检索结果-内蒙古大学图书馆

data-Driven Design of Thermoplastic Composites with Tailored Compliance

Journal of engineering Mechanics 2025年第7期151卷

作者： Upadhyay, Nilay Zawaski, Callie Peco, Christian Reinhart, Wesley F. Dept. of Engineering Science and Mechanics Pennsylvania State Univ. University ParkPA16802 United States Applied Research Laboratory Pennsylvania State Univ. University ParkPA16802 United States Institute for Computational and Data Sciences Pennsylvania State Univ. University ParkPA16802 United States Dept. of Materials Science and Engineering Pennsylvania State Univ. University ParkPA16802 United States Faculty Co-Hire Institute for Computational and Data Sciences Pennsylvania State Univ. University ParkPA16802 United States

Continued advances in manufacturing processes have rapidly increased the complexity of composite parts that can be manufactured, consequently increasing the number of variables that must be considered during design. Traditional computational methods struggle with time efficiency and complex relations in large design spaces, especially for composite materials with intricate, multivariate, and nonlinear process-structure-property connections. Among computational tools, machine learning methods excel at interpreting complex relationships and efficiently generating designs for target properties. In this study, we systematically built and deployed machine learning models to explore the design space of a layered composite material. We modeled two grades of thermoplastics and generated a data set of the compliance of different layered composite geometries using finite-element simulations. A random forest model utilizing a token-counting featurization scheme was selected based on its exceptional performance. It was used to perform a detailed feature importance analysis and then a series of design tasks. We show that this method can reliably obtain single-objective and multiobjective designs. This work demonstrates the feasibility of a simple data-driven approach to designing composite parts with many design variables and highly nonlinear mechanical behavior. © 2025 American Society of Civil Engineers.

关键词： Structural properties

来源：评论

学校读者我要写书评

暂无评论

Blockchain Integration for Robust Intellectual Property Protection in New Product Development (NPD)

Blockchain Integration for Robust Intellectual Property Prot...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： P. Chinnasamy Subashini. B Nijanthan Nijanthan Madasamy Raja. G Devulapally Swetha Sreenivasulu Reddy L Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India Department of Data Science and Business Systems School of Computing SRMIST India Computer Science and Engineering Paavai Engineering College Namakkal Tamilnadu India Information Technology Paavai Engineering College Namakkal Tamilnadu India Dept. of Computer Science and Engineering Vaagdevi Engineering College Telangana India Department of Mathematics School of Advanced Sciences Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

The rapid advancement of Blockchain technology has led to its widespread application in several domains of digital activities, such as e-government concerns and monetary security. This article presents a smart contract-based Blockchain solution for protecting intellectual property rights in new product development. The proposed solution effectively tackles the challenges associated with the confidentiality of personally identifiable information, efficiency in storing transaction-related information, as well as cooperation and monitoring in IPR. Initially, we create a mathematical model based on smart contract enabled Blockchain and intelligent contracts. Subsequently, we develop algorithms for Blockchain generation, and intelligent contracts. The system is suitable for protecting IPR in a blockchain network, by implementation of distributed identity authentication and real-time extensible storage. These features enhance the security and expandability of circuit copyright protection based on blockchain technology. The experimental results demonstrate that the suggested algorithm has decreased the cost for communication and enhanced the effectiveness of storing information and administration. Furthermore, it demonstrates resilience against many common attacks such as double-spending assaults, while maintaining low cost and overhead. Additionally, it exhibits a superior level of security in comparison to three other competing algorithms.

关键词： Patents Technological innovation Costs Smart contracts Intellectual property Product development Blockchains Security Protection Resilience

来源：评论

学校读者我要写书评

暂无评论

UDC-VIT: A REAL-WORLD VIDEO dataSET FOR UNDER-DISPLAY CAMERAS

arXiv

引用

arXiv 2025年

作者： Ahn, Kyusu Kim, JiSoo Lee, Sangik Lee, HyunGyu Ko, Byeonghyun Park, Chanwoo Lee, Jaejin Dept. of Data Science Seoul National University Seoul Korea Republic of Dept. of Computer Science and Engineering Seoul National University Seoul Korea Republic of Research Center Samsung Display Co. Ltd. Yongin Korea Republic of Mobile Display Electronics Development Team Samsung Display Co. Ltd. Yongin Korea Republic of

