检索结果-内蒙古大学图书馆

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Dasari, Kavitha Asha, V. Kansal, Lavish Praveen Parashar, Ashish Kumar Alwan, Adil Abbas Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Master of Computer Applications Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India Lloyd Institute of Management and Technology Plot No.-11 Knowledge Park-II Uttar Pradesh Greater Noida201306 India College of Engineering Technology National University of Science and Technology Dhi Qar Iraq

ISBN: (纸本)9798350357769

In the realm of high-power photovoltaic (PV) systems, ensuring efficient and reliable performance demands precise thermal management. This study delves into the intricacies of thermal management and control strategies for interleaved boost converters (IBC), pivotal components in these systems. Interleaved topology, though recognized for its capability to reduce ripple currents and enhance efficiency, presents unique thermal challenges due to uneven current distribution among the parallel converters. This research introduces a smart thermal control methodology that amalgamates real-time temperature monitoring with adaptive control strategies, ensuring optimal thermal performance and preventing hotspot formation. Employing a combination of advanced sensors and sophisticated algorithms, the proposed system autonomously adapts to varying solar irradiances and ambient conditions, thereby ensuring consistent thermal stability. Experimental results demonstrate a significant reduction in temperature deviations among parallel converters and an overall enhancement in system reliability and efficiency. The findings from this research set the groundwork for future designs of PV systems, ensuring their sustainable and efficient operation under diverse conditions. © 2023 IEEE.

关键词： Adaptive Control Strategies Hotspot Prevention. Top of Form Interleaved Boost Converters Photovoltaic Systems Thermal Management

来源：评论

学校读者我要写书评

暂无评论

An Effective Method for Forecasting Crime Analysis using Deep Learning Classifiers

An Effective Method for Forecasting Crime Analysis using Dee...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： K. Muthumanickam B. Selvalakshmi P. Vijayalakshmi P. Nareshkumar Department of Information Technology Kongunadu College of Engineering and Technology (Autonomous) Thottiyam Tamilnadu India Department of Computer and Engineering Tagore Engineering College Chennai Tamilnadu India Department of Computer Science and Engineering Knowledge Institute of Technology (Autonomous) Salem Tamilnadu India

Crime is one of our society's most serious issues. As a result of its pervasiveness in our culture and society, the task of preventing crime is one of the utmost crucial ones. The suggested model in this article is created to identify crime trends, and the aim of this research is to assess the efficacy of criminal inquiries based on inferences. The study draws conclusions from the crime scene and uses those conclusions to predict the offender. Here, the data set includes It includes details on the crime, such as the location's description, the type of crime, the date, the time, the latitude, and the longitude. Before training the model, data pre-processing will be performed, followed by feature selection and scaling to ensure high accuracy. The categorization techniques help the inquiry reach its objective, and this tactic helps identify a connection between two mathematical values. This technique forecasts the values of the dependent variables based on the independent variables, allowing the multilayer perceptron and machine learning reliant algorithm to classify the datasets and anticipate crimes with a higher degree of accuracy. The proposed method has obtained accuracy rates of 99.2%, recall rates of 98.91 %, precision rates of 98.08%, and F1-score rates of 96.44% in crime detection utilizing MLP architecture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-LSTM Ensembles for Predictive Analysis of Financial Churn Patterns

Autoencoder-LSTM Ensembles for Predictive Analysis of Financ...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Raynukaazhakarsamy Rahul Pradhan Nadhema Ahmed Jaff G Venu Gopal Mariam Fadel Ali P. Nagaraj Department of Computer Applications Nehru Arts and Science College (Autonomous) Coimbatore India Department of Computer Engineering & Applications GLA University Mathura India Department of Business Administration College of Administrative and Financial Sciences Knowledge University Erbil Iraq Computer Science and Engineering (AI & ML) Geethanjali College of Engineering and Technology Telangana India Department of Radiology Techniques Uruk University Baghdad Iraq Department of AI & ML K. Ramakrishnan College of Engineering Trichy Tamilnadu India

