检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hossam, Rania Heakl, Ahmed Gomaa, Walid Department of Computer Science and Engineering Egypt-Japan University of Science and Technology Alexandria Egypt Computer Science Faculty Mansoura University Mansoura Egypt Faculty of Engineering Alexandria University Alexandria Egypt

Traditional fish farming practices often lead to inefficient feeding, resulting in environmental issues and reduced productivity. We developed an innovative system combining computer vision and IoT technologies for precise Tilapia feeding. Our solution uses real-time IoT sensors to monitor water quality parameters and computer vision algorithms to analyze fish size and count, determining optimal feed amounts. A mobile app enables remote monitoring and control. We utilized YOLOv8 for keypoint detection to measure Tilapia weight from length, achieving 94% precision on 3,500 annotated images. Pixel-based measurements were converted to centimeters using depth estimation for accurate feeding calculations. Our method, with data collection mirroring inference conditions, significantly improved results. Preliminary estimates suggest this approach could increase production up to 58 times compared to traditional farms. Our models, code, and dataset are open-source a © 2024, CC BY.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Phase chimera states on nonlocal hyperrings

引用

Physical Review E 2024年第2期109卷 L022201-L022201页

作者： Riccardo Muolo Thierry Njougouo Lucia Valentina Gambuzza Timoteo Carletti Mattia Frasca Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo 152-8552 Japan Department of Mathematics University of Namur B5000 Namur Belgium naXys Namur Institute for Complex Systems University of Namur B5000 Namur Belgium Faculty of Computer Science University of Namur B5000 Namur Belgium Department of Electrical and Electronic Engineering University of Buea P.O. Box 63 Buea Cameroon Department of Electrical Electronics and Computer Science Engineering University of Catania 95125 Catania Italy Istituto di Analisi dei Sistemi ed Informatica “A. Ruberti” IASI-CNR 00185 Roma Italy

Chimera states are dynamical states where regions of synchronous trajectories coexist with incoherent ones. A significant amount of research has been devoted to studying chimera states in systems of identical oscillators, nonlocally coupled through pairwise interactions. Nevertheless, there is increasing evidence, also supported by available data, that complex systems are composed of multiple units experiencing many-body interactions that can be modeled by using higher-order structures beyond the paradigm of classic pairwise networks. In this work we investigate whether phase chimera states appear in this framework, by focusing on a topology solely involving many-body, nonlocal, and nonregular interactions, hereby named nonlocal d-hyperring, (d+1) being the order of the interactions. We present the theory by using the paradigmatic Stuart-Landau oscillators as node dynamics, and we show that phase chimera states emerge in a variety of structures and with different coupling functions. For comparison, we show that, when higher-order interactions are “flattened” to pairwise ones, the chimera behavior is weaker and more elusive.

关键词： Chimera states Collective behavior in networks Dynamics of networks Pattern formation Synchronization Synchronization transition

来源：评论

学校读者我要写书评

暂无评论

Precision and Virtual Care

引用

Yearbook of medical Informatics 2025年第1期33卷 45-51页

作者： Borycki, Elizabeth M. van Sinderen, Femke Peute, Linda Dusseljee Zinovich, Sasha Kaufman, David Vimarlund, Vivian Kushniruk, Andre W. School of Health Information Science University of Victoria VIC Canada Amsterdam University Medical Centers Amsterdam Netherlands SUNY Downstate Health Sciences University NY United States Department of Computer and Information Science (IDA) School of Engineering and Technology Linköping University Sweden

The importance of virtual care has been highlighted by the recent pandemic which emphasized the need for effectively providing care remotely. In addition, the development of a range of emerging technologies to support virtual care has accelerated this trend. Technologies may vary in complexity from low (e.g., technologies that can be used easily by patients) to high (e.g., use of sophisticated software and hardware to support virtual care). In this article virtual care is first defined, followed by a discussion of a range of virtual care technologies. A framework is then described that can be used to consider and reason about virtual care in terms of both technology complexity as well as patient complexity. Examples of virtual care that can be considered using the framework are provided. It is argued that achieving an appropriate fit between the level of complexity of the technology involved and patient context will lead to improved care and ultimately precision virtual care. Implications of the approach presented are explored. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://***/licenses/by/4.0/).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Cardiovascular Detection Approach 10

