检索结果-内蒙古大学图书馆

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Mahalakshmi, V. Poornima, V. Vel's Institute of Science Technology and Advanced Studies Department of Computer Science Tamil Nadu Chennai India

ISBN: (纸本)9798331530013

Cloud Computing (CC) enables organizations and individuals to alter and revolutionize the procedure by which people obtain and utilize resources. Due to the growth of the CC, the complexity increases and the cloud systems demand an effective solution for optimal resource allocation. However, effective utilization of resources in CC systems remains a significant problem due to their scale, heterogeneity, and dynamic nature. Artificial Intelligence (AI) has grown up as an effective means to improve management of resources effectively. Task scheduling is one of the major aspects in resource allocation and this study focuses on dynamic task scheduling algorithms to effectively allocate the task to the appropriate Virtual Machines (VMs). This study examines and suggests the reinforcement learning approach with a whale optimization algorithm (RL-WOA) for efficient task allocation in the cloud environment and its performance in terms of efficiency measures in terms of QoS metrics, makespan, CPU utilization and memory usage. The implementation performed using a CloudSim simulator for demonstrating the efficiency of the suggested model. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Utilizing support vector machines for predictive analytics in chronic kidney diseases

引用

Materials Today: Proceedings 2022年 81卷 951-956页

作者： Shanthakumari, A.S. Jayakarthik, R. Department of Computer Science Vels Institute of Science Technology and Advanced Studies Tamilnadu Chennai India

Chronic kidney disease (CKD), due to rising patients, the high probability of deterioration towards end-stage renal disease and inaccurate estimates of morbidity and mortality, constitutes a heavy burden on the sanitary infrastructure. The aim of this research is to build a model for machine-learning, which uses comorbidity and data on drugs and predicts population prevalence. Predictive health care prediction using machine learning is a daunting activity to help clinicians assess the precise therapies for life-saving. In this paper, the study applies machine learning method in combination with ensemble learning for estimation of chronic kidney disease with clinical evidence. They are based on chronic kidney disease datasets and the efficiency of these models is compared to choose the best classifier for chronic kidney disease prediction. The comparative analysis is estimated in terms of various metrics like classification accuracy, f-measure, percentage error, etc. The results of simulation shows that the proposed ensemble machine learning classifier namely Ensemble Support Vector Machine predicts well the chronic kidney disease from the datasets than other existing ensemble methods. © 2021

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Traffic Light System With Embedded GPS (Global Positioning System) and GSM (Global System for Mobile Communications) Shield

引用

International Journal of Ambient Computing and Intelligence 2023年第1期14卷 1-13页

作者： Gaol, Ford Lumban Alam, Pramasiwo Franklyn, Muhammad Bio Angke, Kevins Matsuo, Tokuro Computer Science Department Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Advanced Institute of Industrial Technology Edogawa Japan

Artificial intelligence traffic controllers are being designed with the primary goal of enabling them to adapt to the most recent sensor data in order to perform ongoing optimizations on the signal timing plan for intersections in a network in order to reduce traffic congestions, the most pressing issue in traffic flow control at present. The authors are employing an intelligent traffic redirection technology to reduce traffic and road congestion. This would operate utilizing sensors to determine weight, with the result communicated to a traffic light PLC to control the detour. The result of experiments reduced the number of automobiles in a given time interval by 51%. There is improvement as well as on the average speed of automobiles that increase within the system by 49%. The authors also found a reduction of the average time a vehicle must wait in a system by 58%. Moreover, the implementation shows that the average wait times at junctions have been reduced by 34%. © 2023 IGI Global. All rights reserved.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Investigating the Efficiency of a Federated Learning-Based Intrusion Detection System for Smart Grid

引用

SN computer science 2025年第3期6卷 1-14页

作者： Hamdi, Najet Department of Computer Science Higher Institute of Technological Studies Medenine 4100 Tunisia

