检索结果-内蒙古大学图书馆

A Comparative Study of Optimized-LSTM Models Using Tree-Structured Parzen Estimator for Traffic Flow Forecasting in Intelligent Transportation

引用

Computers, Materials & Continua 2025年第5期83卷 3369-3388页

作者： Hamza Murad Khan Anwar Khan Santos Gracia Villar Luis Alonso DzulLopez Abdulaziz Almaleh Abdullah M.Al-Qahtani Department of Electronics University of PeshawarPeshawar25120KPKPakistan Department of Project Management(L.A.D.L) Higher Polytechnic School(S.G.V)Universidad Europea del AtlanticoSantander39011Spain Faculty of Engineering Universidad Internacional IberoamericanaCampeche24560Mexico Faculty of Engineering Universidade Internacional do CuanzaCuitoEN250BieAngola Department of Project Management Universidad Internacional IberoamericanaCampeche24560Mexico Department of Project Management Department of Management SciencesUniversid de La RomanaLa Romana22000Dominican Reublic Information Systems Department College of Computer ScienceKing Khalid UniversityAbha61421Saudi Arabia Department of Electrical and Electronic Engineering College of Engineering&Computer ScienceJazan UniversityJazan45142Saudi Arabia

Traffic forecasting with high precision aids Intelligent Transport systems(ITS)in formulating and optimizing traffic management *** algorithms used for tuning the hyperparameters of the deep learning models often have accurate results at the expense of high computational *** address this problem,this paper uses the Tree-structured Parzen Estimator(TPE)to tune the hyperparameters of the Long Short-term Memory(LSTM)deep learning *** Tree-structured Parzen Estimator(TPE)uses a probabilistic approach with an adaptive searching mechanism by classifying the objective function values into good and bad *** ensures fast convergence in tuning the hyperparameter values in the deep learning model for performing prediction while still maintaining a certain degree of *** also overcomes the problem of converging to local optima and avoids timeconsuming random search and,therefore,avoids high computational complexity in prediction *** proposed scheme first performs data smoothing and normalization on the input data,which is then fed to the input of the TPE for tuning the *** traffic data is then input to the LSTM model with tuned parameters to perform the traffic *** three optimizers:Adaptive Moment Estimation(Adam),Root Mean Square Propagation(RMSProp),and Stochastic Gradient Descend with Momentum(SGDM)are also evaluated for accuracy prediction and the best optimizer is then chosen for final traffic prediction in TPE-LSTM *** results verify the effectiveness of the proposed model in terms of accuracy of prediction over the benchmark schemes.

关键词： Short-term traffic prediction sequential time series prediction TPE tree-structured parzen estimator LSTM hyperparameter tuning hybrid prediction model

来源：评论

学校读者我要写书评

暂无评论

Designing a cellular manufacturing system as a step toward creating sustainable cells under uncertain demand condition

引用

Journal of Remanufacturing 2025年第1期15卷 151-177页

作者： Almasarwah, Najat Abdelall, Esraa Bhutta, Mohammed Khurrum S. Saraireh, Mohammad Department of Industrial Systems Engineering Mutah University Alkarak 61710 Jordan Industrial Engineering Department Jordan University of Science and Technology P.O. Box 3030 Irbid 22110 Jordan Department of Management College of Business Ohio University Athens 45701 OH United States Department of Computer Engineering Mutah University Alkarak 61710 Jordan

This paper focuses on designing a cellular manufacturing system as a step toward creating sustainable cells. The proposed design aims to manufacture final products and remanufacture the returned products to diminish waste, where the return rate for each product is known. Firstly, the product families are formed using the uncapacitated mathematical model. Secondly, a nonlinear stochastic mathematical model is utilized for the propounded design as a step toward creating sustainable cells, where machine duplications are allowed. Besides, a simulation model is developed to handle the uncertainty in demand. Further, the performance of the proposed design with flexible cells is compared to regular cells. The results explain the ability of the proposed design to minimize the total number of machines. Furthermore, allowing machine duplication in the proposed design enhances the system flexibility;thus, machine breakdown will not impact system performance. The total number of machines required to cover the demand increases as the risk level of demand cover decreases. Therefore, the average waiting time and average work in process increase. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Designing a cellular manufacturing system as a step toward creating sustainable cells Flexible cells Nonlinear mathematical model Simulation Stochastic demand

