检索结果-内蒙古大学图书馆

Predicting the Soil Suitability using Machine Learning Techniques

Predicting the Soil Suitability using Machine Learning Techn...

2021 IEEE International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications, CENTCON 2021

作者： Jayaraman, Vaishnavi Sridevi, S. Monica, K.M. Lakshminarayanan, Arun Raj B. S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vels Institute of Science Technology Advanced Studies Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665400176

Agriculture is a detracting sector in the global providence, which is defined as the practice of cultivating crops. Precision agriculture using machine learning algorithms is one of the fast-growing methodologies. It explores the usage of modern technologies to increase the crop yield rate by decreasing the utilization of fertilizers. The main aim of this study is to predict the soil suitability by utilizing the sensors and machine learning techniques. The temperature, humidity, pH and soil moisture were the main sources for plant growth. The nature of the soil would be identified, by measuring the above said entities. This paper analyses the soil suitability using diversified machine learning techniques such as KNN, Support Vector Machine, Random Forest, Naive Bayes, and Extreme Learning Machine. ELM model predicts the soil suitability with 99% of accuracy. © 2021 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

High-speed and low-power molecular dynamics processing unit(MDPU)with ab initio accuracy

引用

npj Computational Materials 2024年第1期10卷 559-568页

作者： Pinghui Mo Yujia Zhang Zhuoying Zhao Hanhan Sun Junhua Li Dawei Guan Xi Ding Xin Zhang Bo Chen Mengchao Shi Duo Zhang Denghui Lu Yinan Wang Jianxing Huang Fei Liu Xinyu Li Mohan Chen Jun Cheng Bin Liang Weinan E Jiayu Dai Linfeng Zhang Han Wang Jie Liu College of Integrated Circuits Hunan UniversityChangsha410082P.R.China College of Electrical and Information Engineering Hunan UniversityChangsha410082P.R.China College of Computer National University of Defense TechnologyChangsha410073P.R.China Department of Physics National University of Defense TechnologyChangsha410073P.R.China DP Technology 100080 BeijingP.R.China AI for Science Institute 100080 BeijingP.R.China Academy for Advanced Interdisciplinary Studies Peking University100871 BeijingP.R.China HEDPS CAPTCollege of EngineeringPeking University100871 BeijingP.R.China School of Mathematical Science Peking University100871 BeijingP.R.China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEMCollege of Chemistry and Chemical EngineeringXiamen UniversityXiamen361005P.R.China School of Integrated Circuits Peking University100871 BeijingP.R.China Center for Machine Learning Research Peking University100871 BeijingP.R.China Institute of Applied Physics and Computational Mathematics 100088 BeijingP.R.China Greater Bay Area Institute for Innovation Hunan UniversityGuangzhou511300P.R.China Department of Electrical and Computer Engineering University of WashingtonSeattleWA98195USA

Molecular dynamics(MD)is an indispensable atomistic-scale computational tool widely-used in various *** the past decades,nearly all ab initio MD and machine-learning MD have been based on the general-purpose central/graphics processing units(CPU/GPU),which are well-known to suffer from their intrinsic“memory wall”and“power wall”***,nowadays MD calculations with ab initio accuracy are extremely time-consuming and power-consuming,imposing serious restrictions on the MD simulation size and *** solve this problem,here we propose a special-purpose MD processing unit(MDPU),which could reduce MD time and power consumption by about 103 times(109 times)compared to state-of-the-art machine-learningMD(ab initio MD)based on CPU/GPU,while keeping ab initio *** significantly-enhanced performance,the proposed MDPU may pave a way for the accurate atomistic-scale analysis of large-size and/or longduration problems which were impossible/impractical to compute before.

关键词： consuming power MDP

来源：评论

学校读者我要写书评

暂无评论

Explainable Symbolic Regression Model for Tool Wear Diagnosis 9

Explainable Symbolic Regression Model for Tool Wear Diagnosi...

