检索结果-内蒙古大学图书馆

Fine-Scale Mangrove Species Classification Based on UAV Multispectral and Hyperspectral Remote Sensing Using machine learning

引用

REMOTE SENSING 2024年第16期16卷

作者： Yang, Yuanzheng Meng, Zhouju Zu, Jiaxing Cai, Wenhua Wang, Jiali Su, Hongxin Yang, Jian Nanning Normal Univ Key Lab Environm Change & Resources Use Beibu Gulf Nanning 530001 Peoples R China Guangxi Beihai Wetland Ecosyst Natl Observat & Res Beihai 536001 Peoples R China Univ Kentucky Dept Forestry & Nat Resources TP Cooper Bldg Lexington KY 40546 USA

Mangrove ecosystems play an irreplaceable role in coastal environments by providing essential ecosystem services. Diverse mangrove species have different functions due to their morphological and physiological characteristics. A precise spatial distribution map of mangrove species is therefore crucial for biodiversity maintenance and environmental conservation of coastal ecosystems. Traditional satellite data are limited in fine-scale mangrove species classification due to low spatial resolution and less spectral information. This study employed unmanned aerial vehicle (UAV) technology to acquire high-resolution multispectral and hyperspectral mangrove forest imagery in Guangxi, China. We leveraged advanced algorithms, including RFE-RF for feature selection and machine learning models (Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Light Gradient Boosting machine (LightGBM)), to achieve mangrove species mapping with high classification accuracy. The study assessed the classification performance of these four machine learning models for two types of image data (UAV multispectral and hyperspectral imagery), respectively. The results demonstrated that hyperspectral imagery had superiority over multispectral data by offering enhanced noise reduction and classification performance. Hyperspectral imagery produced mangrove species classification with overall accuracy (OA) higher than 91% across the four machine learning models. LightGBM achieved the highest OA of 97.15% and kappa coefficient (Kappa) of 0.97 based on hyperspectral imagery. Dimensionality reduction and feature extraction techniques were effectively applied to the UAV data, with vegetation indices proving to be particularly valuable for species classification. The present research underscored the effectiveness of UAV hyperspectral images using machine learning models for fine-scale mangrove species classification. This approach has the potential to significantly impr

关键词： mangrove hyperspectral machine learning algorithms unmanned aerial vehicle species classification

来源：评论

学校读者我要写书评

暂无评论

Exploring Quantum machine learning for Enhanced Skin Lesion Classification: A Comparative Study of Implementation Methods

引用

IEEE ACCESS 2024年 12卷 104568-104584页

作者： Reka, S. Sofana Karthikeyan, H. Leela Shakil, A. Jack Venugopal, Prakash Muniraj, Manigandan Vellore Inst Technol Ctr Smart Grid Technol Sch Elect Engn Chennai 600127 India Vellore Inst Technol Sch Elect Engn Chennai 600127 India

Skin diseases affect millions of people worldwide, leading to significant healthcare burdens and challenges in diagnosis and treatment. In the past few years, machine learning techniques have demonstrated potential in assisting dermatologists with diagnosing various skin conditions. As in, conventional machine learning algorithms might encounter challenges in handling the complexity and distinction of skin disease classification tasks, primarily because of the intricate nature of medical image data with its high dimensional properties. In this work, the main analysis is done based on exploring quantum machine learning models for skin disease classification. This approach blends with the aspects of quantum computing with the conventional machine learning techniques to push the boundaries of skin disease classification. This work harnesses the HAM10000 dataset, an extensive compilation of categorized images portraying common skin lesions, to train and assess the efficacy of the proposed methodologies. Quantum computing libraries such as PennyLane and Qiskit is used in this study. Using different combination of qubit rotation encoding and decoding using three types of Pauli gates such as Pauli X, Y and Z gates are implemented and compared using proposed Quanvolutional neural network. Features extracted using MobileNet pre-trained network is used to build Quantum support vector classifier. These quantum machine learning models are compared with some well-known pre-trained models such as Resnet50, Inception-Resnet, Densenet121, DenseNet201 and MobileNet. The combination of RY qubit rotation and PauliZ gate in quantum convolution layer in Quanvolutional neural network produced the optimal classification accuracy of 82.86% more than any other models included in this study. In contrast, Quantum Support Vector Classifier produced similar classification accuracy of 72.5% with respect to pre-trained models.

