检索结果-内蒙古大学图书馆

2nd international Conference on Robotics and Artificial intelligence, RoAi 2021

作者： Aliyev, samir Almisreb, Ali Abd turaev, sherzod Department of IT Infrastructure Solution R.I.S.K. Company BakuAZ1022 Azerbaijan Department of Computer Science and Engineering International University of Sarajevo Sarajevo71210 Bosnia and Herzegovina Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain United Arab Emirates

sign Language recognition is one of the essential and focal areas for researchers in terms of improving the integration of speech and hearing-impaired people into common society. the main idea is to detect the hand gestures of impaired people and convert them to understandable formats, such as text by leveraging advanced approaches. in this paper, we present our contribution to the improvement of Azerbaijani sign Language (AzsL). We worked on AzsL Alphabet static signs real-time recognition. the method applied in this work is Object Classification and Recognition by leveraging pre-trained lightweight Convolutional Neural Networks models. At first, a dataset containing near to 1000 images has been collected, then interesting objects on images have been labeled with bounding boxing option. to build, train, evaluate and deploy the relevant model, tensorFlow Object Detection APi with Python has been employed. MobileNet v2 pre-trained model has been leveraged for this task. in the trial experiment with four sign classes (A, B, C, E) and 5000 step numbers 15.2% training loss and 83% evaluation mean average precision results have been obtained. in the next step of model deployment experiments with all 24 static signs of AzsL, 49700 and 27700 steps (180 and 100 epochs, respectively) 6.4% and 18.2% training losses, 66.5% and 71.6% mAP outcomes gained, respectively. © Published under licence by iOP Publishing Ltd.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Ai for Disaster Management: Predictive Models and Response strategies

AI for Disaster Management: Predictive Models and Response S...

引用

Pervasive Computational technologies (iCPCt), international Conference on

作者： A. shameem Devupalli saroja Damodar s. Hotkar Bijaya Bijeta Nayak Anand Pandey sachin tripathi AMET Business School AMET University Department of Computer Science and Engineering Vignan's Institute of Information Technology (A) Visakhapatnam Department of Computer Science and Engineering R.T.E. Society's Rural Engineering College Hulkoti Karnataka School of Mechanical Engineering KIIT Deemed to be University Bhubaneswar Odisha Computer Science and Application Sharda University Greater Noida U.P India Symbiosis Law School Nagpur Symbiosis International (Deemed) University (SIU) WATHODA Nagpur Maharashtra India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

the application of artificial intelligence (Ai) in managing severe weather events has become more necessary in recent years owing to their increased frequency. Disaster management is required to control and avoid such occurrences. to successfully aid in better and quicker reactions to catastrophes, Ai is widely employed in prediction and disaster preparation, damage mitigation and minimization, and rescue phases. to determine how Ai technology can be used to lessen the damaging impacts of different disasters, this article looks into the potential for connecting artificial intelligence methods based on technological innovation. the study potentially contributes in designing an effective framework for disaster management based on the predictive accuracy and response time.

关键词： technological innovation storms Disasters Prevention and mitigation Disaster management Predictive models software time factors Personnel Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Optical Character Recognition (OCR) in Handwritten Characters Using Convolutional Neural Networks to Assist in Exam Reader system

Optical Character Recognition (OCR) in Handwritten Character...

引用

Advancement in Computation & computer technologies (inCACCt), international Conference on

作者： P L Lekshmy s. Velmurugan indra Kumari s. Kayalvili B. teja sree P. Karthik Kumar Department of Computer Science and Engineering LBS Institute of Technology for Women Kerala India Department of Electronics and Communication Engineering T.J.S. Engineering College Chennai Tamil Nadu India Department of Machine Learning Data Research Applied AI Korea National University of Science and Technology (UST) Daejeon South Korea Department of Artificial Intelligence Kongu Engineering College (Autonomous) Erode Tamilnadu India Department of Information Technology S.R.K.R. Engineering College Chinaamiram Bhimavaram Andhra Pradesh India Department of Computer Science and Engineering (Cyber Security) Karpagam College of Engineering Coimbatore India

ISBN: (数字)9798350371314

ISBN: (纸本)9798350371321

this work aimed to develop a character recognition method to facilitate the correction of answer cards in the Multiprova software through the development of a response card analysis flow that would culminate in the recognition of letters written by students and automatic correction of the tests. to isolate and identify the answers written on the answer cards, image segmentation techniques were used based on fixed marks printed on the cards. to recognize the letters and numbers written on the cards, trained three convolutional neural networks (for digits, letters and true or false). the results achieved (98.84% accuracy for digit CNN, 98.38% accuracy for letter CNN and 99.89% accuracy for true or false CNN) point out a great average success rate.