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

In the financial sector, customer churn is a significant problem that influences the organization’s revenue growth. Churn means that customers have left their current providers which is a negative factor for the providers or financial institutions; therefore, accurate churn prediction helps institutions to increase customer loyalty and satisfaction by improving the quality of service. In this paper, a new method of using Autoencoder and LSTM network for predicting financial churn patterns is introduced. The Autoencoder is used to reduce dimensions and for unsupervised learning acts as a pass through that allows the model to learn the latent patterns in customer behaviour and transactions. Since the LSTM has demonstrated its efficacy in analyzing temporal dependencies of a sequence in time series, it is used to predict churn by analyzing sequential customer activity. The ensemble approach combines the merits of the two models improving the predictive power and especially the stability in a situation of data scarcity and high noise levels. Experimental comparison with conventional predictive models such as decision trees and logistic regression reveal that the Autoencoder-LSTM is more accurate and sensitive than traditional models by comparison. In other words, the proposed model enhances the early identification of potential churners and such institutions can then take appropriate measures of containing it, and in the process, offer relevant retention solutions. The paper describes the benefits of utilizing deep learning models for churn prediction for the financial industry and provides information on how such methods might be used to improve customer retention. Possible future research avenues consist of improving the model interpretability and generalizing the approach to other industries with comparable churn prediction requirements. The accuracy obtained from the proposed method is higher at 99.7% compared to other methods.

关键词： Accuracy Computational modeling Autoencoders Time series analysis Predictive models Stability analysis Churn Predictive analytics Long short term memory Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Academic Evaluation System Using Adaptive Categorized and Authenticated Recommendation

Academic Evaluation System Using Adaptive Categorized and Au...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Haider Abdula Haddad Abdulqadir Ismail Abdullah Qaysar Salih Mahdy Wasfi Kahwachi Department of computer science and information technology College of Science Salahaddin University Erbil Kurdistan Region Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil Kurdistan Region Iraq Department of Mechatronics Engineering College of Engineering Tishk International University Erbil Kurdistan Region Iraq Research Center Tishk International University Erbil Kurdistan Region Iraq

ISBN: (数字)9798350374131

ISBN: (纸本)9798350374148

Teacher performance is an important issue for any academic institution, so these institutions try to develop methodologies and systems to evaluate the performance of its academic staff based on measurable and scientific metrics. These metrics include collecting data from students about classes and how the teacher is performing in the classroom and measuring the learning objectives from students. Major objective of this research work is to develop a web-based multi-user system for academic performance and a recommendation system that depends on the performance and skills of the teacher. The system includes multiple entry points for best factor such as the feedback unit, student attendance unit, teacher classification unit, and teacher recommendation unit, which can be strictly accessed by the administrative authority for academic teachers. The attendance module and the student feedback module are required to achieve better results in the teacher rating module and the teacher recommendation module. A reliability factor has been incorporated to achieve the accuracy of the proposed system. The performance of the system was improved due to the integration of the paperless approach and resulted in less data loss. The developed system was tested for a large university in Kurdistan region, Iraq. For data analysis an adaptive unsupervised learning method was used to categorize teachers according to their performance in the classroom. The system proved very successful in the academic evaluation and recommendation process in the university. This research proved that using student feedback data is the best factor in determining academic performance.

关键词： Performance evaluation Data analysis Adaptive systems Education Data collection Reliability Task analysis

来源：评论

学校读者我要写书评

暂无评论

Investigation of LSSVM and RBFNN-based Techniques for Intrusion Detection Systems for IoT Networks

Investigation of LSSVM and RBFNN-based Techniques for Intrus...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Medida Jayapal Subhashree K B. Ashwini Satheesh Kumar D Sushil Chandra Dimri Neerav Nishant Department of CSE GITAM University (Deemed to be University) Hyderabad Telangana India Department of Computer Science and Engineering Karp agam College of Engineering Coimbatore India Department of CSE Knowledge Institute of Technology Salem Tamilnadu India Department of Computer Science and Engineering Hindusthan College of Engineering and Technology Coimbatore India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science and Engineering School of Engineering Babu Banarasi Das University Lucknow Uttar Pradesh India

