检索结果-内蒙古大学图书馆

Earthquake probability assessment using gumbel extreme value statistics and mapping intensity based isoseismal and land use land cover dynamics with machine learning

引用

PHYSICS AND CHEMISTRY OF THE EARTH 2025年 138卷

作者： Siddhardha, R. Gonavaram, Kalyan Kumar Natl Inst Technol Warangal Civil Engn Dept Warangal 506004 Telangana India

The objective of the present study is to estimate seismicity parameters, evaluate earthquake occurrence probabilities and return periods, perform site characterization, and develop integrated intensity based isoseismal and land use land cover (LULC) maps using advanced statistical and machine learning algorithms for Prakasam district, Andhra Pradesh, in Peninsular India. The estimated seismicity parameters a and b values range from 3.78-4.06 to 0.81-0.83. The probability of occurrence of a 7.5Mw earthquake in the next 1, 25, 50, 75 and 100 years was computed to be 0.2%, 5.6%, 10.9%, 15.9%, and 20.6%, respectively, with a corresponding return period of 434 years. Topography based site characterization was performed utilizing Cartosat-1 PAN Digital elevation model dataset, and spatial variation of Vs30 map was developed for Prakasam district. Intensity based isoseismal maps were developed for six historical earthquakes in the study area, and LULC classification was conducted using advanced statistical and machine learning algorithms such as Maximum likelihood (ML), Random forest (RF), and Support vector machine (SVM) through Landsat satellite imagery. The performance of ML, SVM, and RF was evaluated using overall accuracy (OA), with the SVM classifier achieving the highest OA of 96.21% in classifying various land classes. Finally, integrated intensity based isoseismal and LULC maps for the past six historical earthquakes were developed.

关键词： Isoseismal maps machine learning algorithms Site characterization and Land use land cover classification

来源：评论

学校读者我要写书评

暂无评论

Urine Analysed by FTIR, Chemometrics and machine learning Methods in Determination Spectroscopy Marker of Prostate Cancer in Urine

引用

JOURNAL OF BIOPHOTONICS 2025年第1期18卷 e202400278页

作者： Mitura, Przemyslaw Paja, Wieslaw Klebowski, Bartosz Plaza, Pawel Bar, Krzyszof Mlynarczyk, Grzegorz Depciuch, Joanna Med Univ Lublin Dept Urol & Oncol Urol Lublin Poland Univ Rzeszow Inst Comp Sci Dept Artificial Intelligence Rzeszow Poland Polish Acad Sci Inst Nucl Phys Krakow Poland Med Univ Bialystok Dept Urol Bialystok Poland Med Univ Lublin Dept Biochem & Mol Biol Lublin Poland

Prostate-specific antigen (PSA) is the most commonly used marker of prostate cancer. However, nearly 25% of men with elevated PSA levels do not have cancer and nearly 20% of patients with prostate cancer have normal serum PSA levels. Therefore, in this study, Fourier transform infrared (FTIR) spectroscopy was investigated as a new tool for detection of prostate cancer from urine. Obtained results showed higher levels of glucose, urea and creatinine in urine collected from patients with prostate cancer than that in control. Principal component analysis (PCA) was not noticed possibility of differentiation urine collected from healthy and nonhealthy patients. However, machine learning algorithms showed 0.90 accuracy and precision of FTIR in detection of prostate cancer from urine. We showed that wavenumbers at 1614 cm-1 and 2972 cm-1 were candidates for prostate cancer spectroscopy markers. Importantly, these FTIR markers correlated with Gleason score, PSA and mpMRI PI-RADS category.

