with optimized hyperparameters for identification of malicious access in IoT network

引用

Digital Communications and Networks 2023年第1期9卷 125-137页

作者： Debasmita Mishra Bighnaraj Naik Janmenjoy Nayak Alireza Souri Pandit Byomakesha Dash S.Vimal Department of Computer Application Veer Surendra Sai University of TechnologyBurlaSambalpur768018OdishaIndia Department of Computer Science Maharaja Sriram Chandra Bhanja Deo(MSCB)UniversityBaripada757003OdishaIndia Department of Software Engineering HaliçUniversity34394IstanbulTurkey Department of Information Technology Aditya Institute of Technology and Management(AITAM)Tekkali532201Andhra PradeshIndia Data Analytics Lab Department of Artificial Intelligence and Data ScienceRamco Institute of TechnologyNorth Venganallur VillageRajapalayam 626117 Virudhunagar DistrictTamilnaduIndia

In this paper,an advanced and optimized Light Gradient Boosting Machine(LGBM)technique is proposed to identify the intrusive activities in the Internet of Things(IoT)*** followings are the major contributions:i)An optimized LGBM model has been developed for the identification of malicious IoT activities in the IoT network;ii)An efficient evolutionary optimization approach has been adopted for finding the optimal set of hyper-parameters of LGBM for the projected ***,a Genetic Algorithm(GA)with k-way tournament selection and uniform crossover operation is used for efficient exploration of hyper-parameter search space;iii)Finally,the performance of the proposed model is evaluated using state-of-the-art ensemble learning and machine learning-based model to achieve overall generalized performance and *** outcomes reveal that the proposed approach is superior to other considered methods and proves to be a robust approach to intrusion detection in an IoT environment.

关键词： IoT security Ensemble method Light gradient boosting machine Machine learning Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Health Care Expense Anticipation using Computational intelligence 1

Performance Analysis of Health Care Expense Anticipation usi...

引用

1st International Conference on Innovative engineering sciences and Technological Research, ICIESTR 2024

作者： Gopalakrishnan, A. Kumarganesh, S. Divya Bharathi, G. Anthoniraj, S. Natarajan, Suresh Kumar Gochhait, Saikat Knowledge Institute of Technology Department of Artificial Intelligence and Data Science Salem India Knowledge Institute of Technology Department of Electronics and Communication Engineering Salem India Mahendra Institute of Technology Department of Computer Science and Engineering Namakkal India School of Computer Science and Engineering Ramanagara India Symbiosis International Deemed University Symbiosis Institute of Digital and Telecom Management Maharashtra Pune India

ISBN: (纸本)9798350348637

The escalating costs of healthcare globally necessitate the development of accurate prediction models to address the financial strain on individuals, families, businesses, and governments. This research employs linear regression models to forecast healthcare expenditures, analyzing the intricate relationship between various factors and costs. A comprehensive literature survey explores topics such as the impact of environmental pollution on healthcare spending, prediction of surgical expenses, budget impact analysis for cancer treatment, and the integration of big data in healthcare infrastructure investments. The methodology involves gathering a diverse dataset encompassing patient demographics, medical history, treatment methods, and associated expenditures. Exploratory data analysis employs Pearson's correlation coefficient to identify trends and correlations between variables. Two linear regression models are proposed and compared, with the second model excluding non-significant variables for enhanced accuracy and interpretability. Results indicate that the second model, with refined feature selection, outperforms the first in terms of mean squared error and R-squared values. A comparative analysis of different studies underscores the diverse findings in healthcare economics, ranging from the impact of CO2 emissions on health to predicting surgery costs and budgetary savings in cancer treatment. The research contributes to the growing body of knowledge in healthcare economics, providing decision-makers with a valuable tool for precise expenditure estimation. The emphasis on linear regression models aids stakeholders in understanding factors influencing healthcare costs, guiding resource allocation, policy creation, and financial planning for more sustainable and effective healthcare systems. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

EchoNet Dynamic: Deep Learning-driven Advancements in Dynamic Heart Function Analysis through Echocardiography 3

EchoNet Dynamic: Deep Learning-driven Advancements in Dynami...

