检索结果-内蒙古大学图书馆

Analytical and Neural Network Analysis on Flux-Coated Aluminium Alloy by Activated TIG Welding with Synthesized Nanocomposites

引用

Journal of Nanomaterials 2023年第1期2023卷

作者： Raja, V.L. Kumar, A. M. Senthil Kumari, K. Shantha Bharanidharan, R. Ezhilarasi, P. Rajeshkannan, S. Nithya, T.M. Kumar, S. Venkatesh Department of Mechanical Engineering Loyola Institute of Technology Palanchur Tamil Nadu Chennai600123 India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Tamil Nadu Chennai603203 India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Tamil Nadu Coimbatore641021 India Department of Electronics and Communication Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India Department of Computer Science and Engineering K. Ramakrishnan College of Engineering Tamil Nadu Trichy621112 India Department of Mechanical Engineering College of Engineering and Technology Mettu University P.O. Box: 318 Mettu Ethiopia

This research focused to synthesize the material by the tungsten inert gas (TIG) welding process with support of appropriate flux coating material. Therefore the required amount of flux coating material was utilized to enhance the mechanical properties of the specified localized welded regions. Hence, this study concentrated to select the nano-SiO2 flux particles that were employed for TIG process. This activated TIG welding composes the flux-coated welding on the base metal of AA5083-H111, as this material was highly reactive with SiO2 by the presence of magnesium precipitates and well synthesized after the welding. The post- and preheat treatment process was achieved before and after welding. The selection of activated TIG process parameters composed of strengthened weld specimens along with constant parameters like electrode tip angle and flow rate, respectively. Initially, the process parameters were designed by the statistical analysis of Box Behnken method with support of regression formulation to determine the optimal solution. The maximum tensile strength was attained at the welding process parameters of welding speed (100 mm/min), voltage (13 V), and current (125 amps). The higher hardness was achieved at the process parameters of welding speed (80 mm/min), voltage (12 V), and current (125 amps), respectively. Finally, the neural network approach was utilized to verify the predicted responses of tensile and microhardness properties. The interaction plots, mean plots, and 3D scatter plots were influenced to enhance the process parameters. In this research, mechanical properties were enhanced by the flux-coated SiO2 and the analytical method also advances the optimal parameters. © 2023 V. L. Raja et al.

关键词： Silica

来源：评论

学校读者我要写书评

暂无评论

Forex exchange using big data analytics 1

Forex exchange using big data analytics

引用

1st International Conference on Advances in Computational science and engineering, ICACSE 2020

作者： Sadhasivam, Jayakumar Arun, M. Deepa, R. Muthukumaran, V. Lokesh Kumar, R. Prasanna Kumar, R.B. Vellore Institute of Technology Vellore India School of Computing Kalasalingam Academy of Research and Education Tamilnadu 626128 India Telangana Hyderabad India Department of Mathematics School of Applied Science REVA University Bengaluru64 India Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Vellore632 014 India Department of Computer Science REVA University Bengaluru64 India

Analysis and Prediction of forex has gained immense value in today's economy. The stock price prediction is a difficult process owing to the irregularities in stock prices. Every trader wants to know if the pattern has been repeated in past to know what the possible output of the current situation will be. The primary objective is to propose a methodology that will use a historical dataset and provide a more accurate prediction on stock price. In this paper, we will be using machine learning pattern recognition algorithm on forex tick dataset. The learned model then will produce pattern from the given dataset and on the pattern of increasing or decreasing, the buyer will initiate a buy or sell the stock respectively. We will use python coding to execute the algorithm in jupyter notebook. Matplot library will help us to perform graphing in the process and Numpy will be helpful in doing statistical analysis of data. © Published under licence by IOP Publishing Ltd.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Cognitive-inspired Post-processing of optical character recognition for Swedish addresses

Cognitive-inspired Post-processing of optical character reco...

