检索结果-内蒙古大学图书馆

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Gomathy B Jyothi P Kalyani G Ishwarya Niranjana M Mohanarathinam Jayaraj Velusamy Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Coimbatore India Department of AIMLDS QIS College of Engineering and Technology Ongole India Department of Civil Engineering QIS College of Engineering and Technology Ongole India Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Coimbatore India Department of Biomedical Engineering Karpagam Academy of Higher Education Coimbatore India Department of Electronics and Communication Engineering Nehru Institute of Engineering and Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Machine learning models face imbalanced data as a significant challenge after reaching over two decades of development. The prevalent class imbalance creates imbalanced models which prefer the majority group while reducing performance numbers across minority classes. This research presents an optimized version of SMOTE for Imbalanced Data handling through machine learning (SMOTE-IDEA) that acts as a technique for imbalanced data classification. The process of making minority-class synthetic samples to address class imbalance has been traditionally handled through SMOTE approaches. Standard SMOTE applications allow unwanted irrelevant data points to enter the data which produces undesirable results. The research suggests a new version of SMOTE which addresses past limitations to enhance the oversampling procedure. SMOTE technique generates synthetic data more efficiently through several additions. The method selects significant features through an automated process that removes unimportant information. Sample filtering and high-quality synthetic instance generation take place as part of this method. The method adapts weight distribution schemes to ensure that data generation occurs primarily in high-density regions thereby improving minority class composition. Several classification methods analyzed different ratio-imbalanced datasets to evaluate the newly upgraded SMOTE approach. The proposed strategy demonstrates superior performance against traditional SMOTE implementation and top-level benchmark approaches by delivering improved classifications in terms of accuracy and precision in addition to recall and F1-score operation on minority and majority groups.

关键词： Support vector machines Adaptation models Accuracy Machine learning algorithms Filtering Data handling Classification algorithms Decision trees Standards Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Underwater Image Restoration Based on Improved SwinIR Model

Underwater Image Restoration Based on Improved SwinIR Model

引用

International Conference on Intelligent Control and Information Processing (ICICIP)

作者： Yanke Lu Fang Li Xiaonan Luo Guangxi Key Laboratory of Image and and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Center for Applied Mathematics of Guangxi (GUET) Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

Image restoration is a classic foundational visual task, aimed at recovering damaged images, such as those affected by compression, blurring, or noise, to high-definition clarity. Although current image enhancement techniques largely rely on convolutional neural networks, the efficient capabilities of Transformers demonstrated in complex visual tasks have not yet been extensively applied in the field of image restoration. This paper presents an optimized image restoration strategy based on the SwinlR model, which is applied to the task of underwater image restoration. In the shallow feature extraction phase, deep separable convolution technology is employed; while in the deep feature extraction phase, a Spatial Gated Feedforward Network (SGFN) is utilized. The experimental data suggests that the novel approach surpasses conventional techniques in effectiveness and has effectively minimized both the model's parameter quantity and computational demands.

关键词： Visualization Convolution Computational modeling Noise Information processing Logic gates Feature extraction Transformers Image restoration Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Green Leaf Disease Detection Using Raspberry Pi and Random Forest Machine Learning Algorithm: An Automated Approach for Precision Agriculture

Green Leaf Disease Detection Using Raspberry Pi and Random F...

引用

International Conference on Smart Computing & Communications (ICSCC)

作者： Chitra Sabapathy Ranganathan Amjath Ali Jakul Basha A Vijayalakshmi N. Mohankumar S. Sujatha C. Sasikala Mphasis Corporation Chennai Tamil Nadu India Department of Engineering Computer Engineering Electrical and Electronic Section University of Technology and Applied Sciences Ibra Sultanate of Oman Department of Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India Symbiosis Institute of Technology Symbiosis International (Deemed University) Nagpur Maharashtra India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Electronics and Communication Engineering Sri Sai Ranganathan Engineering College Coimbatore Tamil Nadu India

