检索结果-内蒙古大学图书馆

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and application, HPCC/DSS/SmartCity/DependSys 2022

作者： Li, Gongliang Wen, Zepeng Xie, Xin Institute of Computer Application Technology China Academy of Engineering Physics College of Computer Science Sichuan University Mianyang China Institute of Computer Application Technology China Academy of Engineering Physics Mianyang China

ISBN: (纸本)9798350319934

Current large-scale applications, such as trading systems, blockchain, social software, etc, are increasingly adopting microservice architecture, which bring challenges to manual operation and maintenance, intrusion detection. In both operations and intrusion detection, there are a common characteristic that service metrics and network traffic are normal for most of the time, but anomaly data is more important. In this paper, we propose an unsupervised anomaly detection algorithm based on convolutional neural network with Spectral Residual, which is verified experimentally and has potential application capability with 19.2% f1-score improvement compared to the Variational AutoEncoder. © 2022 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Secure Virtual Machine Allocation for Prevention of Side Channel Attacks in Cloud Computing 1

Secure Virtual Machine Allocation for Prevention of Side Cha...

引用

1st International Conference on Intelligent Controller and Computing for Smart Power, ICICCSP 2022

作者： Rout, Chinmayee Sethi, Srinivas Badajena, J Chandrakanta Sahoo, Ramesh Kumar Computer Science Engineering and Application IGIT Sarang Utkal University Odisha Bhubaneswar India Computer Science Engineering and Application IGIT Sarang Odisha Bhubaneswar India Information Technology Outr Odisha Bhubaneswar India

ISBN: (数字)9781665472586

ISBN: (纸本)9781665472586

Cloud computing allows customers to use a variety of computing resources on-demand and with no maintenance overhead. One of the major issue concerning cloud computing is security. From the end user's perception, migrating to cloud exposes them to additional security risks that are entirely considered to be produced by other occupants who may have some access to shared resources. The co-location or co-residence attack, otherwise called as co-resident assault, is the focus of this research. This is a type of attack in which malevolent individuals construct side channels and steal confidential information from VMs that share the same server. Here we have studied on the co-resident attacks and the mechanisms to detect and prevent the attack. To address this issue, we have focused on the PSSF VM allocation policy as PSSF policy has high security with low energy consumption. © 2022 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Diabetes Prediction System Augmenting Feature Selection and Balancing Techniques 7th

An Intelligent Diabetes Prediction System Augmenting Feature...

引用

7th International Conference on Advanced Computing and Intelligent engineering, ICACIE 2022

作者： Giri, Sourav Kumar Dash, Sujata Sahoo, Tapaswini Department of Computer Science and Engineering Srinix College of Engineering Odisha Balasore756001 India Department of Computer Application Maharaja Sriram Chandra Bhanja Deo University Odisha Baripada757003 India Skill Development Institute Odisha Bhubaneswar India

ISBN: (纸本)9789819950140

Diabetes seems to be a prevalent disease nowadays across the whole globe and is found to be very common on every doorstep. The consequences of this disease are very severe if it remains unnoticed during its initial stage. It affects populations of every age group. The causes of this disease are attributed to genetic links, lack of physical exercise, unhealthy food habits, overstress, etc. Many recent machine learning models have been proposed to predict this disease by considering the historical data of patients who have diabetes. This work attempts to choose a robust and reliable machine learning model for diagnosing the disease from seven widely used classification algorithms such as;Logistic Regression, Decision Tree, Naïve Bayes, Support Vector Machine, Random Forest, XGBoost, and AdaBoost. The model is validated with the PIMA diabetes dataset. The efficiency of the models is augmented by addressing the imbalanced characteristics of the dataset by applying SMOTE technique and a univariate feature selection technique, ‘chi-square’ for feature selection. The experimental findings confirm that the Random Forest model has outperformed other models in terms of accuracy, precision, recall, F-score, and AUC. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Emotion State Detection via Speech using Deep Learning 7

Emotion State Detection via Speech using Deep Learning

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Gupta, Rashmi Kumar, Jeetendra Sharma, Suvarna Atal Bihari Vajpayee University Department of Computer Science and Application Chhattisgarh Bilaspur India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9798350350067

Oral communication is the most efficient and common way to interact with someone. Due to this, voice signalling has attracted researchers for its potential in computer-human communication. Identifying emotions through speech is complex due to various factors like feature selection and vocal diversity. This study uses the RAVDESS and SAVEE datasets and employs techniques including Multilayer Perceptron, Random Forest, Support Vector Machine, k-Nearest Neighbours, Logistic Regression, Gaussian-Neural Network, and Convolutional Neural Network. The identified features encompass the MelFrequency Cepstral Coefficients (MFCC), Chroma, and Mel spectrogram. To conduct a comparison of accuracy rates, we employed seven classifiers across two datasets. Consequently, CNN model demonstrated superior performance in both the RAVDESS and SAVEE databases, with accuracy rates of 96.75% and 92.36% respectively, surpassing other classifiers. © 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

