检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Weinberger, Patrick Fröhler, Bernhard Heim, Anja Gall, Alexander Bodenhofer, Ulrich Senck, Sascha Research Group Computed Tomography University of Applied Sciences Upper Austria Wels Austria School of Informatics Communication and Media University of Applied Sciences Upper Austria Wels Austria Johannes Kepler University Linz Linz Austria Faculty of Computer Science and Mathematics University of Passau Passau Germany Division Development Center X-ray Technology Fraunhofer Institute for Integrated Circuits IIS Erlangen Germany

ISBN: (纸本)9783031781971

For safety critical applications, it is still a challenge to use AI and fulfill all regulatory requirements. Medicine/healthcare and transportation are two fields where regulatory requirements are of fundamental importance. A wrong decision can lead to serious hazards or even deaths. In these fields, semantic segmentation is often utilized to extract features. Especially U-Net architectures are used. This paper shows how to apply layer-wise relevance propagation (LRP) to a trained U-Net architecture. We achieve an efficient explanation of a segmentation by back-propagating the whole resulting image. To tackle the non-linear results of the LRP, we introduce a threshold mechanism in combination with a logarithmic transfer function to preprocess the data for visualization. We demonstrate our method on three use cases: the segmentation of a fiber-reinforced polymer in the field of non-destructive testing, the segmentation of pedestrians in an automotive application, and a lung segmentation example from the medical domain. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Federated Learning on Heterogeneous Images in Internet of Biomedical Things

引用

Big Data Mining and Analytics 2024年第4期7卷 1237-1250页

作者： Yusen Li Zaobo He Peilin He Yulin Cao College of Information Science and Technology Jinan UniversityGuangzhou 510632China Division of Natural and Applied Sciences Duke Kunshan UniversitySuzhou 215316China College of Computer Qinghai Normal UniversityQinghai 810000China

Federated Learning(FL)allows the Internet of bioMedical Things(IoMT)devices to collaboratively train a global model without centralizing data,yet the heterogeneity of biomedical images poses challenges in achieving optimal performance for each IoMT *** many personalized FL methods have been proposed,their adaptability is often limited to data with certain levels of *** this paper,we propose a novel FL method to handle heterogeneous images in ***,we propose a gradient-fusion method that integrates both shared and local gradients into the locally adapted model for improved *** shared gradients,aggregated from all IoMT devices through a learnable matrix,capture collective intelligence,while the local gradients,originating from each device’s data,reflect individual data *** dynamic integration of collective and device-specific insights effectively mitigates data ***,we propose a privacy-enhanced approach that delegates part of the gradient computation to devices,thereby protecting data privacy without compromising the efficacy of the gradient-fusion ***,for enhanced performance,we introduce a layer-wise aggregation method to precisely measure the contribution of different layers in local *** evaluations on imaging datasets,featuring various types and degrees of data heterogeneity,demonstrate the superior performance of our methods over existing baselines.

关键词： Internet of bioMedical Things(IoMT) Federated Learning(KL) data heterogeneity gradient-fusion privacy

来源：评论

学校读者我要写书评

暂无评论

Digital-Twin Enabled Time Ahead Resource Allocation for Integrated Fiber-Wireless Connected Vehicular Network

引用

Journal of Communications and Information Networks 2024年第3期9卷 296-308页

作者： Akshita Gupta Saurabh Jaiswal Martin Maier Vivek Ashok Bohara Anand Srivastava Wirocomm Research Group Department of Electronics&Communication EngineeringIndraprastha Institute of Information Technology Delhi(IIITD)New Delhi 110020India Department of Computer Science&Applied Mathematics Indraprastha Institute of Information Technology Delhi(IIITD)New Delhi 110020India Optical Zeitgeist Laboratory Institute National de la Recherche ScientifiqueMontreal H5A 1K6Canada

The digital twin(DT)is envisaged as a catalyst for pioneering ecosystems of service provision within an immersive environment born from the convergence of virtual and physical ***,DT could enhance the performance of edge-intelligent connected vehicular networks by allocating network resources efficiently based on the key performance indicators(KPIs)of vehicular data ***,this work addresses the key challenge of computation and spectrum resource allocation for vehicular *** allocate the optimal resource allocation,we subdivided the problem into:traffic classification,collective learning,and resource allocation *** order to do so,this paper concentrates on two crucial vehicular applications:brake application and lane-change *** utilize a random forest model to collectively learn vehicular data traffic in the upcoming time ***,a time-ahead resource allocation algorithm is proposed to improve the quality of service(QoS)by intelligently offloading vehicular data traffic to a DT-based integrated fiber-wireless(Fi-Wi)connected vehicular *** evaluate the performance of the resource allocation strategy in terms of resources required by the network alongside the packet loss *** was observed that there was a 44.74%increase in cost as the total computation resources increased from F=50 to 100 GHz,whereas the PLR of the network decreased by 71.43%.