Machine Learning Based Cardiovascular Detection Approach

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Kanna, R. Kishore Ambikapathy, A. Brayyich, Mohammed Reddy, V Venkat Nagpal, Amandeep Jerusalem College of Engineering Department of Biomedical Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Galgotias College of Engineering and Technology Adjunct Faculty India Collage of Engineering National University of Science and Technology Dhi Qar Iraq Institute of Aeronautial Engineering Dundigal Hyderabad India Lovely Professional University Punjab Phagwara India

ISBN: (纸本)9798350382471

Heart failure is one of the most serious and important diseases to predict between the enzymes. Recently., artificial intelligence has become fundamental for the survival of the medical industry. There are more and more examples every day. We are using artificial intelligence methods to solve this. It has been observed that four people between the ages of 30 and 50 suffer from strokes per minute, which is a problem considering that it is being detected. For this experiment, the heart disease datasets were utilised through the Kaggle tool. This work analyses and visualizes the anticipated occurrence of coronary conditions using a variety of machine learning (ML) methods, including Forest randomization, Bayes with no information, SVM, and other approaches. The stacked ensemble training method improves the subsequent use of our classification models. among other things, diseases, pattern identification, SVM, predicting cardiac conditions, an Artificial Neural Network (ANN), data analysis, and data mining. © 2023 IEEE.

关键词： ANN Cardiac Heart Machine Learning ML

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Prediction of COVID-19: A Study on Italy's Pandemic Problems 8

Machine Learning based Prediction of COVID-19: A Study on It...

引用

8th International Conference on Smart Structures and Systems, ICSSS 2022

作者： Gopirajan, P.V. Sivaranjani, Govindarajan Manickam, M. Parkavi, K. Vel Murugesh Kumar, N. Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Sustainable Engineering Chennai India Karpaga Vinayga College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9781665497619

Starting from December 2019, COVID-19 has claimed several thousand lives all around the world. Though the novel Corona virus (SARS-CoV-2) has emerged from China, it has affected most of the western countries like European Union and America. Italy is one of the most affected countries accounting for 16523 deaths until 7th April 2020. This study involves machine learning based approach to analyse the effectiveness of lockdown in containing the COVID-19 problem. It is assumed that, the lockdown was implemented 9 previous dates and total affected cases were predicted accordingly. Also, total deaths were predicted for these conditions. From the results, it is evident that the rate of increase of total cases remained 1.128 on an average during 21 days lockdown starting from 9th March 2020. Furthermore, the rate decreased after the lockdown period. The model also predicted that a 9 days prior lockdown would have reduced the total deaths from 16523 to 2239. During a pandemics, like COVID-19 the essential action taken by any government should be a strict lockdown as early as possible. Also, the public should maintain proper social distancing to avoid community spread of a pandemic disease which is highly contagious like COVID-19. © 2022 IEEE.

关键词： COVID-19 Machine learning algorithms Pandemics Machine learning Predictive models Prediction algorithms Market research

来源：评论

学校读者我要写书评

暂无评论

Socioeconomic Changes Based Climate Training for Agricultural Application Using Deep Learning Model

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 399-410页

作者： Sunitha, M. Durairaj, M. Rajalingam, A. Yusoff, Siti Khalidah Mohd Prasad, S. Hari Chandra Malluvalasa, S. N. Lakshmi Kiran, Ajmeera Department of CSE Vasavi College of Engineering Hyderabad India Department of ECE Saveetha School of Engineering SIMATS Chennai India Department of Engineering University of Technology and Applied Sciences-Shinas and Saveetha Institute of Medical and Technical Sciences Chennai India Management and Science University Selangor Shah Alam Malaysia Department of Electronics & amp Communication Engineering Aditya University Surampalem India Department of Artificial Intelligence & amp Data Science Koneru Lakshmaiah Education Foundation Guntur Dist. Andhra PradeshVaddeswaram 522302 India Department of Computer Science and Engineering MLR Institute of Technology Dundigal Telangana Hyderabad 500043 India

