检索结果-内蒙古大学图书馆

Analysis of New Distributed Differential Evolution Algorithm with Best Determination Method and Species Evolution

Procedia computer science 2020年 167卷 263-272页

作者： Amit Ramesh Khaparde Assistant Professor Computer Science & Engineering G.B. Pant Govt Engineering College New Delhi India

This is a new semi-distributed differential evolution algorithm with best determination method and species evolution (DESBS). This algorithm is based on fact- evolution of species around niche. In DESBS, the best determination method determines the best individuals of population. These best individuals act as niches and the species are evolved around these best individuals. Over the period of time, each species evolved separately, using standard differential evolution algorithm. The evolving efficiency of each species evaluated separately and inefficient species are merge to nearby species. The scale-up study is performed to find out best parameter setting and the results are compared with other state-of-art algorithms like CoDE, EPSDE and standard differential evolution algorithm. The results show that the DESBS perform better than SDE in multimodal functions and CoDE, EPSDE in rotating optimization function

关键词： Evolutionary Algorithm hybrid composite function optimization niches

来源：评论

学校读者我要写书评

暂无评论

Green dream: A deep learning based real-time model for automatic waste segregation from video streams

引用

AIP Conference Proceedings 2023年第1期2773卷

作者： Prince Puthussery Nikhita Mariam Cherian T. K. Gokul Kiran M. U. Sreeja Abin Oommen Philip Department of Computer Science & Engineering Toc H Institute of Science & Technology Ernakulam Kerala India Assistant Professor Department of Computer Science & Engineering Toc H Institute of Science & Technology Ernakulam Kerala India Assistant Professor Department of CSE-Cyber Security Indian Institute of Information Technology Kottayam Kerala India

In this fast-pacing world one of the substantial problems faced is the drastic increase in waste generation and ensuring efficient and rational management of waste. Recycling tasks reduce waste production, mitigate the environment and improve the whole nation’s prosperity in the future. Inappropriate handling and discarding of useless materials have led to the contamination of groundwater and defiled the land resources. Therefore, it is vital that the methods and processes involved in waste collection and segregation is examined as the present-day disposal system is inefficient, time consuming, cumbersome and not completely viable due to their large amount. The proposed model provides a way of solving the above stated problems by detecting, identifying and segregating the waste materials. The proposed system is an automated waste classifier which uses a deep learning-based object detection model to classify objects into different categories. Using YOLOv5, an object detection algorithm the waste can be identified successfully from the image taken with the help of a camera and classify them into categories. This result is then sent to a segregation unit which categorizes the waste into the designated bin by rotating the conveyor belt using a motor. The proposed model operated at a Mean Average Precision(mAP) of 0.726 and an F1-Score of 0.83. This method of segregation of waste will enable faster ways to recycle the waste and save time and resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques with LowDimensional Feature Extraction for Improving the Generalizability of Cardiac Arrhythmia

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2021年第2期48卷 1-10页

作者： Nurmaini, Siti Tutuko, Bambang Rachmatullah, Muhammad Naufal Darmawahyuni, Annisa Firdaus, Firdaus A Professor of Computer Engineering Intelligent System Research Group Universitas Sriwijaya Palembang30139 Indonesia A lecturer of Computer Engineering Department Faculty of Computer Science Universitas Sriwijaya Palembang30139 Indonesia A research assistant of Intelligent System Research Group Universitas Sriwijaya Palembang30139 Indonesia

Automatic heartbeat classification is an important stage in identifying cardiac arrhythmia. Several machine learning (ML) techniques have been proposed to perform this, but they produce an accuracy result of below 99%. In this study, a deep neural network (DNN) structure is applied to improve ML performance. The feature selection method is based on the combination of discrete wavelet transform (DWT) and principal component analysis (PCA). To avoid computational complexity, the components of PCA are derived by low-dimensional DWT coefficients. The results show that the proposed ML model achieves good performance, producing 99.76% accuracy, 91.80% sensitivity, 99.78% specificity, 93.02% precision, and 92.31% F1-score. To benchmark the proposed model, the support vector machine (SVM) and random forest (RF) techniques are used as the baseline models. The DNNs are 2.3% more sensitive than SVM, while the RF fails to classify the ECG heartbeat. Four datasets are used to analyze the robustness and generalization performance of the proposed model: MIT-BIH, SVDB, MITDB, and IncartDB. All testing results produce satisfying performance. The proposed ML model offers a potential solution to improve the generalizability of a DNN-based model in different cardiac datasets for classifying tasks. © 2021. All Rights Reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: ALBAE feature extraction based lung pneumonia and cancer classification

