Artículos (Ciencias de la Computación e Inteligencia Artificial)
URI permanente para esta colecciónhttps://hdl.handle.net/11441/11302
Examinar
Envíos recientes
Artículo Infinite Spike Trains in Spiking Neural P Systems(EDITURA ACAD ROMANE, 2023) Păun, Gheorghe; Pérez Jiménez, Mario de Jesús; Rozenberg, Grzegorz; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialWe initiate the study of spiking neural P systems associated with infinite sequences, by considering them as computability devices which generate infinite sequences of bits (1 indicates a step when a spike exits the system, and 0 indicates a step when the system does not send a spike to the environment), and as devices which process infinite sequence of bits (for instance, computing Boolean operations or other operations on two input sequences). For both the generating and the transduction case we introduce some basic notions illustrated by numerous examples, establish some basic properties, and formulate a number of research topics.Artículo A New Methodology for Software-Simulation of Membrane Systems Using a Multi-Thread Programming Model(2024-01) Cascado Caballero, Daniel; Díaz del Río, Fernando; Cagigas Muñiz, Daniel; Orellana Martín, David; Pérez Hurtado de Mendoza, Ignacio; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Universidad de Sevilla. Departamento de Arquitectura y Tecnología de ComputadoresThe evolution of simulation and implementation of P systems has been intense since the theoretical model of computation was created. In the field of software simulation of P systems, the proposals made so far have taken advantage mainly of the parallelism of GPUs, but not of the parallelism of existing multi-core processors. This paper proposes a methodology for simulating P systems using a multi-threaded methodological approach in a multi-core processor. This proposal has been implemented and tested using a simulator programmed in C#, and its correct operation has been tested for confluent and non-confluent systems. The experimental results confirm that the simulator scales well with the number of hardware threads of a multiprocessor. The results obtained suggest that the methodology is valid and that it is worth testing it with more complex systems to find the limits of the methodologyArtículo Using virus machines to compute pairing functions(World Scientific Publishing, 2023-03) Ramírez de Arellano Marrero, Antonio; Orellana Martín, David; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; FEDER/Junta de Andalucía — Paidi 2020/ProyectoVirus machines are computational devices inspired by the movement of viruses between hosts and their capacity to replicate using the resources of the hosts. This behavior is controlled by an external graph of instructions that opens different channels of the system to make viruses capable of moving. This model of computation has been demonstrated to be as powerful as turing machines by different methods: by generating Diophantine sets, by computing partial recursive functions and by simulating register machines. It is interesting to investigate the practical use cases of this model in terms of possibilities and efficiency. In this work, we give the basic modules to create an arithmetic calculator. As a practical application, two pairing functions are calculated by means of two different virus machines. Pairing functions are important resources in the field of cryptography. The functions calculated are the Cantor pairing function and the G¨odel pairing function.Artículo Ultrasound Diagnosis of Pelvic Organ Prolapse Using Artificial Intelligence(MDPI, 2025-05-22) García Mejido, José Antonio; Galán Páez, Juan; Solís Martín, David; Fernández Palacín, Fernando; Fernández Palacín, Ana; Sáinz Bueno, José Antonio; Universidad de Sevilla. Departamento de Cirugía; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Universidad de Sevilla. Departamento de Medicina Preventiva y Salud Pública; Fondo Europeo de Desarrollo Regional (FEDER); Universidad de Sevilla. TIC137: Lógica, Computación e Ingeniería del Conocimiento; Universidad de Sevilla. CTS312: Análisis de la Demanda SanitariaBackground/Objectives: The aim of this study was to design a fully automated hybrid AI-based method, combining a convolutional neural network (CNN) and a tree-based model (XGBoost), which was capable of diagnosing different pelvic organ prolapses (POPs) in a dynamic two-dimensional ultrasound study from the midsagittal plane. Methods: This was a prospective observational study with 188 patients (99 with POP and 89 without POP). Transperineal pelvic floor ultrasound videos were performed, and normality or POP was defined. These videos were subsequently labeled, and an algorithm was designed to detect POP based on three phases: 1. Segmentation—a CNN was used to locate and identify the visible pelvic organs in each frame of the ultrasound video. The output had a very high dimensionality. 2. Feature engineering and dataset construction—new features related to the position and shape of the organs detected using the CNN were generated. 