In socioeconomic factor studies, the use of the logit and probit models has the disadvantage of representing random variation in preference for unobserved components and time-linked errors. The agricultural sector in the coastal nations of South-East Asia is facing mounting strain due to the adverse effects of climate change. Anticipating and controlling climate variables is challenging and necessitates expensive fixes. Based on social and economic shifts and the use of a deep learning model to detect climate change, the two main facets of agricultural application have been examined in this study. The suggested model focusses on these two factors because the economics and climate are crucial components of agriculture. Initially, financial flow–based data analysis employing recurrent LSTM spatial neural networks for text data analysis was used to assess the social economic analysis for those countries with minimal agricultural development. The study of crop growth data based on climate change is then done using Boltzmann Markov quantile regression neural networks. In terms of training accuracy, sensitivity specificity, and ROC, a performance study is conducted for crop growth data based on climatic change and agricultural development based on economic data. The proposed approach in this instance produced training accuracy of 79%, specificity of 83%, ROC of 84%, and sensitivity of 80% for economic data–based agricultural development;the suggested method achieved 75% training accuracy, 73% specificity, 80% ROC, and 84% SENSITIVITY for climate change–based crop growth data. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Agricultural application Climate change detection Deep learning model Quantile regression Social economic changes

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Sampling and Reduction Methods in Large-Scale Forensic Analysis

Efficient Data Sampling and Reduction Methods in Large-Scale...

引用

2024 OPJU International technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Harika, Ala Sharma, Praveen Aravinda, K. Nagpal, Amandeep Praveen Albawi, Ali Institute of Aeronautical Engineering Hyderabad Dundigal India Ies Insititute of Technology and Management Ies University Department of Computer Science & Engineering M. P Bhopal India New Horizon College of Engineering Department of Electronics and Communication Engineering Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India The Islamic University College of Medical Technology Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350373783

In this era of enormous, continuously changing datasets, forensic analysis needs innovative approaches that can adapt to changing data characteristics while maintaining data security. To satisfy this demand, our recommended system includes all algorithms for large forensic investigations. The adaptive stratified sampling algorithm sets the scene. It adjusts strata and sample quantities based on data attributes. The Feature Weighting with Machine Learning Algorithm improves selection by weighting features using machine learning. Based on them, the dynamic cluster-based sampling algorithm organizes data points dynamically. By determining how much information each data point has, the entropy-guided data reduction algorithm improves the framework. The Temporal Correlation Analysis Algorithm finally allows you to view changing data. Tables3 and Tables4 indicate that our approach outperforms others in several key areas. The recommended technique outperforms others in accuracy, memory, F1 score, usability, stability, legal acceptability, ease of application, computing complexity, and freedom. The findings in Figures.6-10 indicate that the proposed framework can balance accuracy and memory, decrease data, and be highly usable, stable, and versatile. Finally, our technology represents a novel technique to conduct large-scale research. It is fast, adaptable, and data-safe. Machine learning, dynamic changes, and temporal variables make our platform robust and comprehensive for current forensic investigations. © 2024 IEEE.

关键词： Adaptive Stratified Sampling Algorithm Algorithm Optimization Data Reduction Data Sampling Dynamic Cluster-based Sampling Entropy-guided Data Reduction Feature Weighting Forensic Analysis Machine Learning Temporal Correlation Analysis

来源：评论

学校读者我要写书评

暂无评论

Moving Scene Classification And Human Action Recognition Based On Artificial Intelligence 1

Moving Scene Classification And Human Action Recognition Bas...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Hassan, Ahmed R. Taha, Ahmed Hussien, Naseer Ali Khalid Hussain, Angham Ali, Aqeel Matti, Imad National University of Science and Technology Engineering Technologies Department of Medical Devices Nasiriyah Dhi Qar Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Ayen University Information and Communication Technology Research Group Scientific Research Center Thi-Qar Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