引用

IEEE International Conference on Cognitive Informatics

作者： Moa Andersson Summrina Kanwal Faiza Khan School of Electrical Engineering and Computer Science Kth Royal Institute of Technology in Stockholm Sweden School of Electrical Engineering and Computer Science Kth Royal Institute of Technology in Stockholm Centre for Applied Intelligent Systems Research Halmstad University Sweden Faculty of Computing Riphah International University Islamabad Pakistan

Optical character recognition (OCR) has many ap-plications, such as digitizing historical documents, automating processes, and helping visually impaired people read. However, extracting text from images into a digital format is not an easy problem to solve, and the outputs from the OCR frameworks often include errors. The complexity comes from the many variations in (digital) fonts, handwriting, lighting, etc. To tackle this problem, this thesis investigates two different methods for correcting the errors in OCR output. The used dataset consists of Swedish addresses. The methods are therefore applied to postal automation to investigate the usage of these methods for further automating postal work by automatically reading addresses on parcels using OCR. The first method, the lexical implementation, uses a dataset of Swedish addresses so that any valid address should be in this dataset (hence there is a known and limited vocabulary), and misspelled addresses are corrected to the address in the lexicon with the smallest Levenshtein distance. The second approach uses the same dataset, but with artificial errors, or artificial noise, added. The addresses with this artificial noise are then used together with their correct spelling to train a machine learning model based on Neural machine translation (NMT) to automatically correct errors in OCR read addresses. The results from this study could contribute by defining in what direction future work connected to OCR and postal addresses should go. The results were that the lexical implementation outperformed the NMT model. However, more experiments including real data would be required to draw definitive conclusions as to how the methods would work in real-life applications.

关键词： Vocabulary Automation Computational modeling Optical character recognition Lighting Machine learning Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Based Long Short-Term Memory for Android Malware Detection

Hybrid Optimization Based Long Short-Term Memory for Android...

引用

Evolutionary Algorithms and Soft computing Techniques (EASCT), International Conference on

作者： Jayapal Lande M. Maheswari S. M. Kamali R. Dineshkumar Priyanka M S School of Computer Science & Artificial Intelligence SR University Warangal India Department of Computational Intelligence School of Computing SRM Institue of Science and Technology Chennai India Department of Electrical and Electronics Engineering Annapoorana Engineering College Salem India Department of ECE Saveetha School of Engineering Sriperumbudur Thandalam India Department of AI and ML Nitte Meenakshi Institute of Technology Yelahanka Bengaluru India

Malware detection is process of detecting the suspicious files and activities, that can classify as benign and malicious depends on different characters like capability of infection, structure of malware and speed rate. In this paper, proposed a Particle Swarm Optimization and Ant Colony Optimization (HPSALO) based Long Short-Term Memory (LSTM) model for malware detection and classification. The combination of these two algorithms that leads to the balance between exploration and exploitation. The dataset utilized for the research is DREBIN dataset and process of data cleaning is performed by NumPy library. The feature selection is performed by combination of hybrid PSALO algorithms and selected features are given to Long Short-Term Memory (LSTM) classifier that classifies as benign and malware files. The performance of proposed method is estimated by performance metrics of accuracy, precision, recall and f1-score. The proposed method attained accuracy of 99.38%, precision of 99.30%, recall of 99.08% and f1-score of 99.42% which is comparatively higher than other existing methods like Whale Optimization Algorithm-LSTM (WOA-LSTM), Cat Swarm Optimization-LSTM (CSO-LSTM), Particle Swarm Optimization-LSTM and Ant Lion Optimization-LSTM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning vs. Feature Extraction Based Multi-Objective Approach for Sentiment Classification

Deep Learning vs. Feature Extraction Based Multi-Objective A...

引用

International Conference on computing for Sustainable Global Development (INDIACom)

作者： Jitendra Kumar Chaudhary Muddada Murali Krishna Rohit Kumar Singhal Rajesh Singh R. Suganthi Himanshu Rai Goyal School of Computing Graphic Era Hill University Uttrakhand Computer Science & Engineering Department (SOSO) Sanskriti College of Engineering Puttaparthi Andhra Pradesh Department of Computer Science & Engineering Chandigarh University (CU) Mohali Punjab INDIA Uttaranchal Institute of Technology Uttaranchal University India Dr. NGP Arts and Science College Coimbatore India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

Sentiment analysis is used for classification and analyzing of text through data and text mining. The expected output is generated using the identification and extraction of the information from the various sources provided in the Internet that helps in various kind of business and collection of data for researchers. In recent days deep learning and machine learning technologies are used for sentiment analysis for accurate prediction and analysis. Sentiment analysis can be done in 3 different ways like document level aspect level and sentence level. Not only the web sources text messages blogs articles emails are analyzed for extraction of text related to our searches. Sentiment analysis has significant role in in natural language processing and emotional tone identification. Sentiment analysis can be used for numerous applications for market research, reputation of a specific brand, consumer reception of products, success evaluation of marketing campaign and much more. It can be applied in different types of fields for collection of data using text extraction from various sources. The main objective of the study is the development of multi objective approach and comparison of deep learning versus feature extraction for sentiment classification. The proposed multi-objective sentiment classification model give the output of 99% accuracy using multi objective approach.