With integration of IoT technologies, the power grid is getting more connected with external networks. This exposes its supervisory control and data acquisition (SCADA) system, the enabler component of smart grids, to severe cyberattacks. To secure smart grids, early identification of anomalies and threats is of utmost importance. Machine learning based intrusion detection systems (IDS) have shown reliable and efficient performance. Most of the proposed IDS are based on centralized learning where data is collected from remote smart devices and transferred to central server for training. Such centralized-based IDS brought up data security and user privacy concerns. To preserve user privacy, federated learning (FL)-based IDS have recently been suggested. FL keeps training data at the client’s side and distributes an aggregated global model which will be trained locally. However, distributed datasets are usually non Independently and Identically Distributed (non-IID) which can decrease the performance of machine learning models. In this paper, we investigate the efficiency and performance of federated-based IDS under non-IID data settings. We, in this study, investigate a different case of label skew where class distributions are significantly skewed within the same client (as when attacks are recently identified and hence only found in the test dataset). Experimental results show that the efficiency of federated-based IDS is reduced significantly when compared to regular scenarios where attacks in the training and testing datasets are the same. The findings also suggest that missing classes not only affect the performance of the related client but also propagate to other clients. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Centralized learning Class distributions Cyber attacks Federated learning IDS Smart grid

来源：评论

学校读者我要写书评

暂无评论

Analyzing Brain Damages in Children with Image Processing Using KNN and FCM Algorithms

引用

SN computer science 2024年第1期5卷 62页

作者： Kayathri, B. Prasanna, S. School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India Department of Computer Applications Vels Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

In current scenario, children are addicted towards mobile communication devices such as mobile phone, tablet and various wireless devices. Exploring more radio frequencies with these devices causes brain damage in children aged 5–10 years. This paper uses an original calculation for the examination of the cerebral image. Typically, an MRI scan or CT scan will show the Cerebrum’s living structures. The brain of children is scanned in MRI and analyzed through image processing to know whether the children put their lives in danger or not, parents should be aware of their kids’ true health. The analysis of training data selected from MRI scan pictures yields 96.3% accuracy in determining the outcomes through examination of the children’s brains. Hence, the findings of brain analyses on various children are examined. Thus, the existing methods to analysis on finding brain damage which is not enough to sort out the problem still, so proposed method is needed to find Brain Damage Findings (BDF) which has to work prominently compared with the existing methods of FCM and KNN with unique test and trained data of brain. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Communication devices CT (computerized Tomography) Damage FCM (Fuzzy C-Means) KNN (K-Nearest Neighbour) MRI (Magnetic Resonance Imaging)

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Belief Network with Butterfly Optimization Algorithm for the Classification of Paddy Leaf Disease Detection 3

A Novel Deep Belief Network with Butterfly Optimization Algo...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Lathamaheswari, U. Jebathangam, J. Vels Institute of Science Technology and Advanced Studies Department of Computer Science Chennai India

ISBN: (纸本)9781665462167

The widespread presence of a wide variety of diseases during paddy farming is one of the most significant elements that annually contributes to enormous economic losses. These losses occur as a direct result of the widespread prevalence of these diseases. In this paper, a deep learning algorithm using Deep Belief Network (DBN) and a meta-heuristic optimization using Butterfly optimization algorithm (BOA) is used to classify the images to detect the diseases in a Plant Leaf. The steps of classification involve three different process that includes pre-processing, feature extraction and classification. The simulation is conducted in python to test the efficacy of the classifier. The result of simulation shows that the proposed method has obtained higher classification rate than the existing machine learning classifiers.. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

RFECV-DT: Recursive Feature Selection with Cross Validation using Decision Tree based Android Malware Detection 15

RFECV-DT: Recursive Feature Selection with Cross Validation ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Awasthi, Naimisha Gautam, Prateek Raj Sharma, Anuj Kumar Aktu Centre for Advanced Studies Department of Computer Science and Engineering Lucknow India Upes School of Computer Science Dehradun India Aktu Centre For Advanced Studies Department of Mechatronics Lucknow India

ISBN: (纸本)9798350370249

The internet is extremely valuable, but it is also vulnerable to assault. Malware is a persistent and dynamic danger. Malware assaults entail introducing malicious code into software. The task was handled using a variety of machine learning approaches. Previous research utilized various methods, such as chi-square, Fisher's score, and Forward/Backward methods. A recent work used a wrapper strategy of Recursive Feature Elimination with Cross-Validation using the nonlinear Support Vector Machine (SVM) as an estimator. This lowered the number of features from 215 to 74, yielding an accuracy percentage of 95.58%. Our solution improves on the previous strategy by using the same dataset and a decision tree with Recursive Feature Elimination with Cross-Validation using Decision Tree to identify 53 out of 215 feature. Classifiers other than Naive Bayes and Logistic Regression are all obtaining the highest accuracy of 98%. This paper decreases the number of features by using Gini Impurity and Cross Validation for detection of Android Malware. © 2024 IEEE.

