Annals of Data Science最新文献

{"title":"A ML-Driven Framework for Phase Prediction in High-Entropy Alloys","authors":"Yingting Guo,&nbsp;Yan Xu","doi":"10.1007/s40745-025-00657-1","DOIUrl":"10.1007/s40745-025-00657-1","url":null,"abstract":"<div><p>High-entropy alloys (HEAs) represent a state-of-the-art material system, exhibiting exceptional physical and chemical properties that hold great potential for engineering applications. Nevertheless, accurately identifying their complex phase structures remains a significant challenge. This study presents a novel integrated machine learning (ML) framework that combines data processing, feature optimization, and 12 predictive algorithms to enable rapid and precise classification of HEA phase structures. T Comprehensive qualitative and quantitative evaluations demonstrate that the SVM, GBT, and RF algorithms exhibit superior predictive performance. The voting ensemble strategy effectively integrates the strengths of individual methods, achieving the highest overall accuracy. Key features including <span>(:{updelta:})</span>, <span>(:{upalpha:})</span>, <span>(:{{upsigma:}}_{{T}_{m}})</span>, <span>(:{{Delta:}text{H}}_{mix})</span> and <span>(:{{Delta:}text{S}}_{mix})</span> consistently emerge as the most influential predictors across all models. This framework provides a powerful tool for predicting HEA properties, significantly accelerating the discovery and development of advanced materials.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 4","pages":"963 - 985"},"PeriodicalIF":0.0,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148613065","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}

{"title":"Will Market Participants Affect the Volume-Price Relationship in the Chinese Stock Market? An Empirical Analysis Based on the DCC-MIDAS Model","authors":"Zhanpeng Cai,&nbsp;Yong Tang,&nbsp;Jingjing Fang,&nbsp;Shunfeng Wan","doi":"10.1007/s40745-025-00655-3","DOIUrl":"10.1007/s40745-025-00655-3","url":null,"abstract":"<div><p>The connection between stock market prices and trading volume has long been a subject of extensive research interest among scholars. This study examines whether the effective utilization of exogenous information from market participants contributes to a better understanding of the volume-price relationship. Using a DCC-MIDAS model that incorporates multiple mixed-frequency exogenous variables, this study empirically analyzes the influence of various market participants on the volume-price relationship in the Chinese stock market by incorporating a DCC-MIDAS model with multiple mixed-frequency exogenous variables. The results indicate that a dynamic correlation between stock market returns and trading volume in China. The increase in volume-price correlation can be attributed to improvements in the performance and governance of listed companies, accurate information dissemination by intermediary organs, and economic policy uncertainty. Among these factors, the influence of intermediary institutions’ information dissemination is the most persistent. However, the impact of investor sentiment on the volume-price relationship is not significant, as short-term shocks caused by emotional information quickly decay and dissipate. Additionally, the heterogeneity analysis reveals that different market participants exhibit distinct bull and bear market periodic features and industry characteristics in their influence on the volume-price relationship. This study is significant for understanding how exogenous information influences the volume-price relationship in the stock market. Regulatory authorities can formulate appropriate measures to stabilize the volume-price correlation based on both the influence path and the declining speed.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 2","pages":"379 - 400"},"PeriodicalIF":0.0,"publicationDate":"2025-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147607014","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}

{"title":"Special Issue of the Eleventh International Conference on Information Technology and Quantitative Management (ITQM 2024)","authors":"Yong Shi,&nbsp;Florin Gheorghe Filip","doi":"10.1007/s40745-025-00661-5","DOIUrl":"10.1007/s40745-025-00661-5","url":null,"abstract":"","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 6","pages":"1771 - 1774"},"PeriodicalIF":0.0,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145537716","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}

{"title":"Correction: Exponentiated Odd Lindley-X Power Series Class of Distributions: Properties and Applications","authors":"Fastel Chipepa,&nbsp;Nonhle Mdziniso,&nbsp;Shahid Mohammad,&nbsp;Sher Chhetri","doi":"10.1007/s40745-025-00653-5","DOIUrl":"10.1007/s40745-025-00653-5","url":null,"abstract":"","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 2","pages":"375 - 376"},"PeriodicalIF":0.0,"publicationDate":"2025-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s40745-025-00653-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147607270","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}

