Skip to main content

INTELIGENCIA ARTIFICIAL APLICADA AL PROCESO DE DESARROLLO SOFTWARE

RED2022-134647-T

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Redes Investigación /Redes Excelencia
Call year 2022
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE CORDOBA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Co-evolving scenarios and simulated players to locate bugs that arise from the interaction of software models of video games

  • Roca-Mainer, Isis
  • Arcega, Lorena
  • Pastor López, Oscar|||0000-0002-1320-8471
  • Cetina Englada, Carlos
[EN] Context: Game Software Engineering (GSE) is a field that focuses on developing and maintaining the software part of video games. A key component of video game development is the utilization of game engines, with many engines using software models to capture various aspects of the game. Objective: A challenge that GSE faces is the localization of bugs, mainly when working with large and intricated software models. Additionally, the interaction between software models (i.e. bosses, enemies, or environmental elements) during gameplay is often a significant source of bugs. In response to this challenge, we propose a co-evolution approach for bug localization in the software models of video games, called CoEBA. Methods: The CoEBA approach leverages Search-Based Software Engineering (SBSE) techniques to locate bugs in software models while considering their interactions. We conducted an evaluation in which we applied our approach to a commercial video game, Kromaia. We compared our approach with a state-of-the-art baseline approach that relied on the bug localization approach used by Kromaia¿s developers and a random search used as a sanity check. Results: Our co-evolution approach outperforms the baseline approach in precision, recall, and F-measure. In addition, to provide evidence of the significance of our results, we conducted a statistical analysis. that shows significant differences in precision and recall values. Conclusion: The proposed approach, CoEBA, which considers the interaction between software models, can identify and locate bugs that other bug localization approaches may have overlooked., This work was supported in part by the Spanish Ministry of Science and Innovation under the Excellence Network AI4Software (Red2022-134647-T), in part by the Ministry of Economy and Competitiveness (MINECO) through the Spanish National R+D+i Plan and ERDF funds under the Project VARIATIVA under Grant PID2021- 28695OBI00, and in part by the Gobierno de Aragón (Spain) (Research Group S05_20D)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Tesis doctoral (DoctoralThesis)