Under Display Camera (UDC) is an advanced imaging system that places a digital camera lens underneath a display panel, effectively concealing the camera. However, the display panel significantly degrades captured images or videos, introducing low transmittance, blur, noise, and flare issues. Tackling such issues is challenging because of the complex degradation of UDCs, including diverse flare patterns. Despite extensive research on UDC images and their restoration models, studies on videos have yet to be significantly explored. While two UDC video datasets exist, they primarily focus on unrealistic or synthetic UDC degradation rather than real-world UDC degradation. In this paper, we propose a real-world UDC video dataset called UDC-VIT. Unlike existing datasets, only UDC-VIT exclusively includes human motions that target facial recognition. We propose a video-capturing system to simultaneously acquire non-degraded and UDC-degraded videos of the same scene. Then, we align a pair of captured videos frame by frame, using discrete Fourier transform (DFT). We compare UDC-VIT with six representative UDC still image datasets and two existing UDC video datasets. Using six deep-learning models, we compare UDC-VIT and an existing synthetic UDC video dataset. The results indicate the ineffectiveness of models trained on earlier synthetic UDC video datasets, as they do not reflect the actual characteristics of UDC-degraded videos. We also demonstrate the importance of effective UDC restoration by evaluating face recognition accuracy concerning PSNR, SSIM, and LPIPS scores. UDC-VIT enables further exploration in the UDC video restoration and offers better insights into the challenge. UDC-VIT is available at our project site. © 2025, CC BY-NC-SA.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Deep Belief Markov Models for POMDP Inference

arXiv

引用

arXiv 2025年

作者： Arcieri, Giacomo Papakonstantinou, Konstantinos G. Straub, Daniel Chatzi, Eleni Institute of Structural Engineering ETH Zürich Zürich8093 Switzerland Dept. of Civil and Environmental Engineering The Pennsylvania State University University ParkPA16802 United States Engineering Risk Analysis Group Munich Data Science Institute Technical University of Munich Munich80333 Germany

This work introduces a novel deep learning-based architecture, termed the Deep Belief Markov Model (DBMM), which provides efficient, model-formulation agnostic inference in Partially Observable Markov Decision Process (POMDP) problems. The POMDP framework allows for modeling and solving sequential decision-making problems under observation uncertainty. In complex, high-dimensional, partially observable environments, existing methods for inference based on exact computations (e.g., via Bayes’ theorem) or sampling algorithms do not scale well. Furthermore, ground truth states may not be available for learning the exact transition dynamics. DBMMs extend deep Markov models into the partially observable decision-making framework and allow efficient belief inference entirely based on available observation data via variational inference methods. By leveraging the potency of neural networks, DBMMs can infer and simulate non-linear relationships in the system dynamics and naturally scale to problems with high dimensionality and discrete or continuous variables. In addition, neural network parameters can be dynamically updated efficiently based on data availability. DBMMs can thus be used to infer a belief variable, thus enabling the derivation of POMDP solutions over the belief space. We evaluate the efficacy of the proposed methodology by evaluating the capability of model-formulation agnostic inference of DBMMs in benchmark problems that include discrete and continuous variables. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Urban Vertical Farming with IoT and Precision Monitoring for a Sustainable Future

Urban Vertical Farming with IoT and Precision Monitoring for...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Unni Krishnn, A. Dutt, Amit Singh, Jay Bhavana, Munugapati Baswaraju, Swathi Mohammed, Baydaa Fathil Venkatraman, Akila Galgotias university Department of Electrical Electronics & Communication Engineering Uttar Pradesh Gerater Noida203201 India Lovely Professional University Phagwara India Gl Bajaj Institute of Technology and Management Dept. of Eee U.P. Gr. Noida India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India New Horizon College of Engineering Department of Computer Science-Data Science Bangalore India College of Medical Technology The Islamic University Radiology Techniques Department Najaf Iraq Griet Department of Information Technology Bachupally Telangana Hyderabad India

ISBN: (纸本)9798331527495

The fast expansion of population worldwide and urbanisation had been estimated to have 80 % of the population in urban areas in the upcoming 50 years leads to an exponential rise in demand of food. These needs provide an urgent call for developing novel approaches to achieve global food demands amid sustainability problems. Urban Vertical Farming (UVF) offers an attractive solution for growing crops in the vertical dimension of structures, the urban skyscrapers, where land use is limited. However, it is fairly limited research which applies the current state of art in cutting edge technologies such as the Internet of Things, to try to automate and monitor farm processing. Thus, in this review paper, gaps in existing research, the potential for IoT enabled vertical farming, as well as challenges such as energy use, economic feasibility and urban policy integration are examined. Vertical farming can be enhanced through resource efficiency, scalability and level of sustainability through the use of IoT systems and AI driven data analytics which will also help promote urban food security. The research gives a summary of the current state, technological capabilities, and potential way forward in the process of successful vertical farming implementation in urban sets. © 2025 IEEE.

