检索结果-内蒙古大学图书馆

5th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2022

作者： Lertwuthikarn, Thanarit Barroso, Vasco Chibante Akkarajitsakul, Khajonpong King Mongkut's University of Technology Thonburi Department of Computer Engineering Bangkok Thailand Geneva23 Switzerland King Mongkut's University of Technology Thonburi Big Data Experience Center Department of Computer Engineering Bangkok Thailand

ISBN: (数字)9781665479295

ISBN: (纸本)9781665479295

In resource management, resource optimization is a usual technique to proceed for most professional organizations in order to reduce expenses and to dispose unnecessary resource usages. The European Organization for Nuclear Research (CERN) intends to implement a logging system based on AI for A Large Ion Collider Experiment detector, or ALICE. This system has been being implemented by using the Elasticsearch, Kibana, Beats, and Logstash also called ELK Stack which gives us the capability for the logs aggregation from systems and applications. Log data are collected from involved servers at CERN called First Level Processors (FLPs) nodes by Beats. These nodes run a large number of services when tasks are executed and generate a large volume of log data. Filebeat is used as a log shipper to transfer the data to Logstash, a server-side preprocessing pipeline. When Filebeat and Logstash are working together, there are many configurable factors affecting their efficiency. We then apply a factorial experiment to identify the significant factors and their correlation. These parameters are also optimized to find the best possible values of their configurations. Then, the resource usage can be minimized while a suitable performance of the system is maintained. The results of this study show that we can increase the efficiency of the system thanks to the adjusted values of the parameters. This can be used as a guideline for tuning some configurable parameters to optimize resource usage when there is a large amount of log data to be handled. © 2022 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

NONSMOOTH INTERVAL-VALUED MULTIOBJECTIVE OPTIMIZATION PROBLEMS AND GENERALIZED VARIATIONAL INEQUALITIES ON HADAMARD MANIFOLDS

Applied Set-Valued Analysis and Optimization

引用

Applied Set-Valued Analysis and Optimization 2023年第1期5卷 69-84页

作者： Upadhyay, B.B. Li, Lijie Mishra, Priyanka Department of Mathematics Indian Institute of Technology Patna Bihar Patna801103 India Guangxi Colleges Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal University Guangxi Yulin537000 China Mathematics Division School of Advanced Sciences and Languages VIT Bhopal University Bhopal-Indore Highway Kothrikalan Madhya Pradesh Sehore466114 India

In this paper, we study the classes of approximate Minty and Stampacchia type vector variational inequalities along with their local and weak versions on a Hadamard manifold, and a class of nonsmooth interval-valued multiobjective optimization problems, respectively. We obtain the equivalence between the solutions of considered approximate vector variational inequalities and LU-efficient solutions of nonsmooth interval-valued multiobjective optimization problems in which the cost function is assumed to be geodesic approximately LU-convex or geodesic LU-α-convex. ©2023 Applied Set-Valued Analysis and Optimization.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of active contour random walker and watershed algorithms in segmentation of ovarian cancer 6

Comparative analysis of active contour random walker and wat...

引用

6th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2022

作者： Ruchitha, P.J. Sai, Richitha Y Kodipalli, Ashwini Martis, Roshan Joy Dasar, Santosh Ismail, Taha Global Academy of Technology Computer Science and Engineering Bangalore India Global Academy of Technology Artificial Intelligence and Data Science Bangalore India Sdm College of Medical Science Department of Radiologist Dharwad India

ISBN: (数字)9781665487160

ISBN: (纸本)9781665487160

In the recent era, Image processing has been one of the most commonly used domain in the field of medical science that includes different kinds of procedures namely extraction, image gaining, detection, surgical planning and presentation which indeed helps in giving effective treatment to the patient and using all those techniques, the disease could also be detected at a early stage. When it comes to the case of ovarian cancer, it could be treated successfully when detected at an early *** per the following statistics, it is very much important to identify the cancer in the ovaries at the starting stage. Today, there are many algorithms that are being implemented in order to detect the cancer i.e. by segmentation. Here are the three algorithms Random Walker, Active Contour and Watershed that are being implemented in order to segment the ovarian cancer. Finally, a comparative analysis is being performed to identify which gives a better result among the three algorithms. © 2022 IEEE.