Towards Bug Localization in Models in Game Software Engineering

  • Casamayor Moragriega, Rodrigo
[ES] Los videojuegos presentan características únicas que diferencian su desarrollo y mantenimiento del de la ingeniería de software clásica (CSE), lo que ha dado lugar al surgimiento del subcampo de la Ingeniería de Software para Videojuegos (GSE). Una de estas diferencias es que los desarrolladores de videojuegos perciben más dificultades que otros desarrolladores no especializados en juegos a la hora de localizar errores. El objetivo de esta tesis es abordar la localización de errores en modelos de software dentro de la GSE aprovechando los datos (es decir, trazas) generados a partir de simulaciones del comportamiento de los personajes no jugadores (NPCs). Los NPCs (por ejemplo, bots en juegos de disparos en primera persona) no son controlados por el jugador y son componentes clave de los videojuegos. Por tanto, explotar los datos procedentes de simulaciones puede ser fundamental para localizar errores. Las aproximaciones propuestas en este trabajo exploran: 1) cómo los datos de las simulaciones pueden utilizarse para localizar automáticamente posibles elementos defectuosos en modelos de software, que se refieren a representaciones de alto nivel que describen la estructura y el comportamiento del contenido del juego (por ejemplo, los NPCs) y que se interpretan en tiempo de ejecución; 2) cómo el esfuerzo humano dedicado a evaluar soluciones candidatas influye en la localización de errores; y 3) si las operaciones específicas de los componentes pueden mejorar la localización de errores. Las aproximaciones propuestas se evalúan en un contexto industrial con un videojuego comercial (PlayStation 4 y Steam) y 29 desarrolladores profesionales de videojuegos. Los resultados muestran que las aproximaciones mejoran la calidad de la solución del fragmento del modelo que puede contener el error en comparación con los baselines, y que el esfuerzo manual se reduce. Esta tesis presenta un compendio de tres artículos de investigación publicados en revistas y congresos académicos. Las contribuciones demuestran que estas novedosas aproximaciones basadas en búsqueda dentro de la Ingeniería de Software para Videojuegos mejoran significativamente la calidad de las soluciones al localizar los elementos del modelo defectuosos. Esto resulta esencial para el mantenimiento de los videojuegos, ya que reduce la cantidad de trabajo manual tedioso y minimiza el número de errores que pasan desapercibidos., [EN] Video games have unique characteristics that differentiate their development and maintenance from classic software engineering (CSE), which led to the emerging subfield of Game Software Engineering (GSE). One of these differences is that video game developers perceive more difficulties than other non-game developers when it comes to locating bugs. The aim of this thesis is to address bug localization in software models in GSE by leveraging the data (i.e., traces) generated from simulations of the behavior of non-player characters (NPCs). NPCs (e.g., bots in First-Person Shooters) are not controlled by the player and are key components of video games. Hence, exploiting the data from simulations can be instrumental in locating bugs. The approaches that are proposed in this work explore: 1) how the data from simulations can be used to automatically locate potential buggy elements in software models, which refer to high-level representations that describe the structure and behavior of game content (e.g., NPCs) and are interpreted at run-time; 2) how the human effort for assessing candidate solutions influences the location of bugs; 3) whether component-specific operations can boost bug localization. The approaches proposed are evaluated at the scale of industrial settings with a commercial video game (Play Station 4 and Steam) and 29 professional video game developers. The results show that the approaches improve the quality of the solution of the model fragment that may contain the bug compared to the baselines, and the manual effort is reduced. This thesis presents a compendium of three research papers published in academic journals and conference. The contributions demonstrate that these novel Search-Based Game Software Engineering approaches significantly improve the quality of the solution of located model elements. This is essential to the maintenance of video games for reducing the amount of tedious manual work and minimizing the number of bugs that go unnoticed., [CA] Els videojocs presenten característiques úniques que diferencien el seu desenvolupament i manteniment del de la enginyeria de programari clàssica (CSE), fet que ha donat lloc a l'aparició del subcamp de l'Enginyeria de Programari per a Videojocs (GSE). Una d'aquestes diferències és que els desenvolupadors de videojocs perceben més dificultats que altres desenvolupadors no especialitzats en jocs a l'hora de localitzar errors. L'objectiu d'aquesta tesi és abordar la localització d'errors en models de programari dins de la GSE aprofitant les dades (és a dir, traces) generades a partir de simulacions del comportament dels personatges no jugadors (NPCs). Els NPCs (per exemple, bots en jocs de trets en primera persona) no són controlats pel jugador i són components clau dels videojocs. Per tant, explotar les dades provinents de simulacions pot ser fonamental per a localitzar errors. Les aproximacions proposades en aquest treball exploren: 1) com les dades de les simulacions poden utilitzar-se per a localitzar automàticament possibles elements defectuosos en models de programari, que fan referència a representacions d'alt nivell que descriuen l'estructura i el comportament del contingut del joc (per exemple, els NPCs) i que s'interpreten en temps d'execució; 2) com l'esforç humà dedicat a avaluar solucions candidates influïx en la localització d'errors; i 3) si les operacions específiques dels components poden millorar la localització d'errors. Les aproximacions proposades s'avaluaren en un context industrial amb un videojoc comercial (PlayStation 4 i Steam) i 29 desenvolupadors professionals de videojocs. Els resultats mostren que les aproximacions milloren la qualitat de la solució del fragment del model que pot contindre l'error en comparació amb els baselines, i que l'esforç manual es redueix. Aquesta tesi presenta un compendi de tres articles d'investigació publicats en revistes i congressos acadèmics. Les contribucions demostren que estes noves aproximacions basades en cerca dins de l'Enginyeria de Programari per a Videojocs milloren significativament la qualitat de les solucions en localitzar els elements defectuosos del model. Això és essencial per al manteniment dels videojocs, ja que redueix la quantitat de treball manual feixuc i minimitza el nombre d'errors que passen desapercebuts., This work was supported by the Ministry of Science and Innovation through the Spanish National R+D+i Plan and ERDF funds under the Project VARIATIVA (PID2021-128695OB-I00), and by the Gobierno de Aragón (Spain) (Research Groups S05_20D and T61_23R). This work was also partially supported by the Spanish Ministry of Science and Innovation under the Excellence Network AI4Software (Red2022-134647-T). Funding Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Search-based co-creation of software models: The case of particle systems for video games

