检索结果-内蒙古大学图书馆

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Junyao Wang Hanning Chen Mariam Issa Sitao Huang Mohsen Imani Department of Computer Science University of California Irvine CA United States Department of Electrical Engineering and Computer Science University of California Irvine CA United States

ISBN: (纸本)9798350323481

Cybersecurity has emerged as a critical challenge for the industry. With the large complexity of the security landscape, sophisticated and costly deep learning models often fail to provide timely detection of cyber threats on edge devices. Brain-inspired hyperdimensional computing (HDC) has been introduced as a promising solution to address this issue. However, existing HDC approaches use static encoders and require very high dimensionality and hundreds of training iterations to achieve reasonable accuracy. This results in a serious loss of learning efficiency and causes huge latency for detecting attacks. In this paper, we propose CyberHD, an innovative HDC learning framework that identifies and regenerates insignificant dimensions to capture complicated patterns of cyber threats with remarkably lower dimensionality. Additionally, the holographic distribution of patterns in high dimensional space provides CyberHD with notably high robustness against hardware errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polarization-independent ultra-sensitive graphene sensor for the detection of prostate-specific antigen

引用

Optik 2025年 322卷

作者： Rafighirani, Yousef Javidan, Javad Heidarzadeh, Hamid Department of Electrical and Computer Engineering University of Mohaghegh Ardabili Ardabil Iran

This study presents a three-band absorbent structure based on cut graphene, which has been used as a biosensor for the detection of prostate-specific antigen (PSA) due to the tunability of the resonance frequency of graphene and the polarization-independent capability of the proposed structure. The sensor is composed of three layers: a copper substrate with a conductivity of 5.831 ×107, a silicon dioxide (SiO₂) dielectric layer with a permittivity of 3.9, and a graphene layer with strategic cuts to enhance absorption. The performance of the proposed structure was evaluated by measuring its absorption at three terahertz frequency bands: 3.9 THz, 8.52 THz, and 11.83 THz, achieving absorption values of 99.65 %, 99.25 %, and 99.78 %, respectively. These high absorption rates make the sensor an excellent candidate for biosensing applications, particularly for detecting PSA in clinical samples. By testing the sensor with analytes containing PSA at 100, 200, 300, and 400 PM concentrations, the refractive index values were 1.3477, 1.3654, 1.3831, and 1.4008, respectively. When the analyte layer is placed on the three-band absorber structure, the peak shift is absorbed, enabling the detection of the desired analyte. The proposed structure demonstrated remarkable sensitivity, achieving 2638.4 GHz/RIU at a refractive index of 1.3831 and a frequency of 11.451 THz. This high sensitivity is particularly advantageous for detecting low concentrations of analytes. Such a sensor has great potential for enhancing the detection of biomarkers. These findings highlight the sensor's potential for high-sensitivity PSA detection, offering a valuable tool for early prostate cancer diagnosis and screening. © 2025 Elsevier GmbH

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Silicon Carbide Power Devices: Evolution, Applications, and Future Opportunities

IEEE Electron Devices Magazine

引用

IEEE Electron Devices Magazine 2025年第4期2卷 30-35页

作者： Mikael Östling School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Kista-Stockholm Sweden

This review discusses the evolution and development of SiC Device technology over the past 30 years and shows opportunities in improving power efficiency by employing SiC devices in power electrical systems applicatio... 详细信息

关键词： Thermal management of electronics Fabrication Power system measurements Silicon carbide Reviews Green products Silicon Power electronics Reliability Material properties

来源：评论

学校读者我要写书评

暂无评论

Automated Aeroponics System: IoT-Based Monitoring and Control for Optimized Plant Growth 4

Automated Aeroponics System: IoT-Based Monitoring and Contro...

引用

4th International Conference on Power, Control and Computing Technologies, ICPC2T 2025

作者： Tanna, Rajesh Santhosh, Talada Gollavilli, Sanjay Kumar Demudu, Lagudu Suri Naik, Ratala Koteswara Raghuram, Cheepurupalli Department of Electrical and Electronics Engineering Vignan's Institute of Information Technology Visakhapatnam530049 India Department of Electrical and Electronics Engineering Visakha Institute of Engineering & Technology Visakhapatnam530027 India Department of Electrical and Electronics Engineering Vignan's Institute of Engineering for Women Visakhapatnam530046 India Department of Electrical and Electronics Engineering A. M. Reddy Memorial College of Engineering and Technology Narasaraopet522601 India Department of Computer Science and Engineering Sagi Rama Krishnam Raju Engineering College Bhimavaram534204 India

ISBN: (纸本)9798331530402

Challenges of farming are getting worse due to pests, other environmental issues, and changes in the climate. Several novel technologies have been developed to improve plant growth and productivity, yet there are still numerous issues in this field. This suggests that daily improvements are needed. This paper provides an innovative automated system that uses a variety of environmental sensors, including as pH, TDS, and humidity, for hydroponics and aeroponics. These sensors continuously monitor and modify crucial components to provide the perfect growth environment. In addition, the system has autonomous nutrient dosing, which reduces the need for human intervention and boosts overall effectiveness. Better control over the farming process is made possible by the system's ability to scale and monitor in real-time thanks to the integration of IoT technologies. The study also looks at how machine learning (ML) and artificial intelligence (AI) might improve crop health monitoring and growth forecasts. Additionally, an LED-lit indoor farming setup is included in the system. © 2025 IEEE.

