检索结果-内蒙古大学图书馆

Enhancing Security in Automobile Edge Computing through Federated learning and Blockchain

Enhancing Security in Automobile Edge Computing through Fede...

Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security (iQ-CCHESS), International Conference on

作者： Sandosh S Sujay Doshi Atharva Joshi Faculty for Computer Science with specialization in Artificial Intelligence and Machine Learning Vellore Institute of Technology Chennai India Computer Science with specialization in Artificial Intelligence and Machine Learning Vellore Institute of Technology Chennai India

Vehicular networks that consist of interlinked automobiles and transportation network are prone to cyberattacks due to the increased use of software and the presence of wireless interfaces. To counter these threats, intrusion detection systems can be tailored efficiently. In recent years, there has been significant development in detection of malicious attack traffic through the use of machine learning. However, traditional systems require powerful computing devices to continuously train and update complex network models, which can reduce the efficiency and effectiveness of the system due to resource constraints, untimely updates and dealing with large volumes of data. To address this issue, a cooperative intrusion detection mechanism which had been proposed has been improved with a classification based novel approach, that eases the burden by distributing the training model to distributed edge devices such as connected vehicles and roadside units. The previous approach has a slow response time to the increasing network issues. The proposed work offers a new approach through federated learning with the Extra Trees Classification algorithm. The Extra Trees Classifier performs better than other machine learning models in all aspects. The proposed approach provides a faster response to security threats in automobile edge computing. The use of a distributed federated approach reduces the load on the server while maintaining confidentiality by aggregating models using a blockchain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Deep learning: Taxonomy and Survey of the State of the Art

arXiv

引用

arXiv 2024年

作者： Peitz, Sebastian Hotegni, Sedjro Salomon Department of Computer Science TU Dortmund Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Simultaneously considering multiple objectives in machine learning has been a popular approach for several decades, with various benefits for multi-task learning, the consideration of secondary goals such as sparsity, or multicriteria hyperparameter tuning. However—as multi-objective optimization is significantly more costly than single-objective optimization—the recent focus on deep learning architectures poses considerable additional challenges due to the very large number of parameters, strong nonlinearities and stochasticity. This survey covers recent advancements in the area of multi-objective deep learning. We introduce a taxonomy of existing methods—based on the type of training algorithm as well as the decision maker’s needs—before listing recent advancements, and also successful applications. All three main learning paradigms supervised learning, unsupervised learning and reinforcement learning are covered, and we also address the recently very popular area of generative modeling. © 2024, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of Weed Detection Technique Using Yolo Models

Design of Weed Detection Technique Using Yolo Models

引用

Students Conference on Engineering and Systems (SCES)

作者： Sreehari M Ankur Jain Department of computer science engineering specialization Artificial intelligence and Machine Learning Vellore Institiute of Technology Bhopal India

ISBN: (数字)9798350374711

ISBN: (纸本)9798350374728

The use of the ADAM (Adaptive Moment Estimation) and SGD (Stochastic Gradient Descent) algorithms to optimize the YOLOv7(You Only Look Once), YOLOv8, and YOLO-NAS models for weed detection in agricultural landscapes is investigated in this study. Offering a thorough comparative study based on mean Average Precision (mAP), recall, and precision measures is the goal. When compared to YOLOv7, YOLOv8 regularly performs better, exhibiting balanced recall and higher precision. With remarkable mAP scores at IOU (Intersection Over Union) 0.50, YOLOv8 ADAM in particular sticks out, demonstrating strong weed identification abilities. The YOLOv7 ADAM exhibits a precision-recall trade-off, with precision being slightly sacrificed for recall. Model superiority is not solely determined by the optimization algorithm used (ADAM vs. SGD); YOLOv8 variations perform admirably. For real-world implementation, practical factors like processing efficiency and deployment viability are even more important than quantitative criteria. This work establishes the foundation for comprehending the complex trade-offs and advantages that are present in every model and algorithm, in addition to helping with the educated selection of the best YOLO models for weed detection. Future research directions in object detection in agriculture, including ensemble techniques and hyperparameter tuning, promise more advancements in this subject as technology develops.