  • Chueca, Jorge
  • Font, Jaime
  • Cetina Englada, Carlos
  • Pastor López, Oscar|||0000-0002-1320-8471
[EN] Context: The video game industry is one of the fastest-growing industries in the world. However, the creation of content is the bottleneck of the industry nowadays. Objective: In this paper, we propose a new approach for co-creating content by means of combining an evolutionary algorithm Map-Elites, and software models. Our approach involves generating a large number of software models and selecting the best ones based on a fitness function. This fitness function is guided by the human, who chooses which content fits their interests best. Method: We evaluated this approach in the domain of Particle Systems (PS). PS are a popular type of content used to create visual effects such as explosions, fire, smoke, or rain. Our evaluation also involves industry experts of different roles in the video game development process. Using our approach, they were tasked to create PS for their games. Then, they compared the generated models with handmade ones. Results: Our results show that practitioners chose the generated models four out of five times over handmade ones as a better fit for their projects. Furthermore, models created with our approach by non-experts in five minutes are similar in quality to the ones hand-made by an expert in 15 min. Conclusion: In conclusion, using human artistic taste to guide the algorithm renders positive results in creative tasks such as content generation for video games. With minor adjustments, the generated content can be game-ready, accelerating development., This work has been partially supported by the following: Iniciando Lineas de Producto Software Mediante Busquedas Interactivas Dirigidas por Modelos (PID2021-128695OB-I00); Centro para el Desarrollo Tecnológico y la Innovación (CDTI) (SAV-20221011); by the Spanish Ministry of Science and Innovation under the Excellence Network AI4Software (Red2022-134647-T); and in part by the Gobierno de Aragón (Spain) (Research Group S05 20D).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

On the Interaction between the Search Parameters and the Nature of the Search Problems in Search-Based Model-Driven Engineering

  • Roca-Mainer, Isis
  • Font, Jaime
  • Arcega, Lorena
  • Cetina Englada, Carlos
[EN] The use of Search-Based software engineering to address Model-Driven Engineering activities (SBMDE) is becoming more popular. Many maintenance tasks can be reformulated as a search problem, and, when those tasks are applied to software models, the search strategy has to retrieve a model fragment. There are no studies on the influence of the search parameters when applied to software models. This paper evaluates the impact of different search parameter values on the performance of an evolutionary algorithm whose population is in the form of software models. Our study takes into account the nature of the model fragment location problems (MFLPs) in which the evolutionary algorithm is applied. The evaluation searches 1,895 MFLPs (characterized through five measures that define MFLPs) from two industrial case studies and uses 625 different combinations of search parameter values. The results show that the impact on the performance when varying the population size, the replacement percentage, or the crossover rate produces changes of around 30\% in performance. With regard to the nature of the problems, the size of the search space has the largest impact. Search parameter values and the nature of the MFLPs influence the performance when applying an evolutionary algorithm to perform fragment location on models. Search parameter values have a greater effect on precision values, and the nature of the model fragment location problems has a greater effect on recall values. Our results should raise awareness of the relevance of the search parameters and the nature of the problems for the SBMDE community., This work has been supported in part by the Spanish Ministry of Economy and Competitiveness (MINECO) under the project VARIATIVA (PID2021-28695OBI00) and in part by the Gobierno de Aragón (Spain) (Research Group S05_20D). We also thank the Excellence Network AI4Software (Red2022-134647-T) of the Spanish Ministry of Science and Innovation.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Systematic Literature Review of Model-Driven Engineering Using Machine Learning

  • Marcen-Terraza, Ana Cristina
  • Iglesias-Soria, Antonio
  • Lapeña Martí, Raúl
  • Pérez, Francisca
  • Cetina Englada, Carlos
[EN] Model-driven engineering (MDE) is a software engineering paradigm based on the systematic use of models. Over the past few years, engineers have significantly increased the use of MDE, which has been reported as a successful paradigm for developing industrial software. Recently, there have also been remarkable advancements in the Artificial Intelligence (AI) domain, with a significant increase in advanced Machine Learning (ML) techniques. The advances in both fields have led to a surge in works that dwell within the intersection of ML and MDE. This work places the focus on systematically reviewing works that leverage ML to solve MDE problems. We have reviewed a total of 9,194 papers, selecting 98 studies for further analysis. The results of our Systematic Literature Review (SLR) bring light to the current state of the art and trends in the field, discussing the drift in the usage of the different available ML techniques along with the remaining research gaps and open challenges. Our SLR has the potential to produce a positive impact in the research community by steering it towards ML techniques that have been successfully applied to solve MDE challenges., This work was supported in part by the Ministry of Economy and Competitiveness (MINECO) through the Spanish National R+D+i Plan and ERDF funds under the Project VARIATIVA under Grant PID2021-128695OB-I00, in part by the Gobierno de Aragón (Spain) (Research Group T61_23R), in part by the Spanish Ministry of Science, Innovation and Universities under the Project VARNETICA under Grant CNS2023-145422, and in part by the Excellence Network AI4Software under Grant Red2022-134647-
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Boosting bug localization in software models of video games with simulations and component-specific genetic operations

