检索结果-内蒙古大学图书馆

Reset-Free Reinforcement Learning via Multi-State Recovery and Failure Prevention for Autonomous Robots

Tsinghua science and Technology 2024年第5期29卷 1481-1494页

作者： Xu Zhou Benlian Xu Zhengqiang Jiang Jun Li Brett Nener School of Mechanical Engineering Changshu Institute of TechnologyChangshu 215500China School of Automation Nanjing University of Science and TechnologyNanjing 210094China School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou 215009China Faculty of Medicine and Health The University of SydneySydney 2006Australia Department of Electrical Electronic and Computer EngineeringThe University of Western AustraliaPerth 6009Australia

Reinforcement learning holds promise in enabling robotic tasks as it can learn optimal policies via trial and ***,the practical deployment of reinforcement learning usually requires human intervention to provide episodic resets when a failure *** manual resets are generally unavailable in autonomous robots,we propose a reset-free reinforcement learning algorithm based on multi-state recovery and failure prevention to avoid failure-induced *** multi-state recovery provides robots with the capability of recovering from failures by self-correcting its behavior in the problematic state and,more importantly,deciding which previous state is the best to return to for efficient *** failure prevention reduces potential failures by predicting and excluding possible unsafe actions in specific *** simulations and real-world experiments are used to validate our algorithm with the results showing a significant reduction in the number of resets and failures during the learning.

关键词： reinforcement learning manual reset multi-state recovery failure prediction

来源：评论

学校读者我要写书评

暂无评论

Smart Flood Detection and Communication in Hazardous Zones via MANET-Based IoT and Parallely Distributed Slimmable Neural Networks 4

Smart Flood Detection and Communication in Hazardous Zones v...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Sathya, V. Bhadula, Shuchi Srinivasan, R. Bhargav, H.K. Panda, Bhavani Sankar Barve, Amit Department of Computer Science Vallam Tamil Nadu Thanjavur613403 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248 002 India Veltech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Avadi Tiruvallur Tamil Nadu Chennai600054 India Shridevi Institute of Engineering and Technology Department of Computer Science and Engineering Karnataka Tumakuru572106 India Raghu Engineering College Department of Computer Science and Engineering Andhra Pradesh Visakhapatnam531162 India Parul Institute of Technology Parul University Faculty of Engineering and Technology Department of Computer Science and Engineering P.O.Limda Gujarat 391760 India

ISBN: (纸本)9798331540364

Disasters can be mitigated by an early warning signal and proper communication within the hazardous environment using the MANET technology. However, the exact prediction of disaster situation is needed for the timely disaster management. Hence in addition to MANET technology, deep learning algorithms and Inter of Things (IoT) can also be integrated into disaster detection and communication systems. The presented research developed a novel parallely distributed slimmable neural network with orchard algorithm for the accurate flood disaster prediction. The model processed the dataset containing various measurements such as temperature, humidity, precipitation, air, soil moisture and rainfall level that are collected by the IoT sensor deployed in the various location of the hazardous environment. The gathered data are initially pre-processed using the correlation coefficient min-max normalization approach. Further, the relevant characteristics of the flood disaster from the data are extracted through spike driven transformer process. These refined and dimensionality reduced data are then entered into the proposed framework for the disaster prediction. Here the integrated orchard algorithm increased the disaster monitoring accuracy on the basis of better optimized parameters. The model resulted 95% accuracy, 93% precision, 94% recall and 96% f-score. Therefore, the presented method is an effective prediction mechanism for the disaster management in IoT MANET. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Extended Deep Learning Algorithm for Improved Brain Tumor Diagnosis System

引用

Intelligent Automation & Soft Computing 2024年第1期39卷 33-55页

作者： M.Adimoolam K.Maithili N.M.Balamurugan R.Rajkumar S.Leelavathy Raju Kannadasan Mohd Anul Haq Ilyas Khan ElSayed M.Tag El Din Arfat Ahmad Khan Department of Computer Engineering Government Polytechnic CollegeSevvapetTiruvallurTamil Nadu602025India Department of Computer Science and Engineering KG Reddy College of Engineering and TechnologyHyderabadTelangana500075India Department of Computer Science and Engineering Sri Venkateswara College of EngineeringSriperumbudurChennai602117India Department of Computer Science and Engineering Annamalai UniversityChidambaramTamil Nadu608002India Department of Computer Science and Engineering Aarupadai Veedu Institute of TechnologyVinayaka Mission Research FoundationPaiyanurTamil Nadu603104India Department of Electrical and Electronics Engineering Sri Venkateswara College of EngineeringSriperumbudur602117India Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Mathematics College of Science Al-ZulfiMajmaah UniversityAl-Majmaah11952Saudi Arabia Electrical Engineering Department Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand

