检索结果-内蒙古大学图书馆

International Symposium on Telecommunications, IST

作者： Masoud Omidvari Abarghouie Sasan H. Alizadeh Ahmad Khademzadeh Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Faculty of Information Technology ICT Research Institute (ITRC) Tehran Iran ICT Research Institute (ITRC) Tehran Iran

ISBN: (数字)9798350356250

ISBN: (纸本)9798350356267

The rise of cryptocurrencies as a major economic factor has drawn interest from both individual investors and regulators. This has led researchers to explore new ways to predict cryptocurrency volatility. This research proposes a new approach for more accurately predicting the conditional variance of cryptocurrencies while previous research did not investigate cross-correlation among cryptocurrency mean and volatility landscapes. This research precisely uses a method to select the most relevant features based on the cross-correlation between price, returns, and volatility. Experiments on eight cryptocurrencies that have the largest market capacity from 2018 to 2024 show that this approach is effective. By considering stronger cross-correlation when choosing the data used for volatility prediction using LSTM, the research substantially reduces the error of prediction. The findings of this research can be used to predict the volatility of other cryptocurrencies and the stock markets.

关键词： Analytical models Adaptation models Regulators Accuracy Predictive models Cryptocurrency Telecommunications Stock markets Long short term memory Portfolios

来源：评论

学校读者我要写书评

暂无评论

Optical Evanescent Field for Direct Observation of Sub-100nm Particle Motion on Glass Surface

Optical Evanescent Field for Direct Observation of Sub-100nm...

引用

Robotics, engineering, Science, and technology (RESTCON), International Conference on

作者： Panart Khajornrungruang Thitipat Permpatdechakul Keisuke Suzuki Aran Blattler Yutaka Terayama Daiki Goto Pipat Phaisalpanumas Natthaphon Bun-Athuek Amornphun Phunopas Dept. of Intelligent and Control System Faculty of Computer Science and Systems Engineering Mechanical Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Interdisciplinary Informatics Graduate School of Computer Science and Systems Engineering Mechanical Information Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Production and Robotics Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Intelligent and Control System Graduate School of Computer Science and Systems Engineering Mechanical Science and Technology Course Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Industiral Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Mechanical Engineering Technology College of Industrial Technology King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand

To directly investigate the dynamic nanoscale phenomenon on the surface being processed in wet conditions such as precision polishing, and cleaning in semiconductor industrial, an optical method for visualization and observation of each sub-100 nm sized particle that is moving on an interface such as a silica glass surface by applying an evanescent field have been proposing. Subsequently, we developed an experimental apparatus equipped with an optical microscopy system for verifying the moving particle observation method in a laboratory scale. This article introduces some experimentally direct observation results of duplicated wet processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning model for efficient traffic forecasting in intelligent transportation systems

引用

Neural Computing and Applications 2024年 1-14页

作者： Khan, Shakir Alghayadh, Faisal Yousef Ahanger, Tariq Ahamed Soni, Mukesh Viriyasitavat, Wattana Berdieva, Uguloy Byeon, Haewon Riyadh Saudi Arabia University Centre for Research and Development Department of Computer Science and Engineering Chandigarh University Mohali140413 India Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Department of Management Information Systems CoBA Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Dr. D. Y. Patil Vidyapeeth Pune Pune India Dr. D. Y. Patil School of Science and Technology Tathawade Pune India Chulalongkorn Business School Faculty of Commerce and Accountancy Chulalongkorn University Bangkok Thailand The Department of Tax and Taxation Tashkent Institute of Finance Tashkent Uzbekistan Department of Digital Anti-Aging Healthcare Inje University Gimhae50834 Korea Republic of

In this paper, a novel intelligent transportation framework called graph convolutional neural network for distributed machine learning (GCN-DML) is presented. Its primary application is traffic forecasting in large-scale, dynamically-evolving traffic scenarios. One unique method in traffic forecasting, called GCN-DML, is that it allows user data to be processed locally on edge devices, removing the requirement to send all data to CS (CS). Designed specifically for edge computing, this distributed machine learning framework makes it easier to train neural networks on a variety of edge devices. In addition to protecting user privacy, this method reduces the difficulties related to centralised neural network training, minimises communication delays, lowers data transfer quantities, and improves overall data processing efficiency. GCN-LSTM, the composite graph convolutional networks used in this framework, combine edge-enhanced attention mechanisms with the feature transmission capabilities of graph convolutional neural networks to effectively handle the challenging task of traffic forecasting. Even as the number of cars in the network rises, they perform exceptionally well at quickly extracting and sending interaction information between vehicles, while preserving high prediction accuracy and low time complexity. The versatility of GCN-DML is extended to a range of traffic forecasting application scenarios, whereby edge devices can adjust the kind and scale of the neural network according to available compute and storage resources, all without sacrificing performance. The usefulness of GCN-DML in traffic forecasting is demonstrated by experimental evaluations on the NGSIM public dataset, where it outperforms other models with better computation time and prediction performance. It obtains noteworthy F1 scores of 0.9473, 0.9557, and 0.9391, respectively, for recall, precision, and precision. Even when there is an increase in the number of cars, the accuracy remains high,