关键词： Decision Tree Feature Importance Feature Selection Machine Learning Malware Detection Recursive Feature Elimination

来源：评论

学校读者我要写书评

暂无评论

Self-healing hybrid intrusion detection system: an ensemble machine learning approach

引用

Discover Artificial Intelligence 2024年第1期4卷 28页

作者： Kushal, Sauharda Shanmugam, Bharanidharan Sundaram, Jawahar Thennadil, Suresh Energy and Resources Institute Faculty of Science and Technology Charles Darwin University DarwinNT0815 Australia Computer Science and Applications Christ Academy Institute for Advanced Studies Bengaluru India

The increasing complexity and adversity of cyber-attacks have prompted discussions in the cyber scenario for a prognosticate approach, rather than a reactionary one. In this paper, a signature-based intrusion detection system has been built based on C5 classifiers, to classify packets into normal and attack categories. Next, an anomaly-based intrusion detection was built based on the LSTM (Long-Short Term Memory) algorithm to detect anomalies. These anomalies are then fed into the signature generator to extract attributes. These attributes get uploaded into the C5 training set, aiding the ensemble model in continual learning with expanding signatures of unknown attacks. By generating signatures of unknown attacks, the self-healing attribute of the ensemble model contributes to the early detection of attacks. For the C5 classifier, the proposed model is evaluated on the UNSW-NB15 dataset, while for the LSTM model, it is evaluated on the ADFA-LD dataset. Compared to conventional models, the experimental results show better detection rates for both known and unknown attacks. The C5 classifier achieved a True Positive Rate of 97% while maintaining a false positive rate of 8%. Also, the LSTM model achieved a detection rate of 90% while retaining a 17% False Alarm Rate. As the proposed model learns, its performance in real network traffic also improves and it also eliminates human intervention when updating training data. © The Author(s) 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Introduction to the Special Issue on the Bottleneck of Blockchain Techniques Scalability,Security and Privacy Protection

引用

computer Modeling in Engineering & sciences 2024年第12期141卷 1933-1937页

作者： Shen Su Daojing He Neeraj Kumar Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510006China School of Computer Science and Technology Harbin Institute of Technology(Shenzhen)Shenzhen518055China Department of Computer Science and Engineering Thapar Institute of Engineering and TechnologyPatiala147004India

Blockchain technology has been extensively studied over the past decade as a foundation for decentralized information-sharing platforms due to its promising *** the success of existing blockchain architectures like Bitcoin,Ethereum,Filecoin,Hyperledger Fabric,BCOS,and BCS,current blockchain applications are still quite *** struggles with scenarios requiring high-speed transactions(e.g.,online markets)or large data storage(e.g.,video services)due to consensus efficiency *** restrictions pose risks to investors in blockchain-based economic systems(e.g.,DeFi),deterring current and potential *** protection challenges make it difficult to involve sensitive data in blockchain applications.

关键词： services Ether limitations

来源：评论

学校读者我要写书评

暂无评论

Rotten and Fresh Fruits Classification using Deep Learning 5

Rotten and Fresh Fruits Classification using Deep Learning

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Mishra, Prashant Kumar Singh, Jagrati Centre for Advanced Studies Aktu Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350383522

Accurate and timely classification of fresh and decaying fruits is crucial for upholding quality standards in the food industry. This study introduces a deep learning approach that utilizes images to distinguish between fresh and rotten fruits. The proposed solution effectively addresses this classification challenge by control the capabilities of Convolutional Neural Networks. In this research a diverse dataset is used, comprising labeled images of various fruits in varying states of freshness, encompassing both rotten and fresh examples. Key preprocessing steps, including resizing and normalizing the dataset, is implemented to ensure that the model receives a uniform input. The core of the methodology involves initializing a pre-trained CNN architecture. This approach enables the adaptation of the pretrained model to the specific fruit classification task, ultimately providing an efficient and effective solution for quality control in the food sector. Through the utilization of this approach, our model can inherit valuable feature representations from its pretrained counterpart. To evaluate the performance of the trained model, a distinct test dataset is employed and the results encompass key measurements of performance. With an impressive accuracy of 97.5%, the proposed model outperforms the base paper, which achieves 96.05%. This advancement highlights the model's proficiency in distinguishing between fresh and rotten fruits, underscoring its practical effectiveness. © 2024 IEEE.

关键词： Convolutional Neural Networks KNN Rotten and Fresh Fruits Classification VGG16

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：