Annals of Data Science最新文献_第7页

Stock Prices Forecasting by Using a Novel Hybrid Method Based on the MFO-Optimized GRU Network 基于mfo优化GRU网络的新型混合方法预测股价

Annals of Data Science Pub Date : 2025-06-18 DOI: 10.1007/s40745-025-00616-w

Xinjian Zhang, Guanlin Liu

{"title":"Stock Prices Forecasting by Using a Novel Hybrid Method Based on the MFO-Optimized GRU Network","authors":"Xinjian Zhang, Guanlin Liu","doi":"10.1007/s40745-025-00616-w","DOIUrl":"10.1007/s40745-025-00616-w","url":null,"abstract":"<div><p>With the social economy growing at a quick pace and the stock market seeing constant developments, more and more people are voicing concerns about investing in stocks. The importance of forecasting stock values has increased in the domain of engineering's use of cognitive computing. Utilizing data-driven tactics for forecasting stock prices, investors can effectively mitigate risks and enhance profits. Investors can use projections based on historical values and textual data to make well-informed judgments about future patterns in stock prices. Stock price anticipation is a pivotal undertaking in the financial sector that has substantial consequences for traders and investors. This article presents an in-depth comparison analysis of machine learning tactics for forecasting price fluctuations in stocks. The research deploys historical stock data and diverse technical indicators. This paper presents the Gated Recurrent Unit (GRU) model for Nasdaq stock index anticipation, which is optimized by Particle swarm optimization (PSO), Biogeography-based optimization (BBO), and Moth flame optimization (MFO). Among these optimizers, MFO has the best outcomes. Compared to the GRU scheme the optimized PSO-GRU, BBO-GRU, and MFO-optimized GRU for stock forecasting has the outcomes of 0.9807, 0.9824, and 0.9904 in coefficient of determination (<span>({R}^{2})</span>) which shows the improvement of the presented scheme as a result of its development. The criteria used to evaluate this model are mean absolute error, root mean absolute error, and <span>({R}^{2})</span>.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 4","pages":"1369 - 1387"},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145166219","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

Optimization of Oil and Gas Pipeline Leakage Data and Defect Identification Based on Graph Neural Processing 基于图神经处理的油气管道泄漏数据优化及缺陷识别

Annals of Data Science Pub Date : 2025-06-16 DOI: 10.1007/s40745-025-00619-7

Lizhen Zhang

{"title":"Optimization of Oil and Gas Pipeline Leakage Data and Defect Identification Based on Graph Neural Processing","authors":"Lizhen Zhang","doi":"10.1007/s40745-025-00619-7","DOIUrl":"10.1007/s40745-025-00619-7","url":null,"abstract":"<div><p>With the increasing complexity of oil and gas pipeline networks, early identification of leaks and defects is crucial to ensure the safe operation of pipelines. This study proposes a graph neural network (GNN) method for data processing and defect identification aimed at optimizing monitoring and maintenance strategies for oil and gas pipelines. Through the analysis of historical leakage data, we constructed a graph database containing 5000 samples, each containing 10 features such as pressure, flow, temperature, etc. Using graph convolutional network and graph attention network (GAT) to perform feature extraction and pattern recognition on nodes in pipeline network, our model achieves 92% accuracy in defect recognition, which is 15% higher than traditional methods. In addition, we have developed a leakage prediction model based on time series analysis, which is able to predict potential leakage risks 24 h in advance with an accuracy of 85%. The results of this study not only improve the safety management level of oil and gas pipelines, but also provide a new technical path for future intelligent pipeline maintenance.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 4","pages":"1413 - 1430"},"PeriodicalIF":0.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s40745-025-00619-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145165694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling Economics and Finance Data with the Arctan Marshall-Olkin Weibull Distribution 用Arctan Marshall-Olkin Weibull分布建模经济和金融数据

Annals of Data Science Pub Date : 2025-06-12 DOI: 10.1007/s40745-025-00610-2

Mintodê Nicodème Atchadé, Espoir Zyad Kossou, Théophile Otodji, Mahoulé Jude Bogninou, Aliou Moussa Djibril

引用次数: 0

A Study on Quadri-Partitioned Interval-Valued Pythagorean Neutrosophic Fuzzy MCDM 四分区间值毕达哥拉斯中性模糊MCDM的研究

Annals of Data Science Pub Date : 2025-06-06 DOI: 10.1007/s40745-025-00621-z

Manajit Roy, Bhimraj Basumatary, Binod Chandra Tripathy

引用次数: 0

A New Regression Model for Analysis of Count Response and Other Related Patient Outcomes 计数反应及其他相关患者预后分析的新回归模型

Annals of Data Science Pub Date : 2025-06-04 DOI: 10.1007/s40745-025-00620-0

Khawar Javaid, Bilal Ahmad Para

引用次数: 0

Improving Predictive Accuracy in Writing Assessment Through Advanced Machine Learning Techniques 通过先进的机器学习技术提高写作评估的预测准确性

