Annals of Data Science最新文献_第2页

EdgeSculpt-HO: A hybrid optimization AI model for Real-Time 3D sculpture and pottery design EdgeSculpt-HO：用于实时3D雕塑和陶器设计的混合优化AI模型

Annals of Data Science Pub Date : 2026-03-02 DOI: 10.1007/s40745-025-00669-x

Lu kun Huang

{"title":"EdgeSculpt-HO: A hybrid optimization AI model for Real-Time 3D sculpture and pottery design","authors":"Lu kun Huang","doi":"10.1007/s40745-025-00669-x","DOIUrl":"10.1007/s40745-025-00669-x","url":null,"abstract":"<div><p>Digital sculpting is becoming increasingly important in creative design, education, and cultural heritage preservation. Yet, existing techniques for 3D sculpture and pottery modeling often face significant limitations, including poor adaptability to user input, computational inefficiency, and inadequate responsiveness in real-time or edge-computing environments. These challenges hinder intuitive interaction and dynamic design exploration. To overcome these barriers, this work introduces EdgeSculpt-HO, a Hybrid Optimization AI model for real-time, gesture-based 3D sculpture and pottery creation. The framework integrates four key modules: SPFeat-FuseNet for extracting rich multimodal features from spatial, stylistic, and temporal data; EdgeSculptNet, a NAS-enhanced 3D generator optimized for edge deployment; C-GreyGenSelect, a chaotic Grey Wolf and Genetic Algorithm-based selector for robust feature reduction; and the Touch2Form Interaction System, which enables real-time sculptural manipulation using gestures, supported by reinforcement learning, Vision Transformers, and RNN-based haptic feedback. Notably, the system collects Internet of Things-based tactile and environmental input, and utilizes software-defined networking to dynamically manage low-latency data routing between modules across edge devices. Tested on three datasets—6K Sculptures, Art Images, and 3D Model Samples—EdgeSculpt-HO outperformed MeshGAN, AtlasNet, and 3D-StyleGAN, achieving a Dice Similarity of 0.97, Chamfer Distance of 0.0023, 94.6% optimization accuracy, System Usability Scale of 97, Mean Opinion Score of 4.6, and Net Promoter Score of + 72, validating its artistic quality, responsiveness, and deployment readiness.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 2","pages":"455 - 487"},"PeriodicalIF":0.0,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147606930","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

Enhancing Concrete Crack Detection Using Preprocessing Techniques on a Convolutional Neural Network and a Vision Transformer 基于卷积神经网络和视觉变压器的预处理技术增强混凝土裂缝检测

Annals of Data Science Pub Date : 2026-02-24 DOI: 10.1007/s40745-026-00676-6

Joshua Ajayi, Oluwafemi Omotayo

{"title":"Enhancing Concrete Crack Detection Using Preprocessing Techniques on a Convolutional Neural Network and a Vision Transformer","authors":"Joshua Ajayi, Oluwafemi Omotayo","doi":"10.1007/s40745-026-00676-6","DOIUrl":"10.1007/s40745-026-00676-6","url":null,"abstract":"<div><p>Structural cracks pose a significant threat to the safety, serviceability and durability of reinforced concrete structures. Early and accurate crack detection is essential for preventing progressive deterioration and potential structural failure. However, conventional manual inspection methods are time-consuming, labor-intensive and often inconsistent. Recent advances in machine learning (ML) and deep learning (DL) have enabled automated crack detection as a core component of modern structural health monitoring (SHM) systems. Despite the strong performance of DL-based approaches, the influence of image preprocessing on model robustness and generalization remains insufficiently explored. This study presents a systematic evaluation of three commonly used preprocessing techniques: Data Augmentation, Contrast Limited Adaptive Histogram Equalization (CLAHE), and Gaussian blurring, on two DL architectures: ResNet-50 and the Vision Transformer (ViT). A deduplicated version of a publicly available concrete crack dataset was used to reduce redundancy and mitigate evaluation bias. Model performance was evaluated using accuracy, precision, recall and F1-score under consistent training and testing conditions. The results demonstrate that image preprocessing plays a critical role in model reliability and generalization. Data augmentation consistently improved performance across both architectures, while CLAHE achieved the highest overall accuracy, yielding up to a 0.12% improvement for ResNet-50 and emerging as the most effective strategy for this model. In contrast, Gaussian blurring significantly degraded performance for both models, although ViT demonstrated greater resilience under blurred conditions. Unlike prior studies that apply preprocessing heuristically, this work provides a controlled, architecture-aware analysis, offering practical guidance for designing reliable, field-deployable crack detection systems for SHM applications.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 3","pages":"665 - 680"},"PeriodicalIF":0.0,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148459144","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