关键词： training image segmentation image recognition Codes Optical character recognition Neural networks streaming media

来源：评论

学校读者我要写书评

暂无评论

Particle swarm optimization with local search for height-map surface reconstruction from point clouds in reverse engineering

引用

Neural Computing and Applications 2024年 1-20页

作者： Gálvez, Akemi Fister, iztok Deb, suash Fister, iztok iglesias, Andrés Dept. of Applied Mathematics and Computational Sciences E.T.S.I. Caminos Canales y Puertos University of Cantabria Avda. de los Castros s/n Santander39005 Spain Faculty of Pharmaceutical Sciences Toho University 2-2-1 Miyama Funabashi274-8510 Japan Faculty of Electrical Engineering and Computer Science University of Maribor Koroska cesta 34 Maribor2000 Slovenia IT & Educational Consultant Ranchi India Distinguished Professorial Associate Decision Sciences and Modeling Program Victoria University Melbourne Australia

surface reconstruction is a classical process in industrial engineering and manufacturing, particularly in reverse engineering, where the goal is to obtain a digital model from a physical object. For that purpose, the real object is typically scanned or digitized and the resulting point cloud is then fitted to mathematical surfaces through numerical optimization. the choice of the approximating functions is crucial for the accuracy of the process. Real-world objects such as manufactured workpieces often require complex nonlinear approximating functions, which are not well suited for standard numerical methods. in a previous paper presented at the isMsi 2023 conference, we addressed this issue by using manually selected approximation functions via optimization through the cuckoo search algorithm with Lévy flights. Building upon that work, this paper presents an enhanced and extended method for surface reconstruction by using height-map surfaces obtained through a combination of exponential, polynomial and logarithmic functions. A feasible approach for this goal is to consider continuous bivariate distribution functions, which ensures consistent models along with good mathematical properties for the output shapes, such as smoothness and integrability. However, this approach leads to a difficult multivariate, constrained, multimodal continuous nonlinear optimization problem. to tackle this issue, we apply particle swarm optimization, a popular swarm intelligence technique for continuous optimization. the method is hybridized with a local search procedure for further improvement of the solutions and applied to a benchmark of 15 illustrative examples of point clouds fitted to different surface models. the performance of the method is analyzed through several computational experiments. the numerical and graphical results show that the method is able to recover the shape of the point clouds accurately and automatically. Furthermore, our approach outperforms other alternati

关键词： Particle swarm optimization (PsO)

来源：评论

学校读者我要写书评

暂无评论

CNNs in Crop Care: A Comparative Analysis of tomato Disease Detection Models 2

CNNs in Crop Care: A Comparative Analysis of Tomato Disease ...

引用

2nd international Conference on Cyber Resilience, iCCR 2024

作者： Ali, Ali M Nashwan, shadi Al-Qerem, Ahmad Aldweesh, Amjad Alauthman, Mohammad Elgamal, Zenab Almomani, Ammar AlAhliyya Amman University Faculty Of Engineering Communications And Computer Engineering Department Amman19328 Jordan Faculty Of Information Technology Cybersecurity Department Amman11831 Jordan Zarqa University Faculty Of Information Technology Computer Science Department Zarqa13110 Jordan College Of Computing And It Shaqra University Shaqra Saudi Arabia University Of Petra Faculty Of Information Technology Department Of Information Security Amman Jordan School Of Computing Skyline University College University City Of Sharjah Sharjah United Arab Emirates School Of Computing Skyline University College Sharjah United Arab Emirates AlHuson University College AlBalqa Applied University I.T. Department Irbid Jordan

ISBN: (纸本)9798350394962

timely and accurate detection of plant diseases is critical for sustainable crop production. this paper presents a comparative analysis of convolutional neural network (CNN) models for automated tomato leaf disease detection, including VGG16, VGG19, AlexNet and Google Net. A dataset of tomato leaf images with multiple disease types was utilized to train and test the performance of each CNN architecture. Our results demonstrate that the VGG16 model achieved the highest accuracy of 99.38% in classifying tomato leaf diseases. Compared to AlexNet and VGG19 models which obtained 98.67% and 99.29% accuracy respectively, the superior performance of VGG16 highlights its suitability for deploying robust tomato disease detection systems to enable prompt disease control interventions. Our work provides valuable insights on harnessing deep learning for agricultural disease surveillance, allowing farmers and agronomists to identify crop infections early and implement timely management practices to reduce yield losses. © 2024 iEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Dense Feed-Forward Neural Networks

