检索结果-内蒙古大学图书馆

Compact Model Build Upon Dynamic Weighting Artificial Neural Network Approach for Complementary Field Effect Transistors

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 246-253页

作者： Butola, Rajat Li, Yiming Kola, Sekhar Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation The Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program The Institute of Communications Engineering the Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

In this work, a dynamic weighting-artificial neural network (DW-ANN) methodology is presented for quick and automated compact model (CM) generation. It takes advantage of both TCAD simulations for high accuracy and SPICE simulations for cost-effectiveness. This methodology is developed for gate-all-around (GAA) silicon (Si) nanosheet (NS) complementary field effect transistor (CFET), a potential candidate for future CMOS technology due to its innate properties. The critical process variation (PV) sources that severely degrade the CFET performance are estimated using DW-ANN. It reduces the computation cost and predicts the effects of PV sources with less than 1% error. Furthermore, a compact DW-ANN-based Verilog-A model has been developed that captures the dc as well as transient behavior accurately for circuit-level analysis. CFET-based circuits such as inverter, 6T-static random access memory (SRAM), and ring oscillator (RO) are characterized and implemented using DW-ANN-based CM. The overall average error of the model is reported as less than 2%. Therefore, the proposed device and circuit modeling approach provides a feasible solution for the rapid compact modeling of new emerging devices with good convergence and high accuracy. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

T2Remoter: A Remote Table Tennis Coaching System Combining VR and Robotics 29

T2Remoter: A Remote Table Tennis Coaching System Combining V...

引用

29th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2023

作者： Fuchino, Kodai Al-Sada, Mohammed Nakajima, Tatsuo Waseda University Department of Computer Science and Engineering Tokyo Japan Qatar University Department of Computer Science and Engineering Doha Qatar

ISBN: (纸本)9798350337860

The spread of the new corona virus has imposed limitations on social physical interactions, increasing the importance of remote collaboration and work applications. This has especially effected tasks that require direct physical contact, such as skill-transfer. Accordingly, we have developed T2Remoter, a table tennis instruction system that combines robotics and VR. Our system consists of a VR table-tennis environment that is shared between the coach and the trainee, and a robot arm that is teleoperated by the coach and used to guide the hand-movements of the trainee. To the best of our knowledge, T2Remoter is the first teleoperated VR based table tennis training system. We conducted a series of focus groups to explore critical training routines and contexts for T2Remoter, involving 12 table tennis experts. We extract three main categories of training routines and contexts, and discuss their importance for implementation in T2Remoter. © 2023 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Social Distance and Face Mask Detection using vision-based sensors and IP cameras 3

Social Distance and Face Mask Detection using vision-based s...

引用

3rd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Vineela, A. Devi, G. Lavanya Deekshit, G. Vinay GMR Institute of Technology Department of Computer Science and Engineering Rajam India Department of Computer Science and System Engineering Vishakhapatnam India

ISBN: (纸本)9781665494007

Healthcare systems all over the world are strained as the COVID-19 pandemic's spread becomes more widespread. The only realistic strategy to avoid asymptomatic transmission is to monitor social distance, as there are no viable medical therapies or vaccinations for it. A unique computer vision-based framework that uses deep learning is to analyze the images that are needed to measure social distance. This technique uses the key point regressor to identify the important feature points utilizing the Visual Geometry Group (VGG19) which is a standard Convolutional Neural Network (CNN) architecture having multiple layers, MobileNetV2 which is a computer vision network that advances the-state-of-art for mobile visual identification, including semantic segmentation, classification and object identification. VGG19 and MobileNetV2 were trained on the Kaggle dataset. The border boxes for the item may be seen as well as the crowd is sizeable, and red identified faces are then analyzed by MobileNetV2 to detect whether the person is wearing a mask or not. The distance between the observed people has been calculated using the Euclidian distance. Pretrained models like (You only look once) YOLOV3 which is a real-time object detection system, RCNN, and Resnet50 are used in our embedded vision system environment to identify social distance on images. The framework YOLOV3 performs an overall accuracy of 95% using transfer learning technique runs in 22ms which is four times fast than other predefined models. In the proposed model we achieved an accuracy of 96.67% using VGG19 and 98.38% using MobileNetV2, this beats all other models in its ability to estimate social distance and face mask. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis on Covid-19 data Using BERT Model

