Pub Date : 2026-02-01Epub Date: 2025-12-10DOI: 10.1016/j.softx.2025.102449
Karim Elasri, Thomas Lagoarde-Ségot
The objective of this paper is to make ecological macroeconomic modeling accessible to all by sharing the code, technical appendix and User Manual of Philia 1.0, an ongoing modeling project used in several academic papers. Philia 1.0 is a middle-sized model of 500 equations describing the interaction between an artificial economy and a simplified Earth system. This model yields analytical insight into the impact of a wide array of sustainable transition policies on the macroeconomy, climate, inequalities, and postgrowth welfare indicators. The E-views code modules discussed in this paper are scalable so that researchers can easily introduce new variables, recalibrate the model, change parameter value or include new structural relationships to develop their own policy scenarios.
{"title":"Ecological macroeconomics with Philia 1.0","authors":"Karim Elasri, Thomas Lagoarde-Ségot","doi":"10.1016/j.softx.2025.102449","DOIUrl":"10.1016/j.softx.2025.102449","url":null,"abstract":"<div><div>The objective of this paper is to make ecological macroeconomic modeling accessible to all by sharing the code, technical appendix and User Manual of <em>Philia 1.0</em>, an ongoing modeling project used in several academic papers. Philia 1.0 is a middle-sized model of 500 equations describing the interaction between an artificial economy and a simplified Earth system. This model yields analytical insight into the impact of a wide array of sustainable transition policies on the macroeconomy, climate, inequalities, and postgrowth welfare indicators. The E-views code modules discussed in this paper are scalable so that researchers can easily introduce new variables, recalibrate the model, change parameter value or include new structural relationships to develop their own policy scenarios.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102449"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145748540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Environmental Policy Integrated Climate (EPIC) model is a comprehensive, field-scale agroecosystem model widely used for both diagnostic and prognostic analyses in agriculture. However, its application at regional scales is limited due to its original design to simulate a limited number of fields. Custom Python or R scripts have attempted to scale EPIC, but they are often inefficient, non-standardized, and not publicly available. To address these issues, we developed GeoEPIC, a comprehensive Python package that streamlines spatial EPIC implementation. GeoEPIC automates input generation from spatial datasets, model calibration, simulation execution, and output post-processing. This paper introduces GeoEPIC’s structure and functionality through illustrative examples demonstrating its application for crop yield estimation and simulating water use in irrigated soybean systems in Nebraska.
{"title":"GeoEPIC: A comprehensive python package for spatial implementation of EPIC crop simulation model","authors":"Bharath Irigireddy , Varaprasad Bandaru , Sachin Velmurugan , Chaitanya Kulkarni","doi":"10.1016/j.softx.2025.102500","DOIUrl":"10.1016/j.softx.2025.102500","url":null,"abstract":"<div><div>The Environmental Policy Integrated Climate (EPIC) model is a comprehensive, field-scale agroecosystem model widely used for both diagnostic and prognostic analyses in agriculture. However, its application at regional scales is limited due to its original design to simulate a limited number of fields. Custom Python or R scripts have attempted to scale EPIC, but they are often inefficient, non-standardized, and not publicly available. To address these issues, we developed GeoEPIC, a comprehensive Python package that streamlines spatial EPIC implementation. GeoEPIC automates input generation from spatial datasets, model calibration, simulation execution, and output post-processing. This paper introduces GeoEPIC’s structure and functionality through illustrative examples demonstrating its application for crop yield estimation and simulating water use in irrigated soybean systems in Nebraska.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102500"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-14DOI: 10.1016/j.softx.2026.102510
Łukasz Szeremeta
Knows is a command-line property graphs generator for prototyping, testing, database development, and scientific or educational purposes. The tool emphasizes zero-configuration defaults with optional parameters for simple use cases, while also supporting optional schema files for custom graph structures. Knows exports to multiple formats (including YARS-PG, GraphML, CSV, Cypher, and JSON), includes a minimal built-in visualizer, and ensures reproducibility across formats via an optional random seed. The tool is widely available on PyPI and Docker Hub, and is ready for use by researchers, developers, educators, students, and anyone working with graph data.
