Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100796
Lilia Costa , Arthur Azevedo , Michel Miler Rocha dos Santos , Diego Carvalho Nascimento
The Multiregression Dynamic Model (MDM) is a framework that combines graph theory with dynamic linear models, allowing a non-Gaussian multivariate structure to emerge in the context of causal time series. Since an optimal DAG structure is an NP-hard task, this package overcomes the all-combinations search (Integer Programming Algorithm) using heuristic algorithms (like Hill Climbing). Written using R S4 Object programming, it performs learning functions (estimating network structure and its dynamic arcs), as well as includes DAG (causal) visualization, time-varying coefficients visualization, and graphical performance checks. The MDM R package is distributed under the GPL license and is accessible from GitHub.
{"title":"MDM: An R package for causal multivariate time series tasks","authors":"Lilia Costa , Arthur Azevedo , Michel Miler Rocha dos Santos , Diego Carvalho Nascimento","doi":"10.1016/j.simpa.2025.100796","DOIUrl":"10.1016/j.simpa.2025.100796","url":null,"abstract":"<div><div>The Multiregression Dynamic Model (MDM) is a framework that combines graph theory with dynamic linear models, allowing a non-Gaussian multivariate structure to emerge in the context of causal time series. Since an optimal DAG structure is an NP-hard task, this package overcomes the all-combinations search (Integer Programming Algorithm) using heuristic algorithms (like Hill Climbing). Written using R S4 Object programming, it performs learning functions (estimating network structure and its dynamic arcs), as well as includes DAG (causal) visualization, time-varying coefficients visualization, and graphical performance checks. The MDM R package is distributed under the GPL license and is accessible from GitHub.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100796"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145466182","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100792
Boris Prokhorov , Oleg Zolotov , Yulia Romanovskaya , Anton Tatarnikov , Yulia Shapovalova
The pyNusinov package implements Nusinov’s extreme ultraviolet (EUVT) and far ultraviolet (FUVT) solar radiation models. Jointly, these models cover the 5–242 [nm] solar irradiance range but with different wavelength steps and a small gap between 105–115 [nm]. To third-party users, EUVT and FUVT models were published as analytical formulas and tables of corresponding coefficients. The release of the pyNusinov package provides a robust way to use, disseminate, install, and update these models. It significantly improves the models’ usage workflow, benefits from Python3 infrastructure, and facilitates early career researchers’ engagement.
{"title":"pyNusinov: A Python3 software package for Solar Extreme and Far Ultraviolet radiation modeling","authors":"Boris Prokhorov , Oleg Zolotov , Yulia Romanovskaya , Anton Tatarnikov , Yulia Shapovalova","doi":"10.1016/j.simpa.2025.100792","DOIUrl":"10.1016/j.simpa.2025.100792","url":null,"abstract":"<div><div>The pyNusinov package implements Nusinov’s extreme ultraviolet (EUVT) and far ultraviolet (FUVT) solar radiation models. Jointly, these models cover the 5–242 [nm] solar irradiance range but with different wavelength steps and a small gap between 105–115 [nm]. To third-party users, EUVT and FUVT models were published as analytical formulas and tables of corresponding coefficients. The release of the pyNusinov package provides a robust way to use, disseminate, install, and update these models. It significantly improves the models’ usage workflow, benefits from Python3 infrastructure, and facilitates early career researchers’ engagement.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100792"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145363255","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100798
N Annalakshmi , S Umarani
SkinProNet is an AI-powered software tool designed for the classification and segmentation of skin lesions, including potentially life-threatening conditions like melanoma. It employs a novel hybrid deep learning architecture that combines advanced preprocessing methods with state-of-the-art models: EfficientNetV2Small for feature extraction, an optimized ACRNN for accurate classification, and U2-Net++ for precise lesion segmentation. This integrated approach enhances early detection and diagnosis of skin diseases. The model classifies six types of skin diseases with a high accuracy of 94.04% using both benchmark datasets and real-world clinical images. The results highlight the model’s potential as a reliable computer-aided diagnostic tool in dermatology. By leveraging attention-based mechanisms and efficient neural architectures, the software supports healthcare practitioners in diagnosing skin conditions quickly, accurately, and non-invasively.
