检索结果-内蒙古大学图书馆

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Sharma, Aparna Rastogi, Divya Manwal, Manika Tyagi, Ayushi Sharma, Prashant Kumar Computer Science and Applications Sharda University UP Greater Noida India Computer Science & Engineering Graphic Era Hill University Uttarakhand Dehradun India Computer Science & Engineering Raj Kumar Goel Institute of Technology UP Ghaziabad India Computer Applications Hindustan Institute of Management & Computer Studies UP Mathura India

ISBN: (纸本)9798350342338

Reinforcement getting to know (RL) has emerged as a famous method to predict considerable occasions inside the Net of Things (IoT) networks. RL is a form of artificial intelligence that models conduct from praise and punishment alerts for a given venture or aim. It has been efficaciously used to expect numerous events in dynamic systems and Internet of Things (IoT) networks. Predictive maintenance (PM) aims to stumble on and diagnose screw-ups in IoT structures before they occur. PM aims to expect events and situations in IoT devices to avoid unplanned stoppages or steeply-priced maintenance. Using RL for predictive protection helps with the upkeep of IoT networks by providing a proactive technique. The RL set of rules can study styles from the information accumulated in actual time from the IoT network, after which a prediction algorithm can discover ability screw-ups and endorse preventive preservation tactics. RL can also regulate its mastering process over time based on remarks from the IoT network. The RL approach toward PM provides tremendous benefits over conventional renovation strategies because of its self-getting-to-know and predictive skills. Extensive proof suggests that reinforcement mastering enhances the effectiveness of predictive preservation for IoT networks. RL gives many blessings along with personalized preventive renovation pointers and lowering the value of maintenance, amongst others. As a result, increasingly, groups are adopting reinforcement studying for predictive upkeep to take advantage of its cost financial savings and proactive technique. © 2023 IEEE.

关键词： artificial intelligence dynamic systems IoT predictive maintenance Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Moving Target Defense - Challenges, Problems and Suitability for Internet of Things 4

Moving Target Defense - Challenges, Problems and Suitability...

引用

4th International Conference on Computing and Communication Systems, I3CS 2023

作者： Gurung, Dipendra Gurung, Sandeep Pradhan, Mohan Pratap Sikkim Manipal Institute of Technology Department of Computer Applications Majitar India Sikkim Manipal Institute of Technology Department of Computer Science and Engineering Majitar India Sikkim University Department of Computer Applications Gangtok India

ISBN: (纸本)9798350323771

Traditionally cyber attackers have always had an upper hand over defenders as the latter can only react in the event of an attack. Moving Target Defense (MTD) has emerged as a potential game changer by reversing the advantage from attackers to defenders. Together with traditional defenses, MTD is expected to take cyber security up a notch. MTD solutions have been proposed for various levels, namely operating system, network, runtime platform, etc. However, improvement of existing solutions and development of new solutions are required. This paper presents an overview of MTD, the various MTD approaches, attacks mitigated, open research problems in MTD and MTD for the Internet of Things (IoT). © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Classification for Detecting Threats in Cloud Environments Against DDoS Attacks 13

Vulnerability Classification for Detecting Threats in Cloud ...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Jyothi, V. Esther Chowdary, N. Sampreeth Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Applications Vijayawada India P.V.P. Siddhartha Institute of Technology Department of Computer Science and Engineering Vijayawada India

ISBN: (纸本)9798350305463

In order to secure data, infrastructure, and services from potential attacks, cloud security is a wide issue that includes any combination of policies, technologies, and procedures. The cloud has substantially different security needs than traditional settings. Because of its dynamic nature and low client infrastructure ownership, the cloud has decreased traditional security architecture. Internet connectivity and distant servers are used in cloud computing to manage data and applications. It provides users with on-demand software, bandwidth, and dynamic virtualized resources through the internet and ensures that its adapters will share in various financial advantages. The utilization of hardware, software licenses, and system maintenance is decreased for the benefit of the customers. The protocol known as SOAP or Simple Object Access Protocol, it enables communication between various web-based services. Extensible Mark-up Language (XML) and Hyper Text Transport Protocol (HTTP) are both used to develop SOAP communications. A cloud web service that uses HTTP and XML might be bringing down by the new type of Distributed Denial of Service (DDoS) attacks. HTTP and XML Denial of Service (DoS) attacks provide a serious security risk to cloud computing. The Hypertext Extensible-Denial of Service (HX-DoS) attack, which causes the cloud service provider's communication channel to get blocked and go down, is made up of purposefully transmitted HTTP and XML messages. Differentiating between suitable and improper communications is necessary to solve the issue of HX-DoS attacks against cloud web services. To decide and place the packets on the side of the victim, the reconstruct and drop technique is utilized. Detection rate, accuracy, and precision were the performance parameters used to evaluated the model's performance. © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classifiers for Predicting the Risk of Cardiovascular Disease in Healthcare 4.0 3

