检索结果-内蒙古大学图书馆

Marine Ecosystem Monitoring: Applying Remote Sensing and AI to Track and Predict Coral Reef Health

Remote Sensing in Earth Systems sciences 2024年第4期7卷 486-499页

作者： Veeranjaneyulu, Rayavarapu Govindarajan, Dinesh Subramanian, Chandramohan Devi, Deva Uma Banerjee, Sudipta Edpuganti, Sai Krishna Upadhyay, Shrikant Department of Computer Science & amp Engineering PACE Institute of Technology and Sciences Andhra Pradesh Ongole India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur (KTR) Chennai India Department of ECE SCSVMV Deemed University Tamil Nadu Kanchipuram India Department of Computer Science and Engineering Gayatri Vidya Parishad College of Engineering (A) Andhra Pradhesh Visakhapatnam India Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) (SIU) Pune Campus Pune India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur Dist. India Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India

Coral reefs are essential ecosystems, supporting a diverse range of marine life and offering considerable ecological, economic, and cultural benefits. However, they face increasing threats from climate change, pollution, and other human activities. Thus, effective monitoring and management of coral reefs are crucial for their conservation and sustainability. In this study, we employed a hybrid model, HCNN-SVM, which combines convolutional neural networks (CNNs) for feature extraction and support vector machines (SVMs) for classification. We utilized a coral-reef dataset from Kaggle, containing images from CoralNet and the Moorea Coral Reef Long Term Ecological Research (MCR LTER). To enhance image quality and ensure accurate reflectance values, we applied radiometric, geometric, and water column corrections during preprocessing. Feature extraction involved the use of spectral indices such as the Coral Bleaching Index (CBI) and Normalized Difference Vegetation Index (NDVI) to detect healthy and stressed corals, along with texture analysis to differentiate substrates. The model was trained on this diverse dataset, which captures various environmental conditions and reef types, achieving an accuracy of 98.55%. Cross-validation methods were employed to evaluate model performance, ensuring robustness and generalizability. The HCNN-SVM model demonstrated high accuracy in identifying and mapping coral reef components, making it a powerful tool for monitoring coral reef health and supporting conservation efforts. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional neural networks (CNNs) Coral Bleaching Index (CBI) Coral reef monitoring Feature extraction HCNN-SVM Moorea Coral Reef Long Term Ecological Research (MCR LTER) Normalized Difference Vegetation Index (NDVI) Support vector machines (SVMs)

来源：评论

学校读者我要写书评

暂无评论

Effects of different organic fertilizers on nitrous oxide and methane emissions from double-cropping rice fields

引用

Pedosphere 2024年第1期34卷 52-62页

作者： Mingcheng HU Andrew J.WADE Weishou SHEN Zhenfang ZHONG Chongwen QIU Xiangui LIN Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Collaborative Innovation Center of Atmospheric Environment and Equipment TechnologySchool of Environmental Science and EngineeringNanjing University of Information Science&TechnologyNanjing 210044China Department of Geography and Environmental Science University of ReadingReading RG66 DWUK Haina Research Institute of Guangdong Haina Agricultural Co. Ltd.Huizhou 516000China State Key Laboratory of Soil and Sustainable Agriculture Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China

Rice fields are a major source of greenhouse gases,such as nitrous oxide (N_(2)O) and methane (CH_(4)).Organic fertilizers may potentially replace inorganic fertilizers to meet the nitrogen requirement for rice growth;however,the simultaneous effects of organic fertilizers on N_(2)O and CH_(4)emissions and crop yield in paddy fields remain poorly understood and *** this study,experimental plots were established in conventional double-cropping paddy fields in the Pearl River Delta,China,including an unfertilized control and five fertilizer treatments with fresh organic fertilizer (FOF),successively composted organic fertilizer (SOF),chemically composted organic fertilizer (COF),COF supplemented with inorganic fertilizer (COIF),and chemical fertilizers (CFs)(TFOF,TSOF,TCOF,TCOIF,and TCF,respectively).Paddy field soils behaved simultaneously as an N_(2)O sink (cumulative N_(2)O emission:-196 to-381 g N ha^(-1)) and as a CH_(4)source (cumulative CH_(4)emission:719 to 2 178 kg ha^(-1)).Compared to CFs,the effects of organic fertilizers on N_(2)O emission were not *** contrast,total annual CH_(4)emission increased by 157%,132%,125%,and 37%in TFOF,TCOF,TSOF,and TCOIF,respectively,compared to *** TCOIF,rice yield was maintained,while CH_(4)emission was not significantly increased from the paddy fields characterized by a prolonged flood *** important next step is to extend these field-based measurements to larger rice cultivation areas to quantify the regional and national-scale impacts on greenhouse gas emissions and to help determine the optimum practice for fertilizer use.