At present,the prediction of brain tumors is performed using Machine Learning(ML)and Deep Learning(DL)*** various ML and DL algorithms are adapted to predict brain tumors to some range,some concerns still need enhancement,particularly accuracy,sensitivity,false positive and false negative,to improve the brain tumor prediction system ***,this work proposed an Extended Deep Learning Algorithm(EDLA)to measure performance parameters such as accuracy,sensitivity,and false positive and false negative *** addition,these iterated measures were analyzed by comparing the EDLA method with the Convolutional Neural Network(CNN)way further using the SPSS tool,and respective graphical illustrations were *** results were that the mean performance measures for the proposed EDLA algorithm were calculated,and those measured were accuracy(97.665%),sensitivity(97.939%),false positive(3.012%),and false negative(3.182%)for ten *** in the case of the CNN,the algorithm means accuracy gained was 94.287%,mean sensitivity 95.612%,mean false positive 5.328%,and mean false negative 4.756%.These results show that the proposed EDLA method has outperformed existing algorithms,including CNN,and ensures symmetrically improved *** EDLA algorithm introduces novelty concerning its performance and particular activation *** proposed method will be utilized effectively in brain tumor detection in a precise and accurate *** algorithm would apply to brain tumor diagnosis and be involved in various medical diagnoses *** the quantity of dataset records is enormous,then themethod’s computation power has to be updated.

关键词： Brain tumor extended deep learning algorithm convolution neural network tumor detection deep learning

来源：评论

学校读者我要写书评

暂无评论

New solitary waves and exact solutions for the fifth-order nonlinear wave equation using two integration techniques

引用

Journal of Ocean engineering and science 2023年第5期8卷 475-480页

作者： Ahmed H.Arnous Mohammad Mirzazadeh Lanre Akinyemi Arzu Akbulut Department of Physics and Engineering Mathematics Higher Institute of EngineeringEl Shorouk AcademyCairoEgypt Department of Engineering Sciences Faculty of Technology and EngineeringEast of GuilanUniversity of GuilanRudsar-VajargahIran Department of Mathematics Lafayette CollegeEastonPennsylvaniaUSA Department of Mathematics Computer Faculty of Art ScienceEskisehir Osmangazi UniversityEskisehirTurkey

In this paper,we discussed the enhanced Kudryashov’s and general projective Riccati equations tech-niques for obtaining exact solutions to the fifth-order nonlinear water wave(FONLWWE)*** the enhanced Kudryashov’s method,we were able to achieve solitary wave and singular soliton ***-shock hybrid wave,singular soliton,and periodic wave solutions were discovered when we em-ployed the general projective Riccati equations *** can say the given methods are effective and powerful for obtaining exact *** findings in this paper are critical for explaining a wide range of scientific and oceanographic applications involving ocean gravity waves and other related phenomena.

关键词： Enhanced Kudryashov method Riccati equation Water waves Fifth-order nonlinear model Solitons

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Technique for Oropharyngeal Cancer Detection in Medical Imaging 7

Deep Learning Technique for Oropharyngeal Cancer Detection i...

引用

7th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2023

作者： Kumar, R. Pazhanirajan, S. Annamalai University Faculty of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chidambaram India

ISBN: (纸本)9798350340600

Oropharyngeal carcinoma is a life-threatening disease that requires prompt diagnosis and treatment. This study uses deep learning algorithms to present a novel method for improving medical imaging to detect oropharyngeal cancer. Deep learning has demonstrated immense potential for medical image processing applications in recent years. This research capitalizes on this opportunity by devising a dependable model for detecting oropharyngeal cancer. Examining oropharyngeal cancer with an emphasis on the critical significance of early detection. This study emphasizes the need for more precise and efficient diagnostic techniques. This work presents a comprehensive strategy from data acquisition and cleansing to the development of the model's underlying architecture, training, validation, and explication. The results section presents quantitative and qualitative data demonstrating the model's ability to detect oropharyngeal cancer. The proposed model has the potential to improve the quickness and accuracy with which oropharyngeal cancer is diagnosed, thereby benefiting patients. It emphasizes the need for additional research and the implementation of deep learning innovations in healthcare. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Smart Glove with Mobile Application to Detect Static Arabic Hijaiyah Hand Code for Quran Recitation 21