关键词： cancer marker FTIR machine learning algorithms prostate cancer urine

来源：评论

学校读者我要写书评

暂无评论

Amachine learning technique embedded reference-dependent choice model for explanatory power improvement: Shifting of reference point as a key factor in vehicle purchase decision-making

引用

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL 2025年 191卷

作者： Kim, Kyungah Kim, Jinseok Park, Subin Lee, Jongsu Kim, Junghun Seoul Natl Univ Technol Management Econ & Policy Program 1 Gwanak Ro Seoul 08826 South Korea Korea Univ Grad Sch Management Technol 145 Anam Ro Seoul 02841 South Korea Stanford Univ Walter H Shorenstein Asia Pacific Res Ctr 616 Jane Stanford Way Stanford CA 94305 USA

machine learning is a powerful tool with the potential to improve a choice model's ability to explain consumer behavior. Although the reference-dependent choice model, developed with an emphasis on real decision-making processes, has an advantage over general discrete choice models in terms of explanatory power and interpretability, there is still a lack of consensus on how the reference point should be set. Currently, the common practice is to design a reference point-based utility equation to make an arbitrary decision between past experience, the status quo, and future expectations as the reference point. However, as individual consumers may differ from researchers in how they set their reference points, the current method is rather limited for understanding consumer choice behavior. Therefore, this study proposes a new approach to more accurately understand consumer choice behavior by shifting individual reference points using ANNs (Artificial Neural Networks). The analysis results show that the model proposed in this study has better explanatory power than both the discrete choice model and the existing reference-dependent choice model. This implies that the reference point typically set by researchers approximates each individual's actual reference point through artificial neural networks. This study is significant in that it confirms the possibility that the current status, which showed the highest model fit among several reference price proxy candidates in vehicle choice, may not function as the actual reference price, while also proposing a foundational framework for identifying each consumer's true reference price. Furthermore, it can contribute to corporate strategies and government policy recommendations based on consumer preference analysis, where high explanatory power is required.

关键词： Discrete choice experiment Reference-dependent preferences Purchasing price Reference point heterogeneity Reference point shifting machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

FRAME: Feature Rectification for Class Imbalance learning

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第3期37卷 1167-1181页

作者： Cheng, Xu Shi, Fan Zhang, Yao Li, Huan Liu, Xiufeng Chen, Shengyong Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300386 Peoples R China Aalborg Univ Dept Comp Sci DK-9220 Aalborg Denmark Tech Univ Denmark Dept Technol Management & Econ DK-2800 Kongens Lyngby Denmark

Class imbalance learning is a challenging task in machine learning applications. To balance training data, traditional class imbalance learning approaches, such as class resampling or reweighting, are commonly applied in the literature. However, these methods can have significant limitations, particularly in the presence of noisy data, missing values, or when applied to advanced learning paradigms like semi-supervised or federated learning. To address these limitations, this paper proposes a novel and theoretically-ensured latent Feature Rectification method for clAss iMbalance learning (FRAME). The proposed FRAME can automatically learn multiple centroids for each class in the latent space and then perform class balancing. Unlike data-level methods, FRAME balances feature in the latent space rather than the original space. Compared to algorithm-level methods, FRAME can distinguish different classes based on distance without the need to adjust the learning algorithms. Through latent feature rectification, FRAME can effectively mitigate contaminated noises/missing values without worrying about structural variations in the data. In order to accommodate a wider range of applications, this paper extends FRAME to the following three main learning paradigms: fully-supervised learning, semi-supervised learning, and federated learning. Extensive experiments on 10 binary-class datasets demonstrate that our FRAME can achieve competitive performance than the state-of-the-art methods and its robustness to noises/missing values.

关键词： Data models Noise Classification algorithms machine learning Neural networks Training Noise measurement machine learning algorithms Federated learning Fans Class imbalance learning feature rectification latent space learning paradigm

来源：评论

学校读者我要写书评

暂无评论

Improving transformer failure classification on imbalanced DGA data using data-level techniques and machine learning

引用

ENERGY REPORTS 2025年 13卷 264-277页

作者： Azmi, Putri Azmira R. Yusoff, Marina Sallehud-din, Mohamad Taufik Mohd Univ Teknol MARA UiTM Coll Comp Informat & Math Shah Alam 40450 Selangor Malaysia Univ Teknol MARA UiTM Inst Big Data Analyt & Artificial Intelligence IBD Shah Alam 40450 Selangor Malaysia Sohar Univ Fac Business Sohar 311 Oman Kawasan Inst Bangi PETRONAS Res Sdn Bhd Bandar Baru Bangi 43000 Selangor Malaysia