关键词： Food security

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Context Transformer for Multi-level Semantic Scene Understanding

arXiv

引用

arXiv 2025年

作者： Hao, Luoying Hu, Yan Yue, Yang Wu, Li Fu, Huazhu Duan, Jinming Liu, Jiang Research Institute of Trustworthy Autonomous Systems Dept. of Computer Science and Engineering Southern University of Science and Technology China School of Computer Science University of Birmingham United Kingdom Division of Informatics Imaging and Data Sciences School of Health Sciences University of Manchester United Kingdom MGI Tech Co. Ltd. China Singapore

A comprehensive and explicit understanding of surgical scenes plays a vital role in developing context-aware computer-assisted systems in the operating theatre. However, few works provide systematical analysis to enable hierarchical surgical scene understanding. In this work, we propose to represent the tasks set [phase recognition → step recognition → action and instrument detection] as multi-level semantic scene understanding (MSSU). For this target, we propose a novel hierarchical context transformer (HCT) network and thoroughly explore the relations across the different level tasks. Specifically, a hierarchical relation aggregation module (HRAM) is designed to concurrently relate entries inside multi-level interaction information and then augment task-specific features. To further boost the representation learning of the different tasks, inter-task contrastive learning (ICL) is presented to guide the model to learn task-wise features via absorbing complementary information from other tasks. Furthermore, considering the computational costs of the transformer, we propose HCT+ to integrate the spatial and temporal adapter to access competitive performance on substantially fewer tunable parameters. Extensive experiments on our cataract dataset and a publicly available endoscopic PSI-AVA dataset demonstrate the outstanding performance of our method, consistently exceeding the state-of-the-art methods by a large margin. The code is available at https://***/Aurorahao/HCT. Copyright © 2025, The Authors. All rights reserved.

关键词： Transplantation (surgical)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Handover Management in 5G Networks using Machine Learning in Fading Scenarios

Enhanced Handover Management in 5G Networks using Machine Le...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Deepak Upadhyay Sreekanth Rallapalli Zakir Hussain Nookala Venu Rashmi Sharma Shipra Shukla Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Department of MCA Nitte Meenakshi Institute of Technology Bengaluru India Centre for Internet of Things Madhav Institute of Technology & Science Deemed University Gwalior India Department of CSE Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India Dept. of CSE (Data Science) G. L. Bajaj Institute of Technology and Management Greater Noida India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

This study explores the use of machine learning (ML) to improve initial handover performance for 5G networks by analysing fading-affected scenarios. In this study, we assess the ability of ML models to predict optimal handover decisions compared with conventional methods. In this study, simulation results show that our ML-based methods can reduce the handover inaccuracy by 50%, decrease latency up to 10 times and stabilize network performance. We accompany our assessment with a series of graphical analyses to show how ML algorithms change their behaviour dynamically in response to deteriorating link intensity due user mobility and increasing h/o frequency, thereby degrading the network performance. The results clearly illustrate that ML enabled handover optimization is significantly more effective than traditional methods in accommodating fading-channel dynamics, thereby improving both the network performance and user experience of future generation wireless networks.

关键词： Fading channels 5G mobile communication Wireless networks Simulation Wires Machine learning Handover User experience Stability analysis Reliability

来源：评论

学校读者我要写书评

暂无评论

Hyper-IIoT: A Smart Contract-inspired Access Control Scheme for Resource-constrained Industrial Internet of Things

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年

作者： Li, Dun Li, Hongzhi Crespi, Noel Minerva, Roberto Li, Ming Liang, Wei Li, Kuan-Ching Tsinghua University Department of Industrial Engineering China Institut Polytechnique de Paris Samovar Telecom SudParis Palaiseau91120 France Chizhou University College of Big Data and Artificial Intelligence Chizhou247100 China The Hong Kong Polytechnic University Research Institute for Advanced Manufacturing Hung Hom Hong Kong Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Sanya Research Institute Hunan Key Laboratory for Service Computing and Novel Software Technology China Providence University Dept. of Computer Science and Information Engineering Taiwan

