Artículos (Ciencias de la Computación e Inteligencia Artificial)
URI permanente para esta colecciónhttps://hdl.handle.net/11441/11302
Examinar
Envíos recientes
Artículo Reservoir computing models based on spiking neural P systems for time series classification(PERGAMON-ELSEVIER SCIENCE LTD, 2024) Peng, Hong; Xiong, Xin; Wu, Min; Wang, Jun; Yang, Qiang; Orellana Martín, David; Pérez Jiménez, Mario de Jesús; ; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialNonlinear spiking neural P (NSNP) systems are neural-like membrane computing models with nonlinear spiking mechanisms. Because of this nonlinear spiking mechanism, NSNP systems can show rich nonlinear dynamics. Reservoir computing (RC) is a novel recurrent neural network (RNN) and can overcome some shortcomings of traditional RNNs. Based on NSNP systems, we developed two RC variants for time series classification, RC-SNP and RC-RMS-SNP, which are without and integrated with reservoir model space (RMS), respectively. The two RC variants use NSNP systems as the reservoirs and can be easily implemented in the RC framework. The proposed two RC variants were evaluated on 17 benchmark time series classification datasets and compared with 16 state-of-the-art or baseline classification models. The comparison results demonstrate the effectiveness of the proposed two RC variants for time series classification tasks.Artículo Bridges Between Spiking Neural Membrane Systems and Virus Machines(2024) Ramírez de Arellano, Antonio; Orellana Martín, David; Pérez Jiménez, Mario de Jesús; ; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialSpiking Neural P Systems (SNP) are well-established computing models that take inspiration from spikes between biological neurons; these models have been widely used for both theoretical studies and practical applications. Virus machines (VMs) are an emerging computing paradigm inspired by viral transmission and replication. In this work, a novel extension of VMs inspired by SNPs is presented, called Virus Machines with Host Excitation (VMHEs). In addition, the universality and explicit results between SNPs and VMHEs are compared in both generating and computing mode. The VMHEs defined in this work are shown to be more efficient than SNPs, requiring fewer memory units (hosts in VMHEs and neurons in SNPs) in several tasks, such as a universal machine, which was constructed with 18 hosts less than the 84 neurons in SNPs, and less than other spiking models discussed in the workArtículo Sparse Spiking Neural-Like Membrane Systems on Graphics Processing Units(World Scientific, 2024) Hernandez Tello, Javier; Martínez del Amor, Miguel Ángel; Orellana Martín, David; Cabarle, Francis George C.; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos; Ministerio de Ciencia, Innovación y Universidades (MICINN). España; Junta de Andalucía; Grupo de Investigación en Computación Natural TIC193; I3US; SCORE LabThe parallel simulation of Spiking Neural P systems is mainly based on a matrix representation, where the graph inherent to the neural model is encoded in an adjacency matrix. The simulation algorithm is based on a matrix-vector multiplication, which is an operation efficiently implemented on parallel devices. However, when the graph of a Spiking Neural P system is not fully connected, the adjacency matrix is sparse and hence, lots of computing resources are wasted in both time and memory domains. For this reason, two compression methods for the matrix representation were proposed in a previous work, but they were not implemented nor parallelized on a simulator. In this paper, they are implemented and parallelized on GPUs as part of a new Spiking Neural P system with delays simulator. Extensive experiments are conducted on high-end GPUs (RTX2080 and A100 80GB), and it is concluded that they outperform other solutions based on state-of-the-art GPU libraries when simulating Spiking Neural P systems.Informe WebSnapse Tutorial: A Hands-On Approach for Web and Visual Simulations of Spiking Neural P Systems(2023) Ren Tristan A. De La Cruz; Ko, Daryll; Cabarle, Francis George C.; Tristan De La Cruz, Ren; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Grupo de Investigación en Computación Natural TIC193Spiking neural P (SN P) systems were introduced as a special class of P systems. Traditional P systems involve nested membranes through which objects can be transported. This makes natural the idea of distributed or parallel computing, as object transportation may happen simultaneously across different membranes [2, 3]. SN P systems approach distributed computing using different constructs: neurons and synapses. Interactions between these constructs mimic the operation of the human brain: neurons send signals (or spikes) to other