引用

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

作者： Vidhya, K. Nagarajan, B. Jenefa, A. Catherine Joy, R. Cherian, Minu Franz Kingstein, N. School of CST Karunya Institute of Tech. and Sci Coimbatore India Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India Division of ECE Karunya Institute of Tech. and Sci Coimbatore India Computer science and engineering department Amal Jyothi college of engineering kanjirapally Kottayam India

ISBN: (纸本)9798331527549

Advances in echocardiography have significantly improved the diagnostic processes for heart function analysis. However, traditional imaging techniques often struggle with the dynamic complexities of cardiac activities. Existing methods fail to capture detailed variations in cardiac function over time, leading to suboptimal clinical decision-making and patient outcomes. Traditional echocardiography relies heavily on manual interpretation, which can be subjective and varies significantly between observers. This research presents EchoNet Dynamic, a novel method for improving echocardiographic data analysis and interpretation based on deep learning and the Transformer model. The EchoNet Dynamic dataset used in this study comprises 15,000 B-mode echocardiographic images from 750 patients, divided into training, validation, and testing sets for comprehensive model evaluation. The Transformer model demonstrated remarkable effectiveness, achieving an accuracy of 98.5%, an AUC of 0.992, and an F1 score of 0.972, surpassing traditional diagnostic tools by a significant margin. The EchoNet Dynamic model demonstrates a promising enhancement in detecting and diagnosing cardiac functions, offering substantial improvements over conventional echocardiographic methods and setting a new benchmark in cardiac healthcare. © 2025 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fake News Detection Using BERT: A Comparative Analysis of Logistic Regression, RFC, LSTM and BERT

Enhancing Fake News Detection Using BERT: A Comparative Anal...

引用

2024 International Conference on IT and Industrial Technologies, ICIT 2024

作者： Ramzan, Alishba Ali, Raja Hashim Ali, Nisar Khan, Ayesha Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi23460 Pakistan Department of Business University of Europe for Applied Sciences Potsdam14469 Germany Faculty of Engineering and Applied Science University of Regina ReginaS4S0A2 Canada

ISBN: (纸本)9798331504465

The research analyzed how to identify fake news effectively, understanding the developing capabilities to differentiate between misinformation and the correct nature of news in today’s complex media environment. Numerous approaches were tested: mostly the ways of determining if a certain message is valid or false. With application of Logistic Regression, Random Forest and lastly LSTM models, the research has been able to achieve 98.7%, 98.8%, and 95% accuracies respectively, showing that these traditional and advanced techniques are very effective. However, it became apparent that these models performed poorly as soon as tested on a new dataset and the discrepancy was not being able to understand context while being trained. Understanding the context is the key in news identification, so the research turned to BERT, the Transformer model pre-trained with huge contextual data to perform this task. Drawing on its deep and diverse knowledge base, BERT has shown a remarkable aptitude for sorting news articles into fake/real categories based on their context. Logistic Regression, Random Forest, and LSTM models demonstrated that although they were able to build models that were highly accurate up to 99% on familiar data, their accuracy dropped disproportionately as soon as new data was given. BERT, despite having a lower overall accuracy of 84% demonstrated a better sensitivity to contextual nuances in the news data. Here, the importance of contextualized conception in the sphere of fake news detection should be emphasized as a way to take advantage of BERT’s complicated comprehension which is a promising alternative of more accurate and effective identification as the media landscapes of the modern times may be complex and diverse. Despite the fact that the classical models surpass in planned environments, BERT’s capability of contextualization made it irreplaceable for evidence as the news sources in uncommon circumstances can digress from base. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Recognition System

Traffic Sign Recognition System

引用

2024 International Conference on IT and Industrial Technologies, ICIT 2024

作者： Ahmed, Maqsood Ali, Raja Hashim Ali, Nisar Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi23460 Pakistan Department of Business University of Europe for Applied Sciences Potsdam14469 Germany Faculty of Engineering and Applied Science University of Regina ReginaS4S0A2 Canada