关键词： Skin Diseases Accuracy Computational modeling machine learning Lesions machine learning algorithms HAM10000 dataset Qiskit quantum machine learning quanvolutional neural network quantum support vector classifier skin lesion PennyLane

来源：评论

学校读者我要写书评

暂无评论

Effluent parameters prediction of a biological nutrient removal (BNR) process using different machine learning methods: A case study

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2024年 351卷 119899页

作者： Manav-Demir, Neslihan Gelgor, Huseyin Baran Oz, Ersoy Ilhan, Fatih Ulucan-Altuntas, Kubra Tiwary, Abhishek Debik, Eyup Yildiz Tech Univ Environm Engn Dept TR-34220 Istanbul Turkiye Yildiz Tech Univ Stat Dept TR-34220 Istanbul Turkiye Istanbul Tech Univ Environm Engn Dept TR-34469 Istanbul Turkiye De Montfort Univ Sch Engn & Sustainable Dev Gateway Leicester LE1 9BH England

This paper proposes a novel targeted blend of machine learning (ML) based approaches for controlling waste-water treatment plant (WWTP) operation by predicting distributions of key effluent parameters of a biological nutrient removal (BNR) process. Two years of data were collected from Plajyolu wastewater treatment plant in Kocaeli, Turkiye and the effluent parameters were predicted using six machine learning algorithms to compare their performances. Based on mean absolute percentage error (MAPE) metric only, support vector regression machine (SVRM) with linear kernel method showed a good agreement for COD and BOD5, with the MAPE values of about 9% and 0.9%, respectively. Random Forest (RF) and EXtreme Gradient Boosting (XGBoost) regression were found to be the best algorithms for TN and TP effluent parameters, with the MAPE values of about 34% and 27%, respectively. Further, when the results were evaluated together according to all the performance metrics, RF, SVRM (with both linear kernel and RBF kernel), and Hybrid Regression algorithms generally made more successful predictions than Light GBM and XGBoost algorithms for all the parameters. Through this case study we demonstrated selective application of ML algorithms can be used to predict different effluent parameters more effectively. Wider implementation of this approach can potentially reduce the resource demands for active monitoring the environmental performance of WWTPs.

关键词： Municipal wastewater treatment Biological nutrient removal (BNR) process machine learning machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter learning Under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimization

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2024年第11期35卷 16008-16022页

作者： Carnerero-Cano, Javier Munoz-Gonzalez, Luis Spencer, Phillippa Lupu, Emil C. Imperial Coll London London SW7 2AZ England Def Sci & Technol Lab Dstl Salisbury SP4 0JQ Wilts England

machine learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal attacks can be formulated as bilevel optimization problems and help to assess their robustness in worst case scenarios. We show that current approaches, which typically assume that hyperparameters remain constant, lead to an overly pessimistic view of the algorithms' robustness and of the impact of regularization. We propose a novel optimal attack formulation that considers the effect of the attack on the hyperparameters and models the attack as a multiobjective bilevel optimization problem. This allows us to formulate optimal attacks, learn hyperparameters, and evaluate robustness under worst case conditions. We apply this attack formulation to several ML classifiers using L2 and L1 regularization. Our evaluation on multiple datasets shows that choosing an "a priori" constant value for the regularization hyperparameter can be detrimental to the performance of the algorithms. This confirms the limitations of previous strategies and evidences the benefits of using L2 and L1 regularization to dampen the effect of poisoning attacks, when hyperparameters are learned using a small trusted dataset. Additionally, our results show that the use of regularization plays an important robustness and stability role in complex models, such as deep neural networks (DNNs), where the attacker can have more flexibility to manipulate the decision boundary.