Smart Glove with Mobile Application to Detect Static Arabic ...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Elshareif, Mohamed Elgilani Eltahir Ahmad Alias, Nurul Aswani Jomhari, Nazean Sofian, Hazrina University of Malaya Faculty of Computer Science and Information Technology Department of Software Engineering Kuala Lumpur Malaysia

ISBN: (纸本)9798350393569

The use of assistive technology in the field of education is now a common practice in today's tech-driven era. The implementation is quite rampant in all levels and sections of education, including by special needs students with hearing impairments. With the help of technology or Internet of Things (IoT), they are offered with better opportunities to improve their communication and the teaching and learning process especially when it comes to sign language. However, the situation is quite different for Muslim deaf individuals. Sign language is not only used for communication but also as a form for reciting the Quran. Yet, the utilization of technology in the area of sign language for Quranic recitation is still limited. Hence, the goal of this study was to design and develop a sensor-based sign language recognition device consisting of a sensory smart glove and mobile application to detect Arabic sign language alphabets used in Quran recitation. The experimental result shows that the gesture recognition rate of 28 different Arabic alphabet signs, performed by 7 different signers, is 79.08%. The significance of the system lies in its mobility and capability to recognize the hand gestures regardless of the background noise. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

A Parallel Hybrid Testing Technique for Tri-Programming Model-Based Software Systems

引用

computers, Materials & Continua 2023年第2期74卷 4501-4530页

作者： Huda Basloom Mohamed Dahab Abdullah Saad AL-Ghamdi Fathy Eassa Ahmed Mohammed Alghamdi Seif Haridi Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia KTH Royal Institute of Technology StockholmSweden

Recently,researchers have shown increasing interest in combining more than one programming model into systems running on high performance computing systems(HPCs)to achieve exascale by applying parallelism at multiple *** different programming paradigms,such as Message Passing Interface(MPI),Open Multiple Processing(OpenMP),and Open Accelerators(OpenACC),can increase computation speed and improve *** the integration of multiple models,the probability of runtime errors increases,making their detection difficult,especially in the absence of testing techniques that can detect these *** studies have been conducted to identify these errors,but no technique exists for detecting errors in three-level programming *** the increasing research that integrates the three programming models,MPI,OpenMP,and OpenACC,a testing technology to detect runtime errors,such as deadlocks and race conditions,which can arise from this integration has not been ***,this paper begins with a definition and explanation of runtime errors that result fromintegrating the three programming models that compilers cannot *** the first time,this paper presents a classification of operational errors that can result from the integration of the three *** paper also proposes a parallel hybrid testing technique for detecting runtime errors in systems built in the C++programming language that uses the triple programming models MPI,OpenMP,and *** hybrid technology combines static technology and dynamic technology,given that some errors can be detected using static techniques,whereas others can be detected using dynamic *** hybrid technique can detect more errors because it combines two distinct *** proposed static technology detects a wide range of error types in less time,whereas a portion of the potential errors that may or may not occur depending on the 4502 CMC,2023,vol.74,no.2 operating environme

关键词： Software testing hybrid testing technique OpenACC OpenMP MPI tri-programming model exascale computing

来源：评论

学校读者我要写书评

暂无评论

Identifying player skill of dota 2 using machine learning pipeline

引用

Discover Artificial Intelligence 2024年第1期4卷 41页

作者： Pengmatchaya, Methasit Natwichai, Juggapong Data Science Consortium Chiang Mai University Huay Kaew Muang Chiang Mai50200 Thailand Department of Computer Engineering Faculty of Engineering Chiang Mai University Huay Kaew Muang Chiang Mai50200 Thailand