引用

Soft Computing 2023年第2期28卷 589-589页

作者： M Braveen S Nachiyappan R Seetha K Anusha A Ahilan A Prasanth A Jeyam Assistant professor senior School of Computer Science and Engineering Vellore institute of technology Chennai Tamil Nadu India Associate Professor School of Computer Science and Engineering Vellore Institute of Technology Chennai Tamil Nadu India Associate Professor School of Information Technology and Engineering Vellore Institute of Technology Vellore Tamil Nadu India Associate Professor Department of Electronics and Communication Engineering PSN College of Engineering and Technology Tirunelveli Tamil Nadu India Assistant Professor Department of Electronics and Communication Engineering Sri Venkateswara College of Engineering Sriperumbudur India Assistant Professor Computer Science and Engineering Lord Jegannath College of Engineering and Technology Kanyakumari Tamil Nadu 629402 India

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Mammogram Enhancement using Nonlinear Unsharp Masking and L 0 Gradient Minimization

引用

Procedia computer science 2020年 171卷 1848-1857页

作者： Divya Christopher Philomina Simon Assistant Professor in Computer Science and Engineering Lourdes Matha College of Science and Technology Kerala - 695574 Affiliated to APJ Abdul Kalam Technological University Thiruvananthapuram India Assistant Professor in Computer Science University of Kerala Kariavattom Thiruvananthapuram Kerala – 695581 India

Mammography is an effective modality for detecting and diagnosing breast cancer. Mammogram enhancement is used to improve the local contrast of mammograms, such that lesions appear more visible in the enhanced image. This paper introduces two novel approaches for mammogram enhancement based on a new unsharp masking scheme, called nonlinear UM and L 0 Gradient Minimization, NLUM L 0 GMIN for detecting breast cancer at an early stage. Three different techniques are unified in the proposed method; i) a Nonlinear filtering process to enhance the fine details within a 3x3 local neighborhood, ii) an L 0 Gradient Minimization step globally preserving the high-contrast edges while suppressing low-contrast details seen as opaque fibrous tissues; and to obtain a detail mammogram after subtracting smoothed mammogram from the original mammogram, iii) Finally, an Unsharp masking technique combining detail mammogram with filtered mammogram passed through Non-linear filter, using PLIP operators which satisfy both Weber’s law and saturation characteristics of the human visual system.. An HVS-based decomposition scheme is used to analyse and visualize the malignant areas in the enhanced mammogram. The distinct arrangement of PLIP operators in the proposed framework has given rise to two methods NLUM L 0 GMINAUTO and NLUM L 0 GMIN, which outperforms NLUM method and other existing techniques for mammogram enhancement. The former is good at enhancing less-dense and medium-dense mammograms whereas the later enhances unseen masses within high-dense mammograms. Experimental results have stated the significance of the proposed method in effectively diagnosing breast cancer in comparison with the previous methods for mammogram enhancement. The mini-MIAS database has categorized mammograms as fatty, fatty-glandular and dense-glandular, which has helped us in focusing on enhancing images uniquely for each category. The proposed NLUM L 0 GMIN scheme is robust and effective in identifying cance

关键词： L 0 Gradient Minimization ( L 0 GMIN) Nonlinear Unsharp Masking (NLUM) Parameterized Logarithmic Image Processing (PLIP) Human-Visual-System (HVS)-based image decomposition Unsharp Masking (UM) Mammogram enhancement