关键词： Training Robustness Optimization machine learning algorithms Classification algorithms Training data Toxicology Adversarial machine learning (ML) bilevel optimization data poisoning attacks hyperparameter optimization regularization

来源：评论

学校读者我要写书评

暂无评论

machine learning-based technology for asphalt concrete pavement performance decision-making in hot and humid climates

引用

CONSTRUCTION AND BUILDING MATERIALS 2024年 442卷

作者： Mansour, Elise Dhasmana, Heena Mousa, Momen R. Hassan, Marwa Louisiana State Univ Coll Engn Baton Rouge LA 70803 USA Sam Houston State Univ Dept Engn Technol Huntsville TX USA

Highway state agencies incur significant budget savings through optimal allocation of pavement Maintenance, Rehabilitation, and Reconstruction (MR&R) &R) activities. These activities require robust prediction models that can handle large-scale, real-world data and can forecast pavement performance in the long run. Unfortunately, the traditional performance prediction models have been questionable in terms of efficiency and accuracy, are based on a limited number of explanatory variables, and are designated to predict short-term (up to five years) pavement conditions. Therefore, the goal of this study was to propose a machine learning-based technology that can predict the field performance by up to 11 years of Asphalt Concrete (AC) overlays placed on asphalt pavements in Southern states in the US based on key project conditions. The proposed technology resulted from assessing the prediction accuracy of machine learning algorithms, including Decision-Tree (DT), eXtreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), and ensemble-learning method, in forecasting the Pavement Condition Index (PCI) as the pavement performance indicator. For each algorithm, six models were developed sequentially based on historical pavement condition data collected from the Louisiana Department of Transportation and Development (LaDOTD) Pavement Management System (PMS) database. The six models learned from 892 log miles of randomly placed AC overlay sections in Louisiana. The output of these models was the future PCI of AC overlays at a biannual rate from one to 11 years. The findings showed that XGBoost and ensemble learning showed similar performance during model training and were further evaluated using the testing dataset. During model testing, the ensemble learning method yielded higher prediction accuracy than other algorithms, with R2 2 values decreasing from 0.77 at age 1 to 0.67 at age 11, Root Mean Square Error (RMSE) values increasing from +1.65 to +4.74, and Mean

关键词： Pavement Performance Modeling Pavement Condition Index machine learning algorithms Decision Tree XGBoost Artificial Neural Network Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Identification of chronic non-atrophic gastritis and intestinal metaplasia stages in the Correa's cascade through machine learning analyses of SERS spectral signature of non-invasively-collected human gastric fluid samples

引用

BIOSENSORS & BIOELECTRONICS 2024年 262卷 116530页

作者： Si, Yu-Ting Xiong, Xue-Song Wang, Jin-Ting Yuan, Quan Li, Yu-Ting Tang, Jia-Wei Li, Yong-Nian Zhang, Xin-Yu Li, Zheng-Kang Lai, Jin-Xin Umar, Zeeshan Yang, Wei-Xuan Li, Fen Wang, Liang Gu, Bing Xuzhou Med Univ Med Technol Sch Xuzhou Jiangsu Peoples R China Yangzhou Univ Huaian Hosp Peoples Hosp Huaian 5 Huaian Jiangsu Peoples R China Xuzhou Med Univ Sch Med Informat & Engn Xuzhou Jiangsu Peoples R China Southern Med Univ Guangdong Prov Peoples Hosp Guangdong Acad Med Sci Guangzhou Guangdong Peoples R China Shenzhen Univ Sch Med Marshall Lab Biomed Engn Shenzhen Guangdong Peoples R China Univ Western Australia Sch Biomed Sci Div Microbiol & Immunol Crawley WA Australia Edith Cowan Univ Ctr Precis Hlth Sch Med & Hlth Sci Joondalup WA 6027 Australia

The progression of gastric cancer involves a complex multi-stage process, with gastroscopy and biopsy being the standard procedures for diagnosing gastric diseases. This study introduces an innovative non-invasive approach to differentiate gastric disease stage using gastric fluid samples through machine-learning-assisted surfaceenhanced Raman spectroscopy (SERS). This method effectively identifies different stages of gastric lesions. The XGBoost algorithm demonstrates the highest accuracy of 96.88% and 91.67%, respectively, in distinguishing chronic non-atrophic gastritis from intestinal metaplasia and different subtypes of gastritis (mild, moderate, and severe). Through blinded testing validation, the model can achieve more than 80% accuracy. These findings offer new possibilities for rapid, cost-effective, and minimally invasive diagnosis of gastric diseases.