Machine Learning Classifiers for Predicting the Risk of Card...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Kumari, Palak Kumar, Ashish Chatterjee, Kakali Master of Computer Applications Patna Women's College Patna India National Institute of Technology Patna Dept. of Computer Science and Engineering Patna India

ISBN: (纸本)9798331528201

Cardiovascular disease (CVD) generic phrase used to describe heart or blood vessel illness. Conditions that impact the body's, brain's, or heart's blood flow. Reduced blood flow can result from factors such as blood clots, leading to heart attack, angina, or stroke. Other potential meanings of CVD. These models offer key benefits like clear interpretability and the ability to analyze complex patterns, significantly enhancing the accuracy of cardiovascular disease risk predictions. The demerits of using SVM, LR, K-NN, and MLP for CVD prediction include inter-pretability issues, overfitting risks, data requirements, feature selection challenges, scalability concerns, algorithm complexity, and class imbalance. Collaboration between machine learning experts and healthcare professionals is essential for developing accurate and reliable CVD prediction models that enhance patient care. CVD is a significant health threat, often leading to fatal complications. Early detection is crucial for effective intervention. This study employs SVM (accuracy is 0.84%), LR (accuracy is 0.86%), K-NN (accuracy is 0.94%), and MLP (accuracy is 0.79%) machine learning techniques to enhance CVD detection by addressing outliers and null values, contributing to advancing automatic detection initiatives. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

A metaheuristic virtual machine placement framework toward power efficiency of sustainable cloud environment

引用

Soft Computing 2023年第7期27卷 3817-3828页

作者： Singh, Ashutosh Kumar Swain, Smruti Rekha Lee, Chung Nan Department of Computer Applications National Institute of Technology Haryana Kurukshetra136119 India Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung804201 Taiwan

The primary aim of Virtual Machine Placement (VMP) is the mapping of Virtual Machines (VMs) to Physical Machines (PMs), such that the PMs may be utilized to their maximum efficiency, where the already active VMs are not to be interrupted. It provides a list of live VM migrations that must be accomplished to get the optimum solution and reduces energy consumption significantly. The inefficient VMP leads to wastage of resources and excessive energy consumption and increases the overall operational cost of the data center. A Metaheuristic Virtual Machine Placement Framework towards the Power Efficiency of Sustainable Cloud Environment (MV-PESC) approach is suggested to address the issues mentioned above. An Extended Flower Pollination Optimization algorithm is suggested, which combines the concept of the Random Fit algorithm and the Flower Pollination Optimization algorithm. The proposed work’s performance is evaluated using actual workload traces of the benchmark Google Cluster Data set. The obtained results are compared with various state-of-the-art and demonstrate a notable reduction in power consumption, the number of active PMs, and execution time up to 64.89%, 35%, and 21.12%, respectively. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Apply Deep Learning-based CNN and LSTM for Visual Image Caption Generator 3

Apply Deep Learning-based CNN and LSTM for Visual Image Capt...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Indumathi, N. Divyalakshmi, R.J. Stalin, J. Ramachandran, V. Rajaram, P. Srm Institute of Science and Technology Computer Science and Applications Chennai India Sethu Institute of Technology Computer Science and Business Systems Virudhunagar India Computer Science and Engineering Gitam School of Computing Bengaluru India

ISBN: (纸本)9798350399264

Implemented Image captioning is becoming a need. Deep neural network models enable integrated applications to generate and caption images. Image captioning describes an image. It requires identifying an image's main objects, properties, and relationships. It produces correct sentences. The creation of image caption generators, which examine the content of an image and offer pertinent descriptions, makes use of deep learning and computer vision techniques. One element of this method involves classifying objects in the image using English keywords derived from training datasets. The caption generator was created by combining LSTM and CNN. In this paper, we propose a deep-learning model that uses computer vision and machine translation to characterize images and generate captions. The model successfully recognizes and labels visual items and their relationships. Transfer Learning will be used to demonstrate the suggested experiment, coupled with the Flickr8k dataset and the Python3 programming language. This study will also look into the functions and construction of neural networks. The proposed model achieves a BELU Score of 69.8. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Analysis of Various Hyperparameters for Predicting Hypertension using Machine Learning Algorithms 8

Analysis of Various Hyperparameters for Predicting Hypertens...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Duggal, Shallu Sood, Shivani Singh, Amanpreet Singh, Harjeet Malarvel, Muthukumaran Lovely Professional University School of Computer Applications Phagwara144411 India Chitkara Institute of Engineering and Technology Chitkara University Punjab 140401 India Department of Computer Science and Engineering India

ISBN: (纸本)9798350367904

Predicting hypertension, or high blood pressure, is crucial because it's a risky condition that frequently doesn't exhibit any obvious symptoms or indicators until major problems arise. By using predictive models for early identification, the risk of uncontrolled hypertension-related cardiovascular events, strokes, and organ damage can be decreased to take quick action. The study aims to predict the diagnosis of hypertension using three machine learning techniques: Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine(SVM). With the focus on improving accuracy and reliability, the various hyperparameters of each individual algorithm are tuned using the cross validation and grid search approaches. After extensive testing and parameter modification, the SVM algorithm was found to be the most accurate predictor, which achieved a significant accuracy of 9 7. 0 0 %. The best hyper-parameters achieved for SVM are c value 4 and kernel as 'rbf'. The models' performance is evaluated using accuracy, specificity, sensitivity, F1-score, or AUC (Area Under the Curve). This study facilitates proactive healthcare measures by offering insightful information to determine the best algorithms for the early prediction of hypertension. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Review: Concepts, Tools, Research gaps, and Possible solutions 7

Fake News Detection Review: Concepts, Tools, Research gaps, ...

