检索结果-内蒙古大学图书馆

Machine Learning for Data Fusion:A Fuzzy AHP Approach for Open Issues

computers, Materials & Continua 2023年第12期77卷 2899-2914页

作者： Vinay Kukreja Asha Abraham K.Kalaiselvi K.Deepa Thilak Shanmugasundaram Hariharan Shih-Yu Chen Chitkara University Institute of Engineering and Technology Chitkara UniversityPunjab140401India Department of Networking and Communications SRM Institute of Science and TechnologyKattankulathurChengalpattuTamil Nadu603203India Department of Networking and Communications Faculty of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamil Nadu603203India Department of Computer Science and Engineering Vardhaman College of EngineeringHyderabad501218India Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin64002Taiwan

Data fusion generates fused data by combining multiple sources,resulting in information that is more consistent,accurate,and useful than any individual source and more reliable and consistent than the raw original data,which are often imperfect,inconsistent,complex,and *** data fusion methods like probabilistic fusion,set-based fusion,and evidential belief reasoning fusion methods are computationally complex and require accurate classification and proper handling of raw *** fusion is the process of integrating multiple data *** filtering means examining a dataset to exclude,rearrange,or apportion data according to the *** sensors generate a large amount of data,requiring the development of machine learning(ML)algorithms to overcome the challenges of traditional *** advancement in hardware acceleration and the abundance of data from various sensors have led to the development of machine learning(ML)algorithms,expected to address the limitations of traditional ***,many open issues still exist as machine learning algorithms are used for data *** the literature,nine issues have been identified irrespective of any *** decision-makers should pay attention to these issues as data fusion becomes more applicable and successful.A fuzzy analytical hierarchical process(FAHP)enables us to handle these *** helps to get the weights for each corresponding issue and rank issues based on these calculated *** most significant issue identified is the lack of deep learning models used for data fusion that improve accuracy and learning quality weighted *** least significant one is the cross-domain multimodal data fusion weighted 0.076 because the whole semantic knowledge for multimodal data cannot be captured.

关键词： Signal level fusion feature level fusion decision level fusion fuzzy hierarchical process machine learning

来源：评论

学校读者我要写书评

暂无评论

Sand-Dust Image Enhancement Using Anisotropic Guided Filter 15th

Sand-Dust Image Enhancement Using Anisotropic Guided Filter

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Nagarathna, P. Vinutha, C.B. Tirumala Vasu, G. Kubra, Afreen Fiza, Samreen Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Karnataka Bengaluru560064 India Department of Electronics and Communications Engineering Presidency University Karnataka Bangalore560064 India

ISBN: (纸本)9783031810855

Scene recovery is a crucial imaging task that holds significant relevance in various practical domains, such as video surveillance and autonomous vehicles, among others. To improve the visual quality of sand-dust images captured under various weather and imaging situations, we propose the use of Anisotropic Guided Filter (AnisGF). This filter utilizes a weighted averaging technique for an image to minimize diffusion and preserve the sharpness of edges. The weights provided in this study are adjusted using local neighborhood variances in order to obtain robust anisotropic filtering, while the computational efficiency of the original guided filter is preserved. The proposed technique deals with the problem of detail halos and the management of inconsistent structures seen in earlier guided filter variants. Furthermore, experiments with sand-dust, haze and under water images enhancement also show how the AnisGF improves image quality in terms of quality metrics namely Blind/ Referenceless Image Spatial Quality Evaluator, Naturalness Image Quality Evaluator, and Perception based Image Quality Evaluator. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Performance Assessment of an Electrically Reconfigurable Photovoltaic Array in an Off-Grid System 6th

Performance Assessment of an Electrically Reconfigurable Pho...

引用

6th International on Clean Energy and Electrical Systems, CEES 2024

作者： Chan, Aaron Keith Y. Macabebe, Erees Queen B. Ateneo Energy Research Laboratory Department of Electronics School of Science and Engineering Computer and Communications Engineering Ateneo de Manila University Loyola Heights Quezon City1108 Philippines

ISBN: (纸本)9789819757749

Partial shading of photovoltaic (PV) modules reduces the output power of a PV system. Electrically reconfigurable arrays have been proposed to increase the power output of shaded PV systems. In this paper, an electrically reconfigurable PV array was built using the total cross-tied (TCT) topology. The PV array was then tested manually using different shading patterns. Furthermore, the PV array was deployed and allowed to autonomously reconfigure in an environment where shading due to clouds and foliage is expected. Results from the I-V and P-V curves of the PV array show that the power improvements expected of the array after reconfiguration were met. However, when connected to the balance of system components, improvements in the power output were not met. During pilot deployment, the speed of changing shading patterns also affected the outcome. Thus, when designing a PV system that incorporates a reconfiguration of PV modules, the following need to be considered: first, identify the potential causes of partial shading at the target location, which include the expected shading patterns and speed of changing patterns, and second, investigate the effects of the balance of system components, such as component efficiencies, speed of maximum power point tracking, and system type. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Off-grid Photovoltaic System Partial Shading Solar PV Array Reconfiguration

来源：评论

学校读者我要写书评

暂无评论

A high-performance FPGA architecture for Acceleration of SVM Machine Learning Training

A high-performance FPGA architecture for Acceleration of SVM...