3. The POP predictive model—this was created from the dataset generated in the feature engineering phase. To evaluate diagnostic performance, accuracy, precision, recall, and F1-score were considered, along with the degree of agreement with the expert examiner. Results: The best agreements were observed in the diagnosis of cystocele and uterine prolapse (88.1%) and enterocoele (81.4%). The proposed methodology showed an accuracy of 96.43%, an overall accuracy of 98.31%, a recall of 100%, and an F1-score of 98.18% in detecting the presence of POP. However, when differentiating between the various types of POP, we observed that the precision, accuracy, recall, and F1-score were higher when detecting cystocele and uterine prolapse. Conclusions: We have developed the first predictive model capable of diagnosing POP in a dynamic, bi-dimensional ultrasound study from the midsagittal plane using deep learning and machine learning techniques.Artículo The environment as a frontier of efficiency in tissue P systems with communication rules(Elsevier, 2023-03) Orellana Martín, David; Valencia Cabrera, Luis; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; FEDER/Junta de Andalucía – Paidi 2020/ _ProyectoOriginally, in P systems the environment plays a passive role; that is, it can only receive objects, without having the ability to send objects to the system. Later, tissue P systems were introduced, where the cells are located in the environment in the sense that they can communicate between each other but also with the environment. In fact, a special alphabet was introduced as a way to symbolize the chemical elements available in it and that can interact with the cells. In the framework of membrane computing, all the objects of this alphabet are present in the environment with an arbitrary multiplicity at the beginning of the computation; that is, there are enough objects of this type in the environment to fire the rules that can be fired by these objects. From the computational complexity point of view, it seems to be a very strong ingredient, since it adds a virtually infinite number of objects to the system in the whole computation. In this paper, we demonstrate that the behaviour of this special alphabet can be simulated by a generation stage ruled by evolutional communication rules and/or division/separation rules, such that the ability of these systems to efficiently solve presumably hard problems is not changed if the environment does not play an active role.Artículo Generating, computing and recognizing with virus machines(Elsevier, 2023-07) Ramírez de Arellano Marrero, Antonio; Orellana Martín, David; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; FEDER/Junta de Andalucía – Paidi 2020/Natural computing is a research area of computer science where different models of computation arise from the inspiration of real-life natural processes. In particular, virus machines are devices inspired by the transmission of viruses between different hosts, and how they replicate in the organism. This paradigm provides devices that can be seen as a network of hosts where the communication between them is controlled by a set of instructions that lead to the transmission of viruses. Virus machines can be seen as generating devices, computing devices and recognizing devices, depending on the possible input and the output of the systems. In this work, we present some machines generating basic sets, computing basic functions and we present recognizer virus machines, capable of solving decision problems in order to create a new complexity theory paradigm with virus machines.Artículo Attacking cryptosystems by means of virus machines(2023-12-09) Pérez Jiménez, Mario de Jesús; Ramírez de Arellano Marrero, Antonio; Orellana Martín, David; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialThe security that resides in the public-key cryptosystems relies on the presumed computational hardness of mathematical problems behind the systems themselves (e.g. the semiprime factorization problem in the RSA cryptosystem), that is because there is not known any polynomial time (classical) algorithm to solve them. The paper focuses on the computing paradigm of virus machines within the area of Unconventional Computing and Natural Computing. Virus machines, which incorporate concepts of virology and computer science, are considered as number computing devices with the environment. The paper designs a virus machine that solves a generalization of the semiprime factorization problem and verifies it formally.Artículo Towards a general methodology for formal verification on spiking neural P systems(Elsevier, 2024-10-01) Pérez Jiménez, Mario de Jesús; Valencia Cabrera, Luis; Orellana Martín, David; Ramírez de Arellano Marrero, Antonio; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialP systems are non-deterministic, parallel and distributed models of computation inspired by the behaviour and structure of living cells. Spiking neural P systems synthesise the connections that exist between neurons in the human brain, using pulses as a form of transmission of information. Usually, when a spiking neural P system is defined to solve any problem, it is checked in several cases to know if it works for them. But this methodology is not sufficient to verify if the system always works in a correct way. In this work, we introduce a methodology to look for characteristics in computations of spiking neural P systems that can be used to formally verify that the model works as it is intended.Artículo Parallel virus machines(Springer Nature, 2024-05-22) Ramírez de Arellano Marrero, Antonio; Orellana Martín, David; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialWithin the branch of Natural Computing, several models or types of computation arise, some of them are well-established such as neural networks, evolutionary computing or membrane computing, while others have yet to be studied and developed. One such model is virus