检索结果-内蒙古大学图书馆

51st International Conference on Computers and Industrial engineering, CIE 2024

作者： Chen, Wei Fu, Yelin Zhong, Ray Y. Li, Ming Huang, George Q. Department of Data and Systems Engineering The University of Hong Kong Hong Kong College of Economics Shenzhen University Shenzhen China Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong

Both academia and industry have expressed significant interest in Environment, Social, and Governance (ESG) disclosure to advance sustainable development and investment. However, the issue of data authenticity in ESG disclosures remains a pressing and unresolved challenge. This study introduces an innovative approach to address the issue. Initially, the researchers propose an inventive ESG reporting system (BI-ESG) that leverages both blockchain and IoT. The system smoothly combines IoT and blockchain technologies, streamlining automated data collection and transmission in the ESG disclosure process while ensuring data authenticity, consistency, and transparency. Secondly, within BI-ESG, the data authenticity analytics is conducted based on the federated semi-supervised learning (FSSL) method. The analytics consists of gateway level and cloud level based on the TensorFlow Federated. Specifically, a portion of the dataset from the system is labeled with an authenticity index following spatial-temporal analytics, and a neural network model for data authenticity analytics is built using Keras. The model is trained in a federated manner, utilizing labeled data in the central server and unlabeled data in the clients. In addition, the discussion analyses the benefits and possible challenges of adopting the proposed solution in ESG disclosure. This research is expected to benefit both industry and academia by facilitating the application of the solution in comparable situations and sparking innovative concepts. © 2024 Computers and Industrial engineering. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Weld Quality Prediction

引用

Journal of Dynamics, Monitoring and Diagnostics 2024年第4期3卷 237-245页

作者： Shubhranil Chakraborty Sayani Guha Debasish Mishra Surjya K.Pal Department of Electronics and Communication Engineering Jalpaiguri Government Engineering CollegeIndia Data Science and Information Systems IFMR GSBKrea UniversityIndia Department of Mechanical Engineering Indian Institute of Technology KharagpurIndia

This study introduces a monitoring system that can accurately predict the quality of friction stir *** study involved four different sets of welding experiments using varying materials and tool *** goal was to create a universal monitoring system capable of predicting weld quality across these diverse experimental ***-time welding data was collected using instruments such as load cells and a power *** processing methods were then used to analyze this data and extract essential information about welding ***,federated learning(FL)was used to develop the universal monitoring *** method involves collective learning and model training,leading to a global model trained on decentralized data from the different experimental *** approach proved to be effective in forecasting weld quality,achieving a mean absolute error(MAE)of 10.44 for all welding ***,it offered benefits such as reduced latency and enhanced user data protection,while maintaining the accuracy of the global *** artificial neural network model was also developed for comparison with FL,achieving a MAE of 13.85 for the welding ***,this study demonstrates the effectiveness of training global and more reliable models,with multiple devices sharing their knowledge bases to train the global model effectively.

关键词： deep learning federated learning friction stir welding Industry 4.0 manufacturing neural network quality

来源：评论

学校读者我要写书评

暂无评论

Informative Path Planning for Nano-Surgical Robot Adaptive Drug Delivery 59

Informative Path Planning for Nano-Surgical Robot Adaptive D...

引用

59th Annual Conference on Information Sciences and systems, CISS 2025

作者： Alla, Sujatha Bheesetty, Nagesh Park, Hyoshin John Old Dominion University Engineering Management and Systems Engineering Norfolk United States Old Dominion University Department of Data Science Norfolk United States