{"title":"Knows: A flexible and reproducible property graph generator","authors":"Łukasz Szeremeta","doi":"10.1016/j.softx.2026.102510","DOIUrl":"10.1016/j.softx.2026.102510","url":null,"abstract":"<div><div>Knows is a command-line property graphs generator for prototyping, testing, database development, and scientific or educational purposes. The tool emphasizes zero-configuration defaults with optional parameters for simple use cases, while also supporting optional schema files for custom graph structures. Knows exports to multiple formats (including YARS-PG, GraphML, CSV, Cypher, and JSON), includes a minimal built-in visualizer, and ensures reproducibility across formats via an optional random seed. The tool is widely available on PyPI and Docker Hub, and is ready for use by researchers, developers, educators, students, and anyone working with graph data.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102510"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-02DOI: 10.1016/j.softx.2025.102469
Antonio J. Hidalgo-Marín , Antonio J. Nebro , José García-Nieto
ParetoInvest is an advanced software tool that facilitates the application of bio-inspired optimization algorithms to the multi-objective portfolio selection problem. Built on top of the widely used jMetal framework, ParetoInvest supports a range of meta-heuristics, including multi-objective evolutionary algorithms (MOEAs), to model and solve complex asset allocation tasks. A distinguishing feature of the platform is its integration with real-time financial data sources, providing up-to-date information on U.S. market assets and enabling simulations that accurately reflect current market conditions. The tool also includes a reliable data management system for downloading, storing, and manipulating financial datasets, with support for exporting data in various formats for external analysis. By combining real-time data access, advanced optimization techniques, and flexible data handling, ParetoInvest offers a powerful environment for researchers, finance professionals, and developers seeking innovative solutions for portfolio optimization using bio-inspired methods.
{"title":"ParetoInvest: Integrating real-time financial data and multi-objective meta-heuristics for portfolio optimization","authors":"Antonio J. Hidalgo-Marín , Antonio J. Nebro , José García-Nieto","doi":"10.1016/j.softx.2025.102469","DOIUrl":"10.1016/j.softx.2025.102469","url":null,"abstract":"<div><div>ParetoInvest is an advanced software tool that facilitates the application of bio-inspired optimization algorithms to the multi-objective portfolio selection problem. Built on top of the widely used jMetal framework, ParetoInvest supports a range of meta-heuristics, including multi-objective evolutionary algorithms (MOEAs), to model and solve complex asset allocation tasks. A distinguishing feature of the platform is its integration with real-time financial data sources, providing up-to-date information on U.S. market assets and enabling simulations that accurately reflect current market conditions. The tool also includes a reliable data management system for downloading, storing, and manipulating financial datasets, with support for exporting data in various formats for external analysis. By combining real-time data access, advanced optimization techniques, and flexible data handling, ParetoInvest offers a powerful environment for researchers, finance professionals, and developers seeking innovative solutions for portfolio optimization using bio-inspired methods.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102469"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145652092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-15DOI: 10.1016/j.softx.2025.102485
Zhaoyan Li , Dengke Zhao , Ji’an Liao , Zifa Wang
As seismic hazards pose a significant threat to buildings, it is crucial to implement monitoring and risk assessment throughout the entire earthquake process. Existing structural response monitoring and damage prediction methods have limited accuracy, with most risk assessment systems relying on empirical models. These systems often fail to achieve comprehensive data integration and effective assessment across the entire process. This study proposes the Integrated System for Seismic Response Monitoring and Risk Assessment of Buildings (ISRAB), which effectively integrates real-time sensor data with Improved Deep Embedded Clustering (IDEC) and threshold warnings to predict structural state changes. It uses a random field approach to quantitatively assess building loss, casualties, and repair time, and supports future earthquake risk analysis. ISRAB bridges structural response monitoring, damage warning, consequence assessment, and future earthquake risk evaluation, enabling comprehensive applications throughout the entire process. Using a single-layer 3D-printed rural house as an example, the functionality of ISRAB was demonstrated, showing that it can provide at least 5 s of early warning and achieve a 97 % accuracy rate in structural state identification. The application scenarios of ISRAB include enhancing urban seismic resilience, supporting post-disaster emergency management, facilitating insurance claims, and improving risk assessment processes.