Sentiment Analysis on Covid-19 data Using BERT Model

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： ArunKarthi, T. Shanthi, S. Nirmaladevi, K. Ashwinth, K. Dev, R.B. Rajkumar, N. Computer Science And Engineering Kongu Engineering College Erode India Psna College Of Engineering And Technology Department Of Computer Applications Tamilnadu Dindigul India

ISBN: (纸本)9798350371567

In a world where microblogging has become an integral part of modern life., the sudden outbreak of COVID-19 swiftly infiltrated public opinion on various social networking platforms. With individuals adhering to social distancing measures and self-isolation protocols to combat the coronavirus, expressing their fears and concerns on social media became their primary outlet. In order to obtain a thorough comprehension of the pandemic's effects on individuals' lives and the environments in which they live, we must recognize the critical function of social media as a repository of emotions. This paper delves into the realm of sentiment analysis, focusing on the opinions disseminated through Twitter. Our primary dataset comprises these tweets, which we meticulously processed and converted into tokens for analysis. We performed fine-tuning and added an additional classifier layer to BERT, a pre-trained model, in order to classify these feelings into three categories: positive, negative, and neutral. Subsequently, we scrutinized BERT's performance in carrying out this task. Impressively, the BERT model demonstrated an outstanding accuracy rate of 94 percent on our dataset, supplemented by commendable scores in various evaluation metrics. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Review on Donor Selection in Hematopoietic Stem Cell Transplantation (HSCT) 4

A Review on Donor Selection in Hematopoietic Stem Cell Trans...

引用

4th International Conference on Communication, Computing and Industry 6.0, C216 2023

作者： Rashmi, D. Clara Kanmani, A. Department of Computer Science Engineering Presidency University Bengaluru India Department of Computer Science & Engineering PES University Bangalore India

ISBN: (纸本)9798350327328

In the healthcare industry today, machine learning techniques are extensively employed for disease detection, prognosis, and therapy. These methods find use in the domain of Hematopoietic Stem Cell Transplantation (HSCT), a treatment for hematological malignancies that may prove to be curative. A thorough analysis of the use of machine learning (ML) techniques in the context of HSCT was carried out in this article. Using the databases from IEEE Xplore, Web of science, PubMed, and Scopus, a systematic review of English papers was carried out. Hematopoietic stem cell transplantation (HSCT), machine learning and artificial intelligence were among the search terms used. This review included a methodical analysis of machine learning methods used in HSCT. The evidence is not strong enough to establish what minimal data variables are needed, or what ML technique is best to utilize in the HCT situation. In recent years, stem cell therapy has become a focus of very promising and progressive scientific research. There are great expectations for the development of treatments. A framework/model will be developed to match the HLA (Human Leukocyte Antigen) between unrelated donor and patient in Hematopoietic Stem Cell Transplantation (HSCT). Stem cell recordings are collected from donors at the Biomedical Research Center and the data are analyzed. Final results will help determine donor eligibility. © 2023 IEEE.

关键词： Stem cells

来源：评论

学校读者我要写书评

暂无评论

QMCS-IAS: Quantum mechanism and compression sensing-based image authentication and security technique

引用

Multimedia Tools and Applications 2024年 1-27页

作者： Singh, Ranjeet Kumar Tripathi, Kuldeep Narayan Kaur, Gagandeep Agrawal, Rohit Department of Computer Science and Engineering Madhav Institute of Technology & ampScience Race Course Road MP Gwalior474005 India