Annals of Data Science Pub Date : 2025-06-03 DOI: 10.1007/s40745-025-00618-8

Xiao Zhang

{"title":"Improving Predictive Accuracy in Writing Assessment Through Advanced Machine Learning Techniques","authors":"Xiao Zhang","doi":"10.1007/s40745-025-00618-8","DOIUrl":"10.1007/s40745-025-00618-8","url":null,"abstract":"<div><p>This research investigates the application of the Machine Learning (ML) model for effective and equitable essay scoring in education. Unlike their human counterpart, ML models have the capacity to rapidly analyze scores of essays, providing timely and equitable scores that take into account varying student demographics and styles of writing. This function helps in the identification of classroom problems and supports the design of focused teaching methodologies. For the study, a Light Gradient Boosting Classification (LGBC) model was optimized by three optimizers: Black Widow Optimization (BWO), Zebra Optimization Algorithm (ZOA), and Leader Harris Hawks Optimization (LHHO), for the development of the hybrid models with a focus on improved prediction quality. Comparison of these hybrid models with the base LGBC model was performed through different phases, such as Training, Validation, and Testing. The findings show that the LGLH model exhibited improved performance with an accuracy rate of 0.981, followed by the LGZO model with 0.971 and the LGBW model with 0.963. The lowest rate of accuracy was observed in the base LGBC model, which was 0.946. The results demonstrate the efficacy of hybrid models, which harness the optimality of several optimization techniques and provide more robust results for complicated tasks. The study emphasizes the importance of selecting the appropriate model architecture to achieve optimal performance, providing valuable insights into model efficacy at various stages of evaluation.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 4","pages":"1389 - 1412"},"PeriodicalIF":0.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145161714","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

An Explainable Machine Learning-Based Employee Attrition Predictive System 基于机器学习的可解释员工流失预测系统

Annals of Data Science Pub Date : 2025-06-03 DOI: 10.1007/s40745-025-00617-9

Amir Hamja, Mahmudul Hasan, Ziaul Hassan, Md Palash Uddin, Md Jahangir Alam Siddikee

{"title":"An Explainable Machine Learning-Based Employee Attrition Predictive System","authors":"Amir Hamja, Mahmudul Hasan, Ziaul Hassan, Md Palash Uddin, Md Jahangir Alam Siddikee","doi":"10.1007/s40745-025-00617-9","DOIUrl":"10.1007/s40745-025-00617-9","url":null,"abstract":"<div><p>As human capital forms the backbone of any organization, managing and minimizing employee attrition is of paramount importance. Attrition prediction is essential because attrition disrupts projects advancement, increases rehiring and training costs, and risks losing core knowledge and technologies. Thus, minimizing attrition is essential for organizational stability and competitiveness. In this research, we design a Machine Learning (ML)-based predictive system using six ML models namely Logistic Regression, Random Forest, Gradient Boosting (GB), Decision Tree, Support Vector Machine, and K-Nearest Neighbors and evaluate their performances using accuracy, precision, recall, and f1 score. This system predicts employee attrition in advance, allowing organizations to implement proactive talent management strategies instead of relying on traditional reactive approaches. We analyse ‘IBM HR Analytics data’, that contains 1,470 observations and 35 features. Among all the models, GB outperform others with 98% accuracy, and precision, 100% recall and 99% f1 score. Furthermore, using Explainable AI (XAI) methods such as ELI5, SHAP, LIME, and SHAPASH, we analyze the most influencing factors related to employee attrition. XAI analysis show that ‘Over Time’ ‘Toal working years’, ‘job level’ are the most significant factors. Local explainability provide the low level explanation to reveal the inner story and deep insight.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1201 - 1231"},"PeriodicalIF":0.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098413","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

Hybrid Learning Based Visual Facial Emotion Recognition in Speech Videos 基于混合学习的语音视频视觉面部情感识别

Annals of Data Science Pub Date : 2025-06-02 DOI: 10.1007/s40745-025-00613-z

Yogesh Rochlani, A. B. Raut

{"title":"Hybrid Learning Based Visual Facial Emotion Recognition in Speech Videos","authors":"Yogesh Rochlani, A. B. Raut","doi":"10.1007/s40745-025-00613-z","DOIUrl":"10.1007/s40745-025-00613-z","url":null,"abstract":"<div><p>Facial Emotion Recognition (FER) plays a crucial role in understanding human behavior and interactions, with applications in human-computer interaction, healthcare, surveillance, and multimedia content analysis. Emotion recognition from speech videos is particularly challenging as it requires capturing and analyzing subtle variations in facial expressions along with dynamic speech changes. In this paper, a hybrid learning approach is presented that integrates machine learning and deep learning models to enhance the accuracy and robustness of visual facial emotion recognition in speech videos. The proposed approach leverages a pre-trained ResNet-101 model for feature extraction and evaluates three widely used machine learning classifiers, Random Decision Forest (RDF), Decision Tree Boosting (DTB), and Support Vector Machine (SVM) for emotion prediction. Experiments conducted on the RAVDESS dataset demonstrate that our hybrid model, combining Deep CNN with RDF classification, achieves a high accuracy of 92.50%, outperforming existing state-of-the-art models. This work highlights the potential of integrating deep learning and machine learning for FER, offering significant benefits for applications in healthcare, education, and human-computer interaction.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1137 - 1154"},"PeriodicalIF":0.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098022","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