machines, which draws inspiration from the replication and transmission mechanisms of viruses. This model has been successfully applied to mathematical problems, supported by its robust formal structure and the verification of various parallel virus machines. Parallelism has been one of the milestones in several branches of Natural Computing. This paper presents a novel extension: parallel virus machines. Furthermore, several semantics are studied to fix possible ambiguities related to this new variant. Finally, a comparison with well-established neural-like systems, called spiking neural P systems, is discussed.Artículo A solution to the only one object problem with dissolution rules(Springer Nature, 2024-05) Caselmann, Julien; Orellana Martín, David; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialIn the framework of membrane computing, (non-)uniform families of recognizer membrane systems are usually defined to solve abstract decision problems. In this sense, the use of finite resources for each member of the family makes the difference with respect to Turing machines solving these problems. While keeping the finite nature of these systems, it is interesting to know which type of problems can be solved by means of a single membrane system. For this purpose, the complexity class PMC 1p R was defined as the class of problems that can be solved by means of a single membrane system in polynomial time. Due to the polynomial-time encoding of the input, at least all the problems from P can be solved with a trivial system. To go below P, the class PMC 1f R restricts the definition of this encoding. In this work, we study the capability of different types of membrane systems to solve the ONLY-ONE-OBJECT problem, while having the encoding restriction.Artículo Super Virus Machines: Faster Virus Transmission, More Efficiency Using Superchannels(AAAS, 2025-03-21) Ramírez de Arellano Marrero, Antonio; Valencia Cabrera, Luis; Orellana Martín, David; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialSurpassing the classical computing architecture is one of the great challenges of computer science today. The branch that approaches it from a theoretical point of view, inspired by nature, is called natural computation. Within this field, a paradigm arises, called virus machines (VMs), inspired by the propagation and replication of the biological structure of viruses. This work introduces a novel extension to the young computing paradigm of VMs, the super VMs. This extension can develop models with a new kind of channel called superchannel. In addition, several VMs are constructed to generate natural number sets and compute basic arithmetic functions, improving the basic VMs in both time and memory cost (such as hosts and instructions).Artículo Simulating and validating virus machines(Springer Nature, 2025) Orellana Martín, David; Ramírez de Arellano Marrero, Antonio; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialVirus machines are computing devices inspired by the transmission and replication of viruses. This model of computation has been proved to be as powerful as Turing machines, while using very simple semantics: instructions can open channels to let viruses travel between different hosts. The basic model is sequential, in the sense that only one instruction can be executed in each time step. This behaviour is, in principle, easy to follow by using pen and paper, but it can become harder when the model is big enough, as it happens with other models of computation. This paper introduces a base software for virus machines that simulates their behaviour and has an easy approach for both researchers and developers. Besides, apart from the simulator, the software has two other main purposes: on the one hand, a experimental validator has been introduced to help the researcher with both the design and the formal verification of such devices; on the other hand, it has included a tool to create a LaTeX graphic of a virus machine with the usual visuals.Artículo A solution to SAT with virus machines with pre-computed resources(Springer Nature, 2025) Orellana Martín, David; Zandron, Claudio; Leporati, Alberto; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialIn Natural Computing, different real-life processes can appear as the inspiration for a new model of computation. Virus machines use the spread and replication of biological viruses as an inspiration for a model of computation with three well differentiated graphs: the hosts graph, that acts like the memory; the instructions graph, that acts as a program; and the instructions-channel graph, that controls the flow of information through the system. In previous works, the computational power and problem-solving capabilities of this model have been demonstrated. In this work, we provide an application for solving the SAT problem in polynomial time using an EXP-uniform family of super virus machines with OR channel parallelism.Artículo Impact of HIV infection on the dynamics of liver stiffness in patients with hepatitis C virus chronic infection after sustained virological response(Elsevier, 2025-05) Martín-Carmona, Jésica; Corma-Gómez, Anaïs; Moyano Murillo, José María; Téllez, Francisco; Arenga-Barrios, Dolores; Serrano-Fuentes, Miriam; Pineda Vergara, Juan Antonio; Macías Sánchez, Juan; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Universidad de Sevilla. Departamento de MedicinaAfter sustained virological response (SVR), liver stiffness (LS) usually decreases. However, information