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SugarcaneNet: An Optimized Ensemble of LASSO-Regularized Pre-trained Models for Accurate Disease Classification

arXiv

引用

arXiv 2024年

作者： Talukder, Md Simul Hasan Akter, Sharmin Nur, Abdullah Hafez Aljaidi, Mohammad Sulaiman, Rejwan Bin Alkoradees, Ali Fayez Department of Electrical and Electronic Engineering Dhaka University of Engineering & Technology Gazipur Bangladesh Department of Biomedical Engineering Jashore University of Science and Technology Jashore Bangladesh Department of Electronic and Telecommunication Engineering International Islamic University Chittagong Chittagong Bangladesh Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan School of Computer science and Technology Northumbria University United Kingdom Unit of Scientific Research Applied College Qassim University Saudi Arabia

Sugarcane, a key crop for the world's sugar industry, is prone to several diseases that have a substantial negative influence on both its yield and quality. To effectively manage and implement preventative initiatives, diseases must be detected promptly and accurately. In this study, we present a unique model called SugarcaneNet that outperforms previous methods for automatically and quickly detecting sugarcane disease through leaf image processing. Our proposed model consolidates an optimized weighted average ensemble of seven customized and LASSO-regularized pre-trained models, particularly InceptionV3, InceptionResNetV2, DenseNet201, DenseNet169, Xception, and ResNet152V2. Initially, we added three more dense layers with 0.0001 LASSO regularization, three 30% dropout layers, and three batch normalizations with "renorm" enabled at the bottom of these pre-trained models to improve the performance. The accuracy of sugarcane leaf disease classification was greatly increased by this addition. Following this, several comparative studies between the average ensemble and individual models were carried out, indicating that the ensemble technique performed better. The average ensemble of all modified pre-trained models produced outstanding outcomes: 100%, 99%, and 99.45% for f1 score, precision, recall, and accuracy, respectively. Performance was further enhanced by the implementation of an optimized weighted average ensemble technique incorporated with grid search. This optimized "sugarcaneNet" model performed the best for detecting sugarcane diseases, having achieved accuracy, precision, recall, and F1 score of 99.67%, 100%, 100%, and 100%, respectively. © 2024, CC BY.

关键词： Sugar industry

来源：评论

学校读者我要写书评

暂无评论

A Robust Methodology for Fruit Quality Prediction and Estimation Using Intelligent Learning Based Image Processing Logic

A Robust Methodology for Fruit Quality Prediction and Estima...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Malathi K Vunnava Dinesh Babu M. Ramkumar M. Ayyadurai Vivek K Hamzeh J Aljawawdeh Department of CSE Saveetha School of Engineering Saveetha Institute of Science and Technology (SIMATS) Saveetha University Chennai Department of CSE RV Institute of Technology Guntur Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur Department of software engineering Faculty of information technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Fruit quality prediction plays a vital role in agricultural and food industries, ensuring that only high-quality produce reaches the consumer. Traditional methods of assessing fruit quality rely on manual inspection, which is both time-consuming and prone to human error. This paper presents a robust methodology for fruit quality prediction and estimation, utilizing a hybrid deep learning model that integrates DenseN et for feature extraction with LightGBM for efficient classification. The proposed model is designed to automate the process of fruit quality assessment by analyzing key attributes such as color, texture, and shape from high-resolution fruit images. The Fruit360 dataset was used for training and testing, with images classified into categories such as fresh, ripe, overripe, and damaged. A comprehensive comparison with nine existing models, including SVM, Random Forest, and XGBoost, was conducted using performance metrics such as accuracy, precision, recall, and Fl-score. The proposed model achieved an accuracy of 96.78%, significantly outperforming all other models. Furthermore, the model's precision and recall reached 95.33% and 95.67%, respectively, demonstrating its reliability in distinguishing high-quality fruits from low-quality ones.

关键词： Training Support vector machines Accuracy Shape Computational modeling Estimation Predictive models Feature extraction Reliability Testing

来源：评论

学校读者我要写书评

暂无评论

Transforming Business Management Practices for Increased Production through Deep Learning and Cloud Computing integration

Transforming Business Management Practices for Increased Pro...