Comparative Analysis of Node-Dependent and Node-Independent Graph Matrices for Brain Connectivity Network 1

引用

4th International Conference on Machine Intelligence and Signal Processing, MISP 2022

作者： Kose, Mangesh Ramaji Ahirwal, Mitul Kumar Atulkar, Mithilesh Department of Computer Application NIT C.G. Raipur492010 India Department of Computer Science and Engineering MANIT M.P. Bhopal462003 India

ISBN: (数字)9789819900855

ISBN: (纸本)9789819900848

Brain connectivity network (BCN) represents an advanced approach for brain functionality analysis. In BCN, the human brain is modeled as a graph, containing vertices and connectivity links. The electroencephalogram (EEG) signals recorded from the diseased as well as healthy subjects are used to construct a BCN. The graph matrices are a quantitative approach for comparing the network of diseased and healthy subjects. The selection of graph matrices to be extracted from the network depends on whether all the networks have the same or a different number of nodes. In this paper, analysis of matrices dependent to numbers of nodes (DNN) and matrices independent to numbers of nodes (INN) has been performed. These matrices are calculated as features from schizophrenia disease EEG datasets having 16 and 19 channels. Analysis of these matrices has been done based on distance and similarity measures. From the results, it is observed that the INN features show less variability as compared to DNN. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Contingency-Based Learning Strategies for Precision Medicine 15

Evaluation of Contingency-Based Learning Strategies for Prec...

引用

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

作者： Kaushik, Harshita Rajendran, Naveen Kumar Kumar, Ashwini Vivekananda Global University Department of Computer Science& Application Jaipur India Department of Aerospace Engineering Karnataka Bangalore India Arka Jain University Department of Mechnical Engineering Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

Contingency-based learning strategies primarily based on synthetic intelligence (AI) are being hired within the area of precision remedy to enable greater powerful selection-making when treating patients. The overall performance of such learning strategies should be evaluated to make sure they are presenting accurate and dependable outcomes. This paper aims to assess contingency-based learning strategies for precision medication to help clinicians and researchers appropriately assess the efficacy of these learning techniques and decide the first-rate method for given software., a scientific evaluation of the current literature was undertaken to identify existing assessment strategies and analyze their strengths and weaknesses. The assessment criteria used in this analysis are accuracy, interpretability, complexity, scalability, and transferability, which had been selected as they affect the performance of AI-primarily based approaches in real-international settings. Furthermore, a discussion of current equipment and frameworks that could be used to assess AI-based techniques in the area of precision remedy was performed. From this assessment, it has been discovered that most of the present assessment techniques lack the necessary accuracy and transferability essential to appropriately check the efficacy of AI-based strategies for precision medicinal drugs. But, sure, evaluation metrics, together with explain ability, may be employed to degree the overall performance of AI-primarily based techniques in order to decide the nice approach for a given application. © 2024 IEEE.

关键词： Contingency Intelligence Interpretability Scalability Software Strategies

来源：评论

学校读者我要写书评

暂无评论

Vision based intelligent traffic light management system using Faster R‐CNN

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 932-947页

作者： Syed Konain Abbas Muhammad Usman Ghani Khan Jia Zhu Raheem Sarwar Naif R.Aljohani Ibrahim A.Hameed Muhammad Umair Hassan Department of Computer Science and Engineering University of Engineering and TechnologyLahorePakistan Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal UniversityJinhuaChina OTHEM Manchester Metropolitan UniversityManchesterUK Faculty of Computing and Information Technology King Abdulaziz UniversityJeddahSaudi Arabia Department of ICT and Natural Sciences Norwegian University of Science and Technology(NTNU)ÅlesundNorway

Transportation systems primarily depend on vehicular flow on roads. Developed coun-tries have shifted towards automated signal control, which manages and updates signal synchronisation automatically. In contrast, traffic in underdeveloped countries is mainly governed by manual traffic light systems. These existing manual systems lead to numerous issues, wasting substantial resources such as time, energy, and fuel, as they cannot make real‐time decisions. In this work, we propose an algorithm to determine traffic signal durations based on real‐time vehicle density, obtained from live closed circuit television camera feeds adjacent to traffic signals. The algorithm automates the traffic light system, making decisions based on vehicle density and employing Faster R‐CNN for vehicle detection. Additionally, we have created a local dataset from live streams of Punjab Safe City cameras in collaboration with the local police authority. The proposed algorithm achieves a class accuracy of 96.6% and a vehicle detection accuracy of 95.7%. Across both day and night modes, our proposed method maintains an average precision, recall, F1 score, and vehicle detection accuracy of 0.94, 0.98, 0.96 and 0.95, respectively. Our proposed work surpasses all evaluation metrics compared to state‐of‐the‐art methodologies.