Ensuring the security and protection of digital content transmitted over a network is a critical challenge, as data can take various forms, such as text, images, audio, and videos, all of which can be easily manipulated by hackers. Watermarking is one of the practical approaches to address data authentication, copyright protection, and document ownership issues. The primary objective of this research is to develop hybrid watermark encryption and as well as compression of watermark embedding mechanism that ensures secure and efficient watermarking of images using quantum chaos maps and discrete wavelet transformation. This study also introduces a novel dual watermarking approach combining quantum chaos-based encryption and discrete wavelet transformation to achieve robust watermark embedding, also its maintain the capacity of watermarked images. The method involves encrypting watermark components using measurement matrices derived from quantum chaos maps, followed by pixel exchange procedures and embedding into specific frequency sub-bands of the host image, thereby enhancing both the security and quality of watermarking. The objective of this work is to maintain the capacity of watermarked images during the dual embedding process using a compression mechanism. Experimental results show the proposed approach consistently outperforms the existing approach in terms of watermark image quality and robustness. The correlation coefficient (CC) coefficients for the proposed algorithm generally range between 0.95 and 0.99, indicating superior watermark preservation and retrieval capabilities. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Design & Implementation of API Based Software Defined Networking Architecture 26

Design & Implementation of API Based Software Defined Networ...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Nayeem, Tanvir Ahamed Uddin, Md. Riaz Rahman, Md. Habibur Islam, Md. Samiul Dhaka International University Department of Computer Science & Engineering Dhaka Bangladesh University of Dhaka Department of Computer Science & Engineering Dhaka Bangladesh State University of Bangladesh Department of Computer Science & Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Software Defined Networking known as SDN appeared to provide automation across any network system. The SDN architecture is designed to build a flexible and manageable network comparing to traditional networking system. Besides, the SDN plays a vital role in network virtualization, cloud computing, mobility, and programmability to make an efficient network system whereas the traditional networking system has some limitations. In this paper, an SDN architecture has been proposed with API integration using python library on Linux based OpenDaylight framework. The comparative results show that the performance of the proposed SDN architecture is much better than traditional network architecture considering data flow, automated IP address generation, packet transmission consistency. © 2023 IEEE.

关键词： API Data flow IoT IP address Linux OpenDaylight Python Software Defined Networking

来源：评论

学校读者我要写书评

暂无评论

Highly Differentiated Target Detection under Extremely Low-Light Conditions Based on Improved YOLOX Model

引用

computer Modeling in engineering & sciences 2024年第8期140卷 1507-1537页

作者： Haijian Shao Suqin Lei Chenxu Yan Xing Deng Yunsong Qi School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas VegasNV89154USA Zhejiang Geely Automobile Research Institute Ningbo315336China

This paper expounds upon a novel target detection methodology distinguished by its elevated discriminatory efficacy,specifically tailored for environments characterized by markedly low luminance *** methodologies struggle with the challenges posed by luminosity fluctuations,especially in settings characterized by diminished radiance,further exacerbated by the utilization of suboptimal imaging *** envisioned approach mandates a departure from the conventional YOLOX model,which exhibits inadequacies in mitigating these *** enhance the efficacy of this approach in low-light conditions,the dehazing algorithm undergoes refinement,effecting a discerning regulation of the transmission rate at the pixel level,reducing it to values below 0.5,thereby resulting in an augmentation of image ***,the coiflet wavelet transform is employed to discern and isolate high-discriminatory attributes by dismantling low-frequency image attributes and extracting high-frequency attributes across divergent *** utilization of CycleGAN serves to elevate the features of low-light imagery across an array of stylistic *** computational methodologies are then employed to amalgamate and conflate intricate attributes originating from images characterized by distinct stylistic orientations,thereby augmenting the model’s erudition *** validation conducted on the PASCAL VOC and MS COCO 2017 datasets substantiates pronounced *** refined low-light enhancement algorithm yields a discernible 5.9%augmentation in the target detection evaluation index when compared to the original *** Average Precision(mAP)undergoes enhancements of 9.45%and 0.052%in low-light visual renditions relative to conventional YOLOX *** envisaged approach presents a myriad of advantages over prevailing benchmark methodologies in the realm of target detection within environments marked by an acute scarcity of lumi

关键词： Target detection extremely low-light wavelet transformation highly differentiated features YOLOX

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Diagnosis From Smartphone Captured Fundus Images Using Deep Learning 11

