检索结果-内蒙古大学图书馆

7th International Conference on Computing Methodologies and Communication, ICCMC 2023

作者： Hegde, Sandeep Kumar Hegde, Rajalaxmi Krishna Priya, R. Sree Southry, S. Marthanda, A.V.G.A. Logu, K. Karkala Taluk Udupi India Department of Engineering Electrical Section University of Technology and Applied Sciences Shinas campus PO Box 66Al-Aqur Shinas324 Oman Department of ECE Sona College of Technology Salem India Department of EEE Laki Reddy Bali Reddy College of Engineering Mylavaram Permanently Affiliated to JNTU Andhrapradesh Kakinada India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India

ISBN: (纸本)9781665464086

The banking sector has advanced in recent years. Thus, there is an increase in the demand for bank loans. The bank must distribute and sell each of the limited number of available slots to a select group of people. As a result, a usual stage is to identify who will be unable to return the loan and who will prove to be a more trustworthy option to the bank. In order to save the bank time and costs, in the proposed paper machine learning based approach is introduced to reduce the risk involved with finding the safe individual. In order to decide whether or not to grant someone a loan, this paper presents a method of loan approval based on predetermined criteria. The machine learning model for credit approval was implemented using logistic regression, XG Boost, random forest and naïve bayes model. The experimental results indicates that logistic regression model is more accurate for the credit risk analysis. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Improved Approximation Algorithms for Patrol-Scheduling with Min-Max Latency Using Multiclass Minimum Spanning Forests 18th

Improved Approximation Algorithms for Patrol-Scheduling wit...

引用

18th International Conference on Algorithmic Aspects in Information and Management, AAIM 2024

作者： Chen, Li-Hsuan Hung, Ling-Ju Klasing, Ralf Department of Computer Science and Information Engineering National Chung Cheng University Chiayi62102 Taiwan Department of Creative Technologies and Product Design National Taipei University of Business No. 100 Section 1 Fulong Road Pingzhen District Taoyuan32462 Taiwan CNRS LaBRI Université de Bordeaux 351 Cours de la Libération Talence cedex33405 France

ISBN: (纸本)9789819778003

In a weighted complete metric graph G=(V,E,w,d), with w:V→R+ determining the importance of vertices and d:E→R+ defining the distance between vertices, consider k≥1 infinite walks W={W1,⋯,Wk} undertaken by robots r1,⋯,rk throughout G. The term latency L(W,v) is used to describe the maximum interval between successive visits to the vertex v by any robot in {r1,⋯,rk}. The (maximum) weighted latency of W in G is defined as L(W,G)=maxv∈Vw(v)·L(W,v), indicating the longest period a vertex remains unvisited, with adjustments made based on the weight assigned to a vertex to denote its significance. The goal of the k-Robot Patrol-Scheduling Problem is to minimize the weighted latency, thereby ensuring no graph vertex is neglected for extended periods. Addressed as a challenging issue in [Gąsieniec et al., Journal of computer and System sciences, 2024] (where the problem is referred to as the (continuous) Bamboo Garden Trimming Problem), it holds crucial relevance for fields requiring the methodical deployment of robots for tasks such as surveillance, monitoring, and exploration within metric graph-modeled environments. In this paper, we give improved approximation algorithms for k≥1 robots that utilize a novel strategy of constructing multi-class minimum spanning forests. For the single robot case, i.e., k=1, we give a 5h-approximation algorithm which improves the (8h+14)-approximation algorithm given in [Alamdari et al., International Journal of Robotics Research, 2014], where h=⌊log2wmaxwmin⌋+1, wmax=maxv∈Vw(v), and wmin=minv∈Vw(v). For k≥2, we give an approximation algorithm running in O(n2logL∗) time achieving an O(k·logwmaxwmin)-approximation solution, where n is the number of vertices in the input graph and L∗ is the optimum weighted latency. The adoption of a multi-class minimum spanning forest strategy marks a significant improvement over the previous O(k2·logwmaxwmin)-approximation algorithm [Afshani et al., WAFR 2020], not only for the approximation ratio but also

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Design of Runge-Kutta optimization for fractional input nonlinear autoregressive exogenous system identification with key-term separation

