检索结果-内蒙古大学图书馆

Cognitive Robotics and Intelligent systems (ICC - ROBINS), International Conference on

作者： Yuvaraj Natarajan Sri Preethaa K. R Shrinithi Viswanathan Sandhiya Jayarathinam Vikas Balasubramaniam Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Robot and Smart System Engineering Kyungpook National University Daegu Republic of Korea

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

The proposed IoT-based Smart Curve Monitoring and Alert system is designed to improve road safety through the fusion of embedded systems, machine learning and edge computing technologies. The proposed system is primarily powered by ESP32 microcontroller, continuously gathers data from an array of sensors, including accelerometers, gyroscopes and a potentiometer to set the speed limit. This collected data is then subjected to analysis by a Convolutional Neural Network (CNN) model, which has been trained to recognize driving patterns, especially when navigating curves. Here, CNN classifies the vehicle’s behavior as safe and risky, and if a risky behavior is identified, it triggers an alert and dispatches relevant data to a NodeMCU device. The NodeMCU plays a crucial role in the system by monitoring the communication tasks. It receives the alert from the ESP32, validates the vehicle’s speed against the preset limit, and, if necessary, activates a GSM module to send an immediate notification to designated guardian. To ensure real-time monitoring and awareness, all pertinent information will be displayed on the LCD screen, including the vehicle’s behavior classification, current speed, speed limit and alert status. By addressing reckless driving behaviors, particularly on curves, the system contributes significantly to safer roads and reinforces the importance of responsible driving practices.

关键词： Machine learning Road safety Real-time systems Liquid crystal displays Safety Convolutional neural networks Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Advanced Retinal Image Segmentation using U-Net Architecture: A Leap Forward in Ophthalmological Diagnostics 4

Advanced Retinal Image Segmentation using U-Net Architecture...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Hasan, Nobanul Alam Riad, Md Jahid Das, Stabak Roy, Prosenjit Shuvo, Mahfuzur Rahman Rahman, Mafizur International American University Department of Management Information System Los AngelesCA United States ViennaVA United States Prairie View A and M University Department of Electrical and Computer Engineering TX United States Prairie View A and M University Department of Computer Science TX United States International American University Mba Mis Los AngelesCA United States

ISBN: (纸本)9798350343670

The expeditious advancement of deep learning in the field of biomedical imaging has facilitated the emergence of innovative diagnostic instruments, hence revolutionising the domain of ophthalmology. This study focuses on exploring the capabilities of the U-Net architecture, a convolutional neural network that is widely recognized for its proficiency in performing image segmentation tasks. By employing retinal pictures, we have successfully trained the U-Net model to accurately outline complex structures, resulting in a notable F1 score of roughly 94.33% and a Jaccard Score of 89.56%. The highest level of precision was noted at approximately epoch 250, serving as evidence of the model's efficient convergence and capacity. Nevertheless, succeeding periods revealed variations in the loss of validation, highlighting the difficulties in generalizing the model. The results of our study shed light on the diagnostic capabilities of U-Net, highlighting its ability to accurately identify subtle features in retinal pictures. This has the potential to significantly transform the field of ophthalmology by enabling early identification and intervention in many diseases. With the increasing adoption of artificial intelligence (AI) in the healthcare industry, these models hold significant potential as fundamental components for the development of sophisticated, effective, and dependable diagnostic systems. The study not only highlights the promise of deep learning in the field of medical imaging but also lays the foundation for future efforts focused on improving and using artificial intelligence (AI) capabilities in actual clinical environments. © 2024 IEEE.

关键词： Biomedical Imaging Disease Detection Image Segmentation Retinal Images U-Net

来源：评论

学校读者我要写书评

暂无评论

Analysis of EMI Mitigation Techniques in High Speed Printed Circuit Board 2

Analysis of EMI Mitigation Techniques in High Speed Printed ...