Diabetic Retinopathy: An Exploration of Retinal Blood Vessel Segmentation Using Multilayered Thresholding 糖尿病视网膜病变：多层阈值分割视网膜血管的探索

Annals of Data Science Pub Date : 2025-06-02 DOI: 10.1007/s40745-025-00614-y

K Mahesh Babu, K. Bala Chowdappa, M. Kiran Mayee, Adapa Srinivasa Rao, Rudrapati Mounika

{"title":"Diabetic Retinopathy: An Exploration of Retinal Blood Vessel Segmentation Using Multilayered Thresholding","authors":"K Mahesh Babu, K. Bala Chowdappa, M. Kiran Mayee, Adapa Srinivasa Rao, Rudrapati Mounika","doi":"10.1007/s40745-025-00614-y","DOIUrl":"10.1007/s40745-025-00614-y","url":null,"abstract":"<div><p>Diabetic retinopathy is the leading cause of blindness worldwide; it is a consequence of diabetes that affects the retina’s blood vessels. Consequently, correct segmentation of the retinal arteries is essential for accurate diagnosis of such changes in disease progression, which is vital for adequate therapy. A novel approach to segmenting retinal blood vessels is introduced in this research. Starting with the unprocessed retinal picture Utilizing the wavelet transform, a method that incorporates many layers of the threshold approach, to improve samples. New way of brightening the selected vessels is associated with the Wavelet transform, which is effective in representing the multi-scale objects efficiently, and more accurate multilayered thresholding is used to segment the vessels. This approach is specifically aimed at enhancing segmentation of vessels which is exceptionally indispensable for the finding of Diabetic Retinopathy at its beginning phase. To test the proficiency of the proposed technique, different investigations on the openly accessible DRIVE and Gaze information bases. Concerning awareness, particularity, and exactness, that’s what the outcomes show ours outperforms other existing methods. In particular, the proposed technique has been tested and obtained the accuracy of 96%, sensitivity of 97. moderate sensitivity of 86% and specificity of 97% such method can be used for screening of Diabetic Retinopathy in clinical settings. The current review reveals insight into the improvement of strategies utilized in the conclusion of diabetic retinopathy and presents a potentially useful solution for segmenting the retinal blood vessels.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1155 - 1169"},"PeriodicalIF":0.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098023","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

Evaluation of Path-Planning Algorithms for Autonomous Navigation in Unstructured Indian Road Environments Considering the Effects of Weather and Road Curvatures 考虑天气和道路曲率影响的非结构化印度道路环境自主导航路径规划算法评估

Annals of Data Science Pub Date : 2025-06-01 DOI: 10.1007/s40745-025-00615-x

Vivek Patkar, Prachi Bhoir, Ninad Dileep Mehendale

{"title":"Evaluation of Path-Planning Algorithms for Autonomous Navigation in Unstructured Indian Road Environments Considering the Effects of Weather and Road Curvatures","authors":"Vivek Patkar, Prachi Bhoir, Ninad Dileep Mehendale","doi":"10.1007/s40745-025-00615-x","DOIUrl":"10.1007/s40745-025-00615-x","url":null,"abstract":"<div><p>This study presents the development and comprehensive evaluation of an autonomous ground vehicle prototype designed specifically for the diverse and complex road conditions prevalent in India. The prototype incorporates a multi-sensor suite, including RP LIDAR A1M8, Intel RealSense Depth Camera, ultrasonic distance sensor HC-SR04, GPS sensor neo6m, and 1D LIDAR TF LUNA micro, integrated with advanced control algorithms. Steering control utilizes a path-tracking algorithm based on a kinematic bicycle model, while acceleration is managed by a PID controller. The system’s performance was rigorously tested across various scenarios, encompassing different weather conditions, road types, curvatures, and obstacle densities. Results indicate a maximum accuracy of 98.2% under optimal conditions, decreasing to 80% in rainy weather and 79.1% on roads with potholes and uneven surfaces. The prototype demonstrated varying levels of accuracy with increasing road curvature and obstacle density. This research provides valuable insights into the challenges and potential solutions for autonomous vehicle operation in the unique context of Indian road environments, highlighting areas for future improvement in sensor technology and control algorithms to enhance safety and reliability in diverse conditions.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1171 - 1199"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098188","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