Machine learning with applications最新文献_第3页

On the latent distribution of logistic regression — An empirical study on spectroscopic profiling datasets 论逻辑回归的潜在分布——光谱分析数据集的实证研究

IF 4.9

Machine learning with applications Pub Date : 2025-09-04 DOI: 10.1016/j.mlwa.2025.100712

Yinsheng Zhang, Mingming He, Haiyan Wang

引用次数: 0

CNN-CCA: A deep learning approach for anomaly detection in metro rail sensor time-series data CNN-CCA：地铁轨道传感器时间序列数据异常检测的深度学习方法

IF 4.9

Machine learning with applications Pub Date : 2025-09-01 DOI: 10.1016/j.mlwa.2025.100728

Vignesh Rao , Amir Eskandari , Farhana Zulkernine , Mohamed K. Helwa , David Beach

{"title":"CNN-CCA: A deep learning approach for anomaly detection in metro rail sensor time-series data","authors":"Vignesh Rao , Amir Eskandari , Farhana Zulkernine , Mohamed K. Helwa , David Beach","doi":"10.1016/j.mlwa.2025.100728","DOIUrl":"10.1016/j.mlwa.2025.100728","url":null,"abstract":"<div><div>The Internet of Things (IoT) offers new challenges in estimating correlations among data from multiple connected devices to understand their behaviors. Canonical Correlation Analysis (CCA) can be used to measure correlations among several observed variables. Different CCA methods have been proposed in the literature including probabilistic, sparse, kernel, discriminative, and deep learning-based CCAs. However, existing CCA approaches are limited by assumptions of linearity, reliance on predefined kernels, or difficulty in modeling localized patterns in high-frequency IoT sensor data. In this research, we explore two methods, linear CCA and non-linear deep learning-based CCA. Experiments demonstrate the effectiveness of CCA in detecting correlation in synthetic and metro rail time series sensor data collected from Autonomous Train (AT) signaling systems. Also, we propose a novel Convolutional Neural Network (CNN) based CCA method to detect correlation-based mappings and combine it with statistical anomaly detection methods in collective anomaly detection. The results indicate strong performance with an F1-score of 89.0% and a sensitivity of 94.1%, which can pave the way for the application of the proposed models to real-time collective anomaly detection and CCA in IoT systems.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"21 ","pages":"Article 100728"},"PeriodicalIF":4.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144987845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the cost of equity for insurance companies in the world: evidence from machine learning approaches 探索全球保险公司的股权成本：来自机器学习方法的证据

IF 4.9

Machine learning with applications Pub Date : 2025-08-26 DOI: 10.1016/j.mlwa.2025.100726

Indranarain Ramlall, Dineshwar Ramdhony

{"title":"Exploring the cost of equity for insurance companies in the world: evidence from machine learning approaches","authors":"Indranarain Ramlall, Dineshwar Ramdhony","doi":"10.1016/j.mlwa.2025.100726","DOIUrl":"10.1016/j.mlwa.2025.100726","url":null,"abstract":"<div><div>This study investigates the determinants of the WACC for insurance firms, integrating both financial and non-financial factors through advanced machine learning techniques. Analyzing data from 2012 to 2022 for a large sample of 190 insurance companies in the world, we compare nine ML models, revealing that XGBoost and LightGBM outperform traditional methods. Key drivers of WACC include beta, dividend yield, and earnings per share, with Emission score also showing significant influence. This study fills gaps in insurance finance literature by introducing ML-based WACC modeling, enhancing predictive accuracy, and providing policy recommendations for regulatory reporting and Emission score disclosures. From a policy perspective, the global insurance sector is at a crucial turning point, where ESG integration in granular form is found to be vital for financial stability. By mandating standardized ESG disclosures in alignment with the ISSB and TCFD frameworks, regulators can reduce insurers’ cost of equity, enabling a balance between financial sustainability and environmental responsibility, while promoting long-term value creation for both investors and society.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"22 ","pages":"Article 100726"},"PeriodicalIF":4.9,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Classification of System Dynamics model outputs using decision trees 使用决策树对系统动力学模型输出进行分类

IF 4.9

Machine learning with applications Pub Date : 2025-08-25 DOI: 10.1016/j.mlwa.2025.100713

Martina Curran, Enda Howley, Jim Duggan

引用次数: 0

PyRHOH: A meta-learning analysis framework for determining the impact of compilation on malicious JavaScript identification PyRHOH：一个元学习分析框架，用于确定编译对恶意JavaScript识别的影响

IF 4.9

Machine learning with applications Pub Date : 2025-08-18 DOI: 10.1016/j.mlwa.2025.100724

Eli Fulkerson , Eric Yocam , Varghese Vaidyan , Mahesh Kamepalli , Yong Wang , Gurcan Comert