related to the impact of HIV co-infection in patients with advanced fibrosis is scarce. The aim was to analyze the impact of HIV co-infection on the LS dynamics after HCV cure. Methods Prospective study conducted in the GEHEP-011 multicenter cohort (initiated in October 2011–November 2023, ID NCT04460157), including patients with chronic HCV infection, with or without HIV co-infection, fulfilling: 1) SVR with direct-acting antivirals; 2) pre-treatment LS ≥ 9.5 kPa; 3) available measurement of LS at SVR. Pre-treatment, SVR and annual post-treatment LS were assessed. The primary outcome was time to LS normalization achievement (≤7.2 kPa) in two consecutive examinations. Findings 1138 patients were included, 678 (60%) of whom were living with HIV (PLWH). The median time between the first to the last measure was 35 (17–69) months. In total, 390 [34% (95% confidence interval, 31%–37%)] patients achieved LS normalization, 169 [37% (CI 95%, 34%–43%)] individuals with HCV mono-infection vs. 221 [32% (CI 95%, 29%–36%)] PLWH achieved LS normalization (p = 0.003). The propensity score (PS) for HIV infection was calculated. In a multivariate model for competing risks (death was the competing event) adjusted for HIV, PS and diabetes, HIV infection was associated with a lower probability of achieving normalization [sHR = 0.82 (95% CI, 0.67–1.00), p = 0.045]. Matching by closer PS was performed. In the resultant subset, the probability of achieving LS normalization was again lower in PLWH [sHR = 0.76 (0.56–0.97), p < 0.001]. Interpretation After SVR, the probability of reaching LS normalization is significantly lower in PLWH. This could have implications on the development of long-term clinical events.Artículo Using deep learning for predicting the dynamic evolution of breast cancer migration(Elsevier, 2024) Garcia-Moreno, Francisco M.; Ruiz-Espigares, Jesús; Gutiérrez Naranjo, Miguel Ángel; Marchal, Juan Antonio; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Ministerio de Ciencia, Innovación 𝑦 UniversidadesBackground: Breast cancer (BC) remains a prevalent health concern, with metastasis as the main driver of mortality. A detailed understanding of metastatic processes, particularly cell migration, is fundamental to improve therapeutic strategies. The wound healing assay, a traditional two-dimensional (2D) model, offers insights into cell migration but presents scalability issues due to data scarcity, arising from its manual and labor-intensive nature. Method: To overcome these limitations, this study introduces the Prediction Wound Progression Framework (PWPF), an innovative approach utilizing Deep Learning (DL) and artificial data generation. The PWPF comprises a DL model initially trained on artificial data that simulates wound healing in MCF-7 BC cell monolayers and spheres, which is subsequently fine-tuned on real-world data. Results: Our results underscore the model’s effectiveness in analyzing and predicting cell migration dynamics within the wound healing context, thus enhancing the usability of 2D models. The PWPF significantly contributes to a better understanding of cell migration processes in BC and expands the possibilities for research into wound healing mechanisms. Conclusions: These advancements in automated cell migration analysis hold the potential for more comprehensive and scalable studies in the future. Our dataset, models, and code are publicly available at https: //github.com/frangam/wound-healing.Artículo An application of membrane computing to humanitarian relief via generalized Nash equilibrium(Springer Nature, 2025-04) Luque Cerpa, Alejandro; Orellana Martín, David; Gutiérrez Naranjo, Miguel Ángel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialNatural and political disasters, including earthquakes, hurricanes, and tsunamis, but also migration and refugees crisis, need quick and coordinated responses in order to support vulnerable populations. In such disasters, nongovernmental organizations compete with each other for financial donations, while people who need assistance suffer a lack of coordination, congestion in terms of logistics, and duplication of services. From a theoretical point of view, this problem can be formalized as a generalized Nash equilibrium (GNE) problem. This is a generalization of the Nash equilibrium problem, where the agents’ strategies are not fixed but depend on the other agents’ strategies. In this paper, we show that membrane computing can model humanitarian relief as a GNE problem. We propose a family of P systems that compute GNE in this context, and we illustrate their capabilities with Hurricane Katrina in 2005 as a case study.Artículo A membrane computing approach to the generalized Nash equilibrium(Springer Nature, 2025-04-18) Luque Cerpa, Alejandro; Gutiérrez Naranjo, Miguel Ángel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; European Union HORIZON-CL4-2021-HUMAN-01-01Generalized Nash Equilibrium is an extended version of the standard Nash Equilibrium with important implications in reallife problems such as economics, wireless communication, the electricity market, or engineering among other areas. In this paper, we propose a first approach to computing Generalized Nash Equilibria using Membrane Computing techniques. We model an efficient P system that, based on Euler’s method, computes approximations of Generalized Nash Equilibria of population games under Brown–von Neumann–Nash dynamics, bridging both areas and opening a door for a flow of problems and solutions in both