引用

Chaos, Solitons and Fractals 2024年 182卷

作者： Khan, Taimoor Ali Chaudhary, Naveed Ishtiaq Khan, Zeshan Aslam Mehmood, Khizer Hsu, Chung-Chian Raja, Muhammad Asif Zahoor International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Electrical and Computer Engineering International Islamic University Islamabad Pakistan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Information Management National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

Population-based metaheuristic algorithms have gained significant attention in research community due to its effectiveness in solving complex optimization problems in diverse fields. In this study, knacks of population-based Runge-Kutta optimizer (RUN) are exploited for the identification of fractional input non-linear exogenous auto-regressive (FINARX) system with key term separation. The fractional order calculus operator of the Grünwald-Letnikov derivative is exploited to develop FINARX from a conventional non-linear auto-regressive exogenous system. The identification scheme for FINARX model is implemented through a mean-square-error-based fitness function. RUN utilizes the slope variations calculated by the well-known Runge-Kutta method for an effective search mechanism in the exploration and exploitation phases. Moreover, an enhanced solution quality mechanism is employed for speedy convergence and keeping the movement toward the best solution by escaping the local optima. The robustness of the algorithm is analyzed by multiple variations of non-linearity as well as different noise scenarios. The performance of the RUN to identify the FINARX system is validated in terms of convergence rate, fitness value, robustness, and accuracy in weight estimation. The effectiveness of the RUN is further assessed through exhaustive simulations with their statistics as well as comparison with the standard recent counterparts, including the Whale optimization algorithm, Reptile Search algorithm, and Aquila optimizer on different performance indices for the FINARX system. © 2024 Elsevier Ltd

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Human Movement science-Informed Multi-Task Spatio Temporal Graph Convolutional Networks for Fitness Action Recognition and Evaluation

SSRN

引用

SSRN 2023年

作者： Chang, Jia-Wei Chen, Ming-Hung Ma, Hao-Shang Liu, Hao-Lan Department of Computer Science and Information Engineering National Taichung University of Science and Technology No. 129 Section 3 Sanmin Road North District Taichung City404 Taiwan Physical Education Section National Taichung University of Science and Technology No. 129 Section 3 Sanmin Road North District Taichung City404 Taiwan

In recent years, with the rise of health consciousness, people's demand for fitness has been steadily increasing. Improper exercise movements can easily lead to injuries while working out. Therefore, if we could utilize automated human action recognition to continuously monitor users' movements during exercise, it would effectively help prevent incorrect movements. Human action recognition has found extensive applications in multimedia computing, and we aim to leverage it to assess users' fitness conditions. Some existing action motion recognition models rely heavily on CNNs for image processing, which introduces unnecessary noise from the background and surroundings. To address this issue, some researches focus on the skeleton structure information for the action recognition and apply the graph convolutional network to enhance the performance. Generally, the proposed action human recognition method only recognize the type of actions. In this study, we are trying to design an automated fitness adviser system to improve the exercise experience in fitness gyms. The adviser system not only detect the correctness of fitness action but also evaluate the action quality simultaneously. To address this issue, we involve the human movement science such as Five Primary Kinetic Chains(5PKC) to provide the more accurate relations of human skeleton and muscles. Five Primary Kinetic Chains(5PKC) defines the primary physiological principle in human movement. The proposed model adopts Five Primary Kinetic Chains(5PKC) as a partitioning strategy to explore the skeleton partition and designs a multi-task objective function based on the Spatio Temporal Graph Convolutional Networks(ST-GCN) framework. For the experiments, a custom fitness dataset is collected from the gym and used to evaluate the performance of proposed model. In addition, we also compare with existing methods to confirm the effect of the proposed model. © 2023, The Authors. All rights reserved.

关键词： Kinetics

来源：评论

学校读者我要写书评

暂无评论

Inter- and sub-harmonics estimation: Treatise on raptor-inspired Harris Hawks collective wisdom

引用

International Journal of Modern Physics C 2024年第12期35卷

作者： Malik, Naveed Ahmed Chang, Ching-Lung Chaudhary, Naveed Ishtiaq Raja, Muhammad Asif Zahoor Shu, Chi-Min Graduate School of Engineering Science and Technology National Yunlin University of Science and Technology University Road Douliu 123Section 3 Yunlin 64002 Taiwan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology University Road Douliou 123Section 3 Yunlin 64002 Taiwan Future Technology Research Center National Yunlin University of Science and Technology University Road Douliou 123Section 3 Yunlin 64002 Taiwan Department of Safety Health and Environmental Engineering National Yunlin University of Science and Technology University Road Douliou 123Section 3 Yunlin 64002 Taiwan