ISBN: (数字)9798350363104

ISBN: (纸本)9798350363111

Farm production and food security are affected by green leaf diseases. Modern disease detection technologies may discover plant health issues early. This work uses Raspberry Pi, a cheap and flexible single-board computer, along the advanced Random Forest machine learning technique to identify a green leaf disease. To identify crop diseases, the study uses automated, non-invasive technologies. From labeled images of good and sickly leaves, the algorithm extracts color histograms and texture, and form. It feeds a Random Forest classifier these properties for classifying data with high dimensions. Several green leaf diseased plant species were examined. This method detected plant health concerns with high precision. Movement and low cost make the Raspberry Pi ideal for remote and resource-limited agriculture, increasing farming accuracy. Helping farmers and users identify and develop green leaf diseases improves efficient farming. This methodology has the potential to improve crop management, optimize pesticide usage, and increase agricultural productivity. These results might contribute to the development of advanced automatic disease detection techniques to address green leaf diseases in modern agriculture.

关键词： Productivity Precision agriculture Machine learning algorithms Accuracy Plants (biology) Crops Real-time systems Random forests Diseases Farming

来源：评论

学校读者我要写书评

暂无评论

Design of Monopole Transparent Antenna for Satellite Internet Aboard Aircraft

Design of Monopole Transparent Antenna for Satellite Interne...

引用

International Electrical Engineering Congress (iEECON)

作者： Tawan Thianthong Patchadaporn Sangpet Chatree Mahatthanajatuphat Nipont Tangthong Chawalit Rakluea Nonchanutt Chudpooti Thinnawat Jangjing Supphakon Khongchon Siam Airport Ground Services Co. Ltd. Bangkok Thailand Department of Electronics and Telecommunication Engineering Rajamangala Faculty of Engineering University of Technology Thanyaburi Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Industrial Physics and Medical Instrumentation Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

This research presents the design of a transparent antenna for satellite internet aboard aircraft. The presented antenna comprises a triangular arrow monopole antenna fed by a tapered microstrip transmission line. It employs a polycarbonate composite substrate with a dielectric constant (εr) of 2.8 and a thickness (h) of 1 mm. The proposed transparent antenna achieves a bandwidth in the frequency range of 10.42–22.70 GHz, with an omnidirectional radiation pattern and an average gain of 2.57 dBi, effectively covering the Ku band for satellite internet applications. The antenna design was simulated using electromagnetic wave CST simulation software, and a prototype antenna was fabricated. The designed antenna exhibits a reflection coefficient of less than -10 dB throughout the 10.7–12.7 GHz frequency range, which is the operational frequency range for satellite internet and is an acceptable value in research terms. Moreover, a conductor with a thickness of 0.035 mm sits on a composite substrate material to form the antenna structure for satellite internet aboard aircraft. We need to study and apply various techniques to further enhance the antenna's performance in future designs.

关键词： Satellite antennas Airplanes Satellites Microstrip antennas Military aircraft Internet Substrates Gain Antenna radiation patterns Transmission line antennas

来源：评论

学校读者我要写书评

暂无评论

A Process-Oriented Deadlock Recovery Policy for Flexible Manufacturing Systems

A Process-Oriented Deadlock Recovery Policy for Flexible Man...

引用

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Andrei Karatkevich Iwona Grobelna Dept. of Applied Computer Science AGH University of Science and Technology Kraków Poland Autom. Control Electronics and Electr. Eng. University of Zielona Góra Zielona Góra Poland

ISBN: (纸本)9781665476881

This paper proposes a deadlock recovery method for flexible manufacturing systems modeled with Petri nets. Recovery transitions are added to the net allowing to return from all the deadlock markings to the legal ones. Unlike similar methods based on the recovery transitions, the proposed recovery policy focuses on process instances of the system. Its aim is to reset the lowest number of them, with minimal executed number of steps in a process instance. The proposed approach is formally analysed regarding its correctness and complexity, as well as illustrated with some widely used examples and compared with the similar known methods. The comparison shows that the presented method is efficient, despite the slightly different optimization criteria than used in other similar methods.

