检索结果-内蒙古大学图书馆

PPFCM-SMOTE: a novel balancing system for anomaly detection in IoT edge using probabilistic possibilistic fuzzy clustering and SMOTE

引用

International Journal of Information technology (Singapore) 2024年 1-20页

作者： Manokaran, J. Vairavel, G. Vijaya, J. Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai 603 203 India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamil Nadu Tiruchirapalli 621 105 India Department of Data Science and Artificial Intelligence International Institute of Information Technology Chhattisgarh Naya Raipur 493 661 India

The immense growth of the Internet of Things (IoT) technology enables potential intruders easy access to the IoT data. The Anomaly Detection System (ADS) detects abnormal network behavior to prevent these attacks. The imbalanced distribution of IoT data makes the current machine learning-based anomaly detection model ineffective. This study aims to rectify the class imbalance issues by creating a balanced dataset before developing an anomaly detection model. Recently, Synthetic Minority Over-sampling Techniques (SMOTE) is being used to rectify the class imbalance problem in an efficacious way. Further, to reduce the noise in the SMOTE and improve the detection performance, a hybrid balancing technique is developed, combining SMOTE with Probabilistic Possibilistic Fuzzy C-means Clustering (PPFCM-SMOTE). This work is tested with the latest unbalanced IoT network dataset, DS2OS. Our proposed model conducts three sets of investigations: building a balanced dataset for anomaly detection, applying classification techniques to the balanced dataset to evaluate the classification outcome, and confirming the suggested PPFCM-SMOTE performance. The empirical results demonstrate that the proposed hybrid PPFCM-SMOTE with random forest algorithm has obtained 99.45% test accuracy of the anomaly detection systems. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Anomaly detection Hybrid PPFCM-SMOTE Imbalance classification Internet of Things Machine learning

来源：评论

学校读者我要写书评

暂无评论

NEGOTIATOR: A Comprehensive Framework for Human-Agent Negotiation Integrating Preferences, Interaction, and Emotion 33

NEGOTIATOR: A Comprehensive Framework for Human-Agent Negoti...

引用

33rd International Joint Conference on artificial intelligence, IJCAI 2024

作者： Keskin, Mehmet Onur Buzcu, Berk Koçyiğit, Berkecan Çakan, Umut Doğru, Anıl Aydoğan, Reyhan Department of Computer Science Özyeğin University Istanbul Turkey HES-SO Valais-Wallis Sierre Switzerland Department of Artificial Intelligence and Data Engineering Özyeğin University Istanbul Turkey Interactive Intelligence Group Delft University of Technology Delft Netherlands

ISBN: (纸本)9781956792041

The paper introduces a comprehensive human-agent negotiation framework designed to facilitate the development and evaluation of research studies on human-agent negotiation without building each component from scratch. Leveraging the interoperability and reusability of its components, this framework offers various functionalities, including speech-to-text conversion, emotion recognition, a repository of negotiation strategies, and an interaction manager capable of managing gestures designed for Nao, Pepper, and QT, and coordinating message exchanges in a turn-taking fashion. This framework aims to lower the entry barrier for researchers in human-agent negotiation by providing a versatile platform that supports a wide range of research directions, including affective computing, natural language processing, decision-making, and non-verbal communication. © 2024 International Joint Conferences on artificial intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Pre Shoplifting Suspicious Behavior Using Deep Learning 16

Detection of Pre Shoplifting Suspicious Behavior Using Deep ...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Shrestha, Sujan Taniguchi, Yoji Tanaka, Tetsuo Graduate school of Engineering Kanagawa Institute of Tehnology Course of Information and computer sciences Atsugi Japan Daiichi Institute of Technology Artificial Intelligence and Data Science Department of Information Tokyo Japan Kanagawa Institute of Technology Faculty of Information Technology Dept. of Information and Computer Sciences Atsugi Japan