关键词： Watersheds

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-layer Perceptron Training with Prairie Dog Optimizer: Advancing Classification Accuracy in Medical Diagnostics

Enhancing Multi-layer Perceptron Training with Prairie Dog O...

引用

Silchar Subsection Conference (SILCON), IEEE

作者： Tanzil Debbarma Azharuddin Shaikh Anirban Tarafdar Abhijit Baidya Pinki Majumder Uttam Kumar Bera Department of Mathematics National Institute of Technology Agartala India Department of Data Science and Engineering IISER Bhopal Bhopal India

ISBN: (数字)9798331540821

ISBN: (纸本)9798331540838

Multi-layer Perceptron (MLP) networks are widely used for classification and regression due to their flexibility and capacity. However, their performance depends heavily on the optimization algorithm used during training, with traditional backpropagation often failing to achieve globally optimal solutions. This paper presents a Prairie Dog Optimization (PDO) based backpropagation technique for MLP training, aimed at enhancing accuracy, especially in classification tasks. PDO improves MLP optimization by using a dynamic, population-based search strategy to navigate complex loss landscapes effectively, leading to better convergence to global optima. Experiments on breast cancer diagnosis and diabetes classification demonstrate that PDO-MLP significantly outperforms other optimization-based backpropagation methods, including flower pollination algorithm (FPA), ant colony optimization (ACO), standard gradient descent backpropagation (BP), and particle swarm optimization (PSO). Notably, PDO-MLP achieved 97.30% accuracy on the Iris dataset, 82.6% on diabetes classification, and 96.41% on breast cancer diagnosis, proving its effectiveness for various real-world applications.

关键词： Backpropagation Training Grasslands Iris Accuracy Dogs Search problems Breast cancer Diabetes Optimization

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques Based Energy Prediction Analysis and Load Forecasting Using a Dynamic Website 1

Artificial Intelligence Techniques Based Energy Prediction A...

引用

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems, iTech SECOM 2023

作者： Ramesh, R. Dharani, S. Asuvanti, M.A. Gowrijayasree, Gowrijayasree Indhu Rekha, U. Bannari Amman Institute of Technology Department of Electronics and Communication Engineering India Dr. Mahalingam College of Engineering and Technology Department of Electronics and Communication Engineering India Sengunthar Engineering College Department of Electronics and Communication Engineering India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science India

ISBN: (纸本)9798350371185

Electricity plays a crucial part in human living. The use of electricity has become a necessity. Though energy is a renewable resource it is being wasted often due to energy leakage, short circuit, and load balancing. Numerous actions and choices, including the use of load prediction affect countless decisions and actions, including transportation, unit involvement, fuel reservation, and out-of-service network study. Energy consumption data of a building is generated via an energy meter;it is then trained to fewer models for prediction and forecasting. Energy usage forecasting using LSTM with a higher accuracy of 87% than other Autoregressive models and with a Mean Absolute Error of 0.03 is suitable for implementation. Then the model is built into a Web App that enables users to keep track of the energy usage of their appliances. In the next step a threshold value is set, and whenever the appliances reach the maximum threshold value it is notified to the user or consumer which helps in reducing unwanted energy wastage in any particular area of use. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Improved Soft Actor-Critic: Reducing Bias and Estimation Error for Fast Learning

Improved Soft Actor-Critic: Reducing Bias and Estimation Err...