{"title":"SHMADF: A Secure and Intelligent Framework for IoT-Enabled Healthcare Monitoring and Attack Detection","authors":"Renuka Sagar,&nbsp;N. V. Sanjay Kumar,&nbsp;Anitha S. Sastry,&nbsp;Nanditha Krishna,&nbsp;Reshma S","doi":"10.1007/s40745-025-00660-6","DOIUrl":"10.1007/s40745-025-00660-6","url":null,"abstract":"<div><p>The rapid integration of Internet of Things (IoT) devices in healthcare demands a robust framework to ensure secure patient monitoring and timely attack detection. This study proposes a Secure Healthcare Monitoring and Attack Detection Framework (SHMADF) designed to safeguard IoT-enabled healthcare environments by leveraging advanced data processing and security techniques. The framework initiates with comprehensive data collection from IoT sensors and network traffic within healthcare settings. Preprocessing steps—including removal of duplicates, handling missing data, and Z-score normalization—prepare the data for efficient analysis. Feature extraction targets low-level and protocol-specific features, Session-Level and Statistical Features. Thus, the extracted features were fused by Weighted Feature Concatenation (WFC). To optimize feature selection, a novel hybrid metaheuristic—Cuckoo-Bat Echolocation Search (CBES)—combines the strengths of Cuckoo Search and Bat Algorithm, enhancing detection accuracy. Data confidentiality during transmission is ensured through a Chaotic Map-Based Stream Cipher Encryption (CMSCE), tailored for resource-constrained IoT devices. Moreover, the encrypted data are stored in cloud and it support real-time data aggregation and low-latency decision-making. The core detection engine employs a hybrid ConvGRU-Net model, merging Convolutional Neural Networks with Gated Recurrent Units for spatial–temporal pattern recognition of cyber-attacks. Additionally, an interactive alert and feedback system offers real-time visualization and adaptive model refinement, enabling proactive healthcare management. The proposed framework demonstrates potential for comprehensive, efficient, and secure IoT healthcare monitoring. The proposed SHMADF model achieved superior performance with 99.35% accuracy, 99.3% precision, 99.4% recall, and 99.35% F1-score. It demonstrated low FPR (1.0%) and FNR (0.6%), with fast encryption (10.2 ms), decryption (9.8 ms), and key generation (2.6 ms), ensuring secure, real-time IoT healthcare monitoring and attack detection.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 1","pages":"241 - 278"},"PeriodicalIF":0.0,"publicationDate":"2025-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147342637","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}

{"title":"Correction: A New Hyperbolic Tangent Family of Distributions: Properties and Applications","authors":"Shahid Mohammad,&nbsp;Isabel Mendoza","doi":"10.1007/s40745-025-00654-4","DOIUrl":"10.1007/s40745-025-00654-4","url":null,"abstract":"","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 2","pages":"377 - 377"},"PeriodicalIF":0.0,"publicationDate":"2025-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147607025","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}

{"title":"A Hybrid Model of Artificial Neural Network and SARIMA Models for Predicting Inflation Rate Change in Nigeria's Economy","authors":"D. C. Bartholomew,&nbsp;H. C. Iwu,&nbsp;I. P. Ibemere","doi":"10.1007/s40745-025-00656-2","DOIUrl":"10.1007/s40745-025-00656-2","url":null,"abstract":"<div><p>Accurate inflation forecasting is critical for effective economic planning and monetary policy formulation, especially in emerging economies such as Nigeria. Persistent inflation volatility driven by structural inefficiencies, external shocks, and weak monetary frameworks continues to challenge policy responses and macroeconomic stability. Traditional econometric models like Seasonal Autoregressive Integrated Moving Average (SARIMA) often fail to capture the nonlinear dynamics inherent in inflation behavior, while standalone machine learning models such as Artificial Neural Networks (ANNs) lack transparency and reliability in highly variable economic settings. To address this gap, this study proposes a hybrid forecasting framework that integrates SARIMA and Artificial Neural Network models to leverage their respective strengths in modeling linear and nonlinear patterns in Nigeria’s inflation rate. The methodology involves fitting a SARIMA (2,1,2)x(1,1,0)₁₂ model to the historical training set (monthly inflation data from January 2003 to September 2017) to capture trend and seasonality. Residuals and SARIMA-fitted values were then used alongside lagged inflation variables as input features for training a Multi-Layer Perceptron ANN model. A grid search with time-series cross-validation was employed for hyperparameter tuning, ensuring optimal model performance. The final hybrid model was used to forecast inflation rates for the period March 2024 to December 2030. Results show that the hybrid model outperformed both standalone SARIMA and ANN models across multiple metrics, including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared. The hybrid model achieved a forecast R-squared of 92.09%, with a MAPE of 7.68%, indicating excellent predictive accuracy on the test set. The forecast suggests periods of inflation spikes, particularly in 2025 and 2026, followed by relative stabilization toward 2030. The study concludes that the hybrid SARIMA–ANN model is a powerful and reliable tool for inflation forecasting in Nigeria. It is recommended for policymakers and economic analysts seeking to anticipate inflationary trends and design timely interventions. Future research could incorporate exogenous macroeconomic variables and explore deep learning enhancements to further improve forecasting performance.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 6","pages":"1541 - 1580"},"PeriodicalIF":0.0,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149230747","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}