SSRN

引用

ssRN 2023年

作者： Balderas, Luis Lastra, Miguel Benítez, Jose M. Department of Computer Science and Artificial Intelligence DiCITS iMUDS DaSCI E.T.S.I.I. University of Granada Spain Department of Software Engineering DiCITS iMUDS DaSCI E.T.S.I.I. University of Granada Spain

Deep learning models have been widely used during the last decade due to their outstanding learning and abstraction capacities. However, one of the main challenges any scientist has to face using deep learning models is to establish the network’s architecture. Due to this difficulty, data scientists usually build over complex models and, as a result, most of them result computationally intensive and impose a large memory footprint, generating huge costs, contributing to climate change and hindering their use in computational-limited devices. in this paper, we propose a novel feed-forward neural network constructing method based on pruning and transfer learning. its performance has been thoroughly assessed in classification and regression problems. Without any accuracy loss, our approach can compress the number of parameters by more than 70%. Even further, choosing the pruning parameter carefully, most of the refined models outperform original ones. We also evaluate the transfer learning level comparing the refined model and the original one training from scratch a neural network with the same hyper parameters as the optimized model. the results obtained show that our constructing method not only helps in the design of more eﬀicient models but also more effective ones. © 2023, the Authors. All rights reserved.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Fast and stable Zinc Anode‑Based Electrochromic Displays Enabled by Bimetallically Doped Vanadate and Aqueous Zn^(2+)/Na^(+)Hybrid Electrolytes

引用

Nano-Micro Letters 2023年第12期15卷 231-241页

作者： Zhaoyang song Bin Wang Wu Zhang Qianqian Zhu Abdulhakem YElezzabi Linhua Liu William WYu Haizeng Li College of Chemistry and Chemical Engineering Qingdao UniversityQingdao 266071People’s Republic of China Optics and Thermal Radiation Research Center Institute of Frontier and Interdisciplinary ScienceShandong UniversityQingdao 266237People’s Republic of China School of Chemistry and Chemical Engineering Shandong UniversityJinan 250100People’s Republic of China Ultrafast Optics and Nanophotonics Laboratory Department of Electrical and Computer EngineeringUniversity of AlbertaEdmontonAB T6G 2V4Canada

Vanadates are a class of the most promising electrochromic materials for displays as their multicolor ***,the slow switching times and vanadate dissolution issues of recently reported vanadates significantly hinder their diverse practical ***,novel strategies are developed to design electrochemically stable vanadates having rapid switching *** show that the interlayer spacing is greatly broadened by introducing sodium and lanthanum ions into V_(3)O_(8)interlayers,which facilitates the transportation of cations and enhances the electrochemical *** addition,a hybrid Zn^(2+)/Na^(+)electrolyte is designed to inhibit vanadate dissolution while significantly accelerating electrochemical *** a result,our electrochromic displays yield the most rapid switching times in comparison with any reported Zn-vanadate electrochromic *** is envisioned that stable vanadate-based electrochromic displays having video speed switching are appearing on the near horizon.

关键词： Vanadates Hybrid electrolytes Displays Electrochromic

来源：评论

学校读者我要写书评

暂无评论

Analysis of Deep Learning Methods for Fracture segmentation of Road surface under on Encoder and Decoder

Analysis of Deep Learning Methods for Fracture Segmentation ...

引用

2022 international Conference on innovative Computing, intelligent Communication and smart Electrical systems, iCsEs 2022

作者： subha, t.D. sasirekha, N. shamitha, C. Radhika, s. tamilselvi, M. R.M.K. Engineering College Department of Electronics and Communication Engineering Chennai601 206 India Sona College of Technology Department of Electronics and Communication Engineering Salem636005 India MIT MAHE Department of Electronics and Communication Engineering Bengaluru560064 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science Engineering Chennai602105 India T.S.Srinivasan Centre for Polytechnic College and Advanced Training Department of Mechatronics Engineering Chennai600 095 India

ISBN: (数字)9781665474139

ISBN: (纸本)9781665474139

Road imperfections have a significant impact on driving in terms of both safety and convenience. it's for this reason that road degradation identification and restoration assessments are carried out on a regular basis. Road accidents, especially in developing countries like india, are often caused by poorly designed roads and highways that have been damaged by cracks or potholes. Road accident and fatality rates may be reduced if interested parties get timely and accurate information about dangerous road conditions. A new topology for neural networks, as well as training and prediction approaches is discussed in this research. Road surface deterioration conditions may be detected using a unique deep neural network approach proposed here. 1300 training photos and 400 testing photographs with various sorts of road distress are used to train the neural network. Nine deep learning models from diverse disciplines are compared with the suggested approach. the suggested method exceeds all others with a pixel accuracy of 97.61%, according to the comparison findings. the findings of this research might play a significant role in the future in assuring safe driving by quickly identifying dangerous highway conditions. © 2022 iEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel symmetric Key Compact to Reliable Connection between sensor Nodes Using Exploitable Features of ECG

A Novel Symmetric Key Compact to Reliable Connection between...