引用

9th International Conference on Control, Decision and Information Technologies, CoDIT 2023

作者： Mishra, Debasish Han, Seulki Pattipati, Krishna R. Bollas, George M. University of Connecticut Department of Electrical & Computer Engineering 371 Fairfield Way StorrsCT06269 United States Pratt & Whitney Institute of Advanced Systems Engineering University of Connecticut 159 Discovery Dr. StorrsCT06269 United States University of Connecticut Department of Chemical & Biomolecular Engineering 159 Discovery Dr. StorrsCT06269 United States

ISBN: (纸本)9798350311402

In precision machining, predicting the tool health can improve productivity, job quality, and reduce machine downtime and energy consumption. While deep learning (DL) algorithms have garnered recent interest, they lack the physics understanding associated with machining processes. To address this limitation, we present a symbolic regression framework for tool wear diagnostics. The method explores analytical symbolic expressions using health indicators and cutting settings. Tool health indicators are computed from wavelet subspaces of vibration signals by applying a distance metric to the wavelet coefficients. These indicators are strongly correlated with tool wear measurements, making them suitable for tool wear diagnostics. We applied the developed framework to the IEEE PHM 2010 data, which comprises three sets of run-to-failure machining tests conducted with three tools. The framework predicted tool wear with an R2 of 0.947 and a mean absolute error (MAE) of 0.006 mm across test sets. The results demonstrate the effectiveness of the symbolic regression approach for tool wear diagnostics, showcasing the richness of information in the indicators and the quality of the developed model for tool wear estimation. © 2023 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Harvesting Insights: Predicting Vegetable Prices with Hybrid CLA-Conv BiGRU Techniques

Harvesting Insights: Predicting Vegetable Prices with Hybrid...

引用

Innovation in Technology (INOCON), IEEE International Conference for

作者： Kanahaiya Lal Ambashtha Chatakunta Praveen Kumar Vivekanand Pandey S. Sakthivel Padaiyatchi A. Bharathi K. Navaz Faculty of Information Technology GNSU Sasaram Bihar India Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India Amity University Patna Bihar India Department of Electrical and Electronics Engineering Nehru Institute of Engineering and Technology Coimbatore TN India Department of Information Technology Vels Institute of Science Technology and Advanced Studies Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai

The system delves into the important topic of agricultural market pricing, with a specific emphasis on the ever-changing realm of vegetable supply and prices. Stabilizing the supply and prices of vegetables becomes an enormous task when consider that the system are grown outdoors and that weather variables significantly impact harvests. Such unpredictability has far-reaching consequences for the country's economy, highlighting the critical need to develop efficient methods of precise forecasting. The government has made multiple attempts to stabilize vegetable prices and supplies, but these have all been unsuccessful due to the unpredictable weather patterns of late. This system uses state-of-the-art deep learning methods, notably the Hybrid CLA-Conv BiGRU model, which incorporates a novel preprocessing strategy based on the HP Filter, to conquer this obstacle. A strong prediction model for vegetable prices is constructed using the process, which includes feature extraction, scoring, and selection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a digital twin environment for smart collision avoidance algorithms for mobile robots using reinforcement learning

Development of a digital twin environment for smart collisio...

引用

SICE Annual Conference

作者： Natsumi Matsumoto Kazuyuki Kobayashi Tomoyuki Ohkubo Kaiqiao Tian Nashwan J Sebi Ka C Cheok Cai Changqing Graduate School of Science and Engineering Hosei University Tokyo Japan Faculty of Advanced Engineering Nippon Institute of Technology Saitama Japan Electrical & Computer Engineering Department School of Engineering & Computer Science Oakland University Rochester USA School of Electrical Engineering and Information Technology Changchun Institute of Technology China