Economic Profile Generation from Textual Data Using an Algorithm Framework 使用算法框架从文本数据生成经济概况

Annals of Data Science Pub Date : 2026-02-16 DOI: 10.1007/s40745-026-00687-3

Olusola Babalola, Bolanle Ojokoh, Olutayo Boyinbode

{"title":"Economic Profile Generation from Textual Data Using an Algorithm Framework","authors":"Olusola Babalola, Bolanle Ojokoh, Olutayo Boyinbode","doi":"10.1007/s40745-026-00687-3","DOIUrl":"10.1007/s40745-026-00687-3","url":null,"abstract":"<div><p>Business topics are prominent in the news. The non-stop production of news, sometimes in real time, provides a potentially valuable source of data for understanding the business environment of regions or localities covered in the news. This study examines a multistage algorithmic framework to produce economic profiles from a corpus of news headlines. The methodology integrates topic modeling, named entity recognition, TF-IDF refinements, and network analysis in an algorithmic pipeline to identify key economic information. The algorithmic framework is structured around key natural language processing tools and techniques. It provides for processing headlines, assigning them to different topics, identifying business-centric topics, extracting relevant entities, analyzing relationships between business-centric topics, extracting relevant entities, and analyzing relationships between the business topic and other topics. The extracted information can be synthesized into an economic profile. This research is a domain-biased version of a system that has been used to automatically extract social problems from a corpus of 148,000 news headlines. The framework was applied to 1,280 news headlines to demonstrate its functionality in parts.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 3","pages":"741 - 768"},"PeriodicalIF":0.0,"publicationDate":"2026-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148459056","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

Understanding Patient Satisfaction in Online Healthcare: A Study from Doctor-Patient Interaction Perspective 了解线上医疗病患满意度：基于医患互动视角的研究

Annals of Data Science Pub Date : 2026-02-12 DOI: 10.1007/s40745-026-00688-2

Yalin Su, Junli Zhang, Xiaodan Yu

{"title":"Understanding Patient Satisfaction in Online Healthcare: A Study from Doctor-Patient Interaction Perspective","authors":"Yalin Su, Junli Zhang, Xiaodan Yu","doi":"10.1007/s40745-026-00688-2","DOIUrl":"10.1007/s40745-026-00688-2","url":null,"abstract":"<div><p>The digital transformation of healthcare has introduced online healthcare services that offer unprecedented accessibility and convenience. However, the shift to virtual doctor-patient interactions has unveiled new challenges in ensuring patient satisfaction. Prior research has primarily focused on the doctor's perspective, with scant attention given to the patient's perception of informational and emotional support within these digital interactions. Drawing the perspective from Media Synchronicity Theory, this study investigates how online healthcare interaction patterns influence patient perceived satisfaction of informational support and emotional support, and how different interaction patterns across varied media types impact these satisfaction facets. Through an empirical analysis of 7374 patient consultation records from \"www.haodf.com\", this study analyzes the influence of interaction pattern such as doctors' response time, interaction rounds, frequency and media synchronicity in patients' satisfaction. Research results indicate that while doctor's response time might not be the most decisive factor, other interactive factors— interaction rounds and consultation frequency positively influence patient satisfaction with both perceived informational support and emotional support, and media synchronicity positively moderates the impact of the number of interaction rounds on patient satisfaction with perceived informational support and emotional support. By introducing a patient-centric approach to understanding satisfaction in online healthcare interactions, this study highlights the importance of media synchronicity in optimizing communication and provides empirical evidence for the role of interaction patterns in shaping patient satisfaction. The findings offer insights for healthcare providers and platform designers to enhance online service delivery and patient engagement.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 2","pages":"501 - 521"},"PeriodicalIF":0.0,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147606497","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