This study addresses the challenge of imbalanced dissolved gas analysis (DGA) data in transformer failure classification by assessing the impact of data-level balancing techniques on machine learning performance. Five data-level strategies - Random Under-Sampling (RUS), Edited Nearest Neighbors (ENN), NearMiss (NM), Random Over-Sampling (ROS), and ADASYN - were applied to balance the dataset and improve classification outcomes. The dataset includes key gas concentrations (H2, CH4, C2H6, C2H4, and C2H2) and a target defect variable (act). Three machine learning algorithms - Support Vector machine, Decision Tree, and Random Forest - were tested, with results showing that ENN combined with SVM achieved the highest classification performance: 88% accuracy, 89.89% precision, 88.00% recall, 86.64% F1-score, and a runtime of 0.21 s. This approach demonstrates the effectiveness of data-level techniques in improving transformer fault diagnosis, offering a robust path forward for enhancing electrical power system reliability. Future research should refine these techniques and explore their integration with optimized models to enhance the accuracy of the proposed technique.

关键词： Imbalanced data Dissolved gas analysis machine learning algorithms Data-level techniques

来源：评论

学校读者我要写书评

暂无评论

Integrating Sentiment Analysis With machine learning for Cyberbullying Detection on Social Media

引用

IEEE ACCESS 2025年 13卷 78348-78359页

作者： Almufareh, Maram Fahaad Jhanjhi, Noor Zaman Humayun, Mamoona Alwakid, Ghadah Naif Javed, Danish Almuayqil, Saleh Naif Jouf Univ Coll Comp & Informat Sci Dept Informat Syst Sakaka 72311 Saudi Arabia Taylors Univ Sch Comp Sci Lakeside Campus Subang Jaya 47500 Selangor Malaysia Univ Roehampton London Sch Arts Humanities & Social Sci Dept Comp London SW15 5PH England Jouf Univ Coll Comp & Informat Sci Dept Comp Sci Sakaka 72311 Saudi Arabia

The phenomenon of cyberbullying has emerged as a critical challenge in the digital landscape which poses detrimental effects on individuals and broader societal frameworks. A viable approach to addressing this pervasive issue lies in the accurate identification of cyberbullying within social media as it constitutes a substantial portion of digital interactions. State-of-the-art solutions predominantly rely on pre-trained language models and machine learning algorithms;however, these methods are often associated with substantial computational overheads and the development of advanced cyberbullying detection algorithms remains limited. This paper presents a unique framework that integrates sentiment analysis with machine learning algorithms to enhance the detection of cyberbullying on social media. Sentiment analysis explores the linguistic and emotional characteristics of cyberbullying messages which helps the framework to identify key sentiment indicators that differentiate harmful interactions from benign ones. Furthermore, we provide the most optimal text preprocessing steps which are ordered in a way that improves text quality for cyberbullying detection. These steps ensure high-quality input data for machine learning models which significantly enhances their performance. Additionally, we tackle the challenge of penta-class imbalanced data by incorporating resampling within the framework without causing bias. We employ several machine learning algorithms within the framework, the Extra Tree classifier achieved the best results with an accuracy of 95.38% and F1 score of 0.95. The results demonstrate that the integration of sentiment analysis significantly improves classification accuracy compared to conventional methods for the task of cyberbullying detection.