引用

2023 IEEE International Students' Conference on Electrical, Electronics and Computer science, SCEECS 2023

作者： Shil, Manas Pillai, G.N. Gupta, M.K. Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Roorkee247667 India Indian Institute of Technology Roorkee Department of Electrical Engineering Roorkee247667 India Department of Management Studies Indian Institute of Technology Roorkee Roorkee247667 India

ISBN: (纸本)9798350398748

Soft actor critic (SAC) is an off policy deep reinfor-cment learning algorithm that learns by using the principle of maximum entropy regularization. It updates the policy stochas-tically. The actor-critic formulation is combined with off policy learning procedure in SAC which helped it to attain state-of-art performance. This paper suggests some methods to enhance the performance of SAC. Firstly, multi-step look ahead is suggested which deals with the estimation error of q - values followed by an approach of dual actor network and delayed updates of the target and policy networks which minimize the errors transferred during the training. The resulted ImprovedSAC is compared with the original SAC interms of maximum rewards obtained. The simulation results in the benchmark control tasks of MUJOCO environments shows the effectiveness of the suggested methods. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

data Evidence-Based Aircraft Continuing Airworthiness Management Assistant System and Applications 4

Data Evidence-Based Aircraft Continuing Airworthiness Manage...

引用

4th IEEE International Conference on Civil Aviation Safety and Information technology, ICCASIT 2022

作者： Miao, Jiahe Zhang, Chen Jiao, Yang Zhang, Xinyue Li, Qian China Academy of Civil Aviation Science &technology Big Data Analysis and Application Center Beijing China China Academy of Civil Aviation Science &technology Eng. and Technical Research Center of Civil Aviation Safety Analysis and Prevention of Beijing Beijing China

ISBN: (数字)9781665467667

ISBN: (纸本)9781665467667

This paper proposes and introduces the construction scheme of the aircraft continuing airworthiness management assistant system based on data evidence. The system can deeply integrate aircraft fault/event cases, usage information and actual operational airborne QAR data to achieve classified management of fault data, normal data, new aircraft data, and full life cycle data, thereby enhancing the role of data evidence and data intelligence in continuing airworthiness management. QAR data can be used as direct evidence for fault case analysis and investigation. Statistical rules obtained and model trained from historical data can serve as indirect evidence for fleet health management. Taking engine health management as an example, the article introduces the construction and management of engine typical fault case sets based on system database, and shows the real fault cases in actual operation and the application of related engine condition monitoring technologies based on QAR data, including threshold monitoring, dual-engine difference monitoring and trend monitoring. The system can serve not only the supervision of regulators, but also the fleet health management of airlines and manufacturers, which helps all parties improve their continuing airworthiness management capabilities, discover design and manufacturing defects in a timely manner during operation, and continuously track and ensure aircraft airworthiness status. © 2022 IEEE.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

Enhancing Speech Emotion Recognition Combining Silence Elimination and Attention Model with a Novel CNN Architecture 8th

Enhancing Speech Emotion Recognition Combining Silence Elimi...

引用

8th International Conference on Information and Communication technology for Intelligent Systems, ICTIS 2024

作者： Gawali, Piyush P. Takale, Dattatray G. Deshmukh, Gopal B. Kashid, Shraddha S. Mahalle, Parikshit N. Sule, Bipin Ashokrao, Patil Rahul Derle, Deepak R. Department of Computer Engineering Vishwakarma Institute of Information Technology SPPU Pune Pune India Department of Computer Engineering MIT ADT University Pune India Department of Artificial Intelligence and Data Sciences Vishwakarma Institute of Information Technology SPPU Pune Pune India and Humanities Vishwakarma Institute of Technology Pune India Department of Computer Science and Application KTHM College Nashik India

ISBN: (纸本)9789819766772

A natural interface for human–computer interaction is automatic speech emotion recognition, but it encounters challenges in handling non-emotional speech segments, especially silence, since it is non-emotional speech segmentation that requires recognition. Using a carefully designed attention model and a silence elimination approach, this paper proposes a novel method of enhancing emotion recognition performance by combining silence elimination with attention. In the present study, an enhanced Convolutional Neural Network architecture has been proposed, comprising of nine layers, utilizing a combination of convolutional 1D As a result of the research, CNNs have been employed in a revolutionary speech-emotion detection system that reaches an impressive 96.00% accuracy rate. There is great potential in this breakthrough to develop social robots and conversational robots capable of conveying nuanced human emotions. This breakthrough has marked a significant improvement in accuracy compared to prior models based on the same dataset. In addition to the broader classifications of positive, negative, and neutral emotions, the model's accuracy is evaluated across a wide range of emotion classes, such as anger, calmness, fear, happiness, and sadness for both genders. There is considerable evidence to suggest that combined noise cancellation and attention models are more effective than individual models of noise cancellation or attention. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Perceived Social Support and Symptoms of Depression and Anxiety among Chinese Adolescents:A Moderated Chain Mediation Model