来源：评论

学校读者我要写书评

暂无评论

The Terms Estimation of S Robotics using MTRS as well as FEM

The Terms Estimation of S Robotics using MTRS as well as FEM

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： R. Gopal Mustafa Mudhafar Amjad Hashem Venkadeshan Ramalingam Dibyahash Bordoloi Muhammad Numan Ali Khan Myasar Mundher Adnan Zahraa N. Abdulhussain Assistant Professor Information and communication Engineering College of Engineering University of Buraimi Sultanate of Oman Department of Medical Physics Faculty of Medical Applied Sciences University of Kerbala Karbala Iraq Computer Engineer Department Al-kunooze University College Basra Iraq Network Computing College of Computing and Information Sciences University of Technology and Applied Sciences– Shinas Sultanate of Oman Dept of CSE Graphic Era Hill University Adjunct professor Graphic Era Deemed to be University Dehradun Uttarakhand Faculty – Network Computing College of Computing and Information Sciences University of Technology and Applied Sciences – Shinas Sultanate of Oman Department of computers Techniques engineering College of technical engineering The Islamic university Najaf Iraq College of Technical Engineering National University of Science and TechnologyDhi Qar Iraq

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

This look at addresses the critical project of reaching dependable and precise proprioception in soft robots, it really is essential for his or her effective deployment in complicated environments. By integrating multi-tap resistive sensors in the robot’s form, our technique lets in for the distinct sensing of nearby deformations at various factors throughout the robotics’ frame, moving beyond traditional techniques that anticipate steady curvature. We beautify the decision of these deformations and couple the sensory facts with a strong finite detail technique (FEM) model. This included framework allows the correct estimation of the smooth robot’s form and the significance of outside forces applied to it, attaining a mean relative inaccuracy of about 4%. Additionally, our technique proves its software program in tender manipulation structures, in which it achieves thirteen% relative mistakes in external force estimation inside diverse zero to five N. The approach gives a promising direction for enhancing robotic interactions in sensitive and dynamic responsibilities, providing massive enhancements in robotic proprioception without reliance on outdoor monitoring generation.

关键词： Deformable models Deformation Force Estimation Soft robotics Robot sensing systems Software

来源：评论

学校读者我要写书评

暂无评论

Survey on Impact and Learning’s of the Online Courses on the Present Era

引用

Procedia computer science 2020年 172卷 82-91页

作者： T. Anitha Kumari CH. Hemalatha M Subhani Ali R Naresh Assistant Professor Department of Computer Science Engineering HITAM Hyderabad Telangana 501401 India Associate Professor Department of Mechanical Engineering HITAM Hyderabad Telangana 501401 India Assistant Professor Department of Electrical and Electronics Engineering HITAM Hyderabad Telangana 501401 India

Day to day technology is changing to upgrade or adopt technology faculty as well as students preferring online courses like NPTEL. With the fast development of internet techniques, data and communication technology is being more and more employed in curricula, and learning portfolios may be mechanically retrieved and maintained as learners act through e-learning platforms. NPTEL provided open access to hundreds and thousands of learners to take the preferred courses and helped to become experts in a particular area. This paper describes the impact of the online courses (NPTEL) on the learners and challenges and learning’s from the online courses. The participants comprised 114 faculty, who were surveyed regarding their learning experiences, motivation, challenges and intentions to use NPTEL. And what can be improved from the Faculty and student point of view?

关键词： Online courses Learning’s Challenges Motivation

来源：评论

学校读者我要写书评

暂无评论

Multi-class Cancer Classification in Microarray Datasets Using MI-Based Feature Selection and Artificial Neural Network 1

引用

4th International Conference on Nanoelectronics, Circuits and Communication Systems, NCCS 2018

作者： Jansi Rani, M. Devaraj, D. Assistant Professor Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil Virudhunagar India Dean School of Electronics & Electrical Technology Kalasalingam Academy of Research and Education Krishnankoil Virudhunagar India