引用

2nd International Conference for Innovation in Technology, INOCON 2023

作者： Anandan, M. Sajitha, L.P. Geerthik, S. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of ECE Chennai India Agni College of Technology Department of Information Technology Chennai India R.M.K Engineering College Department of Computer Science and Business System Chennai India

ISBN: (纸本)9798350320923

To serve the numerous services, today's wireless communication devices require microwave network systems with multiband and multifunctional capabilities. A growing number of microwave circuits and parts that can handle several frequency bands and larger bandwidths are needed to support the unprecedented systems. The issues in EMI/EMC have grown as a result of research and advances in contemporary wireless network communication equipment. Generally speaking, there are several ways to reduce different EMI issues. Therefore, the necessary tunable and downsized components are required to make these systems smaller, lighter, and less expensive. Most studies on emission measurements have been done in the time domain recently and one of the widely used techniques is the creation of EMI band pass filters. This article presents band pass filters with HIDDS (Hybrid Inter Digital Defected Ground Structure). Additionally, a number of uses for the hybrid S-parameters are provided by fusing Agilent ADS circuit tool and full-wave EM solvers. To provide a complete EM response of the filter construction, 3D EM simulations are performed. The analysis of the simulated findings with the results of previous experiments has revealed that HIDDS (Hybrid Inter Digital Defected ground Structure) provides minimal insertion loss and a larger range of stop band frequencies. Therefore, wireless systems might benefit from the band pass filters with HIDDS that have been proposed. © 2023 IEEE.

关键词： Defected ground structures

来源：评论

学校读者我要写书评

暂无评论

MPI Allgather Utilizing CXL Shared Memory Pool in Multi-Node Computing systems

MPI Allgather Utilizing CXL Shared Memory Pool in Multi-Node...

引用

IEEE International Conference on Big Data

作者： Hooyoung Ahn Seonyoung Kim Yoomi Park Woojong Han Shinyoung Ahn Tu Tran Bharath Ramesh Hari Subramoni Dhabaleswar K. Panda Supercomputing System Research Section Electronics and Telecommunications Research Institute Department of Computer Science and Engineering The Ohio State University

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

In Artificial Intelligence (AI) and high-performance computing (HPC), growing data and model sizes require distributed processing across multiple nodes due to single-node limitations, increasing inter-node communication. To address these challenges, we propose a novel MPI allgather method leveraging CXL technology, which supports composable architectures and dynamic resource allocation in data centers and HPC systems. Notably, CXL 3.1 facilitates cache coherence among nodes. The proposed allgather method uses the CXL shared memory pool as a communication buffer, outperforming existing algorithms for two reasons: First, CXL provides lower latency than Ethernet and IB, and second, by using the CXL shared memory pool as a shared communication buffer across multiple nodes, it significantly reduces the number of communications. To the best of our knowledge, this work is the first to explore combining MPI collective communication with CXL technology to optimize MPI allgather. Our proposed allgather method significantly reduces communication latency compared to traditional allgather methods by up to 42.14x, with a minimum improvement of 2.91x, as measured using the OSU Micro-Benchmark (OMB), a standard MPI benchmarking suite.

关键词： High performance computing Heuristic algorithms Memory management Ethernet Dynamic scheduling Hardware Topology Resource management Artificial intelligence Standards

来源：评论

学校读者我要写书评

暂无评论

Generative AI-Enhanced Cooperative MEC of UAVs and Ground Stations for Unmanned Surface Vehicles 59

Generative AI-Enhanced Cooperative MEC of UAVs and Ground St...

引用

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

作者： You, Jiahao Jia, Ziye Dong, Chao Wu, Qihui Han, Zhu Nanjing University of Aeronautics and Astronautics The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing211106 China Southeast University National Mobile Communications Research Laboratory Nanjing211111 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

ISBN: (纸本)9798331513269

The increasing deployment of unmanned surface vehicles (USVs) require computational support and coverage in applications such as maritime search and rescue. Unmanned aerial vehicles (UAVs) can offer low-cost, flexible aerial services, and ground stations (GSs) can provide powerful supports, which can cooperate to help the USVs in complex scenarios. However, the collaboration between UAVs and GSs for USVs faces challenges of task uncertainties, USVs trajectory uncertainties, heterogeneities, and limited computational resources. To address these issues, we propose a cooperative UAV and GS based robust multi-access edge computing framework to assist USVs in completing computational tasks. Specifically, we formulate the optimization problem of joint task offloading and UAV trajectory to minimize the total execution time, which is in the form of mixed integer nonlinear programming and NP-hard to tackle. Therefore, we propose the algorithm of generative artificial intelligence-enhanced heterogeneous agent proximal policy optimization (GAI-HAPPO). The proposed algorithm integrates GAI models to enhance the actor network ability to model complex environments and extract high-level features, thereby allowing the algorithm to predict uncertainties and adapt to dynamic conditions. Additionally, GAI stabilizes the critic network, addressing the instability of multi-agent reinforcement learning approaches. Finally, extensive simulations demonstrate that the proposed algorithm outperforms the existing benchmark methods, thus highlighting the potentials in tackling intricate, cross-domain issues in the considered scenarios. © 2025 IEEE.