关键词： YOLO Analytical models Accuracy Stochastic processes Ensemble learning Reliability Task analysis

来源：评论

学校读者我要写书评

暂无评论

Leveraging Automated POS Tagging to Decode Parent-Infant Interactions in Digital Gameplays 24

Leveraging Automated POS Tagging to Decode Parent-Infant Int...

引用

8th International Conference on Innovation in artificial intelligence, ICIAI 2024

作者： Yeh, Wan-Ting Knott, Alistair Henderson, Annette M. E. Early Learning Lab School of Psychology University of Auckland Auckland New Zealand Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington New Zealand

ISBN: (纸本)9798400709302

Parental speech plays a crucial role in infant language acquisition, often varying based on contextual activities like gameplay or object learning. In interactive computerized tasks, these utterances can exhibit distinct lexical focuses. Unlike conventional text summarization tasks where structured sentences are expected, parental speech often exhibits a more informal structure. These nuances become especially evident across interactive computerized tasks, each imposing a distinct lexical focus. This study leverages machine learning to analyze parental utterances from computerized gameplays, combining developmental psychology and Natural Language Processing (NLP). We utilized real parent-infant datasets and part of speech (POS) tagging for lexical analysis. Our results elucidate the intricate relationships between diverse social contexts, the intended purposes of digital games, and the digital environment, encompassing shared tablet interfaces and video chat platforms. Such findings are paramount to understanding infants' linguistic development and offer valuable insights for the domains of developmental psychology, linguistic and machine-learning research. © 2024 ACM.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

An Optimal Scheduling of Energy Storage Units in Renewable Energy Systems Using Strength-Pareto Evolutionary Algorithm

An Optimal Scheduling of Energy Storage Units in Renewable E...

引用

2024 International Conference on Intelligent Algorithms for Computational intelligence Systems, IACIS 2024

作者： Kumari, Nalli Vinaya Kumar, Komuravelly Sudheer Alsalami, Zaid Harshitha, P. Ramadan, Ghazi Mohamad Jntuh Malla Reddy Engineering College for Women Department of Computer Science and Engineering Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ahl Al Bayt University College of Mlt Karbala Iraq

ISBN: (纸本)9798350360660

Dual-stage optimization scheduling model by hybrid energy storage for grid-connected renewable energy systems, is proposed in this paper which focuses on both intra-day and day-ahead phases. In day-ahead phase, model improves economic efficiency by considering of price values at its peak value difference. In intra-day phase, its motive is to decrease renewable energy usage and it's related with the day-ahead schedules using accurate, short-term predictions. Strength-pareto evolutionary algorithm 2 (SPEA2) algorithm for optimization is for multiple objective optimizations, achieving optimal and balanced solutions across multiple objectives. This SPEA2 optimization algorithm efficient handles and it enables system to cost-effectively and firmly operate and optimizing scheduling of grid-connected systems by addressing both the aspects of economic and operational. Overall, the model improves economic efficiency, reduces 6.3% the usage of renewable energy, and improves the sustainability power grid through effective integration and utilization of renewable energy sources. © 2024 IEEE.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Spatial Attention Mechanism Integrated Ensemble machine learning for Real Time Prediction and Classification in Precision Agriculture

Spatial Attention Mechanism Integrated Ensemble Machine Lear...