关键词： crop production global warming potential greenhouse gases manure paddy sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Analysis of Employee Attrition using Statistical and Machine Learning Approaches 1st

Analysis of Employee Attrition using Statistical and Machine...

引用

1st International Conference on Artificial Intelligence of Things, ICAIoT 2023

作者： Singh, Akash Kumar Thakral, Prateek Department of Computer Science and Engineering and Information Technology Jaypee University of Information Technology Waknaghat Himachal Pradesh Solan India

ISBN: (纸本)9783031487804

Attrition means exit of employees from an organization due to any reason. The exit may be voluntary or involuntary in nature. Increased rate of employee attrition leads to loss of an organization’s resources in terms of time, cost, customer satisfaction as well as talent acquisition team’s efforts. The pattern of statistical approaches used in this paper to study the causes of attrition provides insights for the decision makers of organizations about the possible constraints due to which employees may think of leaving. This paper analyses an employee dataset and proposes a machine learning based model with an F1 Score of 0.99 and accuracy of 98.63% that can be used and deployed by the companies on their datasets to predict attrition. The timely prediction of attrition using this method will help the companies to prevent the possible attrition of employees and will help in retaining them for good. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Machine Learning for Early Detection of Stroke and Haemorrhage

引用

computers, Materials & Continua 2022年第7期72卷 775-796页

作者： Zeyad Ghaleb Al-Mekhlafi Ebrahim Mohammed Senan Taha H.Rassem Badiea Abdulkarem Mohammed Nasrin M.Makbol Adwan Alownie Alanazi Tariq S.Almurayziq Fuad A.Ghaleb Department of Information and Computer Science College of Computer Science and EngineeringUniversity of Ha’ilHa’il81481Saudi Arabia Department of Computer Science&Information Technology Dr.Babasaheb Ambedkar Marathwada UniversityAurangabad431004India Faculty of Science and Technology Bournemouth UniversityPooleBH125BBUK Department of Computer Engineering College of Computer Science and EngineeringUniversity of Ha’ilHa’il81481Saudi Arabia College of Computer Science and Engineering Hodeidah UniversityHodeidah966Yemen School of Computing Faculty of EngineeringUniversiti Teknologi MalaysiaJohor BahruJohor81310Malaysia

Stroke and cerebral haemorrhage are the second leading causes of death in the world after ischaemic heart *** this work,a dataset containing medical,physiological and environmental tests for stroke was used to evaluate the efficacy of machine learning,deep learning and a hybrid technique between deep learning and machine learning on theMagnetic Resonance Imaging(MRI)dataset for cerebral *** the first dataset(medical records),two features,namely,diabetes and obesity,were created on the basis of the values of the corresponding *** t-Distributed Stochastic Neighbour Embedding algorithm was applied to represent the high-dimensional dataset in a low-dimensional data ***,the Recursive Feature Elimination algorithm(RFE)was applied to rank the features according to priority and their correlation to the target feature and to remove the unimportant *** features are fed into the various classification algorithms,namely,Support Vector Machine(SVM),K Nearest Neighbours(KNN),Decision Tree,Random Forest,and Multilayer *** algorithms achieved superior *** Random Forest algorithm achieved the best performance amongst the algorithms;it reached an overall accuracy of 99%.This algorithm classified stroke cases with Precision,Recall and F1 score of 98%,100%and 99%,*** the second dataset,the MRI image dataset was evaluated by using the AlexNet model and AlexNet+SVM hybrid *** hybrid model AlexNet+SVM performed is better than the AlexNet model;it reached accuracy,sensitivity,specificity and Area Under the Curve(AUC)of 99.9%,100%,99.80%and 99.86%,respectively.

关键词： Stroke cerebral haemorrhage deep learning machine learning t-SNE and RFE algorithms

来源：评论

学校读者我要写书评

暂无评论

Investigation of a New Stator Permanent Magnet with the effects of Flux-Reversal and Flux-Switching 16

Investigation of a New Stator Permanent Magnet with the effe...