Glaucoma Diagnosis From Smartphone Captured Fundus Images Us...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Madhu, K. John, Shinu Mathew Joseph, Asha Abraham, Bejoy APJ Abdul Kalam Technological University Computer Science and Engineering Thiruvananthapuram India St.Thomas College of Engineering and Technology Mattannur Department of Computer Science and Engineering Mattannur India Amal Jyothi College of Engineering Department of Information Technology Kottayam India College of Engineering Muttathara Department of Computer Science and Engineering Thiruvananthapuram India

ISBN: (纸本)9798350379136

The retina contains millions of photoreceptive cells called cones, rods, and blood vessels that nourish these cells. The optic nerve carries visual information from the retina to the brain. Glaucoma is a condition, where optic nerves get damaged often caused by high pressure within the eye. Fundus images provide rich information about the appearance of a patient's retina and optic nerve head region. Even though there are various painless diagnosis methods, conventional fundus photography using Retcams is the most commonly used one. Examinations of the fundus images for structural abnormalities in the optic nerve head region such as increased cup-to-disc ratio, NRR thinning, and Violation of the ISNT rule provide sufficient evidence for the presence of glaucoma. However, conventional fundus imaging costs a lot concerning equipment and operation costs. Nowadays, smartphones can capture retina images and are a cheaper alternative to conventional fundus imaging using retcam devices. So our approach is to analyze smartphone-captured fundus images (SCFI) to detect the presence of glaucoma and provide accurate results at a lower cost. We designed an automated one-step approach-based glaucoma detection system that can detect the presence of glaucoma from smartphone-based fundus images with an accuracy of 93 percent. using a deep learning-based approach, The publicly available smartphone-captured fundus image dataset, BrG is used for conducting ablation studies. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

ViT-SENet-Tom: machine learning-based novel hybrid squeeze–excitation network and vision transformer framework for tomato fruits classification

引用

Neural Computing and Applications 2025年第9期37卷 6583-6600页

作者： Swapno, S M Masfequier Rahman Nobel, S. M. Nuruzzaman Islam, Md Babul Bhattacharya, Pronaya Mattar, Ebrahim A. Department of CSE Bangladesh University of Business and Technology Dhaka1216 Bangladesh Department of Computer Modeling Electronic and System Engineering UNICAL Rende Italy Department of Computer Science and Engineering Amity School of Engineering and Technology and Research and Innovation Cell Amity University West Bengal Kolkata India Robotics - Cybernetic College of Engineering University of Bahrain Manama Bahrain

Tomatoes are essential fruits in numerous nations for their vast demand. It is very important to maintain the freshness of tomatoes. One of the primary challenges in the recent culinary landscape is accurately identifying healthy tomatoes while effectively eliminating damaged or rejected ones. Existing approaches employ various strategies for categorizing tomato fruit, but they often suffer from inaccuracies, slow detection, and suboptimal performance. Thus, motivated by this gap, in this paper, we propose a novel machine learning (ML) framework, ViT-SENet-Tom, which is a hybrid vision transformer (ViT) model with squeeze and excitation (SENet) block network for fast, accurate, and efficient tomato fruit classification. The framework works on three tomato classes, respectively, the ripe, unripe, and reject. In developing the proposed model, we utilized advanced and newly designed layers and functions. This integration created a more complex and sophisticated neural network, significantly enhancing efficiency and contributing to the model’s novelty. Our chosen dataset was small initially, but we implemented augmentation techniques to increase its size. This approach made our system more reliable, efficient, and effective. The hybrid ViT-SENet framework employs encoders and self-attention networks with squeeze and excitation channel functions to allow precise, robust, fast, and efficient tomato classification. In simulation, the framework achieves a training accuracy of 99.87% and validation accuracy of 93.87%, indicating the precise classification of tomatoes. Besides, this work tests accuracy using fivefold cross-validation. The highest accuracy seen at fold-5 is 99.90%. These testing results demonstrate the efficacy of the proposed framework in real-deployment scenarios. The implementation has the potential to provide enhanced and more sustainable food security and safety in future. © The Author(s) 2025.

关键词： Fruits

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：