In contemporary power systems, harmonics as undesired electrical phenomena, have drawn considerable attention of the research community investigating in design and development of optimal electrical networks. Harmonics affect the power electronics devices with a number of negative impacts, including higher power losses, worse power quality, and interference with other delicate grid connected equipment. An objective function of inter- and sub-harmonics is constructed for joint estimation of amplitude and phase with known frequency. Accurate estimation of the harmonics model is carried out with stupendous knacks of raptor-inspired Harris Hawks optimization algorithm (HHOA), a revolutionary population-based, nature-motivated optimization approach. The primary sources of inspiration for HHOA are Harris Hawks cooperative demeanor and surprise pounce chasing style in nature. The HHOA's performance is assessed for harmonics parameter estimation with several noise conditions, differing particle sizes and iterations. The proposed HHOA-based estimation technique provides accurate, convergent and robust performance for harmonics estimation. The reliable level of fitness is achieved consistently in the range of 10^-3 to 10^-10, an evidence of valuable precision, stability and robustness of the proposed algorithm. © 2024 World Scientific Publishing Company.

关键词： harmonics analysis Harris Hawks optimization parameter estimation Power quality swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

A Fully Connected Neural Network For Polar Channel Decoding

A Fully Connected Neural Network For Polar Channel Decoding

引用

International Conference on Electrical engineering, Computing science and Automatic Control (CCE)

作者： Jesús Ángel Sánchez-Rodríguez Ana M. Martinez-Enriquez Mauricio Lara Communications Section Dept. Electrical Engineering CINVESTAV-IPN Mexico City Mexico Dept. Computer Science CINVESTAV-IPN Mexico City Mexico

One of the most essential components of a communications system is channel coding, which provides protection for the original source message. Polar codes have gained great importance due to the fact that they reach the channel capacity for the Binary Discrete Memoryless Channel. Both encoding and decoding, for this type of codes, are serial processes, which increases latency. In this research, we propose a fully connected neural network architecture that tackles this problem in decoding thanks to the inherent parallelization of this type of structure. Our experimental results demonstrate that a fully connected neural network reduces decoding delay, although further study is still needed to reach the accuracy of the probabilistic decoding methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ML Based Phenotype Analysis Using Differential Gene Expression Data in Schizophrenia

ML Based Phenotype Analysis Using Differential Gene Expressi...

引用

Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), International Conference on

作者： Aadhithyan D Shabarirajan KJ Varun Maniappan Shivanesh B Divya S Praghaadeesh R Kalpana Raja I R Oviya Department of Computer Science and Engineering (Artificial Intelligence) Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven Connecticut USA

ISBN: (数字)9798350384628

ISBN: (纸本)9798350384635

In this paper, differential gene expression (DGE) data in schizophrenia is analysed using machine learning approaches with the objective of predicting cell phenotypes related to the condition. The dataset contains information on cis eQTNs, gene orientation, probe information, gene expression profiles, and SNP information. When first investigating well-known machine learning methods, a hybrid model combining Random Forests and XGBoost is suggested, however it only offers a little increase. Increases in predicted accuracy of more than 99.12% are made possible by the H2O AutoML package. The results demonstrate the capability of ML-based analysis to unravel the underlying biological mechanisms of schizophrenia and contribute to the design of individualised therapeutic approaches. The paper represents the capability of machine learning to comprehend the relationship between gene expression patterns and complicated illnesses like schizophrenia.

关键词： Water Training Accuracy Phenotypes Mental disorders Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

Stroke Prediction Using Machine Learning

Stroke Prediction Using Machine Learning

引用

International Conference on Advances in Electronics, computers and Communications (ICAECC)

作者： Abinandhini D M Aman Kumar Gudi Vishnu Teja Mandava Sukesh Divya S Naman Chauhan I R Oviya Kalpana Raja Department of Computer Science and Engineering (Artificial Intelligence) Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven Connecticut USA