关键词： Unmanned surface vehicles

来源：评论

学校读者我要写书评

暂无评论

MULTIMODAL LEARNING TO IMPROVE CARDIAC LATE MECHANICAL ACTIVATION DETECTION FROM CINE MR IMAGES

arXiv

引用

arXiv 2024年

作者： Xing, Jiarui Wu, Nian Bilchick, Kenneth C. Epstein, Frederick H. Zhang, Miaomiao Department of Electrical and Computer Engineering University of Virginia United States Department of Computer Science University of Virginia United States Department of Biomedical Engineering University of Virginia Health System United States School of Medicine University of Virginia Health System United States

This paper presents a multimodal deep learning framework that utilizes advanced image techniques to improve the performance of clinical analysis heavily dependent on routinely acquired standard images. More specifically, we develop a joint learning network that for the first time leverages the accuracy and reproducibility of myocardial strains obtained from Displacement Encoding with Stimulated Echo (DENSE) to guide the analysis of cine cardiac magnetic resonance (CMR) imaging in late mechanical activation (LMA) detection. An image registration network is utilized to acquire the knowledge of cardiac motions, an important feature estimator of strain values, from standard cine CMRs. Our framework consists of two major components: (i) a DENSE-supervised strain network leveraging latent motion features learned from a registration network to predict myocardial strains;and (ii) a LMA network taking advantage of the predicted strain for effective LMA detection. Experimental results show that our proposed work substantially improves the performance of strain analysis and LMA detection from cine CMR images, aligning more closely with the achievements of DENSE. © 2024, CC BY.

关键词： Strain

来源：评论

学校读者我要写书评

暂无评论

Navigating the Future: Artificial Intelligence and Sustainable Transportation in Morocco 9th

Navigating the Future: Artificial Intelligence and Sustainab...

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Chegri, B.E. Rhajbal, Z. El Mettiti, A. Berhich, A. Saadane, R. Charif, M. Chehri, A. Mohammed V University in Rabat Rabat Morocco LRIT-GSCM Faculty of Sciences University Mohamed V Rabat Rabat Morocco AMIPS Research Team Computer Science Department EMI Mohammed V University in Rabat Rabat Morocco Laboratory Engineering System SIRC/LAGeS EHTP Casablanca Morocco Department of Mathematics and Computer Science Royal Military College Kingston Canada

ISBN: (纸本)9783031886522

The integration of Artificial Intelligence (AI) into sustainable mobility represents a transformative paradigm for transportation systems, particularly within the unique socioeconomic landscape of Morocco. This study delves into the dynamic intersection of AI and sustainable mobility, examining its implications for enhancing efficiency, reducing environmental impact, and improving overall accessibility in Moroccan transportation. Against the backdrop of Morocco’s commitment to sustainable development, the research navigates through the intricate web of challenges and opportunities posed by the fusion of AI technologies and mobility solutions. Through a comprehensive literature review, case studies, and recommendations, this article provides a roadmap for policymakers, researchers, and stakeholders to harness the potential of AI in shaping a more resilient and technologically advanced transportation infrastructure. With a focus on both global best practices and Morocco’s specific needs, the study not only underscores the benefits of AI integration but also addresses ethical considerations and potential socio-cultural implications. As Morocco advances towards a sustainable future, the synergies between AI and mobility emerge as a pivotal force in steering transportation towards efficiency, accessibility, and environmental responsibility. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Edge computing hardware design for Cubesat camera 11

Edge computing hardware design for Cubesat camera

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Lee, Pei-Jun Yu, Chun-Hsien Shiu, Shiuan-Hal Weng, Chi Wei Huang, Shu-Chun Xu, Guo-Cheng Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan Research and Development Department Liscotech System Co.Ltd Taipei Taiwan

ISBN: (纸本)9781665492324

In this paper, we designed and implemented an FPGA-based image system for satellite applications. The FPGA utilizes LVDS receivers to capture data up to eight 180MHz channels. The captured image data will be adjusted by the ADC offset compensator immediately, and after this adjustment, the histogram of each color channel will be booked. The summation of all pixels and the summation of pixels of four-color channels are calculated separately. Then, the control system decides whether the calculation of de-bayer, histogram equalization, and automatic white balance is needed. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Optimization Accuracy of MRI Brain Image Based Tumor Detection Using Deep Learning LSTM Technique

Optimization Accuracy of MRI Brain Image Based Tumor Detecti...