引用

2024 International Conference on Intelligent Algorithms for Computational intelligence Systems, IACIS 2024

作者： Adnan, Myasar Mundher Vijay Kumar, Bura Madhura, G.K. Mohammed, G. Das, Abhijeet The Islamic University Engineering College of Technical Engineering Department of Computers Techniques Najaf Iraq Sr University School of Computer Science and Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ahl Al Bayt University Karbala Iraq Department of Civil Engineering Bhubaneswar India

ISBN: (纸本)9798350360660

Generating spatial and temporal features for real time prediction and classification in precision agriculture is challenging due to inaccurate estimation of features from the remote sensing images. Using Geographical Information System (GIS) and systematic data regarding spatial and temporal data for monitoring and management of agricultural activities. The proposed research integrated GIS and used satellite image processing with Ensemble machine learning (EML) algorithms. Initially, the remote sensing data is pre-processed with normalization technique to remove noise. The pre-processed data is given as input to the Improved Speeded Up Robust Features (ISURF) for fast computation and identification of relevant features. The EML algorithms such as Random Forest (RF), Support Vector machine (SVM), and artificial Neural Network (ANN) are used as a prediction and classification models considering the ISURF features as input. Additionally, the Spatial Attention Mechanism (SAM) is integrated with the EML algorithm to particularly focus on the spatial features of the remote sensing data. The experimental results showed that the proposed SAM-EML achieved precise prediction and classification with 98.30% accuracy, and 97.19% precision when compared to the existing methods Random Forest Regression (RFR) and RF-SVM. © 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

learning discrete latent variable structures with tensor rank conditions 24

Learning discrete latent variable structures with tensor ran...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhengming Chen Ruichu Cai Feng Xie Jie Qiao Anpeng Wu Zijian Li Zhifeng Hao Kun Zhang School of Computer Science Guangdong University of Technology and Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence School of Computer Science Guangdong University of Technology Department of Applied Statistics Beijing Technology and Business University Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence and Department of Computer Science and Technology Zhejiang University Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence School of Computer Science Guangdong University of Technology and College of Science Shantou University Shantou Guangdong China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence and Department of Philosophy Carnegie Mellon University

ISBN: (纸本)9798331314385

Unobserved discrete data are ubiquitous in many scientific disciplines, and how to learn the causal structure of these latent variables is crucial for uncovering data patterns. Most studies focus on the linear latent variable model or impose strict constraints on latent structures, which fail to address cases in discrete data involving non-linear relationships or complex latent structures. To achieve this, we explore a tensor rank condition on contingency tables for an observed variable set Xp, showing that the rank is determined by the minimum support of a specific conditional set (not necessary in Xp) that d-separates all variables in Xp. By this, one can locate the latent variable through probing the rank on different observed variables set, and further identify the latent causal structure under some structure assumptions. We present the corresponding identification algorithm and conduct simulated experiments to verify the effectiveness of our method. Our results elegantly expand the application scope of causal discovery with latent variables.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT-Deep learning Based Activity Recommendation System

引用

computer Systems science & Engineering 2023年第5期45卷 2001-2016页

作者： Sharmilee Kannan R.U.Anitha M.Divayapushpalakshmi K.S.Kalaivani Department of Electronics and Communication Engineering Nandha Engineering CollegePerundurai638052TamilnaduIndia Department of Computer Science Sona College of Arts and ScienceSalem636005TamilnaduIndia Department of Artificial Intelligence and Machine Learning Engineering Gokaraju Rangaraju Institute of Engineering and TechnologyHyderabad500090TelanganaIndia Department of Computer Science and Engineering Kongu Engineering CollegePerundurai638060TamilnaduIndia