来源：评论

学校读者我要写书评

暂无评论

Industry 5.0 in Healthcare: An Integrated Framework for Human-Centered Prosthetics Design and Manufacturing

引用

Procedia Computer Science 2025年 253卷 3288-3297页

作者： Giuseppina Ambrogio Carmine Borgia Marco Bortolini Gerardo Catapano Domenico Conforti Luigi De Napoli Francesco Gagliardi Francesco Gabriele Galizia Rosita Guido Francesco Longo Federica Mirabelli Giovanni Mirabelli Domenico Mundo Alberto Regattieri Maria Rosaria Saffioti Gabriele Scordamaglia Vittorio Solina Domenico Umbrello Pierpaolo Veltri University of Calabria Department of Mechanical Engineering Energy Engineering and Management Engineering Italy University of Bologna Department of Industrial Engineering Italy University of Calabria Department of Computer Engineering Modeling Electronics and Systems Engineering Italy

Industry 5.0 emphasizes human-centric approaches in technological advancement, particularly crucial in healthcare applications such as prosthetics development. While individual technologies like additive manufacturing, machine learning, digital twins, and tissue engineering have shown promise in prosthetics innovation, their integration remains a significant challenge. This paper presents a novel multidisciplinary framework developed through the National Centre for High-Performance Computing (CN-HPC) project, which addresses the gap between individual technological capabilities and their coordinated application in personalized prosthetics development. The framework, implemented through collaboration between six research groups from two universities, employs the House of Quality methodology to align technological integration with patient needs. Our approach encompasses a comprehensive seven-step process, from initial patient requirements definition through virtual modeling, production process optimization, virtual sensing, machine learning enhancement, digital twin simulation, to advanced tissue engineering. A data model facilitates seamless information exchange between different technological domains and research groups. This research contributes to the field by providing a scalable, human-centered framework for technology integration in medical device development, potentially extending beyond prosthetics to other healthcare applications. The proposed framework represents a significant step toward realizing the full potential of Industry 5.0 in healthcare manufacturing through the systematic integration of advanced technologies for delivering personalized prosthetic solutions.

关键词： Industry 5.0 Human-Centricity Prosthesis Healthcare House of Quality

来源：评论

学校读者我要写书评

暂无评论

Mining Quantitative Association Rules 17th

Mining Quantitative Association Rules

引用

17th International Conference on Multi-disciplinary Trends in Artificial Intelligence, MIWAI 2024

作者： Yen, Show-Jane Lee, Yue-Shi Lee, Wen-Hao Department of Computer Science and Information Engineering Ming Chuan University Taipei Taiwan Department of Management Information Systems National Chiayi University Chiayi City Taiwan

ISBN: (纸本)9789819606948

Mining quantitative association rules involves identifying the relationships between items based on their purchased quantities from a transaction database. In general, items with varying quantities are treated as distinct new items, making it challenging to meet the criteria for these new items. Previous methods have often relaxed these criteria to uncover quantitative association rules;however, excessive relaxation can lead to the discovery of many irrelevant rules, while insufficient relaxation may result in few or no rules being found. Additionally, the quantity ranges associated with items can be divided into intervals, and some of these intervals need to be combined, potentially leading to information loss during the process. In this article, we present new definitions and an approach for discovering quantitative association rules that address the issues of user-defined criteria, range segmentation, and interval integration, allowing us to identify the quantitative association rules that genuinely interest users. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Design of Navigation Satellite Constellation for Global Lunar PNT

Design of Navigation Satellite Constellation for Global Luna...

引用

2025 International Technical Meeting of The Institute of Navigation, ITM 2025

作者： Kang, Minjae Jeong, Hojoon Park, Jaeuk Kee, Changdon Interdisciplinary Program in Space Systems Seoul National University Korea Republic of Department of Aerospace Engineering and SNU-IAMD Seoul National University Korea Republic of