ISBN: (纸本)9798331513269

Nano-surgical robots are transforming precision medicine by enabling minimally invasive procedures at a microscopic scale. Informative path planning for these robots is critical for ensuring safety, efficiency, and high precision in navigating sensitive anatomical and uncertain environments. This study adapts the RRT*-IT (Rapidly Exploring Random Tree-Information Theoretic) algorithm, traditionally utilized in robotics, to address the unique challenges faced by nano-surgical robots. The proposed methodology offers significant advancements in sub-millimeter precision navigation, reducing collision risks and enhancing procedural efficiency. The adaptive path planning system optimizes a trade-off between collision avoidance and information gain while minimizing surgical trajectory. The algorithm dynamically adjusts paths by incorporating probabilistic models for obstacle detection and uncertainty reduction, accommodating changes in tissue density, obstacle dimensions, and operational constraints. The performance of proposed approach are validated through various scenarios involving dynamic uncertain environments. The findings hold promise for broader applications in automated drug delivery setting a foundation for intelligent nano-robotic systems in healthcare. © 2025 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

A Novel Eccentric Intrusion Detection Model Based on Recurrent Neural Networks with Leveraging LSTM

引用

Computers, Materials & Continua 2024年第3期78卷 3089-3127页

作者： Navaneetha Krishnan Muthunambu Senthil Prabakaran Balasubramanian Prabhu Kavin Kishore Senthil Siruvangur Kavitha Chinnadurai Jehad Ali Department of Computer Applications Karpagam College of EngineeringCoimbatore641032India Department of Computer Science and Engineering Karpagam College of EngineeringCoimbatore641032India Department of Data Science and Business Systems College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyJeppiaar NagarRajiv Gandhi SalaiChennai600119India Department of AI Convergence Network Ajou UniversitySuwon16499Korea

The extensive utilization of the Internet in everyday life can be attributed to the substantial accessibility of online services and the growing significance of the data transmitted via the ***,this development has expanded the potential targets that hackers might *** adequate safeguards,data transmitted on the internet is significantly more susceptible to unauthorized access,theft,or *** identification of unauthorised access attempts is a critical component of cybersecurity as it aids in the detection and prevention of malicious *** research paper introduces a novel intrusion detection framework that utilizes Recurrent Neural Networks(RNN)integrated with Long Short-Term Memory(LSTM)*** proposed model can identify various types of cyberattacks,including conventional and distinctive *** networks,a specific kind of feedforward neural networks,possess an intrinsic memory *** Neural Networks(RNNs)incorporating Long Short-Term Memory(LSTM)mechanisms have demonstrated greater capabilities in retaining and utilizing data dependencies over extended *** such as data types,training duration,accuracy,number of false positives,and number of false negatives are among the parameters employed to assess the effectiveness of these models in identifying both common and unusual *** are utilised in conjunction with LSTM to support human analysts in identifying possible intrusion events,hence enhancing their decision-making capabilities.A potential solution to address the limitations of Shallow learning is the introduction of the Eccentric Intrusion Detection *** model utilises Recurrent Neural Networks,specifically exploiting LSTM *** proposed model achieves detection accuracy(99.5%),generalisation(99%),and false-positive rate(0.72%),the parameters findings reveal that it is superior to state-of-the-art techniques.

关键词： Cybersecurity intrusion detection machine learning leveraging long short-term memory(LLSTM) CICIDS2019 dataset innovative cyberattacks

来源：评论

学校读者我要写书评

暂无评论

Solving Unequal Area Facility Layout Problems with Differential Evolution and Particle Swarm Optimization 7

Solving Unequal Area Facility Layout Problems with Different...

引用

7th Information systems International Conference, ISICO 2023

作者： Muhayat, Hanifan Utamima, Amalia Laboratory of Data Engineering and Business Intelligence Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia

The unequal area facility layout problem (UAFLP) is a problem in industrial engineering that aims to minimize material handling costs between a group of unequal-shaped facilities. In this study, Differential Evolution (DE) with continuous variables and Particle Swarm Optimization (PSO) are employed to solve the UAFLP. This study also compares the performance of the DE method (never used to solve UAFLP) and the PSO method (frequently used to solve facility layout problems). The experimental results demonstrate that PSO is effective in solving small-sized datasets, while DE works well in solving datasets with larger areas. © 2023 The Authors. Published by Elsevier B.V.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