The rising use of mobile technology and smart gadgets in the field of health has had a significant impact on the global *** professionals are increasingly making use of the benefits of these technologies,resulting in a major improvement in health care both in and out of clinical *** Internet of Things(IoT)is a new internet revolution that is a rising research area,particularly in health *** Monitoring Systems(HMS)have progressed rapidly as the usage of Wearable Sensors(WS)and smartphones have *** existing framework of conventional telemedicine’s store-and-forward method has some issues,including the need for a nearby health centre with dedicated employees and medical devices to prepare patient ***’health can be continuously monitored using advanced WS that can be fitted or embedded in their *** research proposes an innovative and smart HMS,which is built using recent technologies such as the IoT and machine learning(ML).In this study,we present an innovative and intelligent HMS based on cutting-edge technologies such as the IoT and Deep learning(DL)+Restricted Boltzmann machine(RBM).This DL+RBM model is clever enough to detect and process a patient’s data using a medical Decision Support System(DSS)to determine whether the patient is suffering from a major health problem and treat it *** recommended system’s behavior is increasingly investigated using a cross-validation test that determines various demographically relevant standard *** a healthcare DSS,this framework is clever enough to detect and analyze a patient’s *** results further reveal that the proposed system is efficient and clever enough to deliver health *** data reported in this study demonstrate the *** device is a low-cost solution for people living in distant places;anyone can use it to determine if they have a major health problem and seek treatment by contacting nearby hospitals.

关键词： Deep learning IoT healthcare system activity recommender system body sensors

来源：评论

学校读者我要写书评

暂无评论

Detecting the Anomaly Attacks in Industrial IoT using Hybrid Feature Selection Based Modified Convolutional Neural Network

Detecting the Anomaly Attacks in Industrial IoT using Hybrid...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Rallapalli, Sreekanth Kumar Tiwari, Vikas Vidya Sagar, S.D. Kumar Pareek, Piyush Nitte Meenakshi Institute of Technology Department of Master of Computer Applications Bengaluru India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350313413

When it comes to digitally transforming classic sectors towards Industry 4.0, the Industrial Internet of Things (IIoT) is crucial. The IIoT improves the efficiency and productivity of businesses by connecting sensors, equipment used in industries to the Internet for the purposes of data collecting, data analysis, and automated control. Because of the intricate nature of the IIoT infrastructure, anomaly detection has emerged as a crucial method for guaranteeing the platform's viability. As IIoT is inherently suited to continuously growing networks, graph-level anomaly detection has proven to be an effective method for detecting and predicting abnormalities across a wide range of application domains, including transportation, energy, and the factory. This research work suggests an optimization strategy using a combination of the fuzzy technique for order of favorite by similarity to ideal solution (FTOPSIS). For network anomaly detection, the selected characteristics are fed into a modified Convolutional Neural Network (MConvNet). The approach is put through its paces using NBaIoT-balanced benign and malicious network traffic so that it can pick up on the differences between the two. When compared to state-of-the-art models, the findings show that the suggested model outperforms them thanks to the optimization approach's feature selection. © 2023 IEEE.

关键词： Anomaly detection Fuzzy analytic hierarchy process Fuzzy Logic Technique Industrial Internet of Things Modified Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

A Study on Integrating machine learning Techniques for Waste Management 7

A Study on Integrating Machine Learning Techniques for Waste...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Vaidya, Ruchika Dattangire, Rahul Biradar, Divya Verma, Prateek Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Data Engineering Publicis Sapient HoustonTX77002 United States University of Texas Department of Computer Science ArlingtonTX76019 United States

ISBN: (纸本)9798350372816

The current study focuses on how various machine learning (ML) algorithms can be used in waste management and emphasizes the significance of intelligent technologies in addressing contemporary issues. By leading a broad writing survey, the paper features the meaning of incorporating these advances into waste management practices. The system segment subtleties the information assortment, preprocessing, model determination, and assessment measurements utilized in the review. The accuracy and performance metrics of various classifiers, including K Nearest Neighbors, Linear Support Vector Classifier, Logistic Regression, Decision Tree, Multi-Layer Perceptron, and Random Forest, are demonstrated by the results of experiments with them. Especially noteworthy is the MLP classifier's 91.81% accuracy. The discoveries highlight the viability of ML approaches in ssmart waste management. In addition, a comparison table that summarizes the classifiers' accuracy scores provides insight into their suitability for applications in waste management. © 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

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：