ISBN: (纸本)9780936406404

This study presents the design of a lunar navigation satellite constellation to provide global Positioning, Navigation, and Timing (PNT) services, beginning with coverage at the lunar South Pole and gradually expanding to the entire Moon. Building upon an initial Phase 1 constellation that ensures reliable PNT at the South Pole, Phase 2 extends this coverage globally, addressing the challenges of providing continuous navigation services across the lunar surface. The proposed Hybrid Frozen Constellation combines Elliptical Lunar Frozen Orbits (ELFOs) and Circular Frozen Orbits to offer a cost-effective and efficient solution, leveraging the stable South Pole-oriented orbits while minimizing the number of satellites required. The study explores various satellite configurations to achieve best Position Dilution of Precision (PDOP) across the entire lunar surface. By carefully analyzing the geometry and phasing of the orbits, the design aims to maximize navigation performance while reducing the satellite volume. Simulation results confirm that the full constellation achieves over 98% PDOP availability, ensuring PDOP values remain below 6, meeting the GPS standards for reliable navigation. This performance guarantees accurate positioning, even in challenging regions of the lunar surface, and supports both robotic and crewed exploration missions. © 2025 Proceedings of the International Technical Meeting of The Institute of Navigation, ITM. All rights reserved.

关键词： Lunar missions

来源：评论

学校读者我要写书评

暂无评论

Single-Loop Variance-Reduced Stochastic Algorithm for Nonconvex-Concave Minimax Optimization

Single-Loop Variance-Reduced Stochastic Algorithm for Noncon...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xia Jiang Linglingzhi Zhu Taoli Zheng Anthony Man-Cho So Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Nonconvex-concave (NC-C) finite-sum minimax problems have broad applications in decentralized optimization and various machine learning tasks. However, the nonsmooth nature of NC-C problems makes it challenging to design effective variance reduction techniques. Existing vanilla stochastic algorithms using uniform samples for gradient estimation often exhibit slow convergence rates and require bounded variance assumptions. In this paper, we develop a novel probabilistic variance reduction updating scheme and propose a single-loop algorithm called the probabilistic variance-reduced smoothed gradient descent-ascent (PVR-SGDA) algorithm. The proposed algorithm achieves an iteration complexity of ${\mathcal{O}}\left({{\varepsilon ^{ - 4}}}\right)$, surpassing the best-known rates of stochastic algorithms for NC-C minimax problems and matching the performance of the best deterministic algorithms in this context. Finally, we demonstrate the effectiveness of the proposed algorithm through numerical simulations.

关键词： Smoothing methods Machine learning algorithms Signal processing algorithms Signal processing Probabilistic logic Numerical simulation Complexity theory Speech processing Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Digitalization trends and industry 4.0: ensuring knowledge workers’ sustainable productivity and innovative capability

引用

Flexible Services and Manufacturing Journal 2025年 1-31页

作者： Sumbal, Muhammad Saleem Amber, Quratulain Hashmi, Fakhar Abbas Chan, Felix T. S. Tariq, Adeel Nauman, Shazia Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong School of Management and Economics University of Kurdistan Hewler Erbil Iraq Sarhad University of Technology and Pakistan Bureau of Statistics Islamabad Pakistan Department of Decision Sciences School of Business Macau University of Science and Technology Taipa China Industrial Engineering and Management Department LUT University Kouvola45100 Finland Riphah International University Lahore Pakistan

Organizations are struggling to ensure knowledge workers’ productivity and innovative capabilities to adopt rapidly changing technologies. This study investigates this under-explored topic of impediments for knowledge workers’ sustainable productivity and innovative capabilities for digitalization and adoption of Industry 4.0 and 5.0 using multi-level and multi-dimensional research approach. Using in-depth structured literature review and refined through expert evaluation, a list of impediments was developed which was further categorized at multiple levels along with cross country comparative analyses using survey data collected from IT professionals from six countries. Analytical Hierarchal Process approach is used to prioritize impediments at four levels of impediment ranking, factors ranking, categories ranking and global ranking along with country-wise analysis to explore IT professionals’ preference. Findings suggest focus areas in three dimensions - organizational, technological, and personal along with three factors of each using relative rankings based on local and global weights. The study has significant theoretical and practical implications in relation to digitalization, knowledge workers and adoption of industry 4.0 and 5.0. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Digitalization Industry 4.0 and 5.0 Innovation Knowledge workers Productivity Sustainability