关键词： connected vehicles digital twin edgeintelligence fiber-wireless machine learning resource allocation

来源：评论

学校读者我要写书评

暂无评论

Automated Fracture Detection and Classification Using Siamese Neural Networks

Automated Fracture Detection and Classification Using Siames...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Anderson, K.L. Engelbrecht, A.P. Birkholtz, F.F. Stellenbosch University Department of Computer Science Stellenbosch South Africa Stellenbosch University Computer Science Division Department of Industrial Engineering Stellenbosch South Africa Gulf University of Science and Technology GUST Engineering and Applied Innovation Research Centre Kuwait Institute of Orthopaedics and Rheumatology Mediclinic Winelands Orthopaedic Hospital Stellenbosch University Stellenbosch Division of Orthopaedic Surgery Department of Surgical Sciences Stellenbosch South Africa

ISBN: (纸本)9798350369106

This study aims to address the critical need for accurate and efficient fracture detection and classification in medical radiography, by leveraging recent developments in deep learning techniques. A two-stage pipeline is proposed combining a cutting-edge convolutional neural network (CNN), You only look once (YOLOv9), for wrist fracture detection using a Siamese neural network (SNN) for fracture type classification. The proposed methods aim to overcome the limitations of a single-stage approach by optimizing detection and classification stages independently. The results obtained demonstrate the efficacy of the two-stage pipeline in improving accuracy and reducing class imbalance issues, highlighting the potential of artificial intelligence (AI) driven solutions in enhancing patient care and reducing diagnosis time. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AI Simulation, IoT, and Digital Twin for Smart Campus 5

AI Simulation, IoT, and Digital Twin for Smart Campus

引用

5th Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2024

作者： Pexyean, Tanapeak Saraubon, Kobkiat Nilsook, Prachyanun Bangkok Suvarnabhumi University Department of Information Technology and Digital Innovation Bangkok Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Computer Science and Information Bangkok Thailand King Mongkut's University of Technology North Bangkok Division of Information and Communication Technology for Education Faculty of Technical Education Bangkok Thailand

ISBN: (纸本)9798331505998

The objective of this research is to Present the use of Artificial intelligence Simulation(AI Simulation), Internet of Things(IoT) and Digital Twin technology to Intelligently To develop the energy management potential of the campus intelligently by using technology to improve the environment, making the system smarter and more connected. This helps to make living in an urban community or university more comfortable. The adoption of various technologies has led to development in many fields, such as smart cities, smart homes, smart robots, smart machines Smart cars, smart agriculture, smart healthcare, and smart traffic control systems have the challenge of developing systems that allow devices to connect to the system quickly. One of the interesting ideas is Smart Campus, which is an educational institution that creates learning to develop individuals to be able to improve the world. The use of Internet of Things (IoT) technology, artificial intelligence, simulation, and the creation of digital twins. The use of IoT helps collect and exchange data from various devices in the network, enabling effective monitoring and control of the operation of various systems. Simulation allows for the creation of different scenario models to experiment and improve the system before it is actually implemented. It is a virtual model of a system or device to be used to track electricity consumption and optimize electrical energy management in real time. The application of these technologies in smart campuses will help to manage resources more efficiently, such as electrical energy management. Improvement of the transportation system within the university Security, and enhancing modern learning experiences. Developing the university into a smart campus not only improves operational efficiency but also helps to use energy efficiently. Reduce energy costs Reduce carbon dioxide emissions and create a sustainable and environmentally friendly learning environment both now and in the futur

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

A Hybrid SARIMAX Model in Conjunction with Neural Networks for the Forecasting of Life Insurance Industry Growth in Thailand 9

A Hybrid SARIMAX Model in Conjunction with Neural Networks f...

引用

Joint 9th International Conference on Digital Arts, Media and technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering, ECTI DAMT and NCON 2024

作者： Huadsri, Supika Mekruksavanich, Sakorn Jitpattanakul, Anuchit Phaphan, Wikanda King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok10800 Thailand University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao56000 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Thailand Research Group in Statistical Learning and Inference Thailand

ISBN: (纸本)9798350318241

This article is conducted with the primary aim of comparing various forecasting models to identify the optimal model for forecasting the growth of the life insurance industry in Thailand. The models under consideration include the SARIMAX model, the Recurrent Neural Network (RNN), and a hybrid model introduced as RNN-SARIMAX. The dataset utilized for this investigation is extensive, consisting of monthly direct premium data from the Thai life insurance sector spanning January 2003 to December 2022. The dataset is segregated into two distinct segments. Initially, data from January 2003 to December 2021 is employed for constructing the forecasting model. Subsequently, data from January 2022 to December 2022 is utilized for a comparative analysis of the forecasting models, to determine the most suitable and accurate model for predicting the growth of the life insurance industry in Thailand. The evaluation criteria for comparing models include the Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R-squared). The consistent findings from our analysis indicate that the SARIMAX model consistently outperforms both the RNN and RNN-SARIMAX models. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An Improved 2-Approximation Algorithm for the Rectilinear Steiner Tree Problem with Minimal Number of Steiner Points 4

An Improved 2-Approximation Algorithm for the Rectilinear St...