ISBN: (数字)9789811528545

ISBN: (纸本)9789811528538

Recent developments in microarray data analysis and improvements in soft computing techniques have played a major role in the field of cancer classification. Classification and identification of cancer are very important as early cancer identification is highly useful for its treatment. Cancer diagnosis is challenging as microarray data has large number of genes. Many gene selection algorithms have been applied to effectively select the most promising gene subsets that can accurately identify cancer samples. In this paper, Mutual Information is used to select the informative genes and Feed Forward Neural Network is used to classify the genes. The proposed MI-ANN based gene selection and ANN classification are applied to classify multi-class microarray datasets. The obtained results show that the proposed method provides higher classification accuracy compared to existing methods. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Soft computing

来源：评论

学校读者我要写书评

暂无评论

Optimized Bit Matrix based Power Aware Load Distribution Policy for Federated Cloud

引用

Procedia computer science 2020年 167卷 1771-1790页

作者： B S Rajeshwari M Dakshayini Assistant Professor Department of Computer Science and Engineering B M S College of Engineering Bangalore 560019 India Professor Department of Information Science and Engineering B M S College of Engineering Bangalore 560019 India

Federated Cloud is a next generation cloud computing model which works towards a new dynamic scenario in smart ecosystems. It consolidates individual clouds together to form single large cloud to satisfy all on-demand requirements of the users. Federated cloud is currently facing many challenges including: monitoring of individual cloud services, maintaining service level agreement, fair load distribution, power usage etc. Hence, to address these challenges this paper presents a brokerage model “ Optimized Bit Matrix based Power Aware Load Distribution Policy for Federated Cloud (OBMPLP) ”. Presented model includes two novel concepts: Bit Matrix and Load Distribution Factor. Bit Matrix constructed by individual cloud members representing resource availability status and environment in executing the user’s request. Load Distribution Factor representing load distribution level at individual cloud. OBMPLP policy dispenses the incoming requests among multiple clouds by analyzing bits pattern and load distribution factor that not only performs fair load distribution among multiple clouds, but also improves response time, alleviate power consumption at each cloud and achieve better quality service. The performance of the proposed policy is evaluated and results demonstrate reduction in response time, optimized power consumption and fair distribution of load compared to existing approaches.

关键词： Cloud Computing Load Distribution Quality Service Power Consumption Federated Cloud

来源：评论

学校读者我要写书评

暂无评论

Machine learning models for evaluating the benefits of business intelligence systems

引用

Journal of High Technology Management Research 2023年第2期34卷

作者： Tripathi, Mano Ashish Madhavi, Kilaru Kandi, V.S. Prasad Nassa, Vinay Kumar Mallik, Banitamani Chakravarthi, M. Kalyan Department of Humanities and Social Sciences Motilal Nehru National Institute of Technology Allahabad Uttar Pradesh Prayagraj India Department of Business Management Velagapudi Ramakrishna Siddhartha Engineering College Kanuru Andhra Pradesh Vijayawada India Greenfields Andhra Pradesh Vaddeswaram India Department of Computer Science Engineering Rajarambapu Institute of Technology Rajaramnagar Maharashtra Sangli India Department of Mathematics Centurion University of Technology and Management Paralakhemundi Odisha Gajapati India Senior Assistant Professor School of Electronics Engineering VIT-AP University Andhra Pradesh Amaravathi India

Due to the uncertainty of the market and the intensity of rivalry, business owners and managers are often compelled to experiment with a wide variety of strategies for enhancing their company's performance. By enhancing the timeliness and quality of inputs to the decision-making process, Business Intelligence (BI) is one such idea and tool that combines operational data with analytical tools to show complex and competitive information to planners and decision-makers. Business intelligence (BI) tools help companies rapidly generate insights that guide managers toward operational efficiencies, lead them to new opportunities, and set them apart from the competition. The literature study shows that there is a debate about whether BI tools have an effect on the quality of decisions and the development of businesses. The present research explores the varied empirical facets of BI application through ML models. This study concluded with a discussion of how Machine Learning models can be used to assess the value of BI tools. Machine learning models, fed with historical data and a wealth of input features, can foresee the effect of new systems on metrics like revenue development, customer behavior, and inventory management. Using these models, businesses will be able to better evaluate potential investments in new tools and systems. © 2023 Elsevier Inc.

关键词： Decision making

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：