引用

Advanced Computing & Communication Technologies (ICACCTech), International Conference on

作者： Aarti Chugh Ranjeet Kumar Yadav Tushar Agarwal School of Computer Science and Engineering IILM University Gurugram India Department of Computer Science and Engineering Shree Guru Gobind Singh Tricentenary University Gurugram India The Galaxy Education System Gujrat India

ISBN: (数字)9798331519056

ISBN: (纸本)9798331519063

Benign brain tumors (BT) are the least dangerous type and arise from brain cells or cells surrounding the brain. Benign tumors grow slowly and do not spread to other body parts. Benign brain tumors have distinct borders. They put the normal brain under stress and interfere with physical and mental function. It is also referred to as a non-cancerous BT. The acquisition of magnetic resonance images introduces noise, and removing this noise is complex. BT has tentacles and diffuse structures, making precise segmentation difficult. Another critical task is to select and extract the best features and the appropriate number of training and test samples to improve the classification. Deep learning (DL) models have received much attention because feature learning happens automatically. However, it necessitates a substantial amount of computing power and memory. As a result, lightweight models with high accuracy and fast computation times were developed. This paper is present on ML and DL model for analysis of BT detection and calculated accuracy. The ML classification i.e. K-NN achieves 78.74% accuracy, LR achieves 81.53% accuracy, VC achieves 86.9% accuracy and DL LSTM achieves 94.07% accuracy. It is clearly that the LSTM technique is provides good accuracy compared to other ML technique.

关键词： Deep learning Training Accuracy Magnetic resonance imaging Computational modeling Noise Brain tumors Feature extraction Long short term memory Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient and Resilient Placement Strategy for Electric Vehicle Charging Stations, Incorporating Renewable Energy and Storage Equipment in Distribution Networks

Efficient and Resilient Placement Strategy for Electric Vehi...

引用

2023 International Conference for Technological engineering and its Applications in Sustainable Development, ICTEASD 2023

作者： Kumar, Rakesh Begam, S. Shajathi Singh, Dev Lazizovich, Tuychiev Komiljon Muthubalaji, S. Al-Farouni, Mohammed Varanasi, Srinivas GLA University Department of Computer Engineering & Applications Mathura India E.G.S. Pillay Engineering College Department of Computer Science and Business System Tamilnadu Nagapattinam India Allenhouse Institute of Technology Mathematics Department Kanpur India Tashkent State University of Economics Department of Marketing Uzbekistan CMR College of Engineering & Technology Department of Electrical and Electronics Engineering Telangana Hyderabad501401 India The Islamic University Najaf Iraq GRIET Telangana Hyderabad India

ISBN: (纸本)9798350336474

The placement of Electric Vehicle Charging Stations (EVCS) is a significant obstacle to the widespread adoption of Electric Vehicles (EVs). However, integrating EVCS with distributed Renewable Energy (RE) sources may help mitigate the variability of RE production. This article focuses on studying a Microgrid (MG) that consists of power distribution sources such as Wind Turbines (WT) and photovoltaic (PV), as well as EVCSs and Energy Storage Structures (ESS). The analysis considers the ambiguities associated with the charging needs of electric vehicles and the production of distributed Renewable Energy Sources (RES). A comprehensive optimization model is provided for computing the best Charging Stations (CS) locations equipped with distributed electricity. This model combines the electrical network and the grid to ensure efficiency and reliability. The usage variation ratio is employed to assess the level of compatibility among the uncertain production curve of RE and the charging request curves to ascertain the suitable size of the WT and photovoltaic-producing method and energy storage system. The kernel prediction function is utilized to address the problem of excessive caution in adaptable optimizing methods. A simulation is conducted on an IEEE 33-nodal energy distributing system and a 50-nodal transit network. The findings from simulations provide evidence of the model's resilience and cost-effectiveness. © 2023 IEEE.

关键词： Electric power distribution

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：