关键词： Agricultural robots

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation Using Generative Adversarial Networks for Medical Image Synthesis 5th

Domain Adaptation Using Generative Adversarial Networks for ...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Ganesh, D. Verma, Upendra K. Patil, Smita Alam, Intekhab Karnataka Bangalore India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India 3School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Latest advancements in state-of-the-art scientific photograph evaluation depend heavily on the availability of large new datasets of cutting-edge annotated scientific photographs for version training. Unfortunately, obtaining massive samples of cutting-edge categorized scientific picas is ultra-modern high-priced, or impossible. Area edition is a way to generalize a version educated on a selected dataset to a brand new area, wherein the model turned into not directly educated. Generative adverse Networks (GANs) were used to generate realistic artificial photographs. It has enabled the opportunity present day the usage of GANs to bridge the domain hole via generating artificial medical photos, which could then be used for education fashions. On this paper;we evaluate the latest progress in making use of area edition the use of GANs for scientific photosynthesis, with an emphasis on applications including pathology, scientific imaging, and optical acceptable imaging. We talk about the benefits of ultra-modern using GANs for area adaptation and present processes for each present day of the above programs. We also speak about various challenges and future directions in this field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Generative AI for the Optimization of Next-Generation Wireless Networks: Basics, State-of-the-Art, and Open Challenges

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Khoramnejad, Fahime Hossain, Ekram University of Manitoba Department of Electrical and Computer Engineering WinnipegMB Canada

Next-generation (xG) wireless networks, with their complex and dynamic nature, present significant challenges to using traditional optimization techniques. Generative Artificial Intelligence (GAI) emerges as a powerful tool due to its unique strengths. Unlike traditional optimization techniques and other machine learning methods, GAI excels at learning from real-world network data, capturing its intricacies. This enables safe, offline exploration of various configurations and generation of diverse, unseen scenarios, empowering proactive, data-driven exploration and optimization for xG networks. Additionally, GAI's scalability makes it ideal for large-scale xG networks. This paper surveys how GAI-based models unlock optimization opportunities in xG wireless networks. We begin by providing a review of GAI models and some of the major communication paradigms of xG (e.g., Sixth Generation) wireless networks. We then delve into exploring how GAI can be used to improve resource allocation and enhance overall network performance. Additionally, we briefly review the networking requirements for supporting GAI applications in xG wireless networks. The paper further discusses the key challenges and future research directions in leveraging GAI for network optimization. Finally, a case study demonstrates the application of a diffusion-based GAI model for load balancing, carrier aggregation, and backhauling optimization in non-terrestrial networks, a core technology of xG networks. This case study serves as a practical example of how the combination of reinforcement learning and GAI can be implemented to address real-world network optimization problems. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Toward a Low-Cost Perception System in Autonomous Vehicles: A Spectrum Learning Approach

arXiv

引用

arXiv 2025年

作者： Alsakabi, Mohammed Erickson, Aidan Dolan, John M. Tonguz, Ozan K. Department of Electrical and Computer Engineering College of Engineering The Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States

We present a cost-effective new approach for generating denser depth maps for Autonomous Driving (AD) and Autonomous Vehicles (AVs) by integrating the images obtained from deep neural network (DNN) 4D radar detectors with conventional camera RGB images. Our approach introduces a novel pixel positional encoding algorithm inspired by Bartlett’s spatial spectrum estimation technique. This algorithm transforms both radar depth maps and RGB images into a unified pixel image subspace called the Spatial Spectrum, facilitating effective learning based on their similarities and differences. Our method effectively leverages high-resolution camera images to train radar depth map generative models, addressing the limitations of conventional radar detectors in complex vehicular environments, thus sharpening the radar output. We develop spectrum estimation algorithms tailored for radar depth maps and RGB images, a comprehensive training framework for data-driven generative models, and a camera-radar deployment scheme for AV operation. Our results demonstrate that our approach also outperforms the state-of-the-art (SOTA) by 27.95% in terms of Unidirectional Chamfer Distance (UCD). © 2025, CC BY-NC-ND.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

T-CacheNet: Transformer-based Deep Reinforcement Learning for Next-Generation Internet Content Caching 24

T-CacheNet: Transformer-based Deep Reinforcement Learning fo...