  • Casamayor, Rodrigo
  • Arcega, Lorena
  • Pérez, Francisca
  • Cetina Englada, Carlos
[EN] The development and maintenance of video games present unique challenges that differentiate them from Classic Software Engineering (CSE) such as the increased difficulty in locating bugs within video games. This distinction has given rise to Game Software Engineering (GSE), a subfield that intersects software engineering and video games. Our work proposes a novel way for bug localization in video games by evolving simulations via an evolutionary algorithm, which helps to explore the large number of possible simulations. Simulations generate data (i.e., traces) from the behavior of non-player characters (NPCs). NPCs are not controlled by the player and are key components of video games. We hypothesize that such traces can be instrumental in locating bugs. Our approach automatically locates potential buggy model elements from traces. Furthermore, we propose a novel way of applying genetic operations to evolve simulations by selectively combining their components, rather than combining all components as a whole. We evaluate our approach in the commercial video game Kromaia, and the results indicate that evolving simulations using our novel component-specific genetic operations boosts bug localization. Specifically, our approach improved the F-measure for all bug categories over randomly combining all components, the baseline (which focuses on CSE and utilizes bug reports), and Random Search by 7.93%, 27.17%, and 46.34%, respectively. This work opens a new research direction for further exploration in bug localization within GSE and potentially in CSE as well. Moreover, it encourages other researchers to explore alternative genetic operations rather than selecting them by default., This work was supported in part by the Ministry of Economy and Competitiveness (MINECO) through the Spanish National R+D+i Plan and ERDF funds under the Project VARIATIVA under Grant PID2021-128695OB-I00 and in part by the Gobierno de Aragon (Spain) (Research Group T61_23R). Moreover, this work was partially supported by the Spanish Ministry of Science and Innovation under the Excellence Network AI4Software (Red2022-134647-T).
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publication Artículo científico (JournalArticle)

Does faster mean greener? Runtime and energy trade-offs in iOS applications with compiler optimizations

  • Aragón Jurado, José Miguel
  • Bangash, Abdul Ali
  • Dorronsoro Díaz, Bernabé
  • Ali, Karim
  • Hindle, Abram
  • Ruiz Villalobos, Patricia
Smartphones outnumber people nowadays, requiring efficient energy management. High application energy use leads to faster battery drain and frequent recharging, negatively impacting both battery life and the environment. This cycle also contributes to rising electronic and chemical waste due to discarded mobile phone batteries. Compiler optimization flags may play a crucial role in mitigating these issues by optimizing software performance. However, there has been little research on examining how compiler optimization flags impact the energy consumption of smartphone applications. This work presents an empirical study on the effect of the most aggressive iOS compiler optimizations on runtime, power consumption, and energy consumption across six different iOS applications. For each application, we developed a benchmark focused on the specified category we aimed to study. Our results show that reducing application runtime does not always directly correlate with improved energy consumption. In fact, we observed that optimizations aimed at enhancing runtime performance often come at an energy cost in the applications studied, highlighting a trade-off between runtime and energy consumption. For example, we found that using -Ounchecked in Swift, combined with -Oz from LLVM in the GhostRun video game, increases energy consumption by 34%, despite improving runtime performance by 9%.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publication Capítulo o parte de un libro (BookPart)

An Analysis of Class Imbalance Challenges in Predictive Mutation Testing

  • Balderas Díaz, Sara
  • Guerrero Contreras, Gabriel José
  • Delgado Pérez, Pedro
  • Medina Bulo, María Inmaculada
This study evaluates the efficacy of Predictive Mutation Testing (PMT) models, focusing on the impact of preprocessing, class rebalancing, and model selection on predictive accuracy. By filtering unreached mutants, artificially inflated metrics caused by trivial correlations were minimized, enhancing the ability of the model to identify complex patterns. While ensemble models like CatBoost and XGBoost showed high effectiveness in detecting killed mutants, their performance in identifying survived mutants was limited, underscoring the need for refined strategies to address class imbalance. The study further identifies that previous PMT research often lacks class-specific metrics, such as the Matthews Correlation Coefficient, essential for assessing balanced performance. This oversight can yield misleading evaluations by favoring the majority class, which may falsely indicate high model reliability. Although SMOTE rebalancing improved recall for survived mutants, balancing sensitivity and precision remains challenging. The findings advocate for the development of more balanced datasets in future PMT research to enhance both accuracy and robustness in real-world testing scenarios.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publication Capítulo o parte de un libro (BookPart)

