检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Gochoo, Munkhjargal Batnasan, Ganzorig Ahmed, Ahmed Abdelhadi Otgonbold, Munkh-Erdene Alnajjar, Fady Shih, Timothy K. Tan, Tan-Hsu Wee, Lai Khin United Arab Emirates University Dept. of Computer Science and Software Engineering Al Ain United Arab Emirates College of EECS National Central University Taoyuan Taiwan National Taipei University of Technology Dept. of Electrical Engineering Taipei Taiwan University of Malaya Dept. of Biomedical Engineering Kuala Lumpur Malaysia

ISBN: (纸本)9798350337020

With the rise of AI, the recognition of Sign Language (SL) through sign-to-text has gained significance in the field of computer vision and deep machine learning. However, there are only a few medium to large open datasets available for this task, as it requires a vast dataset of thousands of signs for words/phrases in different environments, which is a time-consuming and tedious process. Furthermore, there has been very little effort towards Arabic Sign Language Recognition (ArSLR). This research paper presents the results of fine-tuning the Vision Transformer (ViT) model on a small-scale in-house dataset of ArSL. The main goal is to attain satisfactory results by utilizing minimal computing power and a small dataset involving less than 10 individuals, with only one recording made for each sign in every environment. The dataset comprises 49 classes/signs, all of which were made with two hands and belong to the Level I category in terms of popularity. To enhance the dataset, three types of augmentations - translation, shear, and rotation were employed. The ViT model, pre-trained on the Kinetics dataset, was trained on the variation of augmented datasets with 2 to 40 times samples for each original video, where the training set includes original and augmented videos of 8 volunteers and the test set includes only original videos of one particular volunteer. Experimental results reveal that the combination of rotation and shear outperformed the others, achieving an accuracy of 93% on the 20 times augmented samples per class per signer dataset. We believe this study sheds light on small-scale dataset-based SLR tasks and video/action recognition in general. © 2023 IEEE.

关键词： Arabic Sign Language Augmentation Deep Learning Smale-scale dataset Vision Transformer ViT

来源：评论

学校读者我要写书评

暂无评论

MetaSPICE: Metaprogramming SPICE Framework for the Design Space Exploration of PUF Circuits

MetaSPICE: Metaprogramming SPICE Framework for the Design Sp...

引用

International Conference on Modern Circuits and Systems Technologies (MOCAST)

作者： Athanasios Xynos Vasileios Tenentes Dept. of Computer Science & Engineering University of Ioannina Greece

Silicon Physical Unclonable Functions (PUFs) generate challenge-response pairs that are unique to each die, allowing for secure identification, authentication and cryptographic keys generation. However, designing and evaluating PUFs is a complex task that can require a vast amount of SPICE netlists simulation. In this paper, we present MetaSPICE, which is a novel metaprogramming SPICE framework for the design space exploration of PUFs. Metaprogramming refers to the process of writing programs that manipulate other programs, data structures or even themselves. The designer in MetaSPICE, instead of defining multiple SPICE netlists, has to define a single SPICE template that is used to generate multiple netlists. The MetaSPICE is complementary to classical SPICE simulators, and enables the design exploration impact on PUFs’ performance. The framework consists of a template engine for generating SPICE models from SPICE templates, and software for evaluating the performance of PUF circuits in terms of uniqueness, uniformity and reliability from SPICE simulation results. We demonstrate the effectiveness of MetaSPICE by evaluating the performance and presenting improvements on a recently proposed PUF design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Healthcare Medical Imaging through EOA Optimized Hyperparameter in CNN

引用

Procedia computer science 2025年 259卷 1106-1114页

作者： Umang Kumar Agrawal Nibedan Panda Debashreet Das Asish Kumar Dalai B.V. Ramana Ayush Mishra School of Computer Engineering KIIT Deemed to be University Bhubaneswar Odisha India-751024 Dept. of Computer Science and Engineering Centre for UG and PG studies BPUT Rourkela Odisha School of Computer Science and Engineering VIT-AP University Amaravati AP India Department of IT Aditya Institute of Technology and Management Tekkali AP India-532201

Medical imaging (MI) is the prefatory field of healthcare that plays a vital role in the patient’s clinical and medical intervention. Recent developments in MI help healthcare professionals such as doctors and radiologists diagnose patients with improved quality of MI methods such as X-ray, CT and MRI scans. The upsurge of the Convolutional Neural Network (CNN) offers the latent for timely detection and classification of the disease with deeper insights. It adapts the spatial features and learns the input data hierarchically, which makes well-suited for this task. To improve the robustness of the CNN, the parameters are optimized through a nature-inspired dynamic mass balance-based metaheuristic approach named the Equilibrium Optimizer Algorithm (EOA). As a real-life implication, the suggested EOA-CNN approach has been verified by utilizing two benchmark datasets. The competence of EOA-CNN is assessed by present-day methods in terms of parameters namely accuracy, error rate, min, avg, std, accuracy, sensitivity and specificity. By streamlining the workflow, the said approach is a valuable asset conforming to the reliability to resolve healthcare imaging complications with advanced diagnostics support. This framework is being used to optimize the constraints meanwhile bridging the gaps in healthcare convenience.