引用

16th Annual Power Electronics, Drive Systems, and Technologies Conference, PEDSTC 2025

作者： Sarshar, Mohammad Reza Kondelaji, Mohammad Amin Jalali Mirsalim, Mojtaba Montazeri, Seyed Hamid Amirkabir University of Technology Tehran Polytechnic Department of Electrical Engineering Tehran Iran Department of Electrical Engineering and Computer Science Cambridge United States

ISBN: (纸本)9798331533946

This article studies a new stator-permanent magnet (PM) motor with flux-switching (FS) and flux-reversal (FR) effects synergies. The proposed structure benefits from the splitting stator pole PMs and consequent-pole FRPM, which reduces the PM utilization compared to the conventional ones. Also, the proposed structure is optimized by a random search multiobjective algorithm to attain the structure with the highest output torque and minimum torque ripple. Additionally, the proposed motor is compared to a conventional FSPM to investigate the advantages of the main motor. Using finite element analysis (FEA) studies, the flux density distribution results show that the FR effect lowers the saturation risk compared to FSPM. Also, the back-EMF generation of the proposed motor has improved by 135% compared to its benchmark. Correspondingly, fullload results show that the proposed topology has enhanced the average torque by 75% and deteriorated the ripple by about 55% compared to FSPM. Therefore, the proposed structure offers a profitable for high torque density applications. © 2025 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Evaluating Neighboring Site Group Queries with Constraint of Budget Range 23

Evaluating Neighboring Site Group Queries with Constraint of...

引用

11th International Conference on computer and Communications Management, ICCCM 2023

作者： Huang, Yuan-Ko Lin, Lien-Fa Department of Computer Science and Information Engineering National Kaohsiung University of Science and Technology Kaohsiung City Taiwan

ISBN: (纸本)9798400707735

In recent years, many of the location-based queries have been proposed that consider the proximity of spatial sites to provide users with information. However, most studies focus on a single type of sites and do not consider the cost of visiting the sites. As a result, in this paper we present a novel type of location-based queries, namely the Budget-Range-based neighboring site group query (or BR-based NSGQ for short), to find the groups of sites that are within a distance d of each other and have a total cost not exceeding a budget range [bgtm, bgtM]. The site groups are termed the neighboring site groups within budget range (abbreviated as NSGs-BR). In order to efficiently answer the BR-based NSGQs, we modify the R-tree structure to present the RcC-tree, and then design four checking rules to prune the non-qualifying site groups. We propose a query processing algorithm, namely the BR-based NSGQ algorithm, to find all the NSGs-BR by combing the traversal of the RcC-tree and the four checking rules. Finally, numerous experiments are evaluated to demonstrate the efficiency of the BR-based NSGQ algorithm in terms of the CPU time and the number of node accesses of the RcC-tree. © 2023 ACM.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Stacked Bi-LSTM for Advanced Toxicity Detection in Comment Classification 6

Stacked Bi-LSTM for Advanced Toxicity Detection in Comment C...

引用

6th IEEE International Conference on Artificial Intelligence in engineering and technology, IICAIET 2024

作者： Kumar, N. Naveen Abraham, Prabhakaran Kaliba, Syed Ibrahim Diniesh, V.C. Maruthamuthu, R. Balamurugan Seshu Kumar, P. Vekkudu, Naveen Madanapalle Institute of Technology & Science Department of Computer Applications Andhra Pradesh Madanapalle India Mai-nefhi College of Engineering and Technology Department of Computer Science and Engineering Mainefhi Eritrea Kongu Engineering College Department of Electronics & Communication Engineering Tamil Nadu Erode India Jain University Department of Information Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798350389692

The surge in Internet usage has revolutionized online forums, providing dynamic forums for active participation and meaningful debates. However, this has also exposed users to the risk of harassment. Efforts to address toxic comments in online forums have faced challenges, with current solutions unveiling unreliability. Advances in hardware, cloud computing, and natural language processing (NLP) enable the development of more robust approaches, predominantly NLP-based deep learning models. Pre-trained transformer models are gradually utilized for accurate toxic comment classification, bigger traditional methods. Stacked LSTM models, emphasizing hierarchical feature learning and improved contextual understanding, outperform single layer counterparts, offering an effective solution for online content moderation and sentiment analysis. This research indicates a significant stride towards more dependable and sophisticated toxic comment detection, addressing the challenges of social media effectively. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Fabrication of SiC particle dispersed AZ91D magnesium alloy composite by injection molding method and their properties