来源：评论

学校读者我要写书评

暂无评论

Assessing Mobile Nuclear Reactor Usage in the Pacific

引用

Military Engineer 2025年第756期117卷 56-58页

作者： Hurtado, Maria Mbonimpa, Eric Slagley, Jeremy Skipper, Julie Harper, Willie Department of Systems Engineering & Management Air Force Institute of Technology United States Department of Systems Engineering & Management Air Force Institute of Technology United States Department of Systems Engineering & Management Air Force Institute of Technology United States Department of Systems Engineering & Management Air Force Institute of Technology United States Department of Engineering Physics Air Force Institute of Technology Nuclear Expertise for Advancing Technologies Center United States

来源：评论

学校读者我要写书评

暂无评论

Research on Enterprise Risk Decision Support System Optimization based on Ensemble Machine Learning 24

Research on Enterprise Risk Decision Support System Optimiza...

引用

5th International Conference on Computer Science and management Technology, ICCSMT 2024

作者： Gong, Chenwei Lin, Yuzhen Cao, Jinming Wang, Jun Henry Samueli School of Engineering Department of Computer University of California Los Angeles United States School of Information Systems and Management Carnegie Mellon University Jersey City United States Department of Electrical Computer and Systems Engineering Case Western Reserve University Cleveland United States School of Economics and Management Wuhan University Hubei Wuhan China

ISBN: (纸本)9798400709999

Since the advent of artificial intelligence, it has not only transformed the way we live, but is also accelerating the transformation of production methods. Machine learning is a pivotal technology that endows computers with intelligence. The primary driving force behind its advancement is the pursuit of rapid and precise knowledge acquisition. Nevertheless, the existing enterprise risk decision support system is inadequate in terms of both timeliness and effectiveness when confronted with the task of analysing vast quantities of data. Furthermore, it lacks the capacity to assimilate the expertise of managers and to facilitate interaction in an intuitive manner. By combining a variety of machine learning models, the ensemble learning method effectively leverages the advantages of different algorithms, thereby improving the accuracy and stability of risk prediction. Each model provides a unique perspective and decision-making boundaries when dealing with complex enterprise risk data, but a single model may not be adequate when faced with a particular data set or a particular type of risk. The ensemble method overcomes the problem of bias or overfitting that may be caused by a single model by combining the prediction results of multiple models, so as to obtain a more robust prediction effect. These methods optimize the final prediction results based on how well they perform during training by giving different weights to each model. This convergence strategy significantly improves the accuracy of enterprise risk assessment and helps to provide decision-makers with more reliable data support to make more informed risk management decisions in complex business environments. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation

引用

ACM Transactions on Privacy and Security 2025年第2期28卷 1-33页

作者： Hore, Soumyadeep Ghadermazi, Jalal Paudel, Diwas Shah, Ankit Das, Tapas Bastian, Nathaniel Department of Industrial and Management Systems Engineering University of South Florida Tampa United States Department of Operations and Decision Technologies Indiana University Bloomington United States Army Cyber Institute United States Military Academy West Point United States

Recent advancements in artificial intelligence (AI) and machine learning (ML) algorithms, coupled with the availability of faster computing infrastructure, have enhanced the security posture of cybersecurity operations centers (defenders) through the development of ML-aided network intrusion detection systems (NIDS). Concurrently, the abilities of adversaries to evade security have also increased with the support of AI/ML models. Therefore, defenders need to proactively prepare for evasion attacks that exploit the detection mechanisms of NIDS. Recent studies have found that the perturbation of flow-based and packet-based features can deceive ML models, but these approaches have limitations. Perturbations made to the flow-based features are difficult to reverse-engineer, while samples generated with perturbations to the packet-based features are not *** methodological framework, Deep PackGen, employs deep reinforcement learning to generate adversarial packets and aims to overcome the limitations of approaches in the literature. By taking raw malicious network packets as inputs and systematically making perturbations on them, Deep PackGen camouflages them as benign packets while still maintaining their functionality. In our experiments, using publicly available data, Deep PackGen achieved an average adversarial success rate of 66.4% against various ML models and across different attack types. Our investigation also revealed that more than 45% of the successful adversarial samples were out-of-distribution packets that evaded the decision boundaries of the classifiers. The knowledge gained from our study on the adversary's ability to make specific evasive perturbations to different types of malicious packets can help defenders enhance the robustness of their NIDS against evolving adversarial attacks. © 2025 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

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：