引用

13th International Conference on Networks, Communication and Computing, ICNCC 2024

作者： Kim, Hakho Sun, Teh-Jen Huh, Eui-Nam Department of Artificial Intelligence Kyung Hee University Yongin Korea Republic of Department of Computer Science and Engineering Kyung Hee University Yongin Korea Republic of

ISBN: (纸本)9798400717352

The rapid growth of internet users and mobile data traffic has led to increasing demand for efficient content caching strategies. Traditional caching algorithms such as Least Recently Used (LRU) and Least Frequently Used (LFU) struggle to adapt to dynamic environments, resulting in frequent cache misses, inefficient content retrieval, and degraded user experience. A key challenge in content caching is deciding both whether to cache newly requested content and which cached content to replace when capacity is limited. Reinforcement learning (RL)-based approaches offer a dynamic solution by continuously optimizing these decisions based on real-time content demand. In this paper, we propose T-CacheNet, a Transformer-based RL model for content caching, leveraging the self-attention mechanism to effectively manage long-term dependencies in content requests. We introduce two techniques - Miss-based delayed hit reward learning and partial information learning - to address the computational challenges of Transformer models while maintaining high efficiency in making caching and replacement decisions. T-CacheNet significantly improves adaptability in dynamic content delivery networks by increasing cache hit rates and preventing inefficient resource utilization. © 2024 Copyright held by the owner/author(s).

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Partial Discharges in Oil-Impregnated Transformer Paper Insulation and PET-G Insulation

IEEE Open Journal of Instrumentation and Measurement

引用

IEEE Open Journal of Instrumentation and Measurement 2025年 4卷

作者： Kameli, Sayed Mohammad Abuelrub, Abdelaziz AlShaikh Saleh, Mohammad Refaat, Shady S. Ghrayeb, Ali Abu-Rub, Haitham Olesz, Marek Texas A&M University at Qatar Electrical and Computer Engineering Department Doha Qatar Texas A&M University Department of Electrical and Computer Engineering College StationTX77843 United States University of Hertfordshire School of Physics Engineering and Computer Science Department of Engineering HatfieldAL10 9EU United Kingdom Hamad Bin Khalifa University Qatar Foundation Electrical and Computer Engineering Program in College of Science and Engineering Doha Qatar Gdańsk University of Technology Department of Electrical Power Engineering Gdańsk80-233 Poland

Partial discharge (PD) is a widespread phenomenon instigated in power transformer (PT) insulation systems. PDs are triggered by voids that vary in size and position within the PT insulation. The electrical characteristics of those damaging, PD-causing cavities must be well understood, to accelerate the development of advanced PD detection techniques. Thus, the impact of varying the radius and position of spherical air voids on the characteristics of PDs in PTs is examined using a 3-D finite element analysis (FEA) model designed in COMSOL Multiphysics. The spherical voids are positioned between two windings of a 512 kV, three-phase (3φ ) PT. The peak electric field (EF) and aggregate energy in the FEA model are used in conjunction with laboratory measurements of the apparent discharge magnitude, for detailed analysis of Polyethylene Terephthalate Glycol (PET-G)-based cylindrical voids with different heights. Simulations demonstrate that the inception of PD activity in the PT model occurs for spherical voids with a radius exceeding 1 mm. Furthermore, the most severe PDs occur within the press-board insulation, adjacent to the uppermost part of the innermost windings. Experiments demonstrate that a significant increase in PD activity was observed for PET-G-based cylindrical voids with heights exceeding 1 mm. © 2022 IEEE.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Decoupling feature-driven and multimodal fusion attention for clothing-changing person re-identification

引用

Artificial Intelligence Review 2025年第8期58卷 1-26页

作者： Ding, Yongkang Wang, Xiaoyin Yuan, Hao Qu, Meina Jian, Xiangzhou College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Electronic Information Technology East China Normal University Shanghai200241 China Department of Electrical and Computer Engineering Carnegie Mellon University CA94035 United States School of Electronic and Information Harbin Institute of Technology Harbin150001 China Department of Mechanical Engineering Columbia University NY10027 United States

Person Re-Identification (ReID) plays a crucial role in intelligent surveillance, public safety, and intelligent transportation systems. However, clothing variation remains a significant challenge in this field. To address this issue, this paper introduces a method named Decoupling Feature-Driven and Multimodal Fusion Attention for Clothing-Changing Person Re-Identification (DM-ReID). The proposed approach employs a dual-stream feature extraction framework, consisting of a global RGB image feature stream and a clothing-irrelevant feature enhancement stream. These streams respectively capture comprehensive appearance information and identity features independent of clothing. Additionally, two feature fusion strategies are proposed: firstly, an initial fusion of RGB features and clothing-irrelevant features is achieved through the Hadamard product in the mid-network stage to enhance feature complementarity;secondly, a multimodal fusion attention mechanism is integrated at the network’s end to dynamically adjust feature weights, further improving feature representation capabilities. To optimize model performance, a composite loss function combining identity loss and triplet loss is utilized, effectively enhancing the model’s discriminative ability and feature distinctiveness. Experimental results on multiple public datasets, including PRCC, LTCC, and VC-Clothes, demonstrate that DM-ReID surpasses most existing mainstream methods in Rank-1 accuracy and mean Average Precision (mAP) metrics under clothing-changing scenarios. These findings validate the method’s effectiveness and robustness in handling complex clothing variations, highlighting its promising prospects for practical applications. © The Author(s) 2025.

关键词： Multimodal transportation

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：