关键词： Deep learning Text mining Sentiment analysis Analytical models Solid modeling Computational modeling Text categorization

来源：评论

学校读者我要写书评

暂无评论

Quantum Artificial Intelligence: Unlocking the Future of technology

Quantum Artificial Intelligence: Unlocking the Future of Tec...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： G. Ignisha Rajathi L.R. Priya A. Vegi Fernando R. Vedhapriyavadhana S. Sasindharan J. Mohanalin Department of Information Technology Manipal Academy of Higher Education Manipal Institute of Technology Bengaluru Manipal India Department of Electronics and Communication Engineeing Farncis Xavier Engineering College Tirunelveli Tamil Nadu India Department of Computer Science and Engineering (AI & ML) Dayananda Sagar University Bengaluru Karnataka India School of Computing Engineering and Physical Sciences University of the west of Scotland London UK Department of Computer Science and Business Systems Sri Krishna College of Engineering and Technology Coimbatore Tamil Nadu India Electrical and Electronics Engineering College of Engineering Perumon Kerala India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Quantum Artificial Intelligence (QAI) stands for the combination of the exercise of ‘quantum computing’ and ‘artificial intelligence’ that drives breakthrough transformation across various industries. In this paper, it is discussed on how QAI is bringing change across industries including pharmaceuticals, finance, weather prediction, supply chain, security, smart cities, agriculture, telecommunication, and education. With quantum mechanics conceptions, QAI enhance computation ability to address more data, and enhance the algorithms. Quantum technologies have potential for attachment to AI systems and make the previously unachievable innovations with the help of overgrowing the classical models. As a conclusion, this paper also discusses its result on the methodological difficulties and ethical issues of QAI, the need to build strategic partnerships and the need for well-regulated legislation. The results extend our understanding of QAI to apprehend the future of technology and its application for solving some of the greatest problems that the world faces today.

关键词： Drugs Ethics Technological innovation Quantum computing Smart cities Finance Weather forecasting Security Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Welded Joint Performance Analysis through Mechanical and Thermal Property Prediction with Random Forest

Welded Joint Performance Analysis through Mechanical and The...

引用

International Conference on computing and Networking technology (ICCNT)

作者： B. Senthilkumaran C. Sushama S. Bhaggiaraj Ashish Kaushal P Kamalarajan M. Dinesh Babu Department of Computer Science and Engineering School of Computing Veltech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology (deemed to be university) Chennai Tamilnadu India Department of CSE School of Computing Mohan Babu University (erstwhile Sree Vidyanikethan Engineering College) Tirupathi AP India Department of Information Technology Sri Ramakrishna Engineering College Coimbatore Tamilnadu India Jindal Global Business School O P Jindal Global University Sonipat Haryana India Department of Chemistry R. M. D. Engineering College Kavaraipettai Tamilnadu India Department of Mechanical Engineering Rajalakshmi Institute of Technology Chennai Tamilnadu India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The research conducted in this study utilizes a comprehensive dataset that incorporates various materials, welding procedures, and climatic variables in order to train the Random Forest model. Our objective is to conduct a full evaluation of the performance of welded joints, specifically for their applicability in certain applications, by integrating predictions of both mechanical and thermal properties. The Random Forest model exhibits amazing predictive skills, allowing for accurate estimation of crucial parameters such as tensile strength, impact toughness, and thermal conductivity. This methodology not only optimizes the assessment of welded joint efficacy but also mitigates the necessity for significant and laborious physical experimentation. Our research findings emphasize the significance of a number of factors, such as welding parameters, base material selection, and joint shape, in determining the performance of joints.

关键词： Accuracy Shape Welding Thermal conductivity Mechanical factors Stability analysis Thermal analysis Reliability Thermal stability Research and development

来源：评论

学校读者我要写书评

暂无评论

Deviation Backfilling: A Robust Backfilling Scheme for Improving the Efficiency of Job Scheduling on High Performance computing Systems

Deviation Backfilling: A Robust Backfilling Scheme for Impro...

