检索结果-内蒙古大学图书馆

7th International Conference on Data Science and Its Applications, ICoDSA 2024

作者： Yusliani, Novi Nurmaini, Siti Firdaus, Firdaus Nabilah, Aini Darmawahyuni, Annisa Abdiansah, Abdiansah Universitas Sriwijaya Faculty Engineering South Sumatera Palembang Indonesia Universitas Sriwijaya Informatic Engineering Faculty of Computer Science South Sumatera Palembang Indonesia Universitas Sriwijaya Intelligent System Research Group Faculty of Computer Science South Sumatera Palembang Indonesia

ISBN: (纸本)9798350365351

Keyphrase extraction aims to extract a set of keyphrases from the input document that highly summarizes the document. One of the issue in keyphrase extraction is how to extract representative keyphrases that is relevance and describe the information in the document. This study addresses pretrained language model (PLM) and topic-guided graph attention network (TgGAT) to extract a set of keyphrases from the input document. PLM can effectively capture knowledge from massive data and well perform on both language understanding and language generation tasks. BERT is one of PLM that designed to process bidirectionally, allowing BERT to understand word context based on the surrounding words. To enhance the keyphrase relevance, latent-dirichlet allocation used to learn the latent topic information and aiding the semantic understanding of the input document. For capturing semantic relationships between phrases in document based on their topics, this study used TgGAT. TgGAT models the anchoraware graph which organizes the initial anchor phrases. Experiment was conducted on a dataset containing 100 Indonesian accredited scientific article, Sinta 2 and Sinta 3, to evaluate the system' $s$ performance. The experimental results show a precision value of 0.058, a recall value of 0.070, and an F1-score of 0.062 for the five generated keywords across the entire tested dataset. Further in-depth analyses shows that pattern of phrases used has the important role in determining the representative phrases in input document. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Workload Prediction and Distribution in Cloud Computing using Deep Reinforcement Learning and LSTM

引用

Journal of Harbin Institute of Technology(New series) 2025年

作者： Nampally Vijay Kumar Satarupa Mohanty Prasant Kumar Pattnaik School of Computer Engineering KIIT Deemed to be University Department of Computer Science and Business System B V RAJU Institute of Technology

Maintaining high-quality service supply and sustainability in modern cloud computing is essential to ensuring optimal system performance and energy efficiency. A novel approach is introduced in this study to decrease a system.s overall delay and energy consumption by utilising a deep reinforcement learning(DRL)model to predict and allocate incoming workloads flexibly. The proposed methodology integrates workload prediction utilising long short-term memory(LSTM)networks with efficient load-balancing techniques led by deep Q-learning and Actor-Critic algorithms. By continuously analysing current and historical data,the model can efficiently allocate resources,prioritizing speed and energy preservation. The experimental findings demonstrate that our load balancing system,which utilises DRL,significantly reduces average response times and energy usage compared to traditional methods. This approach provides a scalable and adaptable strategy for enhancing cloud infrastructure performance. It consistently provides reliable and durable performance across a range of dynamic workloads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Resilience: Machine Learning Techniques for Autonomous Anomaly Detection and Threat Mitigation

引用

Procedia computer Science 2025年 254卷 68-77页

作者： Shashika Lokuliyana A.G.A. Kalupahanage H.M.S.D. Herath Deemantha Siriwardana D.N. Bulathsinhala H.M.T.M. Herath Department of Computer System Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

The explosive growth of the Internet of Things (IoT) has had a substantial impact on daily life and businesses, allowing for real-time monitoring and decision-making. However, increased connectivity also brings higher security risks, such as botnet attacks and the need for stronger user authentication. This research explores how machine learning can enhance Internet of Things security by identifying abnormal activity, utilizing behavioral biometrics to secure cloud-based dashboards, and detecting botnet threats early. Researchers tested numerous machine learning methods, including K-Nearest Neighbors (KNN), Decision Trees, Logistic Regression, and XGBoost on publicly available datasets. The Decision Tree model earned an impressive accuracy rate of 0.73 for anomaly identification, proving its supremacy in dealing with complex security risks, while the XGBoost model demonstrated strong performance with a 92% accuracy rate for detecting TCP SYN flood attacks. Research findings show the effectiveness of these strategies in enhancing the security and reliability of IoT devices. This study provides significant insights into the use of machine learning to protect IoT devices while also addressing crucial concerns such as power consumption and privacy.