ISBN: (纸本)9798331504465

Traffic Sign Recognition Systems (TSRS) are instrumental in improving road safety by assisting drivers and supporting autonomous vehicles in real-time identification of road regulations. These systems have advanced significantly in recent years, with deep learning approaches achieving promising results. However, despite these developments, existing models face challenges in adapting to the diverse conditions of real-world environments, including variations in lighting, weather, and sign appearance. Addressing this limitation, our study focuses on enhancing the robustness and accuracy of TSRS for practical deployment. In response to this gap, we introduce a novel deep learning model optimized for traffic sign recognition across various conditions. Our approach utilizes a convolutional neural network (CNN) architecture, which was trained on the German Traffic Sign Recognition (GTSR) dataset. We improved the model’s adaptability to new and unseen data while achieving a high accuracy rate of 97.99% by applying techniques like data augmentation and transfer learning. Methodologically, the model workflow includes extensive preprocessing, hyperparameter tuning, and real-time inference evaluations, ensuring suitability for deployment in autonomous driving systems. Our study contributes by providing a scalable, high-accuracy TSRS model that can reliably identify traffic signs in complex environments, supporting both autonomous and assisted driving technologies. The model’s performance paves the way for safer and more efficient road transport, while our results highlight the potential for further interdisciplinary research to expand TSRS capabilities. © 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

Enhancing Healthcare: Incorporating Blockchain into Electronic Health Records

Enhancing Healthcare: Incorporating Blockchain into Electron...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Saniya Saratkar Meher Langote Aarti Chaudhari Trupti Thute Rohini Raut Gayatri Thakre Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

Handling large amounts of medical data on a blockchain can be challenging, maintaining patient privacy while ensuring data accessibility requires careful design. The healthcare sector is constantly changing, and in order to meet the issues of data security, interoperability, and patient empowerment, it is essential to integrate innovative technology. With its reputation for being decentralized and impervious to tampering, blockchain technology has become a disruptive factor in the redesign of electronic health records (EHR). Blockchain technology has long been a fascinating field of study, and many different businesses have benefited from its applications. Similar to this, the security, privacy, secrecy, and decentralization of blockchain technology present enormous opportunities for the healthcare industry. However, issues with data management, security, and integrity plague Electronic Health Record (EHR) systems. This research study explores how blockchain technology might revolutionize electronic health record systems and perhaps address these problems.

关键词： Industries Electric potential data privacy Technological innovation data security Medical services Transforms

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning for Detection and Analysis of Depression in Women Using Machine Learning Approaches 4

Ensemble Learning for Detection and Analysis of Depression i...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Mahalle, Parikshit N. Bhuvaneshwari, K.S. Khurana, Shivam Geetha, B. Samrat, Bhavuk Rao, Srikrishna Baskar Vishwakarma Institute of Technology Department of Artificial Intelligence & Data Science Pune India Karpagam College of Engineering Department of Artificial Intelligence and Data Science Coimbatore641032 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of S&h Chennai127 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India Karnataka Bangalore India

ISBN: (纸本)9798331518981

One of the biggest global health issues is cardiovascular disease, which kills a staggering number of people every year. The requirement for early detection pushed the introduction of strong deep learning computational methods, which have enhanced diagnostic accuracy. The goal of this study is to provide a method for detecting cardiovascular disease risk factors using machine learning. This method combines Bagging the classification algorithms (BaC) and boosting basic learners (BoC), using the heart diseases databases given by UCI, to increase prediction accuracy. This kind of classifier takes into account important metrics including maximal heart rate, age, cholesterol levels, and resting pressure in the blood. We beforehand the dataset and run the model via a tenfold cross-validations procedure to ensure its correctness. In order to reach the highest possible level of efficiency, the Bagging Classifier employs a total of 200 estimators, whilst the Boosting Classifier makes use of 100 estimates and a learning rate of 0.134 throughout the training process. In terms of performance criteria such as data delivery rate and data packets loss rate, the suggested system is superior to the current system in terms of its overall performance. When the bagging and boosting classifiers are combined, the total result is superior than the results obtained by either approach alone 98% in data delivery rate. This system's exceptional success may be attributed to the increased reliability it has as a diagnostic instrument for facilitating the early identification of heart illness. It is possible to improve the generalizability of the model by using deeper learning models in a more efficient manner and by using bigger datasets. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Empowering the Grid: A Comprehensive Review of artificial intelligence Techniques in Smart Grids