neurons via synapses. Investigations on SN P systems have revealed that their computing power is equiv- alent to that of a Turing machine and, at the cost of space, these systems are able to solve NP-hard problems in polynomial time. Understanding theoretical concepts like SN P systems can be made easier by going through examples and manual simulations of such systems. A seminal exam- ple of this is Paun's tutorial. Examples like the even natural number generator in the tutorial help the reader form an adequate mental model of the central con- cepts. The present work follows in a similar fashion, applied to the simulator Web- Snapse. The origin of WebSnapse comes from the Snapse simulator with the following raison d'être: an easy to use and visual simulator for learning about SN P systems. The simulator WebSnapse v1 (that is, version 1) improves on this reason for being by allowing users to access the software by using only their web browser, including more animations and features. Unlike Snapse which requires specific Spiking neural P (SN P) systems were introduced as a special class of P systems. Traditional P systems involve nested membranes through which objects can be transported. This makes natural the idea of distributed or parallel computing, as object transportation may happen simultaneously across different membranes .Informe Analyses and Implementation of Homogenisation Algorithms for Spiking Neural P Systems in the WebSnapse Tool(2024) Kristian Llanto, Tim; Amador, Joshua; Cabarle, Francis George C.; Tristan De La Cruz, Ren; Ko, Daryll; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Grupo de Investigación en Computación Natural TIC193An area of computer science called Membrane Computing (MC) was introduced by Gheorghe P˘aun in. It is a form of computing that takes inspiration from how living cells work. Its system, called the P system, mimics the structure of a cell and how it communicates with its neighbor cells. This is different from the traditional way of computing since cells can communicate in a distributed and parallel manner.Artículo Applicability of Deep Learning to Dynamically Identify the Different Organs of the Pelvic Floor in the Midsagittal Plane(Springer, 2024-05-01) García Mejido, José Antonio; Solís Martín, David; Martín Morán, Marina; Fernández-Conde, Cristina; Fernández Palacín, Fernando; Sáinz Bueno, José Antonio; Universidad de Sevilla. Departamento de CirugíaIntroduction and Hypothesis The objective was to create and validate the usefulness of a convolutional neural network (CNN) for identifying different organs of the pelvic floor in the midsagittal plane via dynamic ultrasound. Methods This observational and prospective study included 110 patients. Transperineal ultrasound scans were performed by an expert sonographer of the pelvic floor. A video of each patient was made that captured the midsagittal plane of the pelvic floor at rest and the change in the pelvic structures during the Valsalva maneuver. After saving the captured videos, we manually labeled the different organs in each video. Three different architectures were tested—UNet, FPN, and LinkNet—to determine which CNN model best recognized anatomical structures. The best model was trained with the 86 cases for the number of epochs determined by the stop criterion via cross-validation. The Dice Similarity Index (DSI) was used for CNN validation. Results Eighty-six patients were included to train the CNN and 24 to test the CNN. After applying the trained CNN to the 24 test videos, we did not observe any failed segmentation. In fact, we obtained a DSI of 0.79 (95% CI: 0.73 – 0.82) as the median of the 24 test videos. When we studied the organs independently, we observed differences in the DSI of each organ. The poorest DSIs were obtained in the bladder (0.71 [95% CI: 0.70 – 0.73]) and uterus (0.70 [95% CI: 0.68 – 0.74]), whereas the highest DSIs were obtained in the anus (0.81 [95% CI: 0.80 – 0.86]) and levator ani muscle (0.83 [95% CI: 0.82 – 0.83]). Conclusions Our results show that it is possible to apply deep learning using a trained CNN to identify different pelvic floor organs in the midsagittal plane via dynamic ultrasound.Artículo A Linear Time Solution to the Partition Problem in a Cellular Tissue-Like Model(AMER SCIENTIFIC PUBLISHERS, 2010) Díaz Pernil, Daniel; Gutiérrez Naranjo, Miguel Ángel; Pérez Jiménez, Mario de Jesús; Riscos Núñez, Agustín; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialTissue-like P systems with cell division is a computing model in the framework of membrane computing that is based on the intercellular communication and cooperation between neurons. In such a model, the structure of the devices is a network of elementary cells. Tissue-like P systems with