As more and more devices become internet-enabled, it's no longer possible to imagine modern life without them. In particular, Internet of Things (IoT) devices have become widespread and indispensable. But there are issues that appear to be worsening and for which there are currently no good solutions. The safety of Internet of Things (IoT) devices and other connected gadgets is a growing concern. There has been a lot of development in the area of safeguarding IoT networks, but there is always room for improvement. The proposed methodology consists of three stages: preprocessing the data, selecting the features to use, and training the model. In data preprocessing, normalization and standardization techniques are utilized. The use of particle swarm optimization helps improve feature selection. Models are trained with SVM-RBFNN after information gain is used to choose relevant features. The proposed method achieves better results than both SVM and LSSVM, two widely usedalternatives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration

arXiv

引用

arXiv 2023年

作者： Ma, Mingrui Wang, Tao Wang, Weijie Song, Lei Liu, Guixia College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun China Department of Information Engineering and Computer Science University of Trento Trento Italy

The Swin transformer has recently attracted attention in medical image analysis due to its computational efficiency and long-range modeling capability. Owing to these properties, the Swin Transformer is suitable for establishing more distant relationships between corresponding voxels in different positions in complex abdominal image registration tasks. However, the registration models based on transformers combine multiple voxels into a single semantic token. This merging process limits the transformers to model and generate coarse-grained spatial information. To address this issue, we propose Recovery Feature Resolution Network (RFRNet), which allows the transformer to contribute fine-grained spatial information and rich semantic correspondences to higher resolution levels. Furthermore, shifted window partitioning operations are inflexible, indicating that they cannot perceive the semantic information over uncertain distances and automatically bridge the global connections between windows. Therefore, we present a Weighted Window Attention (WWA) to build global interactions between windows automatically. It is implemented after the regular and cyclic shift window partitioning operations within the Swin transformer block. The proposed unsupervised deformable image registration model, named RFR-WWANet, detects the long-range correlations, and facilitates meaningful semantic relevance of anatomical structures. Qualitative and quantitative results show that RFR-WWANet achieves significant improvements over the current state-of-the-art methods. Ablation experiments demonstrate the effectiveness of the RFRNet and WWA designs. Our code is available at https://***/MingR-Ma/RFR-WWANet. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

AI-driven Gene Expression Analysis on HPC Platforms: Challenges and Solutions 7

AI-driven Gene Expression Analysis on HPC Platforms: Challen...

引用

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

作者： Devi, V.S. Anusuya Sreevani, N. Nagpal, Amandeep Kalyani, Susmita Rani, K.Pushpa Albawi, Ali New Horizon College of Engineering Departmento of Applied Sciences Bangalore India Dundigal Hyderabad500043 India Lovely Professional University Phagwara India Lloyd Law College Plot No. 11 Knowledge Park II Uttar Pradesh Greater Noida201315 India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India The Islamic University College of Medical Technology Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350350067

HPC technology's rapid rise has simplified gene expression research. A study proposes AI-GEM, which stands for 'AI-Driven Gene Expression on High-Performance Computing Platforms.' We devised an approach to circumvent the issues associated with gene expression studies. We provide a full gene expression research strategy to improve accuracy, scalability, and comprehension. AI-GEM examined six methods: GEA-HPC, Expression AI, Genomic Solver, HPC-GENE, Bio AI-Express, and Gene Xcel. All approaches were tested. The findings suggest that AI-GEM outperforms other approaches. Our new approach averages 10.8 seconds, whereas the previous one took 45.7 seconds. The previous way is faster. AI-GEM is 95.2% accurate. This approach is far more accurate than the standard 71.2%. This differs greatly from proper procedures. AI-GEM has far more potential than prior approaches, which could only handle 20,850 genes. AI-GEM outperforms other gene expression approaches in interpretability (9.2 vs. 4.4). One other reason: AI-GEM works better than conventional approaches. The AI-GEM system achieves 93% client privacy, whereas traditional approaches obtain 58%. AI-GEM uses computer resources well, scoring 85% vs. 66% for other approaches. The final preprocessing time for AI-GEM is under 3.2 seconds. The previous best was 13.4 seconds, a significant improvement. AI-GEM is a novel gene expression data analysis tool for powerful computers. AI-GEM is a novel gene expression data analysis tool that is faster, more accurate, more scalable, simpler to comprehend, better at preserving privacy, more efficient in using resources, and reduces difficulties in pre-processing chores. This technology might aid biology and genetics in many ways. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Preserving Visual Authenticity: Block chain-Augmented AI Frameworks for Advanced Digital Deception Recognition and Mitigation