关键词： String test Gastric fluid Chronic non-atrophic gastritis Intestinal metaplasia Surface-enhanced Raman spectroscopy machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

FairerML: An Extensible Platform for Analysing, Visualising, and Mitigating Biases in machine learning

引用

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 2024年第2期19卷 129-141页

作者： Yuan, Bo Gui, Shenhao Zhang, Qingquan Wang, Ziqi Wen, Junyi Mao, Bifei Liu, Jialin Yao, Xin Southern Univ Sci & Technol Shenzhen Peoples R China Huawei Technol Co Ltd Shenzhen Peoples R China

Given the growing concerns about bias in machine learning, dozens of metrics have been proposed to measure the fairness of machine learning. Several platforms have also been developed to compute and illustrate fairness metrics on platform-provided data. However, most platforms do not provide a user-friendly interface for users to upload and evaluate their own data or machine learning models. Moreover, no known platform is capable of training machine learning models, while considering their fairness and accuracy simultaneously. Motivated by the above insufficiency, this work develops FairerML, an extensible platform for analysing, visualising, and mitigating biases in machine learning. Three core functionalities are implemented in FairerML: fairness analysis of user-uploaded datasets, fairness analysis of user-uploaded machine learning models, and the training of a set of Pareto models considering accuracy and fairness metrics simultaneously by using multiobjective learning. The clear visualisation and description of the fairness analysis and the configurable model training process of FairerML make it easy for training fairer machine learning models and for educational purposes. In addition, new fairness metrics and training algorithms can be easily integrated into FairerML thanks to its extendability.

关键词： Training Measurement Analytical models machine learning algorithms Computational modeling Data visualization machine learning

来源：评论

学校读者我要写书评

暂无评论

Malware Detection With Subspace learning-Based One-Class Classification

引用

IEEE ACCESS 2024年 12卷 81017-81029页

作者： Al-Khshali, Hasan H. Ilyas, Muhammad Sohrab, Fahad Gabbouj, Moncef Altinbas Univ Dept Elect & Comp Engn TR-34217 Istanbul Turkiye Al Ain Univ Coll Engn Dept Cybersecur Abu Dhabi U Arab Emirates Tampere Univ Fac Informat Technol & Commun Sci Tampere 33014 Finland Haltian Oulu 90230 Finland

Detecting malware is crucial for ensuring the security of computer systems. Traditional machine learning models face challenges in effectively detecting malware, mainly due to the class imbalance problem, where the number of malware samples is significantly smaller than that of non-malware samples. Additionally, malware's dynamic and evolving nature, continuously altering its structure and tactics, presents a substantial challenge for conventional artificial intelligence algorithms, further complicating the detection task. In pursuing an optimized malware detection technique, researchers initially explored traditional machine learning algorithms, focusing on the features of Portable Executable (PE) file headers. However, the inherent issues, such as imbalanced datasets and the deceptive nature of malware, have raised concerns about the credibility of the attained results. This can result in misclassifying malware as non-malware, leading to security vulnerabilities. One-Class Classification (OCC) methods have emerged as a promising approach to improve the detection of unknown malware. However, traditional OCC approaches face the challenge of the curse of dimensionality. This research proposes adapting subspace learning-based OCC methods to overcome the curse of dimensionality and effectively handle the class imbalance problem. We propose a pipeline for detecting malware using methods that jointly optimize a subspace and data description for OCC. We evaluate the performance of various one-class classifiers on three different datasets. We observed that the subspace-learning-based OCC is a promising approach. Evaluating various classifiers on three datasets reveals promising results, with a True Positive Rate (TPR) of 100 % for subspace-learning-based OCC. The proposed pipeline can serve as a valuable tool for improving the security of computer systems by accurately detecting malware and protecting against potential attacks.