关键词： Internet of Things machine learning anomaly detection botnet detection behavioral biometrics IoT security

来源：评论

学校读者我要写书评

暂无评论

Analysis and Compensation of PM Manufacturing Tolerances on PMSMs Temperature Estimation During Six-Step Operation Using the D-Axis Current

Analysis and Compensation of PM Manufacturing Tolerances on ...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Orviz, Marcos Laborda, Diego F. Matsuura, Toru Lovison, Giorgio Sasaki, Kensuke Reigosa, David University of Oviedo Dept of Elect. Computer & System Engineering Gijón33204 Spain Nissan Motor Co. Ltd Ev System Laboratory Atsugi Kanagawa Japan

ISBN: (纸本)9798350316445

PM temperature monitoring is a key issue in permanent magnet synchronous machines (PMSMs), as it has a direct impact on the machine torque capability. Measured-stator-current-based PM temperature estimation method during six-step operation has been recently proposed. However, this method requires the use of look-up tables (LUTs), meaning that the estimation accuracy can be compromised by manufacturing tolerances of certain components, e.g., the permanent magnets (PMs). This paper will propose two methods to compensate for PM manufacturing tolerances effects on measured-stator-current-based PM temperature estimation methods. © 2023 IEEE.

关键词： manufacturing tolerances permanent magnet six-step temperature

来源：评论

学校读者我要写书评

暂无评论

Prediction of Post-COVID-19 Pandemic Learning Mode Preferences Using Machine Learning 14

Prediction of Post-COVID-19 Pandemic Learning Mode Preferenc...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Pratondo, Agus Novianty, Astri Putro, Budi Laksono Komala Sari, Siska Telkom University School of Applied Sciences Department of Multimedia Engineering Bandung Indonesia Telkom University School of Electrical Engineering Department of Computer Engineering Bandung Indonesia Indonesia University of Education Department of Computer Science Education Bandung Indonesia Telkom University School of Applied System Diploma Program of Information System Bandung Indonesia

ISBN: (纸本)9798350335095

The COVID-19 epidemic has had a huge impact on the educational landscape, prompting the adoption of online and remote learning as viable alternatives to conventional in-person instruction. In order to create effective educational methods as institutions prepare for the post-pandemic period, it is essential to understand students' preferences for various learning modes. With the aid of machine learning techniques, this study seeks to forecast preferences for learning styles in post-pandemic higher education. The study made use of a dataset compiled from a wide range of college students, which included information on the institution type (public or private), program type (bachelor's or diploma), academic discipline (science or humanities), gender, year of study, internet use, communication costs, comorbidity status, vaccination history, gadget and laptop ownership, and preferred learning mode (online, in-person, or both). For the aim of prediction, a Support Vector Machine (SVM) was used. Its kernel functions included linear, polynomial, radial basis function (RBF), and sigmoid. Performance criteria like accuracy, precision, recall, and F1 score were used to assess the models after the dataset was randomly partitioned into training and testing sets. The findings showed that for identifying the preferred mode of learning, SVM with the RBF kernel had the highest prediction accuracy (91.67%). Further proving the RBF kernel's efficacy, the confusion matrix analysis showed that high values in the diagonal represented accurate predictions for each of the three classes (both online and onsite). The results imply that machine learning approaches, in particular SVM with the RBF kernel, may accurately forecast students' preferences for learning modes in the post-pandemic situation. In a post-pandemic society, the findings provide insightful information that may be used to build adaptable and inclusive learning models and put them into practice. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Improving Facial Recognition Accuracy Using Local Binary Patterns 3

Improving Facial Recognition Accuracy Using Local Binary Pat...