Implementation of a Framework for Early Anomaly Detection in Naval Systems

  • Suano Gallardo, Manuel
  • Gómez Sánchez, Rafael
  • Balderas Díaz, Sara
  • Guerrero Contreras, Gabriel José
  • Medina Bulo, María Inmaculada
The rapid digital transformation and the ongoing paradigm shift towards Industry 4.0 have significantly augmented interconnectivity through the integration of sophisticated technologies within industrial networks, server infrastructure, and cloud environments. Consequently, these interconnected systems are increasingly susceptible to critical security vulnerabilities, including illicit access to confidential information and acts of sabotage. Recognizing the limitations of existing security systems, including intrusion detection systems and security information and event management systems, in addressing novel threats, we propose complex event processing (CEP) as an effective countermeasure. CEP enables the timely and real-time detection of cyberattacks within operational technology (OT) and the Internet of Things (IoT) environments, exhibiting adaptability to the resource constraints of these devices. This work presents a framework of a specific architecture tailored for OT and IoT, implementing CEP on Advanced RISC Machine (ARM) devices to improve the early identification of cyber intrusions, including its human-machine interface (HMI). The proposed framework operates by capturing network traffic and processing it through a CEP engine to automatically identify anomalous patterns. The framework's efficacy is validated through its integration into Navantia's integrated bridge system within a real-world deployment.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publication Capítulo o parte de un libro (BookPart)

A Comprehensive Review on Equivalent Mutant Detection Using Machine Learning

  • Guerrero Contreras, Gabriel José
  • Balderas Díaz, Sara
  • Delgado Pérez, Pedro
  • Medina Bulo, María Inmaculada
Mutation testing evaluates test suite effectiveness by introducing small code modifications ("mutants") and checking if tests detect them. A major challenge is equivalent mutants, which are code changes that do not alter program behavior, making detection computationally expensive and undecidable. This review examines Machine Learning approaches, including Abstract Syntax Tree Neural Networks and Tree-Based Convolutional Neural Networks, to address this issue. Key challenges include limited datasets, inconsistent metrics, and reproducibility concerns. The study highlights the need for standardized frameworks and future research directions in mutation testing.
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Artículo científico (JournalArticle)

Automated machine learning for test case prioritisation

  • Romero, José Raúl
  • Ramírez, Aurora
  • García-Martínez, Carlos
Test case prioritisation (TCP) involves ordering and selecting the most relevant test cases to verify that the current functionality of a software system remains unaffected by code changes. Recently, TCP has been addressed by machine learning (ML), predicting the failure probability of each test case. However, software engineers may struggle to identify and implement the most suitable predictive models for TCP. As new builds adapt the test suite being tested, the model performance may decline with the incorporation of these new builds. In this study, we address these challenges by applying automated workflow composition, including algorithm selection and hyperparameter optimisation. They are considered tasks within automated machine learning (AutoML). With this aim, our proposal employs grammar-guided genetic programming as the underlying mechanism for implementing the AutoML algorithm. Our experimental results demonstrate that our approach can adapt to the particularities of the system under test, selecting the most appropriate ML pipeline and hyperparameters for each build. More importantly, our approach reduces the ML knowledge required by testers---particularly regarding the selection and tuning of algorithms---while enabling them to generate pipelines suited to successive changes in SUT builds. This research showcases the potential of AutoML in software engineering, specifically for the TCP problem.
O2, repositorio institucional de la UOC
Publication Contribución de congreso (ConferenceOutput)

A DSL for Testing LLMs for Fairness and Bias

  • Morales, Sergio
  • Clarisó, Robert
  • Cabot, Jordi
Large language models (LLMs) are increasingly integrated into software systems to enhance them with generative AI capabilities. But LLMs may reflect a biased behavior, resulting in systems that could discriminate against gender, age or ethnicity, among other ethical concerns. Society and upcoming regulations will force companies and development teams to ensure their AI-enhanced software is ethically fair. To facilitate such ethical assessment, we propose LangBiTe, a model-driven solution to specify ethical requirements, and customize and automate the testing of ethical biases in LLMs. The evaluation can raise awareness on the biases of the LLM-based components of the system and/or trigger a change in the LLM of choice based on the requirements of that particular application. The model-driven approach makes both the requirements specification and the test generation platform-independent, and provides end-to-end traceability between the requirements and their assessment. We have implemented an open-source tool set, available on GitHub, to support the application of our approach.