关键词： Malware Feature extraction Vectors Random forests machine learning algorithms Training Software algorithms Support vector machines machine learning malware one-class classification portable executable subspace support vector data description graph embedding

来源：评论

学校读者我要写书评

暂无评论

Predicting Medium-Term Stock Index Direction Using Constituent Stocks and machine learning

引用

IEEE ACCESS 2024年 12卷 84968-84983页

作者： Bareket, A. Parv, B. Babes Bolyai Univ Fac Math & Comp Sci Cluj Napoca 400347 Romania

Predicting stock index movements is challenging due to market randomness. This paper addresses the problem of predicting medium-term stock index direction, an area with limited coverage in existing literature. We propose a novel model based on machine learning algorithms that employs relative indicators of constituent stocks within an index. The objective is to identify market entry points where the likelihood of achieving a significant return threshold is higher. To achieve this, supervised binary classifiers and other machine learning techniques have been applied, setting the class label '1' for significant index rises occurring within a defined medium term of 70 trading days and the class label '0' otherwise. Three indices were investigated: Nasdaq 100, where a significant rise was defined as a 10% increase, Dow Jones Industrial Average with an 8% increase, and the German Dax at 6%. Our investigation into different methods of utilizing constituent stocks revealed that focusing on the most weighted stocks yields the most promising results across various stock indices. The proposed model dynamically selects the most effective classifiers, SVM, KNN, Voting Classifier, and RF, tailored to varying market conditions. Employing a rolling forecast method, it utilizes the relative indicators on heavily weighted stocks and the index, demonstrating accuracy up to 0.97 and F1-scores for the '1' label up to 0.90. This enhances the ability to determine the optimal timing for market entry and, crucially, when the chances for high returns are limited. Additionally, we illuminate the conditions under which the model is most effective.

关键词： Indexes Symbols machine learning Correlation Sorting Predictive models Support vector machines Stock markets Constituent stocks within an index machine learning algorithms predicting medium-term stock index direction relative indicators

来源：评论

学校读者我要写书评

暂无评论

SiO2 Nanolayer Regulated Ag@Cu Core-Shell SERS Platform Integrated machine learning for Intelligent Identification of Jujuboside A, Saikosaponin A and Timosaponin A-III

IEEE PHOTONICS JOURNAL

引用

IEEE PHOTONICS JOURNAL 2024年第4期16卷 1-9页

作者： Zhou, Wenying Han, Xue Wu, Yanjun Shi, Guochao Xu, Shiqi Wang, Mingli Yuan, Wenzhi Cui, Jiahao Li, Zelong Chengde Med Univ Hebei Int Res Ctr Med Engn Chengde 067000 Peoples R China Chengde Med Univ Affiliated Hosp Dept Neurol Chengde 067000 Peoples R China Yanshan Univ Sch Sci State Key Lab Metastable Mat Sci & Technol Key Lab Microstruct Mat Phys Hebei Prov Qinhuangdao 066004 Peoples R China

An effective SERS-based detection method assisted by machine learning algorithm has been developed to intelligently identify the pharmacodynamic substances in traditional Chinese medicine (TCM) which aided in the quality control and identification of TCM. In this work, the ultrasensitive grating-like core-shell Ag@SiO2@Cu@moth wing (Ag@SiO2@Cu@MW) SERS platform was explored which can precisely control the intergap distances by adjusting the thickness of the SiO2 layer. This SERS platform demonstrated reproducibility and reliability, with a low relative standard deviation (RSD) of 7.38% and an enhancement factor (EF) of 2.49 x 10(7). The optimized Ag-30@SiO2(4)@Cu-20@MW substrate were then applied in the accurately analyzing pharmacodynamic substances. Specifically, the label-free SERS analysis showed the distinct spectral features for Jujuboside A, Saikosaponin A and Timosaponin A-III. machine learning algorithms, such as principal component analysis (PCA), decision tree (DT), support vector machine (SVM), k-nearest neighbors (kNN) were employed and further in differentiating with the three pharmacodynamic substances Raman spectrum groups. These results indicate that SERS technology in combination with machine learning algorithms can not only achieve rapid and accurate detection of different types of pharmacodynamic substances, but also promote the modernization and international application of TCM.

关键词： Pharmacodynamics Substrates Gratings machine learning Magnetic cores machine learning algorithms Electromagnetics Grating-like core-shell structure machine learning pharmacodynamic substances in traditional Chinese medicine SERS

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：