引用

2022 international Conference on innovative Computing, intelligent Communication and smart Electrical systems, iCsEs 2022

作者： Riya, K.s. sudhakar, J. Ravichandran, M. tamilselvi, M. sajiv, G. Vel Tech Multi Tech Dr Rangerajan Dr Sakunthala Engineering College Department of Computer Science and Engineering Chennai India Chennai Institute of Technology Kundrathur Department of Biomedical Engineering Chennai600069 India K. Ramakrishnan College of Engineering Department of Mechanical Engineering Trichy621 112 India T.S.Srinivasan Centre for Polytechnic College and Advanced Training Department of Mechatronics Engineering Vanagaram Chennai600 095 India SIMATS Saveetha School of Engineering Department of ECE Chennai602105 India

ISBN: (数字)9781665474139

ISBN: (纸本)9781665474139

Wireless sensor networks (WsNs) have evolved to serve a diverse multitude of uses, including field of health and social systems, as a result of advancements in the technology. in sensing devices, a wireless body area network (WBAN) is a particularly unique network technology that is meant to operate continuously to connect smart equipment and equipment implanted both in and out of person that are used for lengthy healthcare monitoring within even outside a medical environment. A WBAN is a network of sensor nodes that are implanted in and/or fastened on the individual body for the purpose of tracking the individual's physiological features. Although the growth of WBAN technology has the potential to considerably assist medical healthcare systems, the collection and transmission of private physiological data in such an open setting poses severe security and privacy issues. throughout this research, we offer a unique key-agreement mechanism for securing communications between sensor nodes of wireless body area networks (WBANs). in order to communicate, the suggested technique relies on the measurement and verification of shared physiological properties at both the transmitter and receiver sensors. in contrast to current protocols, the suggested protocol allows communicating sensors to leverage their prior session pre-knowledge for encrypted communication during a certain length of time, as opposed to existing protocols. thus, the time necessary for creating the shared key will be reduced. in addition, extracted characteristics will not be repeated in the medium, preventing listening attacks while keeping the unpredictability of the key. the experimental outcomes show the efficacy of the suggested key agreement existing protocols of both the image retrieval and the key establishment phases, with an efficiency of 99.50 percent and an error rate of 0.005 percent in both the image retrieval and based consensus phases. When compared to current key agreement methods, the sug

关键词： sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Design of an efficient deep Learning Model for segmentation and Classification of Psoriasis and Vitiligo skin diseases

Design of an efficient deep Learning Model for Segmentation ...

引用

Advances in Computation, Communication and information technology (iCAiCCit), international Conference on

作者： Dasari Anantha Reddy saroj shambharkar Dipti Chaudhari Kandi Jyothsna Rachna K. somkunwar Amireddy srinish Reddy Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Hyderabad Telangana India Department of Information Technology K.I.T.S. Ramtek Nagpur India Department of Computer Engineering Pimpri Chichwad College of Engineering and Research Ravet Pune India Department of Computer Science and Engineering MLRIT Dundigal Hyderabad India Department of Computer Engineering Dr. D. Y. Patil Institute of Technology Pimpri Pune India Department of Computer Science and Engineering CMRIT Kandlakoya Hyderabad Telangana India

skin diseases such as psoriasis and vitiligo can greatly impact a patient's quality of life. For correct diagnosis and therapy planning, it is crucial to accurately segment and classify various skin disorders. Existing segmentation & classification models for identification of skin diseases either have low efficiency or have higher complexity when used for clinical scenarios. in order to address these problems, we provide a deep learning model in this study that can automatically separate and categorize vitiligo and psoriasis skin lesions from clinical photos. the suggested model is built on a Convolutional Neural Network (CNN) architecture that has been specifically designed for use in medical image processing applications. initially, all the collected images are augmented via scale, rotate, width shift, height shift, shear and zoom operations. in proposed approach, train the model on this augmented dataset of clinical images for psoriasis and vitiligo lesions via transfer Learning based ResNet50 CNN, and evaluate its performance using various metrics such as accuracy, precision, recall, and F1-scores. Proposed approach results show that the proposed model achieves high accuracy in both segmentation and classification tasks. the proposed deep learning model can assist dermatologists and medical professionals in accurately diagnosing and treating skin diseases, potentially leading to better patient outcomes.

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：