引用

Advancement in Electronics & Communication engineering (AECE), International Conference on

作者： P. Santhosh Kumar Anupam Singh Soniya Shaik Farhana Amar Choudhary Susmi Biswas Department of Information Technology Ramapuram Faculty of Engineering and Technology Srm Institute of Science and Technology Chennai India Department of Computer Science and Engineering Graphic Era Hill University Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Management Sanskar College of Engineering Ghaziabad India Department of Computer Science and Engineering CVR College of Engineering Hyderabad India Department Electronics and Communication Engineering Alliance College of Engineering and Design (ACED) Alliance University Bengaluru India Department of Management Science Haldia Institute of Management MAKAUT India

ISBN: (数字)9798350364729

ISBN: (纸本)9798350364736

This research is vital to meet the need for improved predictive maintenance in manufacturing, thus enabling predictive operations and minimizing expensive downtime. The aim is to assess and compare different machine learning models like Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Decision Trees( DT ) with respect to predicting maintenance requirements using historical sales data, social media trends, and machinery sensor readings. The methodology included gathering a dataset of 3,200 records from the industry and then the pre-processing phase to compute the preprocessing operations like data cleaning, normalization and feature selection. The various models were then trained and tested, using 70% of the data for training to generalise the model, with the rest of the unseen test set consisting of the remaining 30%. The models were evaluated based on performance metrics (accuracy, precision, recall, F1 score and Dice Similarity Coefficient or DSC). Results showed the proposed ANN model as the most accurate and efficient prediction mechanism in comparison with precision, recall and F1 score for remaining useful life (RUL) predictions. The SVM model also worked well, with an accuracy of 95.45% but low rates of false positives and negatives. Although the DT model was informative, its performance (93.34% accuracy) was less robust than that of our RF ensemble trainer. This research demonstrates the use of these findings to be applied in real-time maintenance prediction by ANN. This research would help industries and other manufacturing sectors to reduce downtime, achieve optimal planned maintenance scheduling and improve production efficiency.

关键词： Support vector machines Accuracy Computational modeling Artificial neural networks Production Predictive models Data models Real-time systems Maintenance Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Exploring Reinforcement Learning in Large-Scale Data Processing

Exploring Reinforcement Learning in Large-Scale Data Process...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Pawan Bhambu Ritesh Kumar P. Sharmila Vivek D. Patil Shivam Khurana Vivek V Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India

Reinforcement mastering (RL) is vital for big-scale fast processing. RL utilizes the availability of large datasets and dealers skilled in this information to remedy a wide variety of obligations, from automated diagnostics and self-reliant using structures to clinical information analysis. Using exploiting the traits of the modern-day significant information era, RL allows efficient and correct decision-making in massive-scale information processing and answers complicated troubles. This paper explores the use of reinforcement learning (RL) in large-scale data processing. RL is a subfield of machine learning that focuses on decision making in dynamic environments. With the increasing demand for processing large amounts of data, traditional techniques such as rule-based systems and batch processing are becoming inadequate. This has led to the emergence of RL as a potential solution due to its ability to learn and adapt to changing environments. Through a comprehensive review of existing literature, this paper discusses the applications of RL in large-scale data processing and its potential benefits. Furthermore, it examines various challenges and their potential solutions in implementing RL for data processing tasks. The paper concludes by highlighting the future research directions in this domain and the potential impact of RL on improving data processing efficiency and accuracy. It similarly examines some of the demanding situations and possibilities related to using RL for huge-scale records processing and the capability programs of RL in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing Haul Truck Safety: A Deep Neural Network-Based Driver Assistance System for Blind Spot Detection

Advancing Haul Truck Safety: A Deep Neural Network-Based Dri...

引用

Smart World Congress (SWC), IEEE

作者： Qaiser Anwar Muhammad Hanif Daisuke Shimotoku Hill H Kobayashi Kobayashi Lab Center for Spatial Information Science (CSIS) University of Tokyo Chiba Japan Faculty of Computer Science and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Technology (GIKI) Topi Pakistan Kobayashi Lab Center for Spatial Information Science (CSIS) Information Technology Center (ITC) University of Tokyo Chiba Japan Kobayashi Lab Center for Spatial Information Science (CSIS) Information Technology Center (ITC) Graduate School of Frontier Sciences (GSFS) University of Tokyo Chiba Japan