{"title":"PyRHOH: A meta-learning analysis framework for determining the impact of compilation on malicious JavaScript identification","authors":"Eli Fulkerson , Eric Yocam , Varghese Vaidyan , Mahesh Kamepalli , Yong Wang , Gurcan Comert","doi":"10.1016/j.mlwa.2025.100724","DOIUrl":"10.1016/j.mlwa.2025.100724","url":null,"abstract":"<div><div>Automated identification of malicious JavaScript is a core problem within modern malware analysis. Code obfuscation is a common tactic used to evade detection. This obfuscation hinders both manual and automated detection methods, including neural network techniques. In order for these methods to effectively classify malware, it is beneficial to reduce the effects of obfuscation as well as to optimize the configuration and structure of the neural network to be well suited for the task. To overcome these challenges, we present a new framework: “PyRHOH” (“Python Repeatable Hyperparameter Optimization Harness”), a meta-learning framework that implements Bayesian optimization. The automated exploration and maximization of candidate hyperparameters using a Bayesian method adds structure and rigor to the selection of neural network hyperparameters, providing the assurance that an implemented design is optimal. In this study, we used the PyRHOH framework to determine optimal recurrent neural network architectures for the differentiation of malicious and benign JavaScript samples. We then used these neural networks to measure the degree to which compilation of raw JavaScript samples into bytecode via Google’s V8 JavaScript compiler affected classification accuracy. Classifying in-the-wild samples, compilation increased the detection rate from 76.88% to 95.84%. Among uniformly obfuscated samples, compilation increased the detection rate from an average of 76.76% to an average of 91.24% e compilation was performed. This shows that pre-processing JavaScript into compiled bytecode has a clear positive impact on neural network categorization.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"21 ","pages":"Article 100724"},"PeriodicalIF":4.9,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144902998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Novel channel attention-based filter pruning methods for low-complexity semantic segmentation models 基于通道关注的低复杂度语义分割模型滤波剪枝方法

IF 4.9

Machine learning with applications Pub Date : 2025-08-16 DOI: 10.1016/j.mlwa.2025.100725

Md. Bipul Hossain, Na Gong, Mohamed Shaban

{"title":"Novel channel attention-based filter pruning methods for low-complexity semantic segmentation models","authors":"Md. Bipul Hossain, Na Gong, Mohamed Shaban","doi":"10.1016/j.mlwa.2025.100725","DOIUrl":"10.1016/j.mlwa.2025.100725","url":null,"abstract":"<div><div>Semantic segmentation is the area of classifying each pixel in an image using a deep learning model. Examples of widely used semantic segmentation models are the U-Net and DeeplabV3+ models. While the aforementioned models have been deemed very successful in segmenting medical targets including organs and diseases in high resolution images, the computational complexity represents a burden for the real-time application of the algorithms or the deployment of the models on resource-constrained platforms. Until recently, few methods have been introduced for optimizing or pruning of the parameters of the semantic segmentation models. In this paper, we propose two novel channel attention-based filter pruning techniques (i.e., Sub-Sampling Channel Attention (SACA) and Self-Attention Based Attention (SBCA)) in order to reduce the complexity of the semantic segmentation models while maintaining high performance with respect to the benchmark models. This is realized by recognizing the contextual importance of the feature maps in each layer of the models and the significance of each filter to the final model performance. The proposed optimization methods have been validated on the U-Net and DeeplabV3+ models using both lung and skin lesion datasets. The proposed approaches achieved a pruned model performance (i.e., dice coefficient) of up to 96%, as well as an extensively reduced complexity (i.e., percentage of remaining parameters down to 1.1%, model size down to 1.22 MB and number of GFLOPS down to 1.06), outperforming the benchmark magnitude based (i.e., <em>l1-norm</em>, and <em>l2-norm</em>) and the attention-based (i.e., SE, ECA, and CBAM CA) filter pruning methods.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"21 ","pages":"Article 100725"},"PeriodicalIF":4.9,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144885726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Topological data analysis for driver behavior classification driven by vehicle trajectory data 基于车辆轨迹数据的驾驶员行为分类拓扑数据分析

IF 4.9

Machine learning with applications Pub Date : 2025-08-13 DOI: 10.1016/j.mlwa.2025.100719

Debbie Indah , Judith Mwakalonge , Gurcan Comert , Saidi Siuhi , Hannah Musau , Eric Osei , Paul Omulokoli , Methusela Sulle , Denis Ruganuza , Nana Kankam Gyimah