ISBN: (纸本)9798350377903

Shoplifting presents a significant challenge for retailers, leading to substantial financial losses and security concerns. Current surveillance systems effectively identify shoplifting incidents postoccurrence;however, the capability to detect and prevent such activities preemptively remains limited. This research focuses on identifying behaviors that likely precede shoplifting events. To this end, we introduce a novel benchmark dataset, specifically designed for the early detection of suspicious behavior that may lead to shoplifting. This dataset is curated by selecting and segmenting relevant sequences from the UCF101-Crime dataset, encompassing suspicious behavior, actual shoplifting incidents, and normal activities. Our approach addresses the limitations of existing datasets where the brief duration of shoplifting events may skew neural network performance. The dataset includes clips of only a few seconds each, for which we propose a robust neural network architecture combining the strengths of convolutional neural networks (CNN) for efficient feature extraction and Bidirectional long short-term memory (BiLSTM) networks for capturing temporal dependencies within action sequences. Our model achieves an impressive classification accuracy of 86.21 % on the newly created dataset. © 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 Wireless Sensor Network Efficiency through Al-Biruni Earth Radius Optimization

引用

Computers, Materials & Continua 2024年第6期79卷 3549-3568页

作者： Reem Ibrahim Alkanhel Doaa Sami Khafaga Ahmed Mohamed Zaki Marwa M.Eid Abdyalaziz A.Al-Mooneam Abdelhameed Ibrahim S.K.Towfek Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Computer Science and Intelligent Systems Research Center BlacksburgVirginia24060USA Delta Higher Institute for Engineering and Technology Mansoura35511Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Artificial Intelligence and Computational Intelligence Research Center MeridenConnecticut06450USA School of ICT Faculty of EngineeringDesign and Information&Communications Technology(EDICT)Bahrain PolytechnicP.O.Box 33349Isa TownBahrain

The networks of wireless sensors provide the ground for a range of applications,including environmental moni-toring and industrial *** the networks can overcome obstacles like power and communication reliability and sensor coverage is the crux of network *** infrastructure planning should be focused on increasing performance,and it should be affected by the detailed data about node *** work recommends the creation of each sensor’s specs and radius of influence based on a particular geographical location,which will contribute to better network planning and *** using the ARIMA model for time series forecasting and the Al-Biruni Earth Radius algorithm for optimization,our approach bridges the gap between successive terrains while seeking the equilibrium between exploration and *** implementing adaptive protocols according to varying environments and sensor constraints,our study aspires to improve overall network *** compare the Al-Biruni Earth Radius algorithm along with Gray Wolf Optimization,Particle Swarm Optimization,Genetic Algorithms,and Whale Optimization about performance on real-world *** the most efficient in the optimization process,Biruni displays the lowest error rate at *** two other statistical techniques,like ANOVA,are also useful in discovering the factors influencing the nature of sensor data and network-specific *** to the multi-faceted support the comprehensive approach promotes,there is a chance to understand the dynamics that affect the optimization outcomes better so decisions about network design can be *** delivering better performance and reliability for various in-situ applications,this research leads to a fusion of time series forecasters and a customized optimizer algorithm.

关键词： Wireless sensor networks optimization ARIMA model BER algorithm metaheuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Design of 2X1 Monopole Array Antenna for WiMAX and WiLAN Applications 1

Design of 2X1 Monopole Array Antenna for WiMAX and WiLAN App...

引用

1st International Conference on Computational intelligence for Security, Communication and Sustainable Development, CISCSD 2024

作者： Vennela, R. Neeraj, N. Lakshmi Feroze, Abdul Ushasree, A. Kodipalli, Ashwini Satyanarayana, M. Kumar, N. Udaya Griet Department of Electronics and Communication Engineering Hyderabad India Global Academy of Technology Artificial Intelligence and Data Science Bangalore India Mvgr College of Engineering Department of Electronics and Communication Engineering Vizag India Vivekananda Institute of Technology Department of Electronics and Communication Engineering Bangalore India