{"title":"SkinProNet: An attention-based deep learning system for skin disease classification and segmentation","authors":"N Annalakshmi , S Umarani","doi":"10.1016/j.simpa.2025.100798","DOIUrl":"10.1016/j.simpa.2025.100798","url":null,"abstract":"<div><div>SkinProNet is an AI-powered software tool designed for the classification and segmentation of skin lesions, including potentially life-threatening conditions like melanoma. It employs a novel hybrid deep learning architecture that combines advanced preprocessing methods with state-of-the-art models: EfficientNetV2Small for feature extraction, an optimized ACRNN for accurate classification, and U<sup>2</sup>-Net++ for precise lesion segmentation. This integrated approach enhances early detection and diagnosis of skin diseases. The model classifies six types of skin diseases with a high accuracy of 94.04% using both benchmark datasets and real-world clinical images. The results highlight the model’s potential as a reliable computer-aided diagnostic tool in dermatology. By leveraging attention-based mechanisms and efficient neural architectures, the software supports healthcare practitioners in diagnosing skin conditions quickly, accurately, and non-invasively.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100798"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145466179","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100789
Mariusz Oszust, Marian Wysocki
Feature selection in multivariate time series is a key challenge in modern data analysis, as high-dimensional data often include temporal dependencies and irrelevant features degrading classifier performance. To address these issues, a comparison with existing approaches is essential. Therefore, this work introduces the Toolbox for Metaheuristic Feature Selection in Multivariate Time Series (TMFS-MTS), providing an environment for feature selection and metaheuristic evaluation. It supports diverse fitness measures and advanced visualizations, including convergence curves, feature count tracking, runtime analysis, Wilcoxon tests, and 2D embeddings. Implemented in MATLAB, TMFS-MTS offers a standardized framework for advancing research in multivariate time series feature selection.
{"title":"TMFS-MTS: Toolbox for metaheuristic feature selection in multivariate time series","authors":"Mariusz Oszust, Marian Wysocki","doi":"10.1016/j.simpa.2025.100789","DOIUrl":"10.1016/j.simpa.2025.100789","url":null,"abstract":"<div><div>Feature selection in multivariate time series is a key challenge in modern data analysis, as high-dimensional data often include temporal dependencies and irrelevant features degrading classifier performance. To address these issues, a comparison with existing approaches is essential. Therefore, this work introduces the Toolbox for Metaheuristic Feature Selection in Multivariate Time Series (TMFS-MTS), providing an environment for feature selection and metaheuristic evaluation. It supports diverse fitness measures and advanced visualizations, including convergence curves, feature count tracking, runtime analysis, Wilcoxon tests, and 2D embeddings. Implemented in MATLAB, TMFS-MTS offers a standardized framework for advancing research in multivariate time series feature selection.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100789"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221949","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100801
Irsyad Fikriansyah Ramadhan , Ntivuguruzwa Jean De La Croix , Tohari Ahmad
In information security, image steganography remains a crucial technique for covert data transmission. However, achieving an optimal balance between payload capacity, imperceptibility, and robustness against steganalysis attacks remains a significant challenge. This paper presents IRJT-Secure, an open-source software implementation based on the Quadristego Logic paradigm and Huffman coding for data compression. The proposed technique creates four stego images from a single cover image, in contrast to conventional dual-image steganography. This maintains the original image’s visual integrity while enabling more effective and uniform data embedding. IRJT-Secure provides a valuable resource for advancing research and development in spatial domain steganography, supporting the creation of more secure, robust, and efficient data hiding techniques for digital security
{"title":"IRJT-Secure: Open-source image steganography with Quadristego embedding and Huffman compression","authors":"Irsyad Fikriansyah Ramadhan , Ntivuguruzwa Jean De La Croix , Tohari Ahmad","doi":"10.1016/j.simpa.2025.100801","DOIUrl":"10.1016/j.simpa.2025.100801","url":null,"abstract":"<div><div>In information security, image steganography remains a crucial technique for covert data transmission. However, achieving an optimal balance between payload capacity, imperceptibility, and robustness against steganalysis attacks remains a significant challenge. This paper presents IRJT-Secure, an open-source software implementation based on the Quadristego Logic paradigm and Huffman coding for data compression. The proposed technique creates four stego images from a single cover image, in contrast to conventional dual-image steganography. This maintains the original image’s visual integrity while enabling more effective and uniform data embedding. IRJT-Secure provides a valuable resource for advancing research and development in spatial domain steganography, supporting the creation of more secure, robust, and efficient data hiding techniques for digital security</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100801"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145576323","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100800
Manuel Domínguez-Dorado , David Cortés-Polo , Francisco J. Rodríguez-Pérez , Jesús Galeano-Brajones , Jesús Calle-Cancho
This article presents FLECO Studio 2.0, which enhances cybersecurity situational awareness training through realistic scenarios. Organizations face increasing cyber threats but struggle with a global shortage of cybersecurity professionals. To address this, they must upskill existing personnel across all functional areas. Situational awareness is crucial for identifying, understanding, and responding to threats dynamically. FLECO Studio 2.0 includes new features designed to improve this skill, enabling multidisciplinary teams to assess risks, anticipate attacks, and coordinate effective responses. These enhancements strengthen an organization’s cybersecurity posture, fostering a unified and proactive defense against evolving threats.