{"title":"ISRAB: Integrated system for seismic response monitoring and risk assessment of buildings","authors":"Zhaoyan Li , Dengke Zhao , Ji’an Liao , Zifa Wang","doi":"10.1016/j.softx.2025.102485","DOIUrl":"10.1016/j.softx.2025.102485","url":null,"abstract":"<div><div>As seismic hazards pose a significant threat to buildings, it is crucial to implement monitoring and risk assessment throughout the entire earthquake process. Existing structural response monitoring and damage prediction methods have limited accuracy, with most risk assessment systems relying on empirical models. These systems often fail to achieve comprehensive data integration and effective assessment across the entire process. This study proposes the Integrated System for Seismic Response Monitoring and Risk Assessment of Buildings (ISRAB), which effectively integrates real-time sensor data with Improved Deep Embedded Clustering (IDEC) and threshold warnings to predict structural state changes. It uses a random field approach to quantitatively assess building loss, casualties, and repair time, and supports future earthquake risk analysis. ISRAB bridges structural response monitoring, damage warning, consequence assessment, and future earthquake risk evaluation, enabling comprehensive applications throughout the entire process. Using a single-layer 3D-printed rural house as an example, the functionality of ISRAB was demonstrated, showing that it can provide at least 5 s of early warning and achieve a 97 % accuracy rate in structural state identification. The application scenarios of ISRAB include enhancing urban seismic resilience, supporting post-disaster emergency management, facilitating insurance claims, and improving risk assessment processes.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102485"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145797868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-04DOI: 10.1016/j.softx.2025.102462
Tianyu Wang , Xiaozhou He , Bernd R. Noack
The Downhill Simplex Method (DSM) is a fast-converging derivative-free optimization technique for nonlinear systems. However, the optimization process is often subject to premature convergence due to degenerate simplices or noise-induced spurious minima. This study introduces a software package for the robust Downhill Simplex Method (rDSM), which incorporates two key enhancements. First, simplex degeneracy is detected and corrected by volume maximization under constraints. Second, the real objective value of noisy problems is estimated by reevaluating the long-standing points. Thus, rDSM improves the convergence of DSM, and may increase the applicability of DSM to higher dimensions, even in the presence of noise. The rDSM software package thus provides a robust and efficient solution for both analytical and experimental optimization scenarios. This methodological advancement extends the applicability of simplex-based optimization to complex experimental systems where gradient information remains inaccessible and measurement noise proves non-negligible.
{"title":"rDSM—A robust Downhill Simplex Method software package for high-dimensional optimization problems","authors":"Tianyu Wang , Xiaozhou He , Bernd R. Noack","doi":"10.1016/j.softx.2025.102462","DOIUrl":"10.1016/j.softx.2025.102462","url":null,"abstract":"<div><div>The Downhill Simplex Method (DSM) is a fast-converging derivative-free optimization technique for nonlinear systems. However, the optimization process is often subject to premature convergence due to degenerate simplices or noise-induced spurious minima. This study introduces a software package for the robust Downhill Simplex Method (rDSM), which incorporates two key enhancements. First, simplex degeneracy is detected and corrected by volume maximization under constraints. Second, the real objective value of noisy problems is estimated by reevaluating the long-standing points. Thus, rDSM improves the convergence of DSM, and may increase the applicability of DSM to higher dimensions, even in the presence of noise. The rDSM software package thus provides a robust and efficient solution for both analytical and experimental optimization scenarios. This methodological advancement extends the applicability of simplex-based optimization to complex experimental systems where gradient information remains inaccessible and measurement noise proves non-negligible.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102462"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145693272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-13DOI: 10.1016/j.softx.2025.102496
Richard Magala , Lisa A. Schulte
We present apsimNGpy, an open-source Python Application Programming Interface (API) for the Agricultural Production Systems sIMulator (APSIM) Next Generation (NG) process-based agroecosystem model. Specifically, the package provides a comprehensive Python API that extends and augments APSIM NG functionalities by integrating it with Python’s scientific computing libraries to facilitate integration of soil and climate data and support spatially explicit simulations over broad spatial extents. apsimNGpy speeds up computations through multiprocessing and multithreading, and provides a flexible, modular, and object-oriented framework that allows for customization with minimal code configuration. It furthermore provides a comprehensive suite of optimization algorithms for examining trade-offs between agricultural production and environmental outcomes, as well as for calibrating model parameters to enhance predictive performance. By embedding APSIM NG into the Python environment, apsimNGpy facilitates reproducible, scalable, and automatable research workflows for assessing agricultural best management practices and yield forecasting. In doing so, apsimNGpy expands the potential user base and application of the APSIM agroecosystem model, empowering users to test and extend the model to a wider range of research and application contexts.
{"title":"apsimNGpy: A comprehensive Python framework for interactive, reproducible, and scalable simulations of the APSIM Next Generation model","authors":"Richard Magala , Lisa A. Schulte","doi":"10.1016/j.softx.2025.102496","DOIUrl":"10.1016/j.softx.2025.102496","url":null,"abstract":"<div><div>We present apsimNGpy, an open-source Python Application Programming Interface (API) for the Agricultural Production Systems sIMulator (APSIM) Next Generation (NG) process-based agroecosystem model. Specifically, the package provides a comprehensive Python API that extends and augments APSIM NG functionalities by integrating it with Python’s scientific computing libraries to facilitate integration of soil and climate data and support spatially explicit simulations over broad spatial extents. apsimNGpy speeds up computations through multiprocessing and multithreading, and provides a flexible, modular, and object-oriented framework that allows for customization with minimal code configuration. It furthermore provides a comprehensive suite of optimization algorithms for examining trade-offs between agricultural production and environmental outcomes, as well as for calibrating model parameters to enhance predictive performance. By embedding APSIM NG into the Python environment, apsimNGpy facilitates reproducible, scalable, and automatable research workflows for assessing agricultural best management practices and yield forecasting. In doing so, apsimNGpy expands the potential user base and application of the APSIM agroecosystem model, empowering users to test and extend the model to a wider range of research and application contexts.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102496"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-16DOI: 10.1016/j.softx.2026.102509
Konrad Groń, Damian Golonka, Wojciech Książek
This article presents version 2.0 of the DetPy (Differential Evolution Tools) library, a Python toolbox for solving advanced optimization problems using differential evolution and its variants. The updated version introduces 15 additional algorithms, increasing the total number of available methods to 30 and enabling extensive experimental studies in differential evolution. Version 2.0 implements a flexible stopping mechanism, where the number of objective function evaluations (NFE) serves as the default termination criterion, while users may define custom stopping conditions. The update also includes minor bug fixes, code refactoring, and improvements that enhance software robustness and maintainability.