ISBN: (纸本)9798350365405

This paper presents a thorough examination of the performance attributes of a 2x1 monopole array antenna employing variations in strip configurations. The study focuses on evaluating the influence of single, double, and triple strips on key parameters including return loss, VSWR, and gain. The design methodology involves rigorous simulations and optimization techniques to achieve optimal antenna performance. Results reveal significant differences in the performance metrics among the different configurations. The single strip configuration demonstrates a certain level of performance, while the addition of multiple strips, particularly the double strip configuration, exhibits enhanced characteristics in terms of lower return loss, VSWR, and higher gain. Comparative analysis is conducted to highlight the advantages and limitations of each configuration, providing valuable insights for designing monopole array antennas tailored to specific application requirements. This study contributes to advancing the understanding of monopole array antenna design principles and optimization strategies for wireless communication systems. © 2024 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

iCrop: a framework for identification of millet crop diseases via segmentation and feature extraction

引用

Indian Phytopathology 2023年第3期76卷 803-812页

作者： Singh, Sonal Dashore, Swastik Prasad, Jatin Naik, Nenavath Srinivas Data Science and Artificial Intelligence International Institute of Information Technology Chhattisgarh Naya Raipur 493661 India Computer Science and Engineering Indian Institute of Information Technology Design and Manufacturing (IIITDM) Kurnool Andhra Pradesh Kurnool 518008 India

Crop diseases are important in agricultural productivity and quality. It is essential to recognise and diagnose these diseases. Deep learning’s ability to correctly classify small data sets is a major research challenge. This work proposes an approach using image segmentation, feature extraction and deep learning techniques to develop a multi-class classifier for millet crop disease identification. The proposed image processing approach and use of artificial Neural Networks demonstrate disease classification over 2632 images with a training accuracy of 97.25% and a testing accuracy of 96.88%. Compared with the pre-trained model MobileNet V3, the implemented model achieved better training and validation accuracy over 100 epochs and required less training time. The proposed model’s simplicity makes crop disease detection in agriculture fast and efficient. As a result, the suggested method paves the way for large-scale crop disease diagnosis. © 2023, Indian Phytopathological Society.

关键词： artificial neural networks Deep learning Feature extraction Image segmentation Millet crop disease

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heart Disease using Computational Algorithms 6

Prediction of Heart Disease using Computational Algorithms

引用

6th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2022

作者： Shobha, V. Smitha, C. Kodipalli, Ashwini Global Academy of Technology Computer Science and Engineering Bangalore India Global Academy of Technology Artificial Intelligence and Data Science Bangalore India

ISBN: (数字)9781665487160

ISBN: (纸本)9781665487160

Nowadays, peoples are suffering from heart diseases steadily because of their ignorance towards their physical-fitness. Globally there are 32% population are suffering from heart disease by world health organization(WHO).The death rates are increasing because of heart attacks and even the peoples are suffering across the global for all kind of Genders because of heart problems. The cases of heart attack is increasing day-by-day. The prediction of heart diseases are very needful to the health sectors includes the hospitals, sanatoriums, nursing and medical because it is difficult to analyze the huge data. The better prediction of heart disease can prevent the life threats. There are many algorithms had used to predict the heart disease but In this paper many Machine Learning Classification algorithms are applied such as Logistic Regression, K-Nearest Neighbor(KNN), Decision tree-classifier, Random Forest, Naive Bayes and support vector machine. Here we have done the comparative study of all the algorithms mentioned in the above lines. This heart disease dataset is collected from ***. The objective of the paper is to find the better accuracy provided by the algorithm. Several outcomes has achieved and verified using accuracy and confusion matrix. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Machine Learning Methods for Predicting Heart Disease: A Comparative Analysis 8

A Comprehensive Study on Machine Learning Methods for Predic...

引用

8th International Conference on Computing in engineering and technology, ICCET 2023

作者： Das, Trinanjan Sinha, Bam Bahadur Department of Data Science and Artificial Intelligence Indian Institute of Information Technology Jharkhand Ranchi834010 India Department of Computer Science and Engineering Indian Institute of Information Technology Jharkhand Ranchi834010 India