引用

2022 Panhellenic Conference on Electronics and Telecommunications, PACET 2022

作者： Kardaris, Charalampos Kachris, Christoforos Soudris, Dimitrios Ntua Department of Electrical and Computer Engineering Athens Greece Ntua Institute of Communications and Computer Systems Athens Greece

ISBN: (数字)9798350399585

ISBN: (纸本)9798350399585

Support Vector Machines (SVMs) is one of the most popular machine learning algorithms as it provides high-performance and needs minimal tuning. It can be used for classification, regression and other learning tasks. Its design makes the training of large datasets time-consuming, so it is important that solutions are developed that attempt to tackle this problem. One such solution is presented in this paper. Based on the LIBSVM library, one of the most popular and widely used implementations of SVMs, we developed the design that can be executed on an heterogeneous computing system, consisting of an FPGA accelerator card, along with *** first step of the process is to determine the most computationally intensive and parallelizable part of the algorithm. That is found to be a matrix row computation, involving inner products and a mathematical function (one of exp, pow, tanh) for each of the elements. Then, we develop a kernel, that can fully utilize the abilities of the FPGA accelerator card, regarding data processing and computations. In our case that is the Alveo U200 Data Center accelerator card. The results show that the proposed implementation achieves up to 14x speedup in the row computation part of the algorithm compared to a multi-threaded CPU execution on a Ryzen3 2200G, a CPU with a base clock speed of 3.5 GHz. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Adversarial-TransUnet Architecture for Improving LV Segmentation Using Cardiac Cine Images 1st

A Hybrid Adversarial-TransUnet Architecture for Improving L...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Abdeltawab, Hisham Jani, Md. Rafsan Hasan, Md Rakibul Yasser, Ibrahim Khalifa, Fahmi Department of Biomedical Engineering and Systems Cairo University Cairo12613 Egypt Department of Electrical and Computer Engineering Morgan State University BaltimoreMD21251 United States Department of Electronics and Communications Engineering Mansoura University Mansoura35516 Egypt

ISBN: (纸本)9783031823763

Cardiac image segmentation is crucial for the assessment of heart anatomy and function. Deep learning (DL) has been widely employed for cardiac image segmentation and the accuracy of the segmentation has improved due to the advances in DL research and the existence of large cardiac datasets. In this study, we introduce a DL framework based on adversarial training for the delineation of the left ventricle (LV) from cardiac magnetic resonance imagining (CMRI). Our framework consists of two networks: the segmenter which is a neural network that predicts segmentation maps for the myocardium, the discriminator which is a convolutional neural network that discriminates between the ground truth and the predicted segmentation maps. We investigate two different architectures for the segmenter (Unet and TransUnet). The adversarial training can identify and correct the differences between the predicted and the ground truth maps and results in better segmentation accuracy than stand-alone Unet or TransUnet. The proposed framework has been evaluated on cine CMRI, collected from 100 patients, and evaluated using different metrics (Dice coefficient, Jaccard Index, and Hausdorff distance). The results documented an improvement of the segmentation accuracy (0.91, 0.82, 4.69 mm) using the proposed framework with TransUnet compared to the segmentation obtained by stand-alone Unet (0.75, 0.68, 7.54 mm). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Smart Home IoT Network Diagnostics using Big Data Services 30

Smart Home IoT Network Diagnostics using Big Data Services

引用

30th Telecommunications Forum, TELFOR 2022

作者： Vajagic, Nenad Antic, Marija University of Novi Sad Department for Computer Engineering and Computer Communications Faculty of Technical Sciences Novi Sad Serbia

ISBN: (数字)9781665472739

ISBN: (纸本)9781665472739

Internet of Things (IoT) systems use a variety of different devices, which generate large amounts of data. For most of the IoT-oriented companies this data has a big impact on improving the customer experience and system monitoring. Big data systems take raw data and organize it into logical datasets for further analysis. This paper will describe one implementation of the big data services in an already-existing smart home system, and its application to network diagnostics. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Neural Network-based System Identification: A Comprehensive FPGA Design and Implementation

Neural Network-based System Identification: A Comprehensive ...