关键词： Law Firing Machine vision Petri nets System recovery Explosions Flexible manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

Toxic Comment Classification Using S-BERT Vectorization and Random Forest Algorithm

Toxic Comment Classification Using S-BERT Vectorization and ...

引用

Contemporary Computing and Communications (InC4), IEEE International Conference on

作者： Aparna Ashok Kumar Peeta Basa Pati K. Deepa S.Tresa Sangeetha Department of Computer Science & Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Karnataka India Department of Electrical & Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Karnataka India Department of Engineering University of Technology and Applied Sciences AlMusannah Sultanate of Oman

The growing popularity of social media platforms and microblogging websites has led to an increase in the expression of views and opinions. However, conversations and debates on these platforms often lead to the use of toxic comments, which consists of insulting and hateful remarks. To address this issue, it is important for social media systems to be able to recognize harmful comments. With the rising incidence of cyberbullying, it is crucial to study the classification of toxic comments using various algorithms. This study compares the effectiveness of different word and sentence embedding methods, including TF-IDF, InferSent, Bert, and T5 for toxic comments classification. A comparative study is also conducted on the impact of using SMOTE to balance the highly imbalanced dataset. The results of these models are compared and analysed. It is observed that T5 embedding with Random Forest Classifier works best at 0.91 F1-Score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantifying the Contemporary Enablers in Achieving e-Governance for Sustainable Techno-Societal Development: A High Directive SEM Analysis

Quantifying the Contemporary Enablers in Achieving e-Governa...

引用

International Conference on Emerging Trends in Networks and computer Communications (ETNCC)

作者： Sonali Bhati Manish Dadhich Anand A Bhasker Kamal Kant Hiran Roshni Sharma Anurag Shukla School of Management Sir Padampat Singhania University Udaipur India School of Engneering Sir Padampat Singhania University Udaipur India School of Computer Science and Information Technology Symbiosis University of Applied Sciences Indore India Department of EAFM MLS University Udaipur India

This paper quantifies the contemporary determinants (economic, social, environmental, and e-governance) for sustainable techno-societal development. E-governance has the potential to drive sustainable societal development by promoting economic, social, and environmental sustainability. It can improve efficiency, transparency, accessibility, and cost-effectiveness in government processes while contributing to environmental sustainability by reducing paper usage and carbon emissions. This study employed 320 techno-respondents from Southern Rajasthan, and the model was empirically evaluated with statistical tests. This study uses a multidimensional research approach to establish a meaningful relationship between economic, social, and environmental factors in achieving e-Governance for sustainable societal development. The research developed and supported the research model using Smart-PLS. Furthermore, e-governance can improve access to education, healthcare, and social services, improving quality of life and reducing social inequalities. Despite some limitations, e-governance can be a valuable tool for achieving sustainable societal development, and its future scope can further enhance its effectiveness in addressing society's complex challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ON THE IMPLICIT BIAS TOWARDS DEPTH MINIMIZATION IN DEEP NEURAL NETWORKS

arXiv

引用

arXiv 2022年

作者： Galanti, Tomer Galanti, Liane Ben-Shaul, Ido Cbmm Massachusetts Institute of Technology CambridgeMA United States School of Computer Science Tel Aviv University Israel Department of Applied Mathematics Tel Aviv University Israel EBay Research

Recent results in the literature suggest that the penultimate (second-to-last) layer representations of neural networks that are trained for classification exhibit a clustering property called neural collapse (NC). We study the implicit bias of stochastic gradient descent (SGD) in favor of low-depth solutions when training deep neural networks. We characterize a notion of effective depth that measures the first layer for which sample embeddings are separable using the nearest-class center classifier. Furthermore, we hypothesize and empirically show that SGD implicitly selects neural networks of small effective depths. Secondly, while neural collapse emerges even when generalization should be impossible - we argue that the degree of separability in the intermediate layers is related to generalization. We derive a generalization bound based on comparing the effective depth of the network with the minimal depth required to fit the same dataset with partially corrupted labels. Remarkably, this bound provides nontrivial estimations of the test performance. Finally, we empirically show that the effective depth of a trained neural network monotonically increases when increasing the number of random labels in data. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An improved Personalized Customer Banking Model using Machine Learning