The esports industry is one of the prominent business sectors in the digital era, particularly, Multiplayer Online Battle Arena (MOBA) games which gain much attention from gamers and streaming audiences. Among such games, Defense of the Ancient 2 or Dota 2 is the record holder for the highest prize esports tournament. Therefore, various companies and investors start their esports teams to compete in the Dota 2 tournaments, the Internationals. To success in the competition, player recruitment is a crucial process as it usually takes considerable effort to find a skillful player. Watching the game replay to evaluate the player’s skill is one of the approaches. However, it can be too exhaustive, also some player’s ranking, which represent the player’s skill, are often not available. In this paper, we propose an effective machine learning pipeline to evaluate the player’s skill. Our designed pipeline includes data collection, feature engineering, and machine learning modeling. We show the data collection process using open-source API. An effective method for feature engineering is proposed. Features, e.g., end-game, or tactical decision related statistics, are incorporated along with the resource in the game distribution, harassment tactic, or spatiotemporal features, in order to provide effective models. Subsequently, we apply major machine learning models based on a single game data, i.e., logistic regression and random forest, to the processed data. The most effective model can achieve up to 0.7091 precision, 0.5850 recall, 0.6411 F1-score, and 0.8123 ROC AUC score. © The Author(s) 2024.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Optimal parameter estimation of three solar cell models using modified spotted hyena optimization

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 361-372页

作者： Gafar, Mona El-Sehiemy, Ragab A. Hasanien, Hany M. Abaza, Amlak Department of Computer Science College of Science and Humanities in Al-Sulail Prince Sattam Bin Abdulaziz University Kharj Saudi Arabia Machine Learning and Information Retrieval Department Artificial Intelligence Kafrelsheikh University Kafr El Sheikh Egypt Electrical Engineering Department Faculty of Engineering Kafrelsheikh University Kafr El Sheikh Egypt Electrical Power and Machines Department Faculty of Engineering Ain Shams University Cairo11517 Egypt

This paper is concerned with identifying the optimal parameters of solar cell by using a modified spotted hyena optimization algorithm (MSHOA). In the MSHOA, the optimization process initializes random search agents then selects the best agents. The MSHOA modifies the original spotted hyena optimization algorithm by using an accelerating function, which improves the performance of reaching the optimal solution. The convergence occurs rapidly and realizes the global optimization with small iterations number. The numerical results obtained with different models emphasize that the MSHOA has the ability and stability to estimate the global optimal decision variables of solar cell module with a minimal root mean square error compared with other algorithms existed in literature. Moreover, three electrical models called single diode model, double diode model and triple diode model TDM are accurate for depicting electrical behavior of PV modules. It is truth to say that TDM is the most accurate model among the three models. The significant agreements between the estimated model using MSHOA, at different operating temperatures and irradiances, and the measured data assert on the effectiveness of the proposed algorithm and the accuracy of PV model. All results emphasize that the MSHOA is an effective and reliable optimization algorithm for finding the optimal parameters of solar cell modules. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

A distributed B+Tree indexing method for processing range queries over streaming data

引用

Cluster Computing 2024年第2期27卷 1251-1274页

作者： Safaee, Shahab Mirabi, Meghdad Rahmani, Amir Masoud Safaei, Ali Asghar Department of Computer Engineering Faculty of Engineering South Tehran Branch Islamic Azad University Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou Taiwan Department of Medical Informatics Faculty of Medical Sciences Tarbiat Modares University Tehran Iran

A data stream exhibits as a massive unbounded sequence of data elements continuously generated at a high rate. Stream databases raise new challenges for query processing due to both the streaming nature of data which constantly changes over time and the wider range of queries submitted by the user when compared with the traditional databases. In this paper, we propose a system architecture which includes components for both distributed indexing of streaming data and distributed processing of range queries on streaming data. Instead of creating a large and centralized B+Tree index structure, we create a set of small B+Tree indexes in such a way that a B+Tree index can be created for every partition of streaming data. We also design a distributed range search algorithm which can be used by each individual machine inside a Spark cluster to independently process range queries on each partition of streaming data. By exploiting the proposed system architecture, the process of indexing of streaming data and the process of querying over streaming data can be performed in a distributed and parallel manner. By performing several experiments, we demonstrate that our proposed indexing method is scalable and efficient for processing range queries on streaming data compared to the existing centralized B+Tree indexing methods and therefore, it can be used for applications involving data streams with a large volume of data elements and a large number of range queries. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Query processing

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：