Empowering the Grid: A Comprehensive Review of Artificial In...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Elkholy, Marwa Shalash, Omar Hamad, Mostafa S. Saraya, M Sabry College Of Engineering & Technology Arab Academy for Science Technology and Maritime Transport Al Alamein Egypt College of Artificial Intelligence Arab Academy for Science Technology and Maritime Transport Al Alamein Egypt Arab Academy for Science Technology and Maritime Transport Research and Development Center Al Alamein Egypt Mansoura university Faculty of Engineering Mansoura Egypt

ISBN: (纸本)9798350351408

There are many operational and technical obstacles in the way of the shift to a decentralized, sustainable smart grid. In the face of growing renewable energy integration, distributed resources, and cyber threats, traditional grid management techniques are ill-suited to handle the real-time optimization, predictive analytics, and autonomous control necessary for dependable and efficient electricity delivery. This study thoroughly analyzes how artificial intelligence (AI) approaches can be used to address the main problems that smart grid systems face. The paper looks at how cutting-edge AI techniques, such as multi-agent systems, deep learning, machine learning, and optimization algorithms, can be used in important smart grid applications. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Vision BEV-MAE: Masked Bird’s Eye View Autoencoders for Camera-based 3D Object Detection

Vision BEV-MAE: Masked Bird’s Eye View Autoencoders for Cam...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Zhenguo Cao, Yuanzhouhan Zhang, Hui Chen, Naiyue Ren, Chao Li, Yidong Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education China School of Computer Science and Technology Beijing Jiaotong University China College of Electronics and Information Engineering Sichuan University China

ISBN: (纸本)9798350368604

3D object detection is one of the fundamental perception tasks in autonomous driving. In recent years, perception in the Bird’s Eye View (BEV) has attracted tremendous attention due to its outstanding ability in preserving geometric cues. However, like other supervised learning tasks, BEV-based perception suffers from inadequate labeled training data. In this work, we propose the Vision BEV-MAE, a self-supervised learning approach for BEV perception from camera images. Specifically, we design a feature-level masking strategy to mask the mid-level representations, i.e., the encoded BEV features instead of directly masking input multi-view images, and reconstruct BEV features with a light-weight decoder. Our Vision BEV-MAE is independent of any geometric data such as point clouds, or any additional supervision, and can be easily implemented within any state-of-the-art BEV perception frameworks to improve the performance. We conduct experiments on benchmark dataset to validate our approach. © 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

Facial Expression Recognition Model Depending on Optimized Support Vector Machine

引用

Computers, Materials & Continua 2023年第7期76卷 499-515页

作者： Amel Ali Alhussan Fatma M.Talaat El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Mona Alnaggar Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Machine Learning&Information Retrieval Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Robotics and Intelligent Machines Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt

In computer vision,emotion recognition using facial expression images is considered an important research *** learning advances in recent years have aided in attaining improved results in this *** to recent studies,multiple facial expressions may be included in facial photographs representing a particular type of *** is feasible and useful to convert face photos into collections of visual words and carry out global expression *** main contribution of this paper is to propose a facial expression recognitionmodel(FERM)depending on an optimized Support Vector Machine(SVM).To test the performance of the proposed model(FERM),AffectNet is *** uses 1250 emotion-related keywords in six different languages to search three major search engines and get over 1,000,000 facial photos *** FERM is composed of three main phases:(i)the data preparation phase,(ii)Applying grid search for optimization,and(iii)the categorization *** discriminant analysis(LDA)is used to categorize the data into eight labels(neutral,happy,sad,surprised,fear,disgust,angry,and contempt).Due to using LDA,the performance of categorization via SVM has been obviously *** search is used to find the optimal values for hyperparameters of SVM(C and gamma).The proposed optimized SVM algorithm has achieved an accuracy of 99%and a 98%F1 score.

关键词： Facial expression recognition machine learning linear dis-criminant analysis(LDA) support vector machine(SVM) grid search

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：