关键词： EOA CNN Optimizing Parameters Healthcare Imaging Brain MRI Chest X-ray

来源：评论

学校读者我要写书评

暂无评论

An Approach of Fog Computing and Edge Computing for Computing Resources Optimization Strategies

An Approach of Fog Computing and Edge Computing for Computin...

引用

Pioneering Developments in computer science & Digital Technologies (IC2SDT), International Conference on

作者： Deepak Upadhyay Abhay Upadhyay Mridul Gupta Kunj Bihari Sharma Devansh Yadav Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798350365016

ISBN: (纸本)9798350365023

This paper investigates optimization strategies for fog and edge computing systems, focusing on the key challenges of resource allocation, load balancing, latency minimization, and power efficiency. We analyze the results of the simulation study to determine the impact and potential of our strategies and find that the improvements achieved are small to moderate, varying between 1.75% and 2.95%. This knowledge demonstrates that system optimization requires small, gradual increments and that fog and edge computing are dynamic systems. Our results suggest that optimization based on integration and adaptability can produce a significant difference in the performance and reliability of distributed systems.

关键词： System performance Focusing Minimization Load management Reliability Resource management Dynamical systems Distributed computing Optimization Edge computing

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Triple-Branch Diversity Receivers in Composite Gamma-Shadowed Rician Fading Channels with AMC and Asymmetric SNR Conditions

Performance Evaluation of Triple-Branch Diversity Receivers ...

引用

Pioneering Developments in computer science & Digital Technologies (IC2SDT), International Conference on

ISBN: (数字)9798350365016

ISBN: (纸本)9798350365023

This paper provides an in-dept. analysis of the performance enhancement resulting from AMC in triple-branch diversity receivers under composite Gamma shadowed Rician fading channels with uneven SNR conditions. This paper was able to show the level of enhancement in average SNR resulting through simulations of AMC on signal quality in several receiver branches, which clearly shows AMC's ability in alleviating fading and shadowing based degradations. The analysis revealed that AMC adequately alleviates degradations by changing modulation schemes and coding rates based on the current quality of the channel. This reinforces AMC's ability to improve the link's reliability and likelihood to optimize the efficiency of the communication channel. This makes AMC a desirable design and optimization feature for wireless communication in highly fading and shadowed environments, which makes this innovation a potential fundamental technology in the realization of robust, resilient, and adaptive communication systems.

关键词： Wireless communication Fading channels Degradation Technological innovation Adaptive systems Rician channels Modulation Receivers Encoding Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Job Applications Selection and Identification: Study of Resumes with Natural Language Processing and Machine Learning

Job Applications Selection and Identification: Study of Resu...

引用

IEEE Students' Conference on Electrical, Electronics and computer science (SCEECS)

作者： Amit Pimpalkar Aastha Lalwani Roshan Chaudhari Mohd. Inshall Mahak Dalwani Tarandeep Saluja Dept. of Computer Science Engineering JIT Nagpur India

For each job ad, the organization received a high number of applicants. Finding the right person's application from various applications is a time-consuming task for any company these days. The categorization of a representative's resume is a time-consuming, labor-intensive, and resource-intensive procedure. Natural language processing and advanced analytics can understand and analyze unstructured written material to extract the required information. The idea is to teach the machine to study text in the same manner that people do. By reviewing applications with natural language processing and machine-learning processing, we may be able to locate people with the abilities and attributes we need more quickly. This study provides a comprehensive assessment of resume selection and identifies the existing work gaps. Different algorithms for machine learning and methodologies for analyzing and interpreting unstructured data have been researched. This study also addresses the research problems and future potential of resume analysis regarding the writing style, word choice, and grammar of unstructured written communication.

关键词： Machine learning algorithms Semantic search Resumes Machine learning Syntactics Natural language processing Software

来源：评论

学校读者我要写书评

暂无评论

Blockchain Technology: Reshaping Telemedicine and Telehealth Services for Emergency Management