This paper describes a study on building a digital twin environment using point cloud data for mobile robots. A digital twin environment for mobile robots is a method to reproduce almost the same environment in a simulation space as if it were a twin, using data from an actual natural environment. In fact, in the development of mobile robots, experiments on public urban area are conducted, however, they are incredibly time-consuming and labor-intensive, so it would be helpful if a realistic simulation environment could be created. This study focuses on building a digital twin environment using point-cloud-data for mobile robots. In order to verify the effectiveness of this approach, we constructed the environment using data from a real mobile robot that has been driven. The navigation of the mobile robot was performed in the constructed simulation environment, and it was possible to realize a navigation run in the driving environment that was almost the same as the run of the real mobile robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BR-DeFedRL: Byzantine-Robust Decentralized Federated Reinforcement Learning with Fast Convergence and Communication Efficiency

BR-DeFedRL: Byzantine-Robust Decentralized Federated Reinfor...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Jing Qiao Zuyuan Zhang Sheng Yue Yuan Yuan Zhipeng Cai Xiao Zhang Ju Ren Dongxiao Yu School of Computer Science and Technology Shandong University Qingdao China Zhongtai Securities Institute for Financial Studies Shandong University Jinan China Department of Electrical and Computer Engineering The George Washington University DC USA Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science Georgia State University Atlanta GA USA

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

In this paper, we propose Byzantine-Robust Decentralized Federated Reinforcement Learning (BR-DeFedRL), an innovative framework that effectively combats the harmful influence of Byzantine agents by adaptively adjusting communication weights, thereby significantly enhancing the robustness of the learning system. By leveraging decentralized learning, our approach eliminates the dependence on a central server. Striking a harmonious balance between communication round count and sample complexity, BR-DeFedRL achieves efficient convergence with a rate of $\mathcal{O}\left( {\frac{1}{{TN}}} \right)$, where T denotes the communication rounds and N represents the local steps related to variance reduction. Notably, each agent attains an ϵ-approximation with a state-of-the-art sample complexity of $\mathcal{O}\left( {\frac{1}{{\varepsilon N}} + \frac{1}{\varepsilon }} \right)$. Extensive experimental validations further affirm the efficacy of BR-DeFedRL, making it a promising and practical solution for Byzantine-robust decentralized federated reinforcement learning.

关键词： Learning systems Reinforcement learning Robustness Complexity theory Servers Convergence

来源：评论

学校读者我要写书评

暂无评论

Scalable and Sustainable Community Networks for Inclusive Smart Cities 7th

Scalable and Sustainable Community Networks for Inclusive ...

引用

7th EAI International Conference on Science and Technologies for Smart Cities, SmartCity360° 2021

作者： Evangelista, John Marlo Maglalang, Karyn Beltran, Lope Estrada, Colline Mijares, Pio Jonel Salanio, Ken Abryl Eleazar Trajano, Jhon Aaron Zamora, John Patrick Zurbano, Vladimir Axl Von Carlo Montes-Austria, Isabel Festin, Cedric Angelo Podolsky, Matthew Ocampo, Roel Electrical and Electronics Engineering Institute University of the Philippines Diliman Quezon City Philippines Department of Computer Science University of the Philippines Diliman Quezon City Philippines College of Computer Studies New Era University Quezon City Philippines University of California Berkeley Berkeley United States

ISBN: (纸本)9783031063701

Community networks can help build smart cities by interconnecting and empowering the underserved and unconnected. However, communities often face financial and human resource constraints when building and maintaining such networks. We present a network architecture and some design principles aimed at addressing issues of sustainability and scaling in the face of such resource constraints. With our proposed approach however, component selection, qualification, and testing become additional tasks for the community. Programmability and network function virtualization may instead help address compatibility issues, promote resource pooling at the edge, and allow dynamic resource allocation. © 2022, ICST institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

CONTEXT-AWARE LLM-BASED SAFE CONTROL AGAINST LATENT RISKS

arXiv

引用

arXiv 2024年

作者： Luu, Quan Khanh Deng, Xiyu Van Ho, Anh Nakahira, Yorie School of Materials Science Japan Advanced Institute of Science and Technology Ishikawa Nomi Japan Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA United States