cell division have the ability of increasing the number of cells during the computation. In this paper we exploit this ability and present a polynomial-time (actually, linear-time) solution to the NP-complete Partition problem via a uniform family of such P systems.Artículo Deep learning applied to intracranial hemorrhage detection(MDPI, 2023) Cortés Ferre, Luis; Gutiérrez Naranjo, Miguel Ángel; Egea Guerrero, Juan José; Pérez Sánchez, Soledad; Balcerzyk, Marcin; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialIntracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Detection of, and diagnosis of, a hemorrhage that requires an urgent procedure is a difficult and time-consuming process for human experts. In this paper, we propose methods based on EfficientDet’s deep-learning technology that can be applied to the diagnosis of hemorrhages at a patient level and which could, thus, become a decision-support system. Our proposal is two-fold. On the one hand, the proposed technique classifies slices of computed tomography scans for the presence of hemorrhage or its lack of, and evaluates whether the patient is positive in terms of hemorrhage, and achieving, in this regard, 92.7% accuracy and 0.978 ROC AUC. On the other hand, our methodology provides visual explanations of the chosen classification using the Grad-CAM methodology.Artículo Trainable and explainable simplicial map neural networks(ELSEVIER SCIENCE INC, 2024) Paluzo Hidalgo, Eduardo; González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial; Universidad de Sevilla. Departamento de Matemática Aplicada I (ETSII)Simplicial map neural networks (SMNNs) are topology-based neural networks with interesting properties such as universal approximation ability and robustness to adversarial examples under appropriate conditions. However, SMNNs present some bottlenecks for their possible application in high-dimensional datasets. First, SMNNs have precomputed fixed weight and no SMNN training process has been defined so far, so they lack generalization ability. Second, SMNNs require the construction of a convex polytope surrounding the input dataset. In this paper, we overcome these issues by proposing an SMNN training procedure based on a support subset of the given dataset and replacing the construction of the convex polytope by a method based on projections to a hypersphere. In addition, the explainability capacity of SMNNs and effective implementation are also newly introduced in this paper.Artículo Solving the 3-COL problem by using tissue P systems without environment and proteins on cells(ELSEVIER SCIENCE INC, 2018) Díaz Pernil, Daniel; Christinal, Hepzibah A.; Gutiérrez Naranjo, Miguel Ángel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialThe 3-COL problem consists on deciding if the regions of a map can be coloured with only three colors bearing in mind that two adjacent regions must be coloured with different colors. It is a NP problem and it has been previously used in complexity studies in membrane computing to check the ability of a model for solving problems of such complexity class. Recently, tissue P systems with proteins on cells have been presented and its ability to solve NP problems has been proved, but it remained as an open question to know if such model was still able to solve such problems if the environment was removed. In this paper, we provide an affirmative answer to this question by showing a uniform family of tissue P systems without environment and with proteins on cells which solves the 3-COL problem in linear time.Artículo Solving SUBSET SUM by Spiking Neural P Systems with Pre-computed Resources(IOS Press, 2008) Leporati, Alberto; Gutiérrez Naranjo, Miguel Ángel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialRecently the possibility of using spiking neural P systems for solving computationally hard problems has been considered. Such solutions assume that some (possibly exponentially large) pre-computed resources are given in advance, provided that their structure is regular and they do not contain neither hidden information that simplify the solution of specific instances, nor an encoding of all possible solutions (that is, an exponential amount of information that allows to cheat while solving the instances of the problem). In this paper we continue this research line, and we investigate the possibility of solving numerical NP-complete problems such as SUBSET SUM. In particular, we first propose a semi-uniform family of spiking neural P systems in which every system solves a specific instance of SUBSET SUM. Then, we exploit a technique used to calculate ITERATED ADDITION with Boolean circuits to obtain a uniform family of spiking neural P systems in which every system is able to solve any