ISBN: (数字)9798350305449

ISBN: (纸本)9798350305456

A stroke is a serious medical emergency that happens when bleeding or blood clots cut off the blood flow to a part of the brain. With a mortality rate of 5.5 million per year, it ranks as the second leading cause of death globally. Over 15 million individuals experience a stroke each year, and one person dies from one every four minutes. According to the World Health Organization, stroke is the main cause of death and disability worldwide (WHO). Identifying the many stroke warning signs helps lessen the severity of the stroke. A stroke can be avoided in up to 80% of instances because it is typically the result of a poor lifestyle. As a result, stroke prediction becomes important and should be employed to stop it from causing long-term harm. The current study uses a variety of machine learning models, including Gaussian Naive Bayes, Logistic Regression, Support Vector Machine (SVM), KNN and Random Forest to predict stroke. The paper presents the comparison among all machine learning algorithms. Analysis of results revealed that KNN had the least accuracy of 76.32% and Random Forest had the highest accuracy of 94.81%.

关键词： Support vector machines Accuracy Organizations Stroke (medical condition) Predictive models Vectors Physiology

来源：评论

学校读者我要写书评

暂无评论

Procrustean entanglement concentration in quantum-classical networking

引用

Physical Review Applied 2024年第4期21卷 044027-044027页

作者： Hsuan-Hao Lu Muneer Alshowkan Jude Alnas Joseph M. Lukens Nicholas A. Peters Quantum Information Science Section Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak Ridge Tennessee 37831 USA Department of Electrical and Computer Engineering Duke University Durham North Carolina 27708 USA Research Technology Office and Quantum Collaborative Arizona State University Tempe Arizona 85287 USA

The success of a future quantum internet will rest in part on the ability of quantum and classical signals to coexist in the same optical fiber infrastructure, a challenging endeavor given the orders of magnitude differences in flux of single-photon-level quantum fields and bright classical traffic. We theoretically describe and experimentally implement Procrustean entanglement concentration for polarization-entangled states contaminated with classical light, showing significant mitigation of crosstalk noise in dense wavelength-division multiplexing. Our approach leverages a pair of polarization-dependent loss emulators to attenuate highly polarized crosstalk that results from imperfect isolation of conventional signals copropagating on shared fiber links. We demonstrate our technique both on the tabletop and over a deployed quantum local area network, finding a substantial improvement of two-qubit entangled state fidelity from approximately 75% to over 92%. This local filtering technique could be used as a preliminary step to reduce asymmetric errors, potentially improving the overall efficiency when combined with more complex error-mitigation techniques in future quantum repeater networks.

关键词： Entanglement manipulation Optical quantum information processing Quantum entanglement Quantum networks Quantum optics Quantum repeaters Internet Multilayer & multiplex networks

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Power Flow Estimation for MVDC Distribution Systems Based on Physics-Embedded FCN

引用

IEEE Transactions on Smart Grid 2025年

作者： Sun, Pingyang Wu, Rongcheng Shen, Zhiwei Wang, Hongyi Li, Gen Khalid, Muhammad Konstantinou, Georgios School of Electrical Engineering and Telecommunications UNSW Sydney Australia University of Technology Sydney Data Science Institute Australia Aalborg University Department of AAU energy Denmark Energy Technology and Computer Science Section Department of Engineering Technology Ballerup2750 Denmark King Fahd University of Petroleum and Minerals Electrical Engineering Department Interdisciplinary Research Center for Sustainable Energy Systems Dhahran31261 Saudi Arabia

Maintaining high prediction accuracy with varying grid topologies poses a significant challenge to adopting neural network (NN)-based approaches for power flow (PF) estimation in medium-voltage direct current (MVDC) distribution systems. This paper proposes a physics-embedded fully convolutional network (PEFCN) to improve the accuracy. Physics-embedded techniques are incorporated in the proposed PEFCN through 1) architecture reconstruction, and 2) loss function reformulation. Architecture is reconstructed by input channel conversion calculation in a new physics operation layer. This process offers physical connections among the three input matrix channels (voltage, current, and line conductance). Three new physics loss terms are included in the loss function to restrict the outliers violating the limits of converter power ratings and terminal MVDC voltages. The two operations enable the FCN to achieve improved prediction accuracy and strong generalization capabilities. Five MVDC distribution systems, characterized by different dc voltage levels and topology configurations, serve to validate the superiority of the proposed PEFCN over other NNs in the PF estimation for scenarios involving both fixed and varying system structures. Moreover, a modified IEEE 69-bus distribution system is further used to demonstrate the applicability of the proposed PEFCN for larger systems. © 2010-2012 IEEE.

关键词： DC distribution systems

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：