Research on Data Monitoring of Power Grid Operation Status Based on Internet of Things Technology 基于物联网技术的电网运行状态数据监测研究

Annals of Data Science Pub Date : 2026-02-12 DOI: 10.1007/s40745-026-00684-6

Qiang Li, Weijian Zhang, Weizhi Lu, Yuan Liu, Di Cai

{"title":"Research on Data Monitoring of Power Grid Operation Status Based on Internet of Things Technology","authors":"Qiang Li, Weijian Zhang, Weizhi Lu, Yuan Liu, Di Cai","doi":"10.1007/s40745-026-00684-6","DOIUrl":"10.1007/s40745-026-00684-6","url":null,"abstract":"<div><p>With the advancement of power grid informatization, the utilization of Internet of Things (IoT) technology has become increasingly widespread. This study primarily focuses on monitoring the operational status of the power grid, specifically targeting load status. Environmental and load data were collected using IoT technology. Then, the least squares support vector machine (LSSVM) was selected as the predictive model. An improved beluga whale optimization (IBWO) algorithm was developed to optimize the parameters of the LSSVM model, resulting in an IBWO-LSSVM model for load status prediction. An experiment was conducted using the collected data. It was found that the load state predictions generated by the IBWO-LSSVM model closely matched the actual values. The mean absolute error achieved was 30.56 MW, the root mean square error was 38.45 MW, and the mean absolute percentage error was 2.12%. These results also surpassed those of several other prediction methods, demonstrating the effectiveness of this model in load state prediction and its capability to enhance load state data monitoring. The findings validate the efficacy of the IBWO-LSSVM model and highlight its potential application in actual data monitoring of grid operational status.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 2","pages":"489 - 500"},"PeriodicalIF":0.0,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147606496","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

Convolution Neural Network-Based Facial Recognition System for Detecting Student Impersonation in Educational Institution 基于卷积神经网络的教育机构学生冒充人脸识别系统

Annals of Data Science Pub Date : 2026-02-12 DOI: 10.1007/s40745-026-00678-4

Ednah Olubunmi Aliyu, Adedamola Ayobami Adeleke, Felix Ola Aranuwa, Olanike Christianah Akinduyite, Olaniyi Abiodun Ayeni

{"title":"Convolution Neural Network-Based Facial Recognition System for Detecting Student Impersonation in Educational Institution","authors":"Ednah Olubunmi Aliyu, Adedamola Ayobami Adeleke, Felix Ola Aranuwa, Olanike Christianah Akinduyite, Olaniyi Abiodun Ayeni","doi":"10.1007/s40745-026-00678-4","DOIUrl":"10.1007/s40745-026-00678-4","url":null,"abstract":"<div><p>Examination malpractice has eroded moral integrity and ethical principles within many Nigerian institutions. Traditional identification methods, like student ID cards and fee payment receipts, are easily falsifiable, fostering impersonation during examination. This research proposes a convolutional neural network (CNN)-based facial recognition system to address this issue. A facial corpus of students was collected, stored in the database. Uploaded media was saved in Amazon Web Services (AWS) and processed using Open Computer Vision (OpenCV) library. Feature extractor and facial recognition are based on MobileNetV2, ResNet50 and EfficientNet-B0, which aid the translation of incoming images. The database (MySQL) facilitates the retrieval of the data during the verification process. The system was implemented using JavaScript and the Python programming platform (Python Web Framework). In our experiments, MobileNetV2 achieved an overall accuracy of 96%, with precision of 99%, recall of 92%, and an F1-score of 95%. ResNet50 accuracy measure 91%, precision of 93%, Recall of 88% and F1-score of 90% while EfficientNet-B0 accuracy measure 92%, precision of 1%, recall of 83% and F1-score of 91%. These results demonstrate that MobileNetV2 provides high reliability, making it ideal for deployment on resource-constrained devices. Hence, the proposed system is recommended for educational institutions to effectively curb impersonation and enhance examination integrity.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 3","pages":"701 - 714"},"PeriodicalIF":0.0,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148458961","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