关键词： Cyberbullying Accuracy Sentiment analysis Computational modeling Feature extraction Support vector machines machine learning algorithms Blogs Training Linguistics Cyberbullying detection sentiment analysis machine learning resampling

来源：评论

学校读者我要写书评

暂无评论

LASSO-mCGA: machine learning and Modified Compact Genetic Algorithm-Based Biomarker Selection for Breast Cancer Subtype Classification

引用

IEEE ACCESS 2025年 13卷 17673-17682页

作者： Ghosh, Nimisha Kumar Mridha, Sankar Paul, Rourab Siksha O Anusandhan Ctr Internet Things Dept Comp Sci & Engn Bhubaneswar 751030 India Siksha O Anusandhan Dept Comp Sci & Informat Technol Bhubaneswar 751030 India Siksha O Anusandhan Dept Comp Sci & Engn Bhubaneswar 751030 India

Breast cancer is the most common cancer type among females and is one of the leading causes of death worldwide. Being a heterogeneous disease, subtyping breast cancer plays a vital role in its treatment. In this regard, gene expression plays an important role. Thus, in this work gene expression data is used to identify the most significant gene biomarkers. The identified biomarkers are highly associated with each breast cancer subtype such as Luminal A, Luminal B, HER2-Enriched and Basal-Like. To identify such biomarkers, initially LASSO in association with four machine learning models such as Random Forest (RF), Support Vector machine (SVM), K-Nearest Neighbours (KNN) and Naive Bayes (NB) are applied on the dataset to find the initial reduced set of genes as well as the best learning model based on classification accuracy;SVM in this case. Thereafter, Modified Compact Genetic Algorithm (mCGA) is performed to identify the final set of genes as biomarkers for each specific subtype. Experimental results suggest that our proposed method assesses AUC-ROC values of 0.9878 and 0.97311 for LumA and LumB and 1 for Basal and HER2 subtypes. To validate the biological significance of the identified biomarkers, KEGG pathway and GO enrichment analysis are carried out.

关键词： Breast cancer Support vector machines Accuracy Feature extraction Genetic algorithms machine learning Gene expression Pipelines machine learning algorithms Vectors Biomarker breast cancer feature selection LASSO modified compact genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

SASE-TCN: A Multitask learning Network for MDS-UPDRS III Task Classification and Parkinson's Disease Recognition

引用

IEEE SENSORS JOURNAL 2025年第8期25卷 13554-13565页

作者： Zhang, Yiyuan Meng, Long Chen, Chen Chen, Wei Fudan Univ Ctr Intelligent Med Elect Sch Informat Sci & Technol Shanghai 200433 Peoples R China Penn State Univ Dept Mech Engn University Pk PA 16802 USA Fudan Univ Shanghai Pudong Hosp Ctr Med Res & Innovat Pudong Med Ctr Shanghai 201399 Peoples R China Univ Sydney Sch Biomed Engn Sydney NSW 2050 Australia

As wearable technology and machine learning (ML) algorithms have developed by leaps and bounds, many studies have focused on automatically monitoring Parkinson's disease (PD). The procedure includes two steps: first, classifying activities, usually the Movement Disorder Society-sponsored revision of the unified PD rating scale (MDS-UPDRS) part III tasks;second, evaluating the performance of these activities and recognizing PD. To improve the efficiency and precision of the procedure, this study proposes a self-attention squeeze-and-excitation temporal convolutional network (SASE-TCN). Based on the multistage temporal convolutional network (MS-TCN) and attention mechanisms, SASE-TCN can effectively extract the distant sequential and channelwise features. In addition, based on acceleration signals, SASE-TCN can classify MDS-UPDRS III tasks and recognize patients with PD simultaneously with the multitask learning mechanism. The model was tested with two public datasets, PD-BioStampRC21 and PD-motion. The SASE-TCN model obtained an average F1 score of 0.7802-0.9160 for activity classification and an average accuracy of 0.7366-0.8578 for PD recognition. The results demonstrated the feasibility of the SASE-TCN in classifying PD-related activities and recognizing PD with accelerometers. This study will support the diagnosis and treatment of PD.