引用

3rd IEEE Asian Conference on Innovation in Technology, ASIANCON 2023

作者： Bhargava, Prof Neeraj Rathore, Pramod Singh Saxena, Deepshikha Goswami, Ankur School of Engineering and System Sciences Mds University Ajmer India Manipal University Department of Computer and Communication Engineering Jaipur India Mds University Ajmer India Govt. Engineering College Department of Computer Applications Bikaner India

ISBN: (纸本)9798350302288

The proposed method involves pre-processing of the dataset, which includes normalization and resizing of the images to a standard size. Local binary pattern is then used to extract features from the pre-processed images. These features are used to train a machine learning model, specifically a support vector machine, to recognize faces in the images. The effectiveness of the proposed approach was evaluated using a publicly available dataset, and the results indicate a high level of accuracy in face detection, with a recognition rate of over 90%. The approach was also tested on images with varying contrast and rotation angles, and the results demonstrate its ability to accurately identify faces under such conditions. The proposed method has practical applications in various areas such as surveillance, access control, and forensics. It has the potential to be integrated into security systems for real-time face recognition and identification, improving the accuracy and efficiency of such systems. Furthermore, the method can be extended to include more complex features for more accurate and robust face detection. Overall, this research contributes to the growing body of knowledge on face detection techniques and their practical applications. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Single Shot Multibox Detector based Face Mask Detection 2

A Novel Single Shot Multibox Detector based Face Mask Detect...

引用

2nd International Conference on Augmented Intelligence and Sustainable systems, ICAISS 2023

作者： Bhargava, Neeraj Rathore, Pramod Singh Vaishnav, Parul Goswami, Ankur Mds University School of Engineering & System Sciences Ajmer India Manipal University Department of Computer and Communication Engineering Jaipur India Mds University Ajmer India Govt. Engineering College Department of Computer Applications Bikaner India

ISBN: (纸本)9798350325799

Face mask detection has gained significant importance in recent times due to the COVID-19 pandemic. This research work proposes a face mask detection method using the Single Shot MultiBox Detector (SSD) framework. The proposed method aims to accurately identify whether individuals are wearing masks or not in real-time scenarios. To begin with, a dataset comprising images of masked and unmasked faces is collected from kaggle and annotated with corresponding labels. The SSD model is then trained on this dataset, utilizing its ability to simultaneously perform object localization and classification. By leveraging the pre-trained weights and the architecture of SSD, the model is able to detect faces and classify them as either wearing masks or not. During the inference phase, the trained SSD model is applied to input images or video frames. The model analyzes the detected faces and assigns a label based on the presence or absence of masks. The output includes bounding box coordinates around the detected faces, along with the corresponding mask or non-mask label. Experimental evaluations are conducted on various real-world datasets to assess the performance of the proposed method. The results demonstrate the effectiveness and efficiency of the approach, achieving high accuracy in face mask detection. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Meteorology Predicting Technology Based on Artificial Intelligence Algorithms

Meteorology Predicting Technology Based on Artificial Intell...

引用

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent systems, ICETSIS 2024

作者： Abitova, Gulnara Mukashev, Daniyar Aitmukhanbetova, Elvira Rakhimzhanova, Mira Uskenbayeva, Gulzhan Kulniyazova, Korlan Binghamton University Dept Electrical Engineering and Computer Science Binghamton United States Astana It University Dept. of Computer Engineering Astana Kazakhstan L.N. Gumilyov Eurasian National University Dept. System Analysis and Management Astana Kazakhstan