Tracy and Tracer: AI-Powered Mobile Applications for Privacy-Preserving Contact Tracing and Health Monitoring Tracy和Tracer：用于保护隐私的接触追踪和健康监测的人工智能移动应用程序

Annals of Data Science Pub Date : 2026-02-11 DOI: 10.1007/s40745-026-00682-8

Bolanle Adefowoke Ojokoh, Benjamin Segun Aribisala, Arome Junior Gabriel, Olusola Tope Babalola, Oluwafemi Abimbola Sarumi, Tobore Victor Igbe, Olatunji Omisore, Abimbola Helen Afolayan, Abiola Ezekiel Taiwo, Uchechukwu M. Chukwuocha, Tolulope Anthonia Ugwu, Daniel Adeniyi

{"title":"Tracy and Tracer: AI-Powered Mobile Applications for Privacy-Preserving Contact Tracing and Health Monitoring","authors":"Bolanle Adefowoke Ojokoh, Benjamin Segun Aribisala, Arome Junior Gabriel, Olusola Tope Babalola, Oluwafemi Abimbola Sarumi, Tobore Victor Igbe, Olatunji Omisore, Abimbola Helen Afolayan, Abiola Ezekiel Taiwo, Uchechukwu M. Chukwuocha, Tolulope Anthonia Ugwu, Daniel Adeniyi","doi":"10.1007/s40745-026-00682-8","DOIUrl":"10.1007/s40745-026-00682-8","url":null,"abstract":"<div><p>During the COVID-19 pandemic, there was a conspicuous void in the integration of contemporary technological solutions in the public health sector. Tracy and Tracer are mobile applications designed to address this gap by enabling users to contribute extensive datasets through real-time surveillance, thus facilitating both effective contact tracing and integration of health data. Tracy leverages Bluetooth and GPS to automatically record movement data and proximity interactions, generating comprehensive datasets for advanced analytics. Tracer, on the other hand, collects self-assessed health data, which can be further refined for public health analysis. Developed using Flutter and Android Studio with data securely stored in Firebase, both applications implement privacy-focused data processing protocols, ensuring anonymization and adherence to ethical standards. By combining data collection with privacy-centric processes, Tracy and Tracer serve as complementary AI-powered tools that can significantly enhance public health decision-making during health crises. The system architecture, data capture mechanisms, and data transfer protocols emphasize privacy protection and secure data handling, with promising applications for future epidemic mitigation efforts.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 3","pages":"591 - 608"},"PeriodicalIF":0.0,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148458825","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

Post-COVID Health Behaviours and Perceptions Among Nigerian University Students: Insights for Sustainable Public Health Policy and Future Pandemic Preparedness 尼日利亚大学生的后covid健康行为和观念：对可持续公共卫生政策和未来大流行防范的见解