Blockchain Technology: Reshaping Telemedicine and Telehealth...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Neelam Singh Varsha Mittal Vandana Rawat Priyansh Kumar Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttrakhand India Dept. of Computer Applications Graphic Era Deemed to be University Dehradun Uttrakhand India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Both consumers and healthcare providers have benefited greatly from the quick development of software-based technology. The dominance of blockchains is impending as the medical care sector moves quickly towards digitization and customization. The development of blockchain provided answers to several problems that had long plagued the healthcare sector. However, not only in healthcare due to its capabilities, blockchain technology has found great success in a variety of industrial fields. The important factors propelling the growth of the healthcare blockchain market are the rise in data breaches, privacy concerns, fake pharmaceuticals, and provided answers to numerous problems that had long plagued the healthcare sector. Although telemedicine had been developing for a while, the covid-19 epidemic gave it the necessary kick. In order to facilitate social isolation, the pandemic made it necessary to expand virtual healthcare and distant therapy. Over the past year, the telemedicine market has experienced rapid expansion. In the current study, the adaptation issues and prospective prospects for blockchain technology in the telehealth and telemedicine sectors are *** on a systematic review, we have determined the existing state of the use of blockchain technology in a number of healthcare-related areas, the ideal state that would be achieved, the research gap regarding the usage of blockchain technology in a number of healthcare-related application areas, as well as a number of potential research agendas for future studies.

关键词： Pandemics Telemedicine Medical services Data breach Propulsion Emergency services Blockchains Security Systematic literature review Pharmaceuticals

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Stroke Disease Using Machine Learning Algorithms

Classification and Prediction of Stroke Disease Using Machin...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Podutur Lahari Akarsh Kumar D. Usha Nandini M. D. Anto Praveena Mercy Paul Selvan Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Using text mining tools and machine learning algorithms, the paper presents a prototype for classifying strokes. The significance of machine learning extends across various domains, including surveillance, medicine, and data management, where appropriately trained algorithms prove invaluable. The study incorporates data mining techniques, offering a comprehensive understanding of information tracking from both semantic and syntactic perspectives. By analyzing medical case sheets, the proposed approach extracts symptoms and trains the system based on that information. A total of 507 case sheets are collected at "Sugam Multispecialty Hospital" in "Kumbakonam", Tamil Nadu, India, during the data collection phase. A tagging and maximum entropy approach was used to mine these case sheets. Stroke classification relies heavily on the suggested stemmer for distinguishing between common and special features. To handle the data that has been processed, support vector machines, XG Boost algorithms, SGD algorithms, decision trees, and random forests were used as machine learning algorithms. Random Forest demonstrated the highest accuracy among stroke classification algorithms evaluated. This integration of text mining and machine learning offers a promising framework for enhancing stroke classification based on patients' symptoms extracted from medical case sheets. The synergy between these technologies provides a robust methodology that can contribute significantly to improving the efficiency and accuracy of stroke diagnosis and classification in a medical.

关键词： Text mining Machine learning algorithms Accuracy Surveillance Stroke (medical condition) Tagging Syntactics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Customer Experience, and Brand Awareness through Familiar Gameplay in Advergames

Enhancing Customer Experience, and Brand Awareness through F...

引用

2022 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2022

作者： Khezrian, Navid Farzinnejad, Forouzan Baghaei, Nilufar Coburg University of Applied Sciences Dept. Electrical Engineering and Computer Science Coburg Germany University of Queensland Dept. Information Technology and Electrical Engineering Brisbane Australia

ISBN: (纸本)9781665453059

The marketing field has been looking for more creative and effective ways to attract customers. Advergames have recently attracted a lot of attention in increasing brand awareness and attracting wider groups of audiences. Research studies have indicated that customers have a more positive attitude toward a brand and stronger purchase intentions when playing advergames with brand interactivity rather than without brand interactivity. Despite the increased use of advergames as a brand promotion strategy by a range of well-known brands, there is still a limited understanding of several issues related to the effective use of such games. In this paper, we conducted one study (n= 242) held in one exhibition to examine familiar gameplay in advergames and its effectiveness in attracting and engaging more people. Our results showed that the presence of familiar gameplay in advergames is an essential feature in attracting more people, enhancing their user experience, and increasing brand awareness. © 2022 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Systolic Array Placement on FPGAs

Systolic Array Placement on FPGAs

引用

IEEE International Conference on computer-Aided Design

作者： Hailiang Hu Donghao Fang Wuxi Li Bo Yuan Jiang Hu Dept. of Electrical and Computer Engineering Texas A&M University AMD Inc Dept. of Electrical and Computer Engineering Rutgers University Dept. of Computer Science and Engineering Texas A&M University

Systolic array designs have regained popularity in recent years, particularly for their applications in accelerating CNN (Convolutional Neural Network) computing in hardware, including on FPGAs. However, existing FPGA layout techniques are primarily designed for general-purpose applications and have not fully leveraged the regularity of systolic arrays to enhance solution quality. This paper presents a new algorithmic approach for systolic array placement on FPGAs. Our approach enables 23% – 25% wirelength reduction for CNN circuits compared to an industrial tool and state-of-the-art academic methods. Moreover, it usually leads to significantly reduced routing resource utilization, accelerated placement runtime and improved timing performance.

关键词：

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：