本文介绍了FLECO Studio 2.0，它通过现实场景增强了网络安全态势感知训练。企业面临着越来越多的网络威胁，但却面临着全球网络安全专业人员短缺的问题。为了解决这个问题，他们必须提高所有职能领域现有人员的技能。态势感知对于动态识别、理解和响应威胁至关重要。FLECO Studio 2.0包含了旨在提高此技能的新功能，使多学科团队能够评估风险、预测攻击并协调有效的响应。这些增强增强了组织的网络安全态势，促进了对不断变化的威胁的统一和主动防御。
{"title":"Version 2.0 — FLECO, enhancements for cyber situational awareness training and research","authors":"Manuel Domínguez-Dorado , David Cortés-Polo , Francisco J. Rodríguez-Pérez , Jesús Galeano-Brajones , Jesús Calle-Cancho","doi":"10.1016/j.simpa.2025.100800","DOIUrl":"10.1016/j.simpa.2025.100800","url":null,"abstract":"<div><div>This article presents FLECO Studio 2.0, which enhances cybersecurity situational awareness training through realistic scenarios. Organizations face increasing cyber threats but struggle with a global shortage of cybersecurity professionals. To address this, they must upskill existing personnel across all functional areas. Situational awareness is crucial for identifying, understanding, and responding to threats dynamically. FLECO Studio 2.0 includes new features designed to improve this skill, enabling multidisciplinary teams to assess risks, anticipate attacks, and coordinate effective responses. These enhancements strengthen an organization’s cybersecurity posture, fostering a unified and proactive defense against evolving threats.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100800"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623824","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100787
Zhanqi Cui, Yuanxin Qiao, Ruilin Xie, Li Li, Qifan He
Textual adversarial attacks generate adversarial examples that retain similar semantics to the original text and feed them into the target model to detect potential vulnerabilities by comparing output differences. This approach effectively addresses the scarcity of annotated test data during the testing phase. Existing methods often rely on greedy strategies for candidate word selection, which may result in contextually inappropriate or unnatural perturbations, thereby compromising the overall quality of the adversarial examples. To address this issue, we propose MOBTAG, a tool for generating textual adversarial examples based on multi-objective optimization. MOBTAG integrates principles from both multi-objective optimization and genetic algorithms. It improves the attack success rate while maintaining high semantic similarity and readability between adversarial examples and the original texts, thereby enabling the generation of high-quality adversarial examples
{"title":"A tool for textual adversarial attack via multi-objective optimization","authors":"Zhanqi Cui, Yuanxin Qiao, Ruilin Xie, Li Li, Qifan He","doi":"10.1016/j.simpa.2025.100787","DOIUrl":"10.1016/j.simpa.2025.100787","url":null,"abstract":"<div><div>Textual adversarial attacks generate adversarial examples that retain similar semantics to the original text and feed them into the target model to detect potential vulnerabilities by comparing output differences. This approach effectively addresses the scarcity of annotated test data during the testing phase. Existing methods often rely on greedy strategies for candidate word selection, which may result in contextually inappropriate or unnatural perturbations, thereby compromising the overall quality of the adversarial examples. To address this issue, we propose MOBTAG, a tool for generating textual adversarial examples based on multi-objective optimization. MOBTAG integrates principles from both multi-objective optimization and genetic algorithms. It improves the attack success rate while maintaining high semantic similarity and readability between adversarial examples and the original texts, thereby enabling the generation of high-quality adversarial examples</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100787"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145268606","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100795
Lejla Arapovic, Emir Sokic
This paper presents DefectDetect, a lightweight desktop tool for manual image annotation and automatic patch extraction, developed to assist in creating annotated datasets for machine learning problems. Although it is initially designed for annotating leather defects, the application supports broader use cases. Users can annotate freely, automatically extract smaller image patches and corresponding binary masks with adjustable stride, selected defect types and rating (0–2), and export data in PNG, JSON, YOLO, or Pascal VOC formats. The tool is fully GUI-based, requires no coding knowledge for usage, and supports session saving and batch image loading. The application has proven effective in academic contexts through its use in research activities. Future plans include the addition of shape annotation functionality and support for batch processing.