关键词： Convolutional neural networks Feature extraction Multitasking Diseases Data mining Motors machine learning algorithms Electronic mail Accuracy Accelerometers Attention mechanism multitask learning Parkinson's disease (PD) temporal convolutional network (TCN)

来源：评论

学校读者我要写书评

暂无评论

XAI-Enhanced machine learning for Obesity Risk Classification: A Stacking Approach With LIME Explanations

引用

IEEE ACCESS 2025年 13卷 13847-13865页

作者： Azad, Mohammad Khan, Md Faraz Kabir Abd El-Ghany, Sameh Jouf Univ Coll Comp & Informat Sci Dept Comp Sci Sakaka 72341 Saudi Arabia Univ Western Australia Dept Comp Sci & Software Engn Perth WA 6009 Australia Jouf Univ Coll Comp & Informat Sci Dept Informat Syst Sakaka 72341 Saudi Arabia

Obesity remains a critical global health challenge, necessitating early risk assessment to guide preventive measures and mitigate potential complications. While various research endeavors have explored obesity classification, many existing approaches lack reliability due to limited integration with explainable artificial intelligence (XAI) methodologies. In this study, we propose a robust machine learning framework that incorporates Explainable AI (XAI) principles to accurately estimate obesity levels and provide insights into the factors influencing the predictions. We utilize the publicly available dataset from Palechor and Manotas available in the UCI ML repository which contains relevant information on individuals' physical characteristics and behaviors. Our proposed model employs an ensemble approach, specifically a stacking algorithm, where the base estimators include the Light Gradient Boosting machine (LGBM) classifier, the Logistic Regression (LR) classifier, and the Random Forest (RF) Classifier, and the Stochastic Gradient Descent (SGD) classifier is selected as the final estimator. To enhance model interpretability and reliability, we integrate a widely accepted XAI method, Local Interpretable Model-agnostic Explanations (LIME). Our proposed framework achieves a peak accuracy of 98.82%, surpassing most existing techniques. By incorporating LIME, we not only enhance model trustworthiness but also provide deeper insights into the factors driving obesity risk. Overall, our approach contributes to advancing personalized interventions and bridging the gap between model complexity and human understanding.

关键词： Obesity Data models Random forests Boosting Accuracy Numerical models machine learning algorithms Correlation machine learning stacking explainable AI stacking explainable AI

来源：评论

学校读者我要写书评

暂无评论

State-of-the-Art Fault Detection and Diagnosis in Power Transformers: A Review of machine learning and Hybrid Methods

引用

IEEE ACCESS 2025年 13卷 48156-48172页

作者： Mashifane, Lebo Dina Mendu, Bongumsa Monchusi, Bessie Baakanyang Univ South Africa Dept Elect & Smart Syst Engn ZA-0002 Pretoria South Africa Natl Transmiss Co South Africa Asset Management Dept ZA-2157 Sandton South Africa

Fault detection and diagnosis (FDD) in power transformers is essential for maintaining reliability and safety in modern power systems. Recent trends in transformer fault diagnosis include the use of advanced monitoring systems and data analysis techniques, and implementing effective FDD strategies can prevent costly repairs, minimize downtime, and enhance the overall reliability of power systems. In this work, a systematic review of FDD in power transformers, focusing on machine learning and hybrid methods applications is presented. The methodology comprised a detailed systematic process undertaken to gather, filter, and analyze relevant research papers using Scopus database, while VOSviewer, and bibliometrix tools were utilized for results analysis. The research findings indicate that there is clear progress in detecting transformer faults, moving from older methods like Dissolved Gas Analysis (DGA) to machine learning models such as Random Forest and Convolutional Neural Networks (CNN). Hybrid models combining machine learning with optimization have made detection more accurate. New tools, including optical sensors, now allow for real-time monitoring. Still, issues like limited data and complex models remain. This study contributes by reviewing how machine learning is applied to transformer fault detection, exploring hybrid methods that combine traditional techniques like DGA with advanced models for better accuracy. It identifies key research patterns, trends, and themes, while also highlighting gaps and offering suggestions for future research to improve diagnostics and monitoring.

关键词： Power transformers Oil insulation machine learning Circuit faults machine learning algorithms Accuracy Windings Fault detection Power systems Partial discharges Dissolved gas analysis hybrid methods fault detection and diagnosis machine learning algorithms power transformer

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：