引用

2024 International Conference on Artificial Intelligence and Mechatronics System, AIMS 2024

作者： Abdulnabi, Saif Hasan Mudhafar, Yousif Samer Kadhim, Ali Abdulhassan Mahdi, Mohammad Baqer Sojar, Hassan Hadi University of Kufa Faculty of Engineering Department of Electronic and Communications Engineering Najaf54001 Iraq College of Engineering University of Baghdad Department of Electrical Engineering Al-Jadriya Baghdad10001 Iraq Information Technology College Imam ja'Afar Al-Sadiq University Department of Computer Techniques Engineering Najaf Iraq College of Technical Engineering Computer Techniques Engineering Department The Islamic University Najaf Iraq

ISBN: (纸本)9798350350524

Neural networks are more commonly used to identify systems for system diagnostics without fully implementing and building the system. The project aims to design and implement the neural network identification system and implement it based on a Field Programmable Gate Array (FPGA) by interfacing between MATLAB / Simulink and Xilinx programs. The work was done thanks to God through two methods: The first through the simulation method through the coupling between MATLAB and Xilinx. While the second method was practically done by loading the simulation designs onto the FPGA. Work performance is measured by subtracting the value resulting from the actual system operation of the identification signal system and the simplified system and the difference between the simulation result and practical result. The use of FPGA with system identification in this project gives us a big advantage that simulation results are equal to practical results (difference is zero). © 2024 IEEE.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Non-zero Dispersion Shifted Fiber with Multi-concentricring Cores for OAM Modes

Non-zero Dispersion Shifted Fiber with Multi-concentricring ...

引用

2024 Frontiers in Optics, FiO 2024

作者： Huang, Yuxiang Zhao, Wenqian Pan, Zhongqi Yue, Yang School of Information and Communications Engineering Xi'an Jiaotong University Xi'an710049 China Department of Electrical & Computer Engineering University of Louisiana at Lafayette LafayetteLA70504 United States

A multi-concentric-ring-core non-zero dispersion shifted fiber is proposed and designed to support 70 OAM modes while adhering to the ITU-T G.655.C standard. The corresponding nonlinear effects and confinement loss of... 详细信息

关键词： Dispersions

来源：评论

学校读者我要写书评

暂无评论

Road Signs Recognition by Using YOLOv8 Model 14

Road Signs Recognition by Using YOLOv8 Model

引用

14th International Conference on Intelligent Systems: Theories and Applications, SITA 2023

作者： Nabou, Abdellah Salih, Atheer L. Ben Rabbaa, Ibtissam Abdelwahed, El-Hassan Ait Ahmed Ouhamou, Mouaad Computer Science Dept Marrakesh Morocco Dhbw University - Campus Electrical & Communications Engineering Department Friedrichshafen Germany Cadi Ayyad University Computer Science Dept Marrakesh Morocco

ISBN: (纸本)9798350308211

Efficient Road sign recognition is key to improving road safety, navigation and to enhance driver assistance for an intelligent transportation system (ITS). However, achieving efficient road sign and traffic recognition is accompanied by many challenges, in our last few years, several deep learning algorithms have been deployed for responding to these limitations. With the exponential increase in the number of vehicles in Morocco, the need for accurate and real-time detection and classification of road signs has become essential. In this paper, we propose an advanced approach for recognizing Moroccan road signs utilizing the YOLOv8 (You Only Look Once) model that very known for its efficiency and effectiveness in object detection tasks. the model is trained and evaluated under a comprehensive dataset that comprising diverse Moroccan road signs. The test of YOLOv8 model give an encouraging result in different performance metrics such as accuracy, recall, precision and mAP which have respectively an average of 0.95, 0.94, 0.96 and 0.97. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

New Beamforming Approach Based EGWO for Beyond 5G Communication

New Beamforming Approach Based EGWO for Beyond 5G Communicat...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Farghaly, Samar I. Fouda, Mostafa M. Tanta University Faculty of Engineering Electronics and Electrical Communications Engineering Dept. Tanta31527 Egypt Idaho State University Department of Electrical and Computer Engineering PocatelloID United States

ISBN: (纸本)9798350351408

Beamforming has attracted the attention of many researchers in recent years. It significantly enhances the performance of many communication systems, especially beyond 5G communication, in terms of spectral and energy efficiency. In addition, beamforming is done in the analog domain, so it adds no complexity to the existing system. Consequently, in this paper, the new beamforming approach is based on a hybrid combination between GWO and L2-norm called enhanced garay wolf optimizer (EGWO). This approach is used to reduce the side lobe level (SLL) and the number of antenna elements. Hence, the signal-to-interference noise ratio (SINR) is maximized, and complexity is suppressed via the reduction of elements. The simulation results show the proposed algorithm outperforms other algorithms in comparison. © 2024 IEEE.

关键词： Signal to noise ratio

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：