{"title":"Version [2.0.0] - [DetPy (Differential evolution tools): A python toolbox for solving optimization problems using differential evolution]","authors":"Konrad Groń, Damian Golonka, Wojciech Książek","doi":"10.1016/j.softx.2026.102509","DOIUrl":"10.1016/j.softx.2026.102509","url":null,"abstract":"<div><div>This article presents version 2.0 of the DetPy (Differential Evolution Tools) library, a Python toolbox for solving advanced optimization problems using differential evolution and its variants. The updated version introduces 15 additional algorithms, increasing the total number of available methods to 30 and enabling extensive experimental studies in differential evolution. Version 2.0 implements a flexible stopping mechanism, where the number of objective function evaluations (NFE) serves as the default termination criterion, while users may define custom stopping conditions. The update also includes minor bug fixes, code refactoring, and improvements that enhance software robustness and maintainability.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102509"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-06DOI: 10.1016/j.softx.2025.102494
Jose Saldana
This paper presents a user-space C implementation of Simplemux, an experimental network protocol designed to improve efficiency and reliability in packet-switched networks. It provides two main functionalities: (i) traffic saving, by aggregating small packets into larger ones to reduce bandwidth consumption and packets per second; and (ii) fast delivery grant, by redundantly sending critical packets to minimize latency over unreliable links. The implementation includes three flavors (compressed, fast, blast), multiple transport modes, Robust Header Compression, and configurable multiplexing policies. Simplemux has been applied in research on online gaming, VoIP optimization, and smart grid communications.
{"title":"Simplemux traffic optimization protocol","authors":"Jose Saldana","doi":"10.1016/j.softx.2025.102494","DOIUrl":"10.1016/j.softx.2025.102494","url":null,"abstract":"<div><div>This paper presents a user-space C implementation of Simplemux, an experimental network protocol designed to improve efficiency and reliability in packet-switched networks. It provides two main functionalities: (i) traffic saving, by aggregating small packets into larger ones to reduce bandwidth consumption and packets per second; and (ii) fast delivery grant, by redundantly sending critical packets to minimize latency over unreliable links. The implementation includes three flavors (compressed, fast, blast), multiple transport modes, Robust Header Compression, and configurable multiplexing policies. Simplemux has been applied in research on online gaming, VoIP optimization, and smart grid communications.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102494"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-06DOI: 10.1016/j.softx.2025.102491
Weihao Gao, Jiarou Lu
AutoImageSeg is a zero-code, open-source image segmentation software toolkit that integrates nine mainstream models. It offers a closed-loop workflow encompassing training, inference, evaluation, and re-annotation. Through its graphical user interface (GUI), users can effortlessly benchmark models, predict new data, and auto-generate editable LabelMe labels—all without any programming. This streamlined process facilitates rapid iteration and high-quality ground-truth accumulation, especially in small-sample scenarios. By accelerating dataset construction across multiple domains, AutoImageSeg serves as a powerful tool for both researchers and industry professionals.
{"title":"AutoImageSeg: A zero-code image segmentation software toolkit","authors":"Weihao Gao, Jiarou Lu","doi":"10.1016/j.softx.2025.102491","DOIUrl":"10.1016/j.softx.2025.102491","url":null,"abstract":"<div><div>AutoImageSeg is a zero-code, open-source image segmentation software toolkit that integrates nine mainstream models. It offers a closed-loop workflow encompassing training, inference, evaluation, and re-annotation. Through its graphical user interface (GUI), users can effortlessly benchmark models, predict new data, and auto-generate editable LabelMe labels—all without any programming. This streamlined process facilitates rapid iteration and high-quality ground-truth accumulation, especially in small-sample scenarios. By accelerating dataset construction across multiple domains, AutoImageSeg serves as a powerful tool for both researchers and industry professionals.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"33 ","pages":"Article 102491"},"PeriodicalIF":2.4,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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