instance of SUBSET SUM of a fixed size. All the systems here considered are deterministic, and their size generally grows exponentially with respect to the instance size.Artículo PBIL for optimizing inception module in convolutional neural networks(Oxford University Press, 2023) García Victoria, Pedro; Gutiérrez Naranjo, Miguel Ángel; Cárdenas Montes, Miguel; Vasco Carofilis, Roberto A.; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialInception module is one of the most used variants in convolutional neural networks. It has a large portfolio of success cases in computer vision. In the past years, diverse inception flavours, differing in the number of branches, the size and the number of the kernels, have appeared in the scientific literature. They are proposed based on the expertise of the practitioners without any optimization process. In this work, an implementation of population-based incremental learning is proposed for automatic optimization of the hyperparameters of the inception module. This hyperparameters optimization undertakes classification of the MNIST database of handwritten digit images. This problem is widely used as a benchmark in classification, and therefore, the learned best configurations for the Inception module will be of wide use in the deep learning community. In order to reduce the carbon footprint of the optimization process, policies for reducing the redundant evaluations have been undertaken. As a consequence of this work, an evaluation of configurations of the inception module and a mechanism for optimizing hyperparameters in deep learning architectures are stated.Artículo P systems with input in binary form(WORLD SCIENTIFIC PUBL CO PTE LTD, 2006) Leporati, Alberto; Zandron, Claudio; Gutiérrez Naranjo, Miguel Ángel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialCurrent P systems which solve NP-complete numerical problems represent the instances of the problems in unary notation. However, in classical complexity theory, based upon Turing machines, switching from binary to unary encoded instances generally corresponds to simplify the problem. In this paper we show that, when working with P systems, we can assume without loss of generality that instances are expressed in binary notation. More precisely, we propose a simple method to encode binary numbers using multisets, and a family of P systems which transforms such multisets into the usual unary notation. Such a family could thus be composed with the unary P systems currently proposed in the literature to obtain (uniform) families of P systems which solve NP-complete numerical problems with instances encoded in binary notation. We introduce also a framework which can be used to design uniform families of P systems which solve NP-complete problems (both numerical and non-numerical) working directly on binary encoded instances, i.e., without first transforming them to unary notation. We illustrate our framework by designing a family of P systems which solves the 3-SAT problem. Next, we discuss the modifications needed to obtain a family of P systems which solves the PARTITION numerical problem.Artículo On a partial affirmative answer for a Paun's Conjecture(WORLD SCIENTIFIC PUBL CO PTE LTD, 2011) Pérez Hurtado de Mendoza, Ignacio; Pérez Jiménez, Mario de Jesús; Riscos Núñez, Agustín; Gutiérrez Naranjo, Miguel Ángel; Rius Font, Miquel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialAt the beginning of 2005, Gheorghe Pun formulated a conjecture stating that in the framework of recognizer P systems with active membranes (evolution rules, communication rules, dissolution rules and division rules for elementary membranes), polarizations cannot be avoided in order to solve computationally hard problems efficiently (assuming that P ≠ NP). At the middle of 2005, a partial positive answer was given, proving that the conjecture holds if dissolution rules are forbidden. In this paper we give a detailed and complete proof of this result modifying slightly the notion of dependency graph associated with recognizer P systems.Artículo Membrane computing and image processing: a short survey(SPRINGER; SPRINGERNATURE, 2019) Díaz Pernil, Daniel; Gutiérrez Naranjo, Miguel Ángel; Peng, Hong; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialMembrane computing is a well-known research area in computer science inspired by the organization and behavior of live cells and tissues. Their computational devices, called P systems, work in parallel and distributed mode and the information is encoded by multisets in a localized manner. All these features make P systems appropriate for dealing with digital images. In this paper, some of the open research lines in the area are presented, focusing on segmentation