It is challenging for autonomous control systems to perform complex tasks in the presence of latent risks. Motivated by this challenge, this paper proposes an integrated framework that involves Large Language Models (LLMs), stochastic gradient descent (SGD), and optimization-based control. In the first phase, the proposed framework breaks down complex tasks into a sequence of smaller subtasks, whose specifications account for contextual information and latent risks. In the second phase, these subtasks and their parameters are refined through a dual process involving LLMs and SGD. LLMs are used to generate rough guesses and failure explanations, and SGD is used to fine-tune parameters. The proposed framework is tested using simulated case studies of robots and vehicles. The experiments demonstrate that the proposed framework can mediate actions based on the context and latent risks and learn complex behaviors efficiently. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Exploring the Synergy of Artificial and Computational Intelligence for Technological Advancements

Exploring the Synergy of Artificial and Computational Intell...

引用

Data, Computation and Communication (ICDCC), International Conference on

作者： Suresh Palarimath Pyingkodi Maran Prajoona Valsalan Wilfred Blessing N. R S. J. Kavitha Steffi S College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Sultanate of Oman Department of Computer Applications Kongu Engineering College Erode India Electrical and Computer Engineering Department College of Engineering Dhofar Univesity Salalah Sultanate of Oman College of Computing and Information Sciences Univesity of Technology and Applied Sciences Ibri Sultanate of Oman Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331532956

ISBN: (纸本)9798331532963

Due to the ongoing advancements in science and technology, it seems that artificial intelligence and computers have encountered a limitation in their progress. Contemporary scientific research requires more sophisticated interconnection technology to ensure the continued progress of science and technology. Amidst this setting, the technology of Internet of Things (IoT) has progressively been visible to individuals. This technology will significantly impact human lifestyle and quality of life, and the Internet of Things has seen substantial progress. Information technology is intricately intertwined with the lives of citizens. The integration of information technology with the IoT is aimed at maximizing the technological advancement of the Internet of Things, with Internet technology serving as the central component. The use of artificial intelligence and computer intelligence in Internet technology is versatile, and issues pertaining to artificial intelligence and computing intelligence are progressively emerging. Artificial intelligence and computational intelligence play a significant role in the Internet of Things. However, their application process is challenging and lacks creativity, necessitating ongoing improvements at the application level. This study examines the use of artificial intelligence and computational intelligence in the Internet of Things.

关键词： computers Planets Internet of Things Artificial intelligence Information technology Computational intelligence Creativity

来源：评论

学校读者我要写书评

暂无评论

Systematic Stress Detection in CNN Application 10

Systematic Stress Detection in CNN Application

引用

10th International Conference on Reliability, Infocom Technologies and Optimization ,Trends and Future Directions, ICRITO 2022

作者： Mohapatra, Srikanta Kumar Kishore Kanna, R. Arora, Ginni Sarangi, Prakash Kumar Mohanty, Jayashree Sahu, Premananda Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Vels Institute of Science Technology & Advanced Studies Department of Biomedical Engineering Amity University Department of Computer Science and Engineering New Delhi Noida India Hyderabad India Odisha Bhubaneswar India Srm Institute of Science and Technology Srmist UP Ghaziabad India

ISBN: (数字)9781665474337

ISBN: (纸本)9781665474337

Emotional strain is referred to as stress. Both our mental health and the mental health of others around us may be affected. While anxiety is a normal response to stress that may be frightening, it can also cause panic attacks. Everyone needs to address these mental health problems. The method we use to identify stress and anxiety in a person using vocal/audio information is described in this study. We have created a deep neural network model for stress and anxiety detection. Here, Kaggle audio datasets with 7 different emotions―joy, fear, disgust, neutral, sorrow, surprise, and anger―are taken into consideration. To train and evaluate classification algorithms like CNN, these audio datasets are employed. The audio is then pre-processed using acoustic feature extraction, and CNN is used to classify it, providing accuracy based on those seven emotions. This allows us to foretell if the individual is stressed out or anxious. © 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

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：