{"title":"Autism Spectrum Disorder Identification Using Dual-Branch Fusion Model with Privacy-Preserving","authors":"Hezi Jing,&nbsp;Wanyi Chen,&nbsp;Qingyang Xu,&nbsp;Jianjun Yang,&nbsp;Danushka Bandara,&nbsp;Rongzhen Wang,&nbsp;Ziping Zhao,&nbsp;Chao Liu","doi":"10.1007/s40745-025-00603-1","DOIUrl":"10.1007/s40745-025-00603-1","url":null,"abstract":"<div><p>Autism Spectrum Disorder (ASD) are neurodevelopmental disorders that severely impact daily life and social interactions. According to research, early diagnosis and intervention of autism is crucial to improve the overall quality of life of patients. Although existing machine learning and deep learning methods have been applied to the identification and detection of autism, healthcare organizations often refuse to share or disclose medical data with the improvement of laws and regulations. Therefore, we propose a privacy-preserving deep learning method based on the local client using a dual-stream model to further improve the ASD recognition performance by capturing the features of functional MRI in both temporal and spatial structures, and further ensure that each client improves the performance of the local recognition task through federated learning by optimizing the two steps of the local client update and the client aggregation during federated learning. The experimental results show that our model achieves the best AUC of 0.952, which ensures the overall performance of the classification model, and the recognition accuracy is significantly improved by using federated learning compared to the results when clients are trained independently.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 1","pages":"79 - 104"},"PeriodicalIF":0.0,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147338983","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}

{"title":"Optimization Study of Electric-Hydrogen Hybrid Energy Storage Capacity in Warehouse Park for Smart Grid","authors":"Yanyang Fu,&nbsp;Jinbao Li,&nbsp;Lichong Cui,&nbsp;Huayu Chu,&nbsp;Qi Wang,&nbsp;Shuman Yang","doi":"10.1007/s40745-025-00649-1","DOIUrl":"10.1007/s40745-025-00649-1","url":null,"abstract":"<div>\u0000 \u0000 <p>To address the seasonal energy imbalance resulting from the high penetration of renewable energy sources in power systems, this study leverages smart grid technologies to innovatively design a hybrid electric-hydrogen energy storage system. The system integrates battery storage, above-ground hydrogen tanks, and salt cavern hydrogen storage facilities, forming a comprehensive energy framework tailored for warehouse parks, which operates synergistically with the smart grid. Based on a two-stage optimization approach, the upper-level model focuses on capacity allocation with objectives of economic efficiency and environmental protection, while the lower-level model minimizes daily operational costs. The lower-level problem is reformulated as a mixed-integer linear programming(MILP) problem using the Karush-Kuhn-Tucker(KKT) conditions and the Big-M method, enabling iterative coordination between the two layers to determine the optimal capacity configuration. The results demonstrate that: 1)The adoption of salt cavern hydrogen storage significantly reduces total system costs across all scenarios, with the largest reduction of ¥153,200 in the environment-prioritized scenario. In the dual-objective scenario, annual carbon emissions are reduced by 20.35t. 2)By optimally sizing photovoltaic panels, wind turbines, salt cavern storage, and compressor systems, and coordinating with grid energy purchases, the system achieves effective economic-environmental synergy, validating the adaptability of multi-energy complementarity to the electric-hydrogen demands of warehouse parks. 3)Seasonal hydrogen storage in salt caverns reduces energy purchase requirements in autumn and winter, mitigating economic and safety risks associated with large-scale above-ground hydrogen storage. Overall, the study verifies the economic and environmental feasibility of salt cavern hydrogen storage for integrated energy systems in warehouse parks and offers practical guidance on equipment selection and capacity optimization to support synergistic planning for both economic and environmental objectives.</p>\u0000 </div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 6","pages":"1501 - 1540"},"PeriodicalIF":0.0,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149230749","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}

{"title":"Dataset Distillation: Recent Advances of Methods and Challenges","authors":"Muyang Li,&nbsp;Yong Shi","doi":"10.1007/s40745-025-00651-7","DOIUrl":"10.1007/s40745-025-00651-7","url":null,"abstract":"<div><p>Dataset lightweighting is the process of constructing a small dataset from a large original dataset to reduce the pressure of data storage, distribution, and model training. Dataset distillation(DD) is an emerging dataset lightweight method in recent years. This paper mainly focuses on DD problem. The mainstream algorithms of DD can be divided into several categories: meta learning framework, parameter matching framework, distribution matching framework and generative model-based DD. In this paper, we provide a comprehensive review of the distillation methods of datasets since 2018 in the above order. At the end of the article, we present some discussions on the current state of development in this field and suggest some potential future research directions.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 6","pages":"1883 - 1901"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145537718","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}