引用

advanced computing and Analytics (ACOMPA), International Conference on

作者： Thanh Hoang Le Hai Khang Nguyen Duy Thin Nguyen Manh Danh Mai Hoang Nam Thoai High Performance Computing Laboratory Faculty of Computer Science and Engineering Advanced Institute of Interdisciplinary Science and Technology Ho Chi Minh City University of Technology (HCMUT) Ho Chi Minh City Vietnam Vietnam National University Ho Chi Minh City Ho Chi Minh City Vietnam

The Big Data era has led to the rapid development of modern sciences. Making effective use of extremely large amounts of collected data is putting extremely urgent demands on High Performance computing (HPC) systems, especially the resource allocation process, which is commonly managed by the job scheduler. Despite the potential for improved scheduling outcomes offered by modern algorithms, these systems still continue to favor the FCFS and EASY backfilling approach due to its straightforward implementation and fair resource allocation. In this paper, we propose a novel and robust backfilling scheme called Deviation Backfilling to enhance the efficiency of job scheduling on HPC systems while maintaining user fairness. Combined with the job runtime prediction method using kNN, the Deviation Backfilling uses the deviation between user estimates and system prediction as the delay threshold for the first job at the backfilling queue. Our experimental results show that Deviation Backfilling outperforms existing scheduling strategies regarding performance metrics on real-world datasets. This performance improvement also signifies the capability to motivate users to offer more accurate estimates for assisting the HPC scheduling procedures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evidence for a Field-Independent Enhancement Factor in the Real Tunneling Potential Barrier of Nanotube Emitters

Evidence for a Field-Independent Enhancement Factor in the R...

引用

International Conference on Vacuum Nanoelectronics (IVNC)

作者： Caio P. de Castro Thiago A. de Assis Roberto Rivelino Fernando B. Mota Caio M C. de Castilho Richard G. Forbes Institute of Physics Federal University of Bahia Salvador BA Brazil Institute of Physics Fluminense Federal University Niterói RJ Brazil Advanced Technology Institute & School of Computer Science and Electronic Engineering University of Surrey Guildford Surrey UK

We have demonstrated evidence that: (a) a constant characteristic induced field enhancement factor (FEF) can be determined from ab initio density functional theory (DFT) calculations on carbon nanotubes; and (b) this FEF adequately describes the real tunneling barrier. We have confirmed this finding in capped (6,6) armchair, (10,0) zigzag and (10,5) single walled carbon nanotubes (SWCNTs). In all these cases, we have verified that the characteristic local induced field enhancement factor (LIFEF) does not significantly depend on the macroscopic applied field. This establishes the LIFEF as a field-independent characterization parameter for nano-emitters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel U-Net Based CNN Algorithm for High-Accuracy Weather Forecasting

A Novel U-Net Based CNN Algorithm for High-Accuracy Weather ...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Thirumurugan Shanmugam Chirag Chandrashekar Arun Kumar Sivaraman Janakiraman Nithiyanantham Priya Ravindran S T Sarvesh Narayanan Department of Computing and Information Sciences University of Technology and Applied Sciences Suhar Oman School of CSE Vellore Institute of Technology Chennai India Digital Engineering Solution Centre Photon Interactive Inc. Ontario Canada Department of ECE K.L.N. College of Engineering Tamilnadu India School of Computer Science Dalhousie University Halifax Canada

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

Accurate weather forecasting is essential for sectors like agriculture, aviation, and disaster management. However, deep learning algorithms face challenges in prediction accuracy due to issues like vanishing gradients, overfitting, and high computational demands. This research proposes a novel U-Net based architecture utilizing a Convolutional Neural Network (CNN) bottleneck layer to improve weather forecasting. Key features include a skip-connection mechanism, modified weight update rules, Gaussian-mutation operations, and the Adam optimizer for enhanced feature extraction and faster, more accurate predictions. The model was tested using precipitation data from Doppler Weather Radar (DWR) Chennai Radar and weather parameters from European Centre for Medium-Range Weather Forecasts (ECMWF). A dedicated GeoServer facilitates realtime data processing. Experimental results show the proposed algorithm achieves 97.5% accuracy, outperforming CNN and long short-term memory (LSTM) models by 5.84% and 2.41%, respectively.

关键词： Accuracy Computational modeling Atmospheric modeling Weather forecasting Predictive models Feature extraction Prediction algorithms Convolutional neural networks Long short term memory Meteorology

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：