{"title":"Topological data analysis for driver behavior classification driven by vehicle trajectory data","authors":"Debbie Indah , Judith Mwakalonge , Gurcan Comert , Saidi Siuhi , Hannah Musau , Eric Osei , Paul Omulokoli , Methusela Sulle , Denis Ruganuza , Nana Kankam Gyimah","doi":"10.1016/j.mlwa.2025.100719","DOIUrl":"10.1016/j.mlwa.2025.100719","url":null,"abstract":"<div><div>With urbanization and rising vehicle numbers, road safety has become increasingly critical. Robust, trajectory-level risk assessment is essential for next-generation active safety systems, accident prevention, autonomous driving, and intelligent transportation networks. This paper presents a novel framework for driver behavior classification using Topological Data Analysis (TDA) — a mathematical approach for analyzing high-dimensional data — via persistent homology applied to vehicle trajectory data. Traditional methods often struggle with the complexity of such data, but TDA captures topological features that reveal subtle, meaningful behavioral patterns. Using the HighD dataset, we train a class-weighted XGBoost classifier on persistence image (PI) features, achieving 96.8% overall accuracy, macro-F<span><math><msub><mrow></mrow><mrow><mn>1</mn></mrow></msub></math></span> = 0.93, and retaining 87% F<span><math><msub><mrow></mrow><mrow><mn>1</mn></mrow></msub></math></span> on the minority Aggressive class. Unsupervised K-means clustering of the same PI features naturally separates the data into three behavioral clusters whose ANOVA-verified risk profiles align with the MOR-defined classes, confirming the behavioral relevance of the topological descriptors. These results provide empirical evidence that PI features capture safety-critical structure more effectively than raw kinematics and demonstrate the robustness and scalability of TDA for analyzing large, noisy datasets. The proposed approach shows strong potential for real-time driver monitoring, risk assessment, and data-driven transportation management, with implications for traffic safety, autonomous systems, and personalized insurance.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"21 ","pages":"Article 100719"},"PeriodicalIF":4.9,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144842287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-frequency stock price prediction via deep learning 基于深度学习的高频股价预测

IF 4.9

Machine learning with applications Pub Date : 2025-08-13 DOI: 10.1016/j.mlwa.2025.100716

Jianlong Bao , Takayuki Morimoto

引用次数: 0

Framework for detecting and recognizing sign language using absolute pose estimation difference and deep learning 基于绝对姿态估计差分和深度学习的手语检测与识别框架

IF 4.9

Machine learning with applications Pub Date : 2025-08-11 DOI: 10.1016/j.mlwa.2025.100723

Kasian Myagila , Devotha Godfrey Nyambo , Mussa Ally Dida

{"title":"Framework for detecting and recognizing sign language using absolute pose estimation difference and deep learning","authors":"Kasian Myagila , Devotha Godfrey Nyambo , Mussa Ally Dida","doi":"10.1016/j.mlwa.2025.100723","DOIUrl":"10.1016/j.mlwa.2025.100723","url":null,"abstract":"<div><div>Computer vision has been identified as one of the key solutions for human activity recognition, including sign language recognition. Despite the success demonstrated by various studies, isolating signs from continuous video remains a challenge. The sliding window approach has been commonly used for translating continuous video. However, this method subjects the model to unnecessary predictions, leading to increased computational costs. This study proposes a framework that use absolute pose estimation differences to isolate signs from continuous videos and translate them using a model trained on isolated signs. Pose estimation features were chosen due to their proven effectiveness in various activity recognition tasks within computer vision. The proposed framework was evaluated on 10 videos of continuous signs. According to the findings, the framework achieved an average accuracy of 84%, while the model itself attained 95% accuracy. Moreover, SoftMax output analysis shows that the model exhibits higher confidence in correctly classified signs, as indicated by higher average SoftMax scores for correct predictions. This study demonstrates the potential of the proposed framework over the sliding window approach, which tends to overwhelm the model with excessive classification sequences.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"21 ","pages":"Article 100723"},"PeriodicalIF":4.9,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MLPro 2.0 - Online machine learning in Python MLPro 2.0 - Python中的在线机器学习

IF 4.9

Machine learning with applications Pub Date : 2025-08-09 DOI: 10.1016/j.mlwa.2025.100715

Detlef Arend, Laxmikant Shrikant Baheti, Steve Yuwono, Syamraj Purushamparambil Satheesh Kumar, Andreas Schwung

{"title":"MLPro 2.0 - Online machine learning in Python","authors":"Detlef Arend, Laxmikant Shrikant Baheti, Steve Yuwono, Syamraj Purushamparambil Satheesh Kumar, Andreas Schwung","doi":"10.1016/j.mlwa.2025.100715","DOIUrl":"10.1016/j.mlwa.2025.100715","url":null,"abstract":"<div><div>In this paper, we present version 2.0 of the open-source middleware MLPro for applied machine learning in Python. Notably, it introduces the new sub-framework MLPro-OA for online machine learning, focusing on standards and templates for classic and online-adaptive data stream processing (DSP/OADSP). As part of this, we provide three novel adaptation mechanisms:The first, event-oriented adaptation, enables localized, event-driven parameter updates within individual tasks. The second, cascaded adaptation, allows adaptation events to propagate across multiple dependent tasks, creating task-spanning adjustment cascades decoupled from the forward-facing DSP. The third, reverse adaptation, allows tasks to revise prior adjustments by explicitly processing obsolete instances discarded from a preceding sliding window. Furthermore, we provide insights into the underlying design criteria of MLPro-OA, which were developed through extensive requirements engineering. In the practical part of this work, we demonstrate the essential functionalities of MLPro-OA using reproducible examples.</div></div>","PeriodicalId":74093,"journal":{"name":"Machine learning with applications","volume":"21 ","pages":"Article 100715"},"PeriodicalIF":4.9,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144826585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0