引用

4th International Conference on applied mathematics, Modeling and computer Simulation, AMMCS 2024

作者： Li, Jianglin Wang, Wencheng Chen, Yinhua Zhang, Tongquan School of Mathematics and Computer Science Yunnan Minzu University Yuehua Street NO.2929 Yunnan Kunming650504 China School of Applied Technology Yunnan Minzu University Yuehua Street NO.2929 Yunnan Kunming650504 China

ISBN: (纸本)9781643685519

In this paper, we present an improved algorithm for the rectilinear Steiner trees problem with minimal number of Steiner points. Given a set X of n terminal points in the L1 plane and a positive constant L, it is asked to construct a Steiner tree T interconnecting of these n terminal points, with the length of each edge in that tree T is no more than L. It has been proven that this problem is NP-hard and there exists a 2-approximation algorithm in time O(n3). By using the strategies of the sweep-line algorithm and a leaf-deletion technique in a special forest composed of selected edges from a rectilinear minimum spanning tree on X, we propose an effective 2-approximation algorithm in time O(n log n). © 2024 The Authors.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of Virtual Reality Platform through Human computer Interaction using Artificial Intelligence 3

Development of Virtual Reality Platform through Human Comput...

引用

3rd International Conference on applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Saranya, S. Channarayapriya, B. Harshavardhini, U. Nandhini, A.Sunitha Revathi, J. Venkatesan, R. New Horizon College of Engineering Department of Computer Science and Engineering Bangalore India Vel Tech Multi Tech Dr.Rangarajan Dr Sakunthala Engineering College Deparment of Information Technology Chennai India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Kongu Engineering College Department of Mathematics Erode India Bannari Amman Institute of Technology Deparment of Information Technology Erode India

ISBN: (纸本)9798350375190

The development of a virtual reality platform through human-computer interaction (HCI) is obtained using deep learning with a genetic algorithm. The human-computer interaction forms a bridge between users and the VR system. This helps in providing a natural interaction experience to the users. Deep learning techniques help in obtaining the realistic nature of the physical world in the virtual platform. The personalized experiences are obtained using the integration of deep learning with VR platforms. The optimization algorithm helps in achieving user interaction in a real-time platform. The adaptive learning helps in increasing the overall immersion with a user-friendly interface. The VR development process is done using a genetic algorithm. This helps to evolve and optimize themselves within the period of time. This helps the VR platform to iteratively improve its performance and complete design through adopting successful combinations of various parameters. The proposed approach helps the VR system to evolve towards an optimal condition. This helps to satisfy the various needs and preferences of the users. Thus the proposed system helps in obtaining adaptive and intelligent virtual environments. This helps in overcoming various challenges in designing immersive VR experiences with personalized digital environments. © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

引用

computers, Materials & Continua 2024年第9期80卷 4791-4812页

作者： Ahmad Yahiya Ahmad Bani Ahmad Jafar Alzubi Sophers James Vincent Omollo Nyangaresi Chanthirasekaran Kutralakani Anguraju Krishnan Department of Accounting and Finance Faculty of BusinessMiddle East UniversityAmman11831Jordan Faculty of Engineering Al-Balqa Applied UniversitySalt19117Jordan Department of Mathematics Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo210-40601Kenya Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering Saveetha Engineering College(Autonomous)Chennai602105India Department of Computer Science and Engineering Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant *** developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic *** images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human *** lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging *** unimodal-based HAR approaches are not suitable in a real-time ***,an updated HAR model is developed using multiple types of data and an advanced deep-learning ***,the required signals and sensor data are accumulated from the standard *** these signals,the wave features are *** the extracted wave features and sensor data are given as the input to recognize the human *** Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition ***,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition *** experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR *** EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,*** result proved that the developed model is effective in recognizing human action by taking less ***,it reduces the computation complexity and overfitting issue through using an optimization approach.

关键词： Human action recognition multi-modal sensor data and signals adaptive hybrid deep attentive network enhanced archerfish hunting optimizer 1D convolutional neural network gated recurrent units

来源：评论

学校读者我要写书评

暂无评论

A Fast Exponential Analysis and Variable Projection-Based Method for Linear Array Synthesis

引用

IEEE Antennas and Wireless Propagation Letters 2025年第6期24卷 1527-1531页

作者： Sengupta, Ramonika Knaepkens, Ferre Cuyt, Annie Prinsloo, David S. Schäfer, Thomas Smolders, A. Bart Eindhoven University of Technology Department of Electrical Engineering Eindhoven5600 MB Netherlands University of Antwerp Faculty of Applied Engineering Antwerp2020 Belgium University of Stirling Computing Science and Mathematics Division StirlingFK9 4LA United Kingdom ASTRON Dwindloo 7991 PD Netherlands SATCUBE Gothenburg41263 Sweden

This letter presents a fast exponential analysis and variable projection method to reduce the number of elements in linear phased arrays. The numerical examples given in this work demonstrate a reduction of approximately 20% or 10% in the number of elements, with only a slight decrease in directivity of 0.63 dBi observed for a scan range of [-45°,45° ]. Compared with the combined matrix pencil and Tabu search algorithm, the proposed technique converges in fewer iterations and exhibits ≈ 5 dB reduction in maximum sidelobe level. © 2002-2011 IEEE.

关键词： Antenna phased arrays

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：