{"title":"DefectDetect: A lightweight application for manual image annotation and patch extraction","authors":"Lejla Arapovic, Emir Sokic","doi":"10.1016/j.simpa.2025.100795","DOIUrl":"10.1016/j.simpa.2025.100795","url":null,"abstract":"<div><div>This paper presents DefectDetect, a lightweight desktop tool for manual image annotation and automatic patch extraction, developed to assist in creating annotated datasets for machine learning problems. Although it is initially designed for annotating leather defects, the application supports broader use cases. Users can annotate freely, automatically extract smaller image patches and corresponding binary masks with adjustable stride, selected defect types and rating (0–2), and export data in PNG, JSON, YOLO, or Pascal VOC formats. The tool is fully GUI-based, requires no coding knowledge for usage, and supports session saving and batch image loading. The application has proven effective in academic contexts through its use in research activities. Future plans include the addition of shape annotation functionality and support for batch processing.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100795"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145466177","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100786
Marta Moreno , Hugo Rocha , André Pilastri , Guilherme Moreira , Luís Miguel Matos , Paulo Cortez
Modern screwdriver systems generate real-time angle-torque data that form tightening curves that are valuable for quality inspection issues (e.g., detect faulty processes). This work describes the Screw Process Anomaly Visualization (SPAV) Python module, which provides several eXplainable AI (XAI) graphs for Machine Learning (ML) screw tightening results, namely global and local errors, with identification of most probable anomaly angle-torque locations. SPAV integrates seamlessly with the scientific Python ecosystem and is compatible with several ML implementations, including H2O and Keras deep AutoEncoders (AE).
{"title":"Screw Process Anomaly Visualization (SPAV): A Python module for local and global machine learning visualizations for screw tightening anomaly detection","authors":"Marta Moreno , Hugo Rocha , André Pilastri , Guilherme Moreira , Luís Miguel Matos , Paulo Cortez","doi":"10.1016/j.simpa.2025.100786","DOIUrl":"10.1016/j.simpa.2025.100786","url":null,"abstract":"<div><div>Modern screwdriver systems generate real-time angle-torque data that form tightening curves that are valuable for quality inspection issues (e.g., detect faulty processes). This work describes the Screw Process Anomaly Visualization (SPAV) Python module, which provides several eXplainable AI (XAI) graphs for Machine Learning (ML) screw tightening results, namely global and local errors, with identification of most probable anomaly angle-torque locations. SPAV integrates seamlessly with the scientific Python ecosystem and is compatible with several ML implementations, including H2O and Keras deep AutoEncoders (AE).</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100786"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221950","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}
Pub Date : 2025-10-01DOI: 10.1016/j.simpa.2025.100797
Gihan S. Edirisinghe , Charles L. Munson
This paper introduces a MATLAB-based framework for shelf-space optimization in retail, integrating AMPL via an API for solving linear and nonlinear programs. It supports two strategies: (1) Guided Random Rearrangement, creating constraint-aware layouts without prior data, and (2) Data-Driven Rearrangement, using association rule mining and mixed-integer programming to boost impulse buys. Core data structures are developed in MATLAB, while CPLEX and BARON solvers are employed through AMPL when required. The system adapts to varied retail environments, enhancing profitability and customer experience. New experiments with the Microsoft FoodMart dataset show that the data-driven method consistently outperforms random strategies.
{"title":"MATLAB-AMPL integration with heuristics and association mining: An optimization-driven framework for retail shelf space allocation","authors":"Gihan S. Edirisinghe , Charles L. Munson","doi":"10.1016/j.simpa.2025.100797","DOIUrl":"10.1016/j.simpa.2025.100797","url":null,"abstract":"<div><div>This paper introduces a MATLAB-based framework for shelf-space optimization in retail, integrating AMPL via an API for solving linear and nonlinear programs. It supports two strategies: (1) Guided Random Rearrangement, creating constraint-aware layouts without prior data, and (2) Data-Driven Rearrangement, using association rule mining and mixed-integer programming to boost impulse buys. Core data structures are developed in MATLAB, while CPLEX and BARON solvers are employed through AMPL when required. The system adapts to varied retail environments, enhancing profitability and customer experience. New experiments with the Microsoft FoodMart dataset show that the data-driven method consistently outperforms random strategies.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"26 ","pages":"Article 100797"},"PeriodicalIF":1.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145525789","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号