directions.Artículo Brain size predicts bees' tolerance to urban environments(The Royal Society, 2023-11-29) Lanuza, J.B.; Collado Aliaño, Miguel Ángel; Sayol, F.; Sol, D.; Bartomeus, I.; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialThe rapid conversion of natural habitats to anthropogenic landscapes isthreatening insect pollinators worldwide, raising concern regarding the nega-tive consequences on their fundamental role as plant pollinators. However, notall pollinators are negatively affected by habitat conversion, as certain speciesfind appropriate resources in anthropogenic landscapes to persist and prolifer-ate. The reason why some species tolerate anthropogenic environments whilemost find them inhospitable remains poorly understood. The cognitive bufferhypothesis, widely supported in vertebrates but untested in insects, offers apotential explanation. This theory suggests that species with larger brainshave enhanced behavioural plasticity, enabling them to confront and adaptto novel challenges. To investigate this hypothesis in insects, we measuredbrain size for 89 bee species, and evaluated their association with the degreeof habitat occupancy. Our analyses revealed that bee species mainly foundin urban habitats had larger brains relative to their body size than those thattend to occur in forested or agricultural habitats. Additionally, urban beesexhibited larger body sizes and, consequently, larger absolute brain sizes.Our results provide the first empirical support for the cognitive buffer hypo-thesis in invertebrates, suggesting that a large brain in bees could conferbehavioural advantages to tolerate urban environments.Artículo Artificial intelligence to determine correct midsagittal plane in dynamic transperineal ultrasound(Wiley, 2025-04-25) García Mejido, José Antonio; Galán Páez, Juan; Solís Martín, David; Martín Morán, Marina; Borrero González, Carlota; Fernández-Gómez, Alfonso; Fernández Palacín, Fernando; Sáinz Bueno, José Antonio; Universidad de Sevilla. Departamento de Cirugía; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Agencia Estatal de Investigación. España; European Commission (EC). Fondo Europeo de Desarrollo Regional (FEDER); Universidad de Sevilla. TIC137: Lógica, Computación e Ingeniería del ConocimientoPurpose: To create and validate a machine learning(ML) model that allows for identifying the correct capture of the midsagittal plane in a dynamic ultrasound study, as well as establishing its concordance with a senior explorer and a junior explorer. Methods: Observational and prospective study with 90 patients without pelvic floor pathology. Each patient was given an ultrasound video where the midsagittal plane of the pelvic floor was recorded at rest and during the Valsalva maneuver. A segmentation model was used that was trained on a previously published article, generating the segmentations of the 90 new videos to create the model. The algorithm selected to build the model in this project was XGBoost(Gradient Boosting). To obtain a tabular dataset on which to train the model, feature engineering was carried out on the raw segmentation data. The concordance of the model, of a junior examiner and a senior examiner, with the expert examiner was studied using the kappa index. Results: The first 60 videos were used to train the model and the last 30 videos were reserved for the test set. The model presented a kappa index 0.930(p < 0.001) with very good agreement for detection of the correct midsagittal plane. The junior explorer presented a very good agreement (kappa index = 0.930(p < 0.001)). The senior explorer presented a kappa index 0.789(p < 0.001) (good agreement) for detection of the correct midsagittal plane. Conclusion: We have developed a model that allows determining the correct midsagittal plane captured through dynamic transperineal ultrasound with a level of agreement comparable to or greater than that of a junior or senior examiner, using expert examiner assessment as the gold standard.Artículo A comprehensive view of biometric payment in retailing: A complete study from user to expert(Elsevier, 2024) Zarco, Carmen; Giraldez Cru, Jesus; Cordón, Oscar; Liébana-Cabanillas, Francisco; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialThe new financial and commercial scenario driven by technological advances has undergone a rapid reconfiguration in the recent years. Innovation has generated new payment alternatives that are transforming the concept of money and payment habits among consumers. One of the most novel payment systems nowadays is known as biometric payment. Improved payment systems will improve retailing and consumer services. The aim of this study is to develop an analysis of biometric payment based on two complementary studies. In the first one, the variables predicting the intention to use this technology are determined on a sample of 1905 potential users by means of different feature selection methodologies from artificial intelligence in a holistic model that integrates the principles of the UTAUT2 model, the General Risk Theory, and the Trust Theory. In the second study, two panels of Fintech industry experts compare these results. The overall insights obtained show that perceived risk, trust, and social influence are the variables that, from the experts’ experience, users consider most important when employing this technology. This research provides useful information for financial and business decisionmakers in companies interested in commercializing this type of technology.