引用

International Journal of Mental Health Promotion 2025年第1期27卷 29-40页

作者： Le-Qing Jin Chen-Wei Pan Chun-Hua Zhao Dan-Lin Li Yi-Bo Wu Tian-Yang Zhang School of Public Health Suzhou Medical CollegeSoochow UniversitySuzhou215123China Department of General Medicine and Big Data Center The Affiliated Suzhou Hospital of Nanjing Medical UniversitySuzhou215008China School of Public Health Peking UniversityBeijing100191China Graduate School of Interdisciplinary Science and Engineering in Health Systems Okayama UniversityOkayama700-8530Japan

Background:Although previous studies indicate that perceived social support might be associated with adolescent psychological problems,the specific mechanism has not been thoroughly *** on theoretical and empirical research on problematic Internet use(PIU)and sleep quality,this study explored whether they play a mediating role between perceived social support and symptoms of depression and anxiety among ***,we investigated whether these relationships varied by place of ***:A sample of 2115 Chinese adolescents was included,and analyzed data related to perceived social support,PIU,sleep quality,symptoms of depression and anxiety,and sociodemographic *** analysis,mediation,and moderation analysis were mainly ***:Perceived social support was negatively correlated with depressive symptoms(r=−0.22,p<0.001)and anxiety symptoms(r=−0.20,p<0.001)among *** and sleep quality played a chain mediating role in the relationship between perceived social support and symptoms of depression and anxiety in ***,the place of residence moderated the relationships between perceived social support and PIU and symptoms of depression and *** social support was a significant negative predictor of PIU and symptoms of depression and anxiety among adolescents in urban areas but not in rural ***:The findings suggest that low levels of perceived social support may lead to more PIU and poorer sleep quality,which may further increase the risk of symptoms of depression and anxiety in adolescents,especially in urban areas.

关键词： Perceived social support psychological problems problematic internet use sleep quality urban-rural difference

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of the Imputing of Missing data on Air Pollution

A Comparative Analysis of the Imputing of Missing Data on Ai...

引用

Networking and Communications (ICNWC), International Conference on

作者： M. Gayathri V. Kavitha Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

Air pollution is a significant environmental hazard in modern society because of its serious impact on human health and the environment. In point of fact, there has been a substantial rise in the levels of pollution in the environment over the course of the past few years. data analyst is commonly encountering the issue of data missing. It is crucial to handle them efficiently to get more accurate and dependable data analysis findings. This study aims to improve understanding of data missing mechanisms, data imputation techniques, and examine the efficacy of frequently utilized data imputation techniques on quantitative datasets. Analysts and data scientists frequently face the challenge of missing data in their investigations. Therefore, it is essential to handle them in an efficient manner so as to gain improved and more trustworthy results through the analysis of the data. The objective of this research is to enhance comprehension of data missing processes and data imputed methods, while also evaluating the effectiveness of data imputed approaches often employed in quantitative datasets. A complete comparison of 5 different data imputation methods is presented in this article. These approaches include mean imputation, median imputation, mode imputation, kNN imputation and Linear Regression. For the purpose of analysing and contrasting the efficacy of the various data imputation approaches, we have utilized five distinct numeric datasets that were gathered from several air pollution repositories. Standardized Root Mean Square Error (RMSE) is the technique for assessing the efficacy of data imputation techniques. According on the findings of the analysis, the kNN imputation approach offers superior performance than the other methods. There is no correlation between the length of the dataset or the number of values that are missing in the dataset and the accuracy of the data imputed approach.

关键词： data analysis Correlation data integrity Linear regression Pollution control Air pollution Hazards

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：