ISBN: (纸本)9781839539237

The objective of the research is to create a robust and precise machine learning model capable of accurately predicting the presence of heart disease in patients based on various clinical attributes. The study employed supervised machine learning techniques, including Support Vector Machine (SVM), Naive Bayes, Decision Tree, K-Nearest Neighbour, Logistic Regression, and artificial Neural Network, as well as ensemble techniques to enhance the performance of the model. The Statlog Heart Disease dataset, consisting of 14 attributes and 270 instances, was utilized for model development and testing. The results demonstrated that the Support Vector Machine (SVM) and Voting Classifier, among the ensemble techniques, exhibited the highest classification accuracy. The developed model has the potential to assist healthcare professionals in identifying the risk of heart disease in patients, facilitating early diagnosis and treatment, and potentially reducing mortality rates. In conclusion, this paper emphasizes the significant role of machine learning techniques in the early detection and diagnosis of heart disease, offering an accurate and efficient method to identify individuals at risk. © The Institution of engineering & technology 2023.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Autonomous Learning of Fuzzy Recurrent Neural Networks for Human Activity Recognition

Autonomous Learning of Fuzzy Recurrent Neural Networks for H...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Liang, Shuai Bing Loo, Chu Kiong Sabri, Aznul Qalid Md Wong, Kok Wai Universiti Malaya Faculty of Computer Science and Information Technology Department of Artificial Intelligence Malaysia School of Engineering and It Murdoch University MurdochWA Australia

ISBN: (纸本)9798350303780

In this article, an Autonomous Fuzzy Echo State Network (AFESN) algorithm is being proposed. This algorithm combines Autonomous Learning Multi-Model Systems and Echo State Network (ESN) to perform Human Activity Recognition on the Heterogeneity Human Activity Recognition HHAR dataset. We incorporate the structural information of the dataset into the ESN by using the Takagi-Sugeno (TS) models/rules concept. The process of obtaining the structural information in the dataset was fully automated by the unimodal density based membership function, which then acts as the antecedent part. Subsequently, a consequent part composed by ESN was used to replace the affine models commonly used in TS models. The final model predictions are inferred by the fuzzy-weighed mechanism in a new fuzzy rule composed of multiple ESNs. Since our algorithm is fully automatic and does not require any prior knowledge, its use in online learning scenarios is adequately applicable. Lastly, the effectiveness of the algorithm is tested using the HHAR dataset and an accuracy of 42.9% was obtained. Compared with the performance of recent Autonomous Learning Multi-Model Systems (19.6%), our algorithm has gained a significant improvement. © 2023 IEEE.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Real Time Crop Health Monitoring Through Convolution Neural Networks 4

Real Time Crop Health Monitoring Through Convolution Neural ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Sridevi, Bommagani Padma, Nanda Manjusha, Puram Tirunagari, Sharanya Hariharan, Shanmugasundaram Famila, S. Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Hyderabad India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics & Communication Engineering Tamil Nadu Chennai602001 India

ISBN: (纸本)9798331529635

The agriculture sector, also known as the primary sector in India, is currently facing significant challenges due to the increasing number of pests and insects. These pests can cause serious damage to crop fields, negatively affect crop health, reduce yields, and lead to substantial economic losses for farmers. Early detection of crop diseases can help minimize yield losses by 20-40%, depending on the specific crop type and its various growth stages. The paper discusses the important use of deep learning algorithms in agriculture, specifically focusing on developing an effective approach for the automatic detection of crop diseases through advanced image analysis techniques. The proposed Convolutional Neural Network (CNN) model architecture consists of multiple layers that extract meaningful features from images using convolution and pooling operations. After the feature extraction process, additional layers are used for accurately classifying the images into different disease categories. This model is trained using the Adam optimizer, which is known for its efficiency in handling large datasets and improving the overall training speed. It employs sparse categorical cross-entropy loss over 50 epochs, with a batch size of 32, to effectively optimize the learning process. During the training phase, the model's accuracy is continuously monitored to assess its performance and make any necessary adjustments to enhance its effectiveness. One of the key innovations of this approach is the ability to perform real-time crop disease detection using a camera. This advancement eliminates the need for manual picture collection from the fields, making the entire process faster and much more efficient. By enabling farmers to quickly identify diseases, this cutting-edge technology can significantly help improve crop management practices and increase overall agricultural productivity. Ultimately, the goal is to enhance food security and reduce economic losses in the agriculture sect

关键词： Convolutional neural networks

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：