关键词： access control artificial intelligence computer vision intelligent control

来源：评论

学校读者我要写书评

暂无评论

Geological Information Extraction from Satellite Imagery Using Machine Learning 10

Geological Information Extraction from Satellite Imagery Usi...

引用

10th International Conference on Reliability, Infocom Technologies and Optimization ,Trends and Future Directions, ICRITO 2022

作者： Yadav, Anupam Saraswat, Shipra Faujdar, Neetu Gla University Dept of Computer Engineering and Application Mathura India Abes Institute of Technology Computer Science & Engineering Ghaziabad India

ISBN: (数字)9781665474337

ISBN: (纸本)9781665474337

Satellite imagery has become widely available for detecting patterns by applying different deep learning and machine learning techniques to it. This paper will cover water monitoring, land cover and tree cover visualization. The main aim is to establish the effectiveness of ML and the insights provided by it to promote sound governance, better decision and policy making. Python libraries have been used extensively in Earth Observation applications and resources such as land-use patterns, crop-yield patterns, disaster control, and others. Majority of the data has been made available by Copernicus, World Bank's open data and Landsat programs. Various libraries that have been used are shapely, geopandas, rasterio, fiona, numpy, eo-learn, gdal, and s2cloudless. Detailed use of each of these libraries has been discussed in this paper. The process for analysis is as follows - defining region of interest, downloading satellite imagery, setting appropriate path to provide the algorithm (on jupyter notebook) access to the data, cloud masking, extract various features that are required according to objectives, fetch and save results. We have talked about satellite data, but another important aspect is ground- truth data to reference the results obtained from machine learning and deep learning algorithms. To increase the chances of successful prediction a series of steps are executed before drawing out the results including adding reference, sampling, merging features, postprocessing, and detection of changes. The performance majorly depends upon the distribution of data. It is usually a supervised technique. Recent developments have also provided us an option to fully automate the process, manually handle it or create a hybrid model. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Framework for Intrusion Detection in Cloud Computing Based on HLA-CNN-BiLSTM-SVM Model

A Collaborative Framework for Intrusion Detection in Cloud C...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： Amit K. Mogal Vaibhav P. Sonaje Department of Computer Science & Application School of Computer Science and Engineering Sandip University Nashik India

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

In addition to describing a way to make better use of preexisting computer infrastructures, the phrase “cloud computing” describes a technology that facilitates the sale of access to shared computer resources and services. The flip side is that these dispersed and convoluted infrastructures are attractive targets for attackers. Because cyberattacks can reduce the quality of service offered to clients, the system constitute a substantial risk. This proposed method consists of three steps like preprocessing, feature selection, and model training. Data preprocessing, which includes both feature discretization and feature normalization, is a critical step in any knowledge discovery process. In this proposed to evaluate the impact of feature selection on improving classifier algorithm accuracy by comparing two feature selection methods: one that takes linear correlation into account, and another that takes mutual information into account. When training the model, an HLA-CNN-BiLSTM-SVM was utilized. With a 92.35 percent average accuracy, the suggested method surpasses CNN-SVM and BiLSTM.

关键词： Training Cloud computing Accuracy Correlation Computational modeling Intrusion detection Bidirectional long short term memory Feature extraction Classification algorithms Mutual information

来源：评论

学校读者我要写书评

暂无评论

Improving Accuracy and Robustness in Depression Detection with Ensemble Learning and Optimization Techniques 1

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Kumari, Meena Singh, Gurpreet Pande, Sagar Dhanraj School of Computer Application Lovely Professional University Punjab Phagwara India School of Computer Science and Engineering Lovely Professional University Punjab Phagwara India VIT-AP University Andhra Pradesh Amaravati India

ISBN: (数字)9789819997077

ISBN: (纸本)9789819997060

Chronic melancholy, lack of interest or enjoyment in activities, changes in diet or weight, abnormalities in sleep patterns, feelings of guilt or unworthiness, difficulty in concentration, and suicide or death thoughts are all symptoms of depression. Depression, if left untreated, can lead to a variety of problems, including an increased risk of self-harm or suicide, substance abuse, physical health issues, and social isolation. In this work we attempt to utilize machine learning techniques to detect a likely depressed social media user based on social media posts and compare the accuracy of built-in models using a variety of comparison methodologies. The machine learning algorithms were fine-tuned on five various optimization techniques. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Health risks

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：