PDNet: A Novel Approach to Plant Disease Detection using CNN and Keras 6

PDNet: A Novel Approach to Plant Disease Detection using CNN...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Jain, Garima Shukla, Amita Chaudhary, Anamika Sharma, Nidhi Bisht, Sovers Singh Jain, Ankush Department of Computer Science and Buisness Systems Noida Institute of Engineering and Technology Greater Noida India Department of Data Science Noida Institute of Engineering and Technology Greater Noida India Department of Data Science Noida Institute of Engineering and Technology Delhi India Department of Computer Science and Engineering Netaji Subhas University of Technology Delhi India

ISBN: (纸本)9798331522667

This research addresses the pressing global demand for food by leveraging cutting-edge deep learning techniques for automating plant disease detection. Focusing on tomato and potato leaf diseases, the study utilized the PlantVillage dataset to compare classical machine learning methods, such as Local Binary Patterns (LBP) combined with classifiers like kNN, SVM, and Extreme Learning Machines, against modern Convolutional Neural Network (CNN) architectures. These included MobileNet, DenseNet201, ResNet50, Inception V3, and VGG16/19. A custom-designed CNN model was developed with unique configurations implemented using Keras and TensorFlow. The model was tested for binary, 6-class, and 10-class classifications, achieving remarkable accuracy rates of 99.6%, 98.4%, and 97.2%, respectively. Notably, after 50 training epochs, the model achieved a peak accuracy of 99.78% for plant disease classification. A practical web-based application was also developed, integrating the best-performing model to facilitate real-time leaf disease detection and notify farmers via email. This approach demonstrates a significant advancement in sustainable agriculture by providing an efficient, accurate, and scalable solution for early disease detection, which is critical for improving crop yield and productivity. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Solving Preemptive Single Machine Scheduling with Lovebird Algorithm and Constructive Heuristics for Equal-Length Jobs 7

Solving Preemptive Single Machine Scheduling with Lovebird A...

引用

7th Information systems International Conference, ISICO 2023

作者： Fernanda, Nita Utamima, Amalia Laboratory of Data Engineering and Business Intelligence Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia

Scheduling is essential in manufacturing to maintain machinery and increase revenue. Machines that are routinely maintained will boost production, whereas scheduling based on total weighted completion time (TWCT) can improve the performance of production equipment. The Lovebird Algorithm (LBA), Constructive Heuristics (CH), and combination of LBA-CH are used in this study to schedule a single machine with equal processing times. LBA, a population-based algorithm, represents job parts as birds for jobs that can be preempted. The experiments, which used ten jobs divided into dozens of job parts, show that LBA-CH can effectively reduce TWCT compared to CH by 18.16%. © 2023 The Authors. Published by Elsevier B.V.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Ruppert's Delaunay Triangulation Refinement Scheme for Optimal RSUs Placement in Vehicle to Infrastructure Communication Network

引用

China Communications 2023年第7期20卷 303-320页

作者： Selvakumari P Chinnasamy A Sree Rathna Lakshmi NVS Sheela D Department of Computer Science and Engineering Tagore Engineering CollegeChennai 600048India Department of Data Science and Business Systems School of ComputingSRMIST kattankulathur CampusChennai 603203India Department of Electronics and Communication Engineering Department of ECE at Agni College of TechnologyChennai 603103India Department of Electronics and Communication Engineering Saveetha School of Engineering SIMATSChennai 600124India