ISBN: (纸本)9798350372229

The research explores the transformative impact of Artificial Intelligence in meteorology, weather forecasting. The study presented historical prediction methods overview, evolution highlighting from traditional models to advanced AI-driven systems. It delves into the integration of machine and deep learning techniques in data analysis, emphasizing technologies that significantly enhanced the accuracy and efficiency of weather predictions. Key aspects covered include the neural networks application in interpreting complex atmospheric data, the big data role in providing comprehensive training sets for AI models, the predictive analytics utilization for short-term and long-term weather forecasts. The study also examines case-study with AI implemented in weather forecasting, capability demonstrating in handling extreme weather events and climate anomalies. The study addresses the challenges and limitations faced in the meteorology AI integration, such as data quality concerns, computational requirements, and the specialized expertise need. It proposes potential solutions, future directions for research domain, suggesting a multidisciplinary approach involving meteorologists, data scientists, and AI experts. The conclusion underscores the revolutionary impact of AI-technology in meteorology, projecting how continuous advancements in AI-technology could redefine the predicting weather patterns approach. The work highlights the AI current state in weather forecasting but also sets the future innovations stage. © 2024 IEEE.

关键词： artificial intelligence data analysis machine learning neural networks predictive analytics weather Forecasting

来源：评论

学校读者我要写书评

暂无评论

Inspecting and Finding Faults in Railway Tracks using Wireless Sensor Networks 6

Inspecting and Finding Faults in Railway Tracks using Wirele...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Ahamad, Firoj Lobiyal, D.K. Degadwala, Sheshang Vyas, Dhairya School of Computer and System Sciences Jawaharlal Nehru University New Delhi India Computer Engineering Department Sigma Institute of Engineering Gujarat Vadodara India The Maharaja Sayajirao University of Baroda Gujarat Vadodara India

ISBN: (纸本)9798350398496

The railway sector is one that sees a significant number of incidents on a daily basis. The inspection of railway tracks for defects makes use of a diverse array of technological methods. The technology of wireless sensor networks is now employed in the railway sector to identify faults such as track cracks, track misalignment, and bridge cracks. Many different kinds of tests are carried out in order to identify problems with railway tracks. The sensors that make up a wireless sensor network get their power from very tiny batteries. Therefore, in order to connect with the base station, they were necessary to utilise a tiny amount of electricity. In the event that a sensor fails, critical data will be unable to reach the base station. Currently use the LEACH algorithm in order to save the sensor batteries and increase the lifespan of the wireless sensor network. After that, execute more algorithms that save energy, compare the outcomes, and choose the method that provides superior performance for wireless sensor networks. There are some parameters that need to be improved, such as the amount of time, the dead node, the energy of the sensor, and the position. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Two-Step Approach for Multi-topology Identification and Parameter Estimation of Power Distribution Networks

引用

CSEE Journal of Power and Energy systems 2024年第6期10卷 2446-2456页

作者： Li Ma Lei Wu Nian Liu Wei Pei Institute of Electrical Engineering and Key Laboratory of Long-Duration and Large-Scale Energy StorageChinese Academy of SciencesBeijing 100190China Department of Electrical and Computer Engineering Stevens Institute of TechnologyHobokenNJ 07030USA State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources North China Electric Power UniversityBeijing 102206China

To improve observability in power distribution networks(PDN),a two-step framework of multi-topology identification and parameter estimation is proposed in this ***,in the first step,a mixed-integer linear program(MILP)model-based split method is proposed to recognize mixed topologies in a multi-record dataset without a prerequisite on the number of topology categories and values of nodal voltage phase *** the second step,line parameters and nodal voltage phase angles are estimated using the Newton-Raphson method based on nodal measurements of real and reactive power injections,as well as voltage ***,a modified estimation model is proposed to apply to the multitopology ***,case studies on an IEEE 33-bus system illustrate the effectiveness of the proposed models in identifying the PDN’s topologies,as well as estimating line parameters and voltage phase angles.

关键词： MILP Newton-Raphson method parameter estimation power distribution system topology identification

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：