Annals of Data Science Pub Date : 2026-02-11 DOI: 10.1007/s40745-026-00677-5

Abimbola H. Afolayan, Chukwuemeka C. Ugwu

{"title":"Post-COVID Health Behaviours and Perceptions Among Nigerian University Students: Insights for Sustainable Public Health Policy and Future Pandemic Preparedness","authors":"Abimbola H. Afolayan, Chukwuemeka C. Ugwu","doi":"10.1007/s40745-026-00677-5","DOIUrl":"10.1007/s40745-026-00677-5","url":null,"abstract":"<div><p>The outbreak of the COVID-19 pandemic underscored the critical importance of public knowledge, attitudes, and perceptions (KAP) in managing infectious disease outbreaks and informing sustainable health policies. This study examines post-COVID-19 knowledge, attitudes, perceptions, and preventive awareness among university students at the Federal University of Technology, Akure (FUTA), Nigeria, using the KAP framework augmented by constructs from the Health Belief Model (HBM) and the Theory of Planned Behaviour (TPB). A cross-sectional survey of 500 students across nine academic schools was conducted in February 2023. Descriptive statistics and Pearson correlation analysis were used to examine relationships among knowledge, beliefs, and behaviours, revealing generally weak linear associations, suggesting complex, non-linear behavioural dynamics. To uncover latent behavioural patterns, unsupervised machine learning techniques: K-means clustering, and Principal Component Analysis (PCA) were applied, identifying three distinct behavioural profiles: compliant knowledgeables, high-conformity but misinformed individuals, and cautiously aware but less active students. Multiple linear regression was further employed to assess the influence of demographic factors on preventive practices, with gender, religion, academic level, and faculty emerging as significant predictors. By integrating behavioural theory with data-driven modelling, the study provides actionable insights for designing targeted interventions, strengthening campus-level health strategies, and enhancing preparedness for future infectious disease outbreaks.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 3","pages":"531 - 560"},"PeriodicalIF":0.0,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148458826","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

A Data-Driven Ensemble Deep Learning Framework for Intelligent Intrusion Detection in Ethical Telehealth Systems 面向伦理远程医疗系统智能入侵检测的数据驱动集成深度学习框架

Annals of Data Science Pub Date : 2026-02-10 DOI: 10.1007/s40745-026-00683-7

Josephine Olamatanmi Mebawondu

{"title":"A Data-Driven Ensemble Deep Learning Framework for Intelligent Intrusion Detection in Ethical Telehealth Systems","authors":"Josephine Olamatanmi Mebawondu","doi":"10.1007/s40745-026-00683-7","DOIUrl":"10.1007/s40745-026-00683-7","url":null,"abstract":"<div><p>The growing reliance on telehealth solutions has reshaped healthcare delivery while introducing new and persistent cybersecurity vulnerabilities. Telehealth systems operate across diverse networked medical devices and rely on continuous data exchange involving highly sensitive patient information, making them susceptible to increasingly complex cyber intrusions. Existing intrusion detection approaches often struggle to adapt to the dynamic and resource-constrained nature of these environments. This work presents a data-driven ensemble deep learning framework designed to enhance intrusion detection within ethically governed telehealth infrastructures. The proposed framework integrates Long Short-Term Memory networks, Convolutional Neural Networks, and Deep Belief Networks to capture sequential network behavior, extract discriminative traffic features, and model abstract attack patterns. Model training and evaluation are conducted using the UNSW-NB15 dataset, which represents contemporary attack vectors relevant to healthcare networks. The experimental findings demonstrate that the ensemble approach attains a detection accuracy of 79% while achieving a lower false positive rate than individual deep learning models, thereby improving operational reliability in clinical settings. Beyond performance outcomes, the framework emphasizes responsible artificial intelligence practices by supporting privacy protection, balanced classification decisions, and dependable system behavior. The results indicate that ensemble-based deep learning can provide an effective, trustworthy, and deployable intrusion detection mechanism capable of strengthening cybersecurity resilience in modern telehealth systems.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 3","pages":"715 - 725"},"PeriodicalIF":0.0,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148458680","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

Two new multi-view robust principal component analysis methods 两种新的多视图鲁棒主成分分析方法

Annals of Data Science Pub Date : 2026-02-09 DOI: 10.1007/s40745-026-00675-7

Fukang Long, Ling Jing, Yi Li, Bai Xue, Qiuyang Zhang

引用次数: 0