Preserving Visual Authenticity: Block chain-Augmented AI Fra...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： M Priya J Murugesan P Bhuvaneswari M Rubigha S Lalithambikai B Mohanraj Department of Information Technology Knowledge Institute of Technology Salem India Department of Computer Science and Engineering Sona College of Technology Salem India Department of Information Technology Sona College of Technology Salem India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

The rapid advancements in deep learning have given rise to sophisticated DeepFake technologies, posing significant threats to visual integrity and authenticity in digital media. This paper presents an innovative approach to DeepFake detection and mitigation by integrating blockchain technology with artificial intelligence frameworks. The proposed Blockchain-Augmented AI (BAAI) framework utilizes the immutability and decentralized nature of block chain to enhance the security and reliability of the detection process. Our method involves the development of advanced AI models for detecting DeepFakes, which are then integrated with a blockchain-based ledger to ensure the verifiability and traceability of detection results. In this proposed work, a novel integration of blockchain technology and AI designed to enhance DeepFake detection capabilities. The framework achieves a $97 \%$ accuracy rate, ensuring reliable identification of manipulated media, while maintaining a low false positive rate of 3%. These results highlight the BAAI framework’s effectiveness in minimizing erroneous detections and its robustness in safeguarding digital visual content. In the face of increasingly sophisticated DeepFake technologies, this framework offers a crucial advancement in combating digital deception.

关键词： Deep learning Deepfakes Visualization Prevention and mitigation Face recognition Media Robustness Blockchains Security Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Analysis Method for Probabilistic Verification for Smart IoT Systems with Process Algebra 5

Analysis Method for Probabilistic Verification for Smart IoT...

引用

5th IEEE International Conference on Smart Internet of Things, SmartIoT 2021

作者： Lee, Sunghyeon Song, Junsup Karagiannis, Dimitri Lee, Moonkun Department of Computer Science and Engineering Jeonbuk National University Jeonju Korea Republic of Research Group Knowledge Engineering University of Vienna Vienna Austria

ISBN: (纸本)9781665445115

Process algebra is one of the most suitable formal methods to model Smart IoT Systems to specify their probabilistic behavior, since process algebra may include probability property for choice operation as shown in PAROMA and PACSR, which, however, do not have enough analytic methods to control the degree of nondeterminism for the operation. In order to overcome the limitation, the paper presents a new formal method, called dTP-Calculus, and an analytic method to control the nondeterminism in order to satisfy safety and security requirements of the IoT systems. To prove the concept of the approach in the paper, the SAVE tool suite has been developed on the ADOxx and is used to demonstrate its applicability with a Smart EMS (Emergence Medical Service) Example. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Smart water quality analysis using IoT and big data analytics: A review 2

Smart water quality analysis using IoT and big data analytic...

引用

2nd IEEE International Conference on Electronic engineering, ICEEM 2021

作者： Hemdan, Ezz El-Din Essa, Youssef M. El-Sayed, Ayman Shouman, Marwa Moustafa, Abdullah N. Menofia University Computer Science and Engineering Department Faculty of Electronic Engineering Menouf Egypt Principle Data and Knowledge. Bayer Berlin Germany

ISBN: (纸本)9781665418423

In recent times, water quality monitoring, observing, and testing have become a significant research study with the advancement on the Internet of Things, and Big Data analytics research ideas. The relationship between water demand and supply is very crucial for every country and is likewise a complex challenge to satisfy this requirement around the world. Water is compulsory for human survival being on the earth. Therefore, for survival, the preservation and taking care of the existing water resource are also equally substantial. Moreover, for a healthier society, access to clean and safe water resources is also imperative. To recognize the water quality effects and provide an automated water quality mentoring and a testing system can support in guaranteeing the safety of the water. This paper presents a study on water quality analysis using IoT and Big Data analytics. This can help in developing an agile environment that can handle the massive flow of water big data generated by the smart sensors spread everywhere around us. © 2021 IEEE.

关键词： Data Analytics

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：