In friendly correspondence, human behavior was generally a basic part. All signs that permit an assessment of the human way of behaving are human action and activity acknowledgment. Recognizing human action is a huge issue in different applications, including human-PC cooperation and innovative video observing, to further develop security in many fields. Often, recognizing human exercises with the single perception of the human body and the elements of the climate and the related items is conceivable. Look at this subject and proposition as a system for distinguishing human action that incorporates various utilitarian channels from different things, like items, views, and individuals. This paper sums up current headways in acknowledgment of human movement. By and large, distinguishing human exercises with the single perception of the human body and the highlights of the climate and comparing items is conceivable. This study offers artificial intelligence-based human action recognition (AI-HAR). Given the rising notoriety and late forward leaps in human conduct acknowledgment because of manufactured reasoning, the review gives information on the latest things and possible core values for future logical endeavors. © 2023 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Discrete RKZD (Reciprocal-Kind Zhang Dynamics) Algorithm Solving Time-Independent Linear Matrix-Vector Equation (TILMVE) Simplified from Time-Dependent Situation 42

Discrete RKZD (Reciprocal-Kind Zhang Dynamics) Algorithm Sol...

引用

42nd Chinese Control Conference, CCC 2023

作者： Zhang, Yunong Lu, Ji Mao, Mingzhi Li, Shuai School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China School of Software Engineering Sun Yat-sen University Zhuhai519082 China University of Oulu Faculty of Information Technology and Electrical Engineering Oulu90570 Finland

ISBN: (纸本)9789887581543

We present a continuous reciprocal-kind Zhang dynamics (RKZD) model for solving the time-dependent linear matrixvector equation. On the basis of the model, we deduce its simplified form for solving the time-independent linear matrix-vector equation (TILMVE). Subsequently, for more efficient computation and easier implementation in digital hardware, we utilize Euler forward difference formula (EFDF) to discretize the continuous RKZD model, resulting in a discrete RKZD algorithm. Finally, numerical experimental results attest to the feasibility and high effectiveness of the discrete RKZD algorithm for solving TILMVE. Comparisons with the discrete gradient neural network (or termed discrete gradient dynamics), Jacobi iteration, as well as Gauss-Seidel iteration highlight the superior convergence properties of the discrete RKZD algorithm. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Classification and Contrast of Supervised Machine Learning Algorithms

Classification and Contrast of Supervised Machine Learning A...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Raman, Ramakrishnan Shamim, Rejuwan Akram, Shaik Vaseem Thakur, Lalit Pillai, Biju G. Ponnusamy, R. Symbiosis Institute of Business Management Maharashtra Pune India Maharishi University of Information Technology Department of Computer Science and Engineering with Data Science Noida India Uttaranchal University Uttaranchal Institute of Technology India Parul University Department of Civil India Biib & Dean - Faculty of Management Department of It & Business Analytics India Chennai Institute of Technology Department of Computer Science & Engineering India

ISBN: (纸本)9798350322309

Supervised Classification (SML) is the pursuit of systems that reasoning from externally given instances to generate broad hypotheses, which subsequently generate predictions for future instances. One of the jobs performed by intelligent systems most commonly is supervised classification. Based on the data set, number of occurrences and variables in this study, the most efficient classification algorithm is selected. It is comprehensively described and contrasted with various supervised learning methods. Seven distinct machine learning algorithms were taken into consideration utilizing the Waikato Environment for Data Analysis (WEDA) machine learning tool. For the identification process, the data set was used with 780 instances, eight independent variables (quality), and one dependent variable (variable). According to the data, SVM was the technique with the highest degree of precision and accuracy. Accordingly, the next accurate classification algorithms after SVM were determined to be Naive Bayes and Random Forest. The study demonstrates that precision (accuracy) and model construction time are two factors, whereas kappa statistics and mean error percentage (MAE) are two other factors. Therefore, controlled predictive machine learning requires precision, accuracy, and minimal error in ML algorithms. © 2023 IEEE.

关键词： Intelligent systems

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：