引用

Keikinzoku/Journal of Japan Institute of Light Metals 2024年第3期74卷 141-146页

作者： Hideshima, Yasutoshi Maeda, Fumiya Fukuta, Tadao Ozaki, Koichi Graduate School of Computer Science and Systems Engineering Okayama Prefectural University 111 Kuboki Okayama Soja-shi719-1197 Japan Process Technology Development Department Technology Development Division Seiko Epson Co. Suwa-shi Nagano Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama Soja-shi Japan

AZ91D magnesium alloy chips were coated with SiC powder using a binder, and injection molding was attempted using SiC powder coated magnesium chips as raw material. The metallurgical structure of the injection molded products showed uniform dispersion of SiC particles in the matrix, and there were no significant defects such as voids at the SiC particle-matrix interface. The hardness and 0.2% proof stress of the injection molded products tended to improve with increasing SiC content, while the elongation decreased with increasing SiC content. The Young's modulus of the injection molded products improved with increasing SiC content. It was confirmed that the specific bending rigidity of the injection molded products also improves due to the significant increase in the Young's modulus, although the addition of SiC leads to an increase in density. © 2024 The Japan Institute of Light Metals.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Enhanced Brain Tumor Classification from MRI Images Using Deep Learning Model 26

Enhanced Brain Tumor Classification from MRI Images Using De...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Rahman, Asadullah Bin Touhid Islam, Md. Islam, Md. Rashedul Sohrawordi, Md. Sultan, Md. Nahid Hajee Mohammad Danesh Science and Technology University Department of Computer Science and Engineering Dinajpur5200 Bangladesh

ISBN: (纸本)9798350359015

In the realm of image classification, traditional algorithms, encompassing both machine learning and deep learning, grapple with formidable challenges arising from uneven pixel ranges and dimensionality reduction. This results in a significant impediment to achieving accurate image categorization. Numerous examples of such traditional methods, including KNN, Random Forest, SVM, DNN, CNN etc, have encountered persistent issues such as inefficient performance of feature engineering, limited accuracy, etc. In response to these challenges, this paper introduces a novel image classification method that integrates pixel mapping, DWT, and CNN for improved efficiency and reliability. By resolving irregular pixel ranges through initial pixel mapping, our method establishes uniformity as a foundation for subsequent image analysis. Subsequently, DWT is employed to dissect and reduce image dimensionality, extracting essential features while lowering computational complexity. This two-step preprocessing approach forms a robust foundation for effective data classification. Within this framework, our proposed CNN architecture plays a pivotal role, utilizing both spectral and spatial information to address image categorization challenges. The network's capacity to learn complex patterns enhances classification accuracy. In extensive evaluations, our methodology surpasses conventional classification techniques, yielding impressive results. With an Overall Accuracy (OA) of 96.9% and a Kappa statistic of 95.16%, our method showcases excellence and practical potential. These compelling achievements underscore the significance of our approach in tackling image classification challenges, paving the way for enhanced precision and efficiency across various domains. © 2023 IEEE.

关键词： Brain Tumor CNN Contrast Enhanced MRI(CE-MRI) Discrete Wavelet Transformation(DWT)

来源：评论

学校读者我要写书评

暂无评论

CDA-GNN: A Chain-driven Accelerator for Efficient Asynchronous Graph Neural Network 24

CDA-GNN: A Chain-driven Accelerator for Efficient Asynchrono...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Yu, Hui Zhang, Yu He, Ligang He, Donghao Li, Qikun Zhao, Jin Liao, Xiaofei Jin, Hai Gu, Lin Liu, Haikun National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798400706011

Asynchronous Graph Neural Network (AGNN) has attracted much research attention because it enables faster convergence speed than the synchronous GNN. However, existing software/hardware solutions suffer from redundant computation overhead and excessive off-chip communications for AGNN due to irregular state propagations along the dependency chains between vertices. This paper proposes a chain-driven asynchronous accelerator, CDA-GNN, for efficient AGNN inference. Specifically, CDA-GNN proposes a chain-driven asynchronous execution approach into novel accelerator design to regularize the vertex state propagations for fewer redundant computations and off-chip communications and also designs a chain-aware data caching method to improve data locality for AGNN. We have implemented and evaluated CDA-GNN on a Xilinx Alveo U280 FPGA card. Compared with the cutting-edge software solutions (i.e., Dorylus and AMP) and hardware solutions (i.e., BlockGNN and FlowGNN), CDA-GNN improves the performance of AGNN inference by an average of 1,173x, 182.4x, 10.2x, and 7.9x and saves energy by 2,241x, 242.2x, 12.4x, and 8.9x, respectively. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph 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：