In recent years, the refinements in industrial processes and the increasing complexity of managing privacy-sensitive data in Industrial Internet of Things (IIoT) devices have highlighted the need for secure, robust, and adaptive data management solutions. In this work, we propose a smart contract-assisted access control scheme for IIoT, which employs the Attribute-Based Access Control (ABAC) model to set access permissions for different industrial components. Besides, we defined a storage model and data format for private data by designing and deploying smart contracts to manage system operations and access policies. In addition, the bloom filter component is deployed to optimize the efficiency of contract management and system performance. Experimental results show that in real-world simulations, Hyper-IIoT demonstrates excellent contract execution time control, stable system throughput, and rapid consensus processes that are capable of handling high throughput and efficient consensus in distributed systems, even in large-scale request scenarios. © 2016 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

XANNLight: A Novel Hybrid Ensemble Model for Accurate Health Insurance Prediction and Trend Forecasting

XANNLight: A Novel Hybrid Ensemble Model for Accurate Health...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Kafila Sajja Suneel Jayendra Gopal Thatipudi M Jini Kumari K. Penyameen Anubhav Sharma School of Business SR University Warangal Telangana India Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dept. of Computer Science Jayendra Gopal Thatipudi Student University of North Texas USA Department of ECE Chennai Institute of Technology Velammal College Of Engineering And Technology Madurai Department of CSE IES institute of Technology and management IES University Bhopal Mp India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Health insurance is a critical industry that requires precise data analysis and predictive capabilities to ensure operational efficiency and cost management. In an era where large datasets are readily available, machine learning models have become indispensable for predicting claims and identifying trends in insurance data. The rapid growth of the health insurance industry has increased the need for accurate prediction models to optimize claim management and trend forecasting. This study presents XANNLight, a novel hybrid ensemble model that integrates Artificial Neural Networks (ANN) and LightGBM to predict health insurance claims with high precision. The proposed model handles complex, non-linear relationships using ANN while LightGBM provides fast and accurate predictions for structured data. The dataset used for model training and evaluation consists of 1338 records, with features including age, sex, BMI, number of children, smoker status, and region. The model's performance is evaluated based on accuracy, precision, recall, and F1 score. The XANNLight model achieves an accuracy of 98.12%, outperforming nine existing models, including Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting, which achieved accuracy levels between 85% and 96%. Furthermore, XANNLight demonstrates superior precision (97.83%), recall (97.90 % ), and F1 score (97.86 % ). These results highlight the model's efficiency in processing large datasets and predicting insurance claims, making it an effective tool for health insurance companies aiming to enhance operational efficiency and cost management.

关键词： Industries Accuracy Costs Computational modeling Insurance Artificial neural networks Predictive models Market research data models Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Real Time approach for detecting and counting Vehicles using OpenCV and NumPy

A Real Time approach for detecting and counting Vehicles usi...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Irala Suneetha Ch. Prathima Srinivasulu Sirisala S. S.D.K Mahalakshmi K. Balaji Nanda Kumar Reddy Bosubabu Sambana ECE Department Annamacharya Institute of Technology and Sciences Tirupati Dept. of DS Mohan Babu University Tirupati India Department of CSE CVR College of Engineering Telagana Department of CSE Lendi Institute of Engineering and Technology Vizianagaram EEE Department Annamacharya Institute of Technology and Sciences Tirupati Department of Data Science School of Computing Mohan Babu University Tirupathi Andhra Pradesh India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Vehicle detection and counting using OpenCV is a crucial aspect of modern traffic management systems. This mini project aims to develop a robust solution for detecting vehicles in real-time video streams and accurately counting them as they pass through a designated area. OpenCV, a popular computer vision library, is utilized for its extensive functionality and ease of implementation. First, the video stream is captured and processed to extract individual frames. Subsequently, each frame undergoes preprocessing techniques such as resizing, grayscale conversion, and noise reduction to enhance vehicle detection accuracy. Vehicle detection is achieved through the implementation of a deep learning- based object detection algorithm, such as YOLO (You Only Look Once) or SSD (Single Shot MultiBox Detector). These algorithms are trained on large datasets to recognize vehicles with high precision. Once vehicles are detected, a tracking algorithm is employed to maintain continuity between frames and accurately count the number of vehicles passing through the specified region of interest. This tracking algorithm ensures that vehicles are not double-counted and provides a reliable count for traffic analysis purposes.

关键词： YOLO Vehicle detection System performance Roads Noise reduction Transforms Streaming media Real-time systems Streams Research and development

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：