引用

7th International Conference on Internet applications, Protocols, and Services, NETAPPS 2024

作者： Yakkundi, Sapana Patil, Rudragoud Goudar, Swetha Indudhar Department of Computer Science and Engineering KLS Gogte Institute of Technology Karnataka Belagavi India Department. of Master of Computer Applications KLS Gogte Institute of Technology Karnataka Belagavi India

ISBN: (纸本)9798331519513

The increasing number of social platforms means that there is a rapid expansion of online data. However, not all of this data can be trusted, as some users intentionally manipulate information to spread false news for personal or political reasons. Fake news can significantly impact public perception and societal outcomes. Its widespread influence was especially noticeable during the 2016 United States election cycle, leading to heated discussions about its role and consequences. Given the changing nature of news, real-time data processing has become essential for effectively identifying and countering misinformation. This research provides a comprehensive examination of the datasets, tools, and techniques utilized for detecting and combating fake news. Many researchers have developed models based on specific datasets, limiting their scope to particular domains. A thorough review of advanced models for real-time fake news detection highlights existing research gaps. The analysis of the review reveals that numerous datasets used in the literature are outdated, and there is a methodological challenge associated with the use of traditional machine learning approaches. With the continuous evolution of news, there is an urgent demand for utilizing sophisticated deep learning models for the automated, real-time verification of misinformation. This research presents promising approaches to tackle the challenge of detecting fake news. © 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

Inspired Detection Model For Clustering Based Surveillance System: A Non-Conventional Review

Inspired Detection Model For Clustering Based Surveillance S...

引用

2024 IEEE International Conference on Automation and Computation, AUTOCOM 2024

作者： Gupta, Anil Kumar Sharma, Rupak Ojha, Rudra Pratap Srm Institute of Science and Technology Department of Computer Science and Engineering NCR Campus Ghaziabad Uttar Pradesh Modinagar India Srm Institute of Science and Technology Department of Computer Applications NCR Campus Ghaziabad Uttar Pradesh Modinagar India Department of Computer Science and Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350382723

in current years, there has been a growing hobby in growing superior surveillance systems for detecting and monitoring anomalous activities. Traditional surveillance systems depend upon handmade policies and features, which are frequently limited of their capacity to accurately become aware of complex anomalies. To conquer this problem, we suggest a better visible anomaly detection version for clustering-based surveillance structures the use of long brief-time period reminiscence (LSTM) Diffusion manner. The proposed version incorporates the temporal context of the CCTV photos with the aid of making use of the LSTM network, which has been proven to deal with sequential data effectively. The LSTM community is used to extract movement features from the video frames, which are then fed into the clustering set of rules. This allows for the identification of comparable styles of sports and grouping them into clusters. Furthermore, we combine the concept of the Diffusion technique into the LSTM version to decorate the clustering method. The Diffusion procedure entails the gradual propagation of information among nodes in a network, which is particularly beneficial in figuring out abrupt changes in activities. This permits the version to locate anomalies with better accuracy and decrease fake alarms. To assess the performance of our proposed version, we behavior experiments on a real-global surveillance dataset. The consequences display that our model outperforms current techniques in terms of accuracy and detection price. © 2024 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

The Prediction of Diabetes Using Machine Learning in the Healthcare System 5th

The Prediction of Diabetes Using Machine Learning in the Hea...

引用

5th International Conference on Trends in Computational and Cognitive engineering, TCCE 2023

作者： Deep, Ishaan Singh, Payaswini Senapati, Biswa Ranjan Swain, Rakesh Ranjan Nayak, Subrat Kumar Patra, Binaya Kumar University Odisha Bhubaneswar751030 India Department of Computer Science Engineering and Applications Indira Gandhi Institute of Technology Sarang Dhenkanal India

ISBN: (纸本)9789819719228

Diabetes has been increasing at an exponential rate in India in recent years, and it is expected to reach 537 million by 2030. Diabetes will also cause a large rise in a variety of other health issues. Many machine learning techniques are being employed to solve the problem of diabetes prediction. In this paper, the authors have considered two machine learning techniques, such as support vector machine (SVM) and logistic regression (LR) for diabetes prediction. The SVM accuracy was found to be 87% when eight independent parameters were used to predict it, whereas the logistic regression accuracy was 87.01%. © 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

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：