problems, skeletonization and algebraic-topological aspects of the images. An extensive bibliography about the application of membrane computing to the study of digital images is also provided.Artículo Local Search with P Systems(IGI GLOBAL, 2011) Gutiérrez Naranjo, Miguel Ángel; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialLocal search is currently one of the most used methods for finding solutions in real-life problems. It is usually considered when the research is interested in the final solution of the problem instead of the how the solution is reached. In this paper, the authors present an implementation of local search with Membrane Computing techniques applied to the N-queens problem as a case study. A CLIPS program inspired in the Membrane Computing design has been implemented and several experiments have been performed. The obtained results show better average times than those obtained with other Membrane Computing implementations that solve the N-queens problem.Artículo Implementation on CUDA of the Smoothing Problem with Tissue-Like P Systems(IGI GLOBAL, 2011) Peña Cantillana, Francisco; Díaz Pernil, Daniel; Christinal, Hepzibah Anandharaj; Gutiérrez Naranjo, Miguel ÁngelSmoothing is often used in Digital Imagery for improving the quality of an image by reducing its level of noise. This paper presents a parallel implementation of an algorithm for smoothing 2D images in the framework of Membrane Computing. The chosen formal framework has been tissue-like P systems. The algorithm has been implemented by using a novel device architecture called CUDA (Compute Unified Device Architecture) which allows the parallel NVIDIA Graphics Processors Units (GPUs) to solve many complex computational problems. Some examples are presented and compared; research lines for the future are also discussed.Artículo How to express tumours using membrane systems(ELSEVIER SCIENCE INC, 2007) Gutiérrez Naranjo, Miguel Ángel; Pérez Jiménez, Mario de Jesús; Riscos Núñez, Agustín; Romero Campero, Francisco José; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialIn this paper we discuss the potential usefulness of membrane systems as tools for modelling tumours. The approach is followed both from a macroscopic and a microscopic point of view. In the first case, one considers the tumour as a growing mass of cells, focusing on its external shape. In the second case, one descends to the microscopic level, studying molecular signalling pathways that are crucial to determine if a cell is cancerous or not. In each of these approaches we work with appropriate variants of membrane systems.Artículo Evolutionary game theory in a cell: A membrane computing approach(ELSEVIER SCIENCE INC, 2022) García Victoria, Pedro; Cavaliere, Matteo; Gutiérrez Naranjo, Miguel Ángel; Cárdenas Montes, Miguel; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialEvolutionary Game Theory studies the spreading of strategies in populations. An important question of the area concerns the possibility that certain population structures can facilitate the spreading of more cooperative behaviours associated to the sustainability and resilience of many different systems ranging from ecological to socio-economic systems. In this paper, we propose a novel approach to study the spreading of behaviours in structured populations by combining Evolutionary Game Theory and membrane computing. We show that there is a general way to encode Evolutionary Game Theory into membrane computing, leading to a novel computational framework which can be used to study, analyze and simulate the spreading of behaviours in structured populations organized in communicating compartments. The proposed approach allows to extend the works on membrane systems, population and ecological dynamics, and, at the same time, suggests a novel bio-inspired framework, based on formal languages theory, to investigate the dynamics of evolving structured populations.Artículo An approach to Ballistic deposition based on membrane computing(Old City Publishing, Inc., 2009) Graciani Díaz, Carmen; Gutiérrez Naranjo, Miguel Ángel; Pérez Jiménez, Mario de Jesús; Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia ArtificialBallistic Deposition was proposed by Vold [10] and Sutherland [9] as a model for colloidal aggregation. These early works were later extended to simulate the process of vapour deposition. In general, Ballistic Deposition models involve (d+1)-dimensional particles which rain down sequentially at random onto a d-dimensional substrate; when a particle arrives on the existing agglomeration of deposited particles, it sticks to the first particle it contacts, which may result in lateral growth. In this paper we present a first P system model for Ballistic Deposition with d = 1.