An improved Personalized Customer Banking Model using Machin...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Piyush Rohella Sheetal Temara Sagar Varma Samanthapudi T. Kiruthiga Payments & Commerce GoDaddy Edmonds Washington USA Dept of Computer & Information Sciences University of the Cumberlands Williamsburg KY USA Applied Data Science The Polis Center at Indiana University Purdue University Indianapolis Indianapolis Indiana USA Department of ECE Vetri Vinayaha College of Engineering and Technology Trichy Tamil Nadu INDIA

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

System getting to know has come to be a chief tool in many areas of modern-day lifestyles. One such place is patron banking. Via its predictive energy, gadget mastering has the potential to improve the manner banks interact with consumers substantially. In particular, gadget learning can supply effective and personalized carriers to clients, allowing banks to provide greater tailored solutions to personal customers. At the same time, device studying can help banks automate and streamline many strategies. By automating the execution and interpretation of patron records, banks can serve customers quicker and greater appropriately. Moreover, the system getting to know can be used to locate anomalous activities and frauds, supporting banks in defending their customers from dangers and threats. Furthermore, system-gaining knowledge can empower banks to improve their consumer segmentation, marketing, and pricing. With the aid of leveraging the information they’ve available, banks can craft new techniques and techniques to better birthday celebrations for their clients. They are able to offer greater centered rewards to customers with healthy positive profiles, as well as extra tailored offerings and pricing. In precis, device studying can revolutionize customer banking. Through their predictive and analytical skills, banks can dramatically enhance the way they interact with customers.

关键词： Industries Accuracy Banking Pricing Machine learning Fraud Financial services

来源：评论

学校读者我要写书评

暂无评论

Study of nuclear corrections on the charged hadron fragmentation functions in a Neural Network global QCD analysis

arXiv

引用

arXiv 2023年

作者： Soleymaninia, Maryam Hashamipour, Hadi Khanpour, Hamzeh Shoeibi, Samira Mohamaditabar, Alireza P.O.Box 19395-5531 Tehran Iran AGH University Faculty of Physics and Applied Computer Science Al. Mickiewicza 30 Kraków30-055 Poland Department of Physics University of Science and Technology of Mazandaran P.O.Box 48518-78195 Behshahr Iran

In this work, we present a new global QCD analyses, referred to as PKHFF.23, for charged pion, kaon, and unidentified light hadrons. We utilize a Neural Network to fit the high-energy lepton-lepton and lepton-hadron scattering data, enabling us to determine parton-to-hadron fragmentation functions (FFs) at next-to-leading-order (NLO) accuracy. The analyses include all available single-inclusive e+e− annihilation (SIA) and semi-inclusive deep-inelastic scattering (SIDIS) data from the COMPASS Collaboration for charged pions, kaons, and unidentified light hadrons. Taking into account the most recent nuclear parton distribution functions (nuclear PDFs) available in the literature, we evaluate the effect of nuclear corrections on the determination of light hadrons FFs. The Neural Network parametrization, enriched with the Monte Carlo methodology for uncertainty estimations, is employed for all sources of experimental uncertainties and the proton PDFs. Our results indicate that incorporating nuclear corrections has a marginal impact on the central values of FFs and their corresponding uncertainty bands. The inclusion of such corrections does not significantly affect the fit quality of the data as well. The study suggests that while nuclear corrections are a consideration, their impact in such QCD analysis is limited. Copyright © 2023, The Authors. All rights reserved.

关键词： Hadrons

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：