Road Side Units(RSUs)are the essential component of vehicular communication for the objective of improving safety and mobility in the road *** are generally deployed at the roadside and more specifically at the intersections in order to collect traffic information from the vehicles and disseminate alarms and messages in emergency situations to the neighborhood vehicles cooperating with the ***,the development of a predominant RSUs placement algorithm for ensuring competent communication in VANETs is a challenging issue due to the hindrance of obstacles like water bodies,trees and *** this paper,Ruppert’s Delaunay Triangulation Refinement Scheme(RDTRS)for optimal RSUs placement is proposed for accurately estimating the optimal number of RSUs that has the possibility of enhancing the area of coverage during data *** RDTRS is proposed by considering the maximum number of factors such as global coverage,intersection popularity,vehicle density and obstacles present in the map for optimal RSUs placement,which is considered as the core improvement over the existing RSUs optimal placement *** is contributed for deploying requisite RSUs with essential transmission range for maximal coverage in the convex map such that each position of the map could be effectively covered by at least one RSU in the presence of *** simulation experiments of the proposed RDTRS are conducted with complex road traffic *** results of this proposed RDTRS confirmed its predominance in reducing the end-to-end delay by 21.32%,packet loss by 9.38%with improved packet delivery rate of 10.68%,compared to the benchmarked schemes.

关键词： road side units(RSUs) ruppert’s delau-nay triangulation refinement area of global coverage optimal RSUs placement

来源：评论

学校读者我要写书评

暂无评论

Practical tracking of MIMO uncertain stochastic systems driven by colored noises via active disturbance rejection control

引用

Science China(Information Sciences) 2022年第6期65卷 203-217页

作者： Chunwan LV Zhengyong OUYANG Zehao WU Feiqi DENG Mingqing XIAO School of Mathematics and Big Data Foshan University Systems Engineering Institute South China University of Technology Department of Mathematics Southern Illinois University

This study addresses the practical tracking problem for a class of multi-input multi-output(MIMO) uncertain stochastic systems driven by colored noises via the active disturbance rejection control approach. The extended state observer is designed to estimate in real time the unmeasurable states and the stochastic total disturbance of each subsystem, including unknown coupling system dynamics between subsystems, colored noises, and uncertainty caused by partly unknown control parameters. Active disturbance rejection controllers based on the timely estimation of the extended state observer and compensation are then designed, guaranteeing the mean square practical convergence of the tracking errors. Some numerical simulations are performed to validate the effectiveness of the proposed control strategy.

关键词： uncertain stochastic systems active disturbance rejection control extended state observer tracking colored noise

来源：评论

学校读者我要写书评

暂无评论

The Inhibition Activity of Fatty Imidazoline Acetate Derived from Waste Cooking Oil on the AISI 1018 Mild Steel Corrosion

引用

Journal of Bio- and Tribo-Corrosion 2025年第1期11卷 1-11页

作者： Cholidah, Tsana Kusumasari, Lutfiah Lila Febriyanti, Tria Firdaus, Achmad Fadjar Maulana Fuadi, Raihana Putri Nariswari Madurani, Kartika A. Chemistry Department Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Sukolilo East Java Surabaya60111 Indonesia Department of Materials and Metallurgical Engineering Faculty of Industrial Technology and Systems Engineering Institut Teknologi Sepuluh Nopember Sukolilo East Java Surabaya60111 Indonesia

Imidazoline and its derivatives have been proposed as effective organic corrosion inhibitors for AISI 1018 mild steel, though challenges remain regarding their production processes and efficiency in CO2/H2S-saturated brine solutions. In this study, fatty imidazoline acetate (FIA) was synthesized from waste cooking oil and evaluated for its ability to protect AISI 1018 steel in corrosive environments. The chemical composition of the synthesized FIA was confirmed through gas chromatography-mass spectroscopy (GC–MS) and Fourier transform infrared (FTIR) spectroscopy. Corrosion inhibition performance was assessed using potentiodynamic polarization at room temperature, with the most promising results further examined via weight loss measurements and contact angle analyses. A commercial inhibitor commonly used in pipelines with CO2/H2S-saturated brine was also evaluated for comparison. Surface characterization of the steel samples, both with and without inhibitors, was conducted using scanning electron microscopy (SEM). The FIA demonstrated an inhibition efficiency (IE%) of 99.89% at a concentration of 40 mg/L, closely matching the performance of the commercial inhibitor (IE% = 99.96%). This study underscores the potential of FIA as a sustainable and effective corrosion inhibitor in CO2/H2S-saturated environments. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Gas chromatography

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：