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

The utilization of haul trucks within the mining industry presents a myriad of safety challenges, primarily due to their considerable size. Haul trucks serve as indispensable assets in large-scale construction projects, owing to their unparalleled capacity for transporting heavy loads. Tailored specifically for such rigorous tasks, these trucks are restricted to traversing non-crowded roads to uphold safety standards. Nonetheless, their sheer size and design contribute to numerous blind spots, rendering them challenging to operate. In this study, we address the issue of blind spots in haul trucks by proposing a cutting-edge machine vision system. Our innovative approach integrates machine vision technology with advanced Deep Neural Network (DNN) algorithms to detect objects within the truck’s blind spots and promptly alert the driver in real time. Leveraging a comprehensive dataset of images, the DNN is trained to identify objects of varying sizes and shapes accurately. To facilitate seamless monitoring, our system incorporates a visual display unit installed in the truck’s cab, offering the driver a real-time panoramic view of the surroundings. Initial testing conducted in controlled laboratory settings yielded promising results, with the DNN algorithm demonstrating high accuracy in object detection. To validate our concept, we opted to employ a standard car as a surrogate for the haul truck. Equipped with four strategically positioned cameras providing a 360 -degree field of view, we scaled down the truck’s dimensions to match those of a car. Utilizing the D455 Intel RealSense camera, we precisely measure the distances of detected objects and issue alerts to the driver within a 4 -meter range via a built-in buzzer. Our system is further fortified with the inclusion of the Jetson Orin Nano developer kit. Real-world testing conducted in a moving vehicle showcased the effectiveness of our system, garnering favorable results. Our endeavor underscores a significant ste

关键词： YOLO Visualization Artificial neural networks Cameras Real-time systems Safety Automobiles Standards Vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

An Optimal Makespan-Energy Aware Workflow Scheduling in Iot-Fog-Cloud System Using Assa

SSRN

引用

SSRN 2024年

作者： Salehnia, Taybeh Abualigah, Laith Department of Computer Engineering and Information Technology Razi University Kermanshah Iran Computer Science Department Prince Hussein Bin Abdullah Faculty for Information Technology Al al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Faculty of Information Technology Middle East University Amman11831 Jordan Applied Science Research Center Applied Science Private University Amman11931 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang 11800 Malaysia College of Engineering Yuan Ze University Taoyuan Taiwan School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia

Today, with the increasing use of the Internet of Things (IoT) in the world, various workflows that need to be stored and processed on the computing platforms. But this issue, causes an increase in costs for computing resources providers, and as a result, system Energy Consumption (EC) is also reduced. Therefore, this paper examines the workflow scheduling problem of IoT devices in the fog-cloud environment, where reducing the EC of the computing system and reducing the MakeSpan Time (MST) of workflows as main objectives, under the constraints of priority, deadline and reliability. Therefore, in order to achieve these objectives, the combination of Aquila and Salp Swarm Algorithms (ASSA) is used to select the best Virtual Machines (VMs) for the execution of workflows. So, in each iteration of ASSA execution, a number of VMs are selected by the ASSA. Then by using the Reducing MakeSpan Time (RMST) technique, the MST of the workflow on selected VMs is reduced, while maintaining reliability and deadline. Then, using VM Merging (VMM) and Dynamic Voltage Frequency Scaling (DVFS) techniques on the output from RMST, the static and dynamic EC is reduced, respectively. Experimental results show the effectiveness of the proposed method compared to previous methods. © 2024, The Authors. All rights reserved.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

The Enhanced Optimization on Deep Learning Technologies for Data Science Practices

The Enhanced Optimization on Deep Learning Technologies for ...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Dharmesh Dhabliya B Reddy S. Rajarajeswari Ranganathaswamy M K Nivesh Megha Pandey Department of Information Technology Vishwakarma Institute of Information Technology Pune Maharashtra India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Mechanical Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Ramnagar Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

Deep studying technologies (DLTs) were adopted with the aid of many fields, consisting of healthcare, finance, and records technology. This paper ambitions to take a look at how DLTs can be improved for facts technological know-how practices, in addition to to speak about their capacity for driving advances in statistics-pushed studies. First of all, we provide a top level view of the contemporary kingdom of DLTs, and the important thing algorithms that cause them to appealing for data science packages. Then, we delve into a number of the ways wherein DLTs may be optimized for better overall performance. We illustrate the optimization strategies via numerous examples, which include community structure search, computational useful resource management, and active mastering. Moreover, we explore the use of switch studying and reinforcement getting to know to in addition improve the performance of DLTs in information science. In the end, we talk the benefits of DLTs for statistics technology and their ability for advancing the field. This paper highlights the significance of optimizing DLTs for records technological know-how, and the numerous possibilities that leveraging these technology will offer.

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：