Generative AI has been widely used in the higher education sector in a variety of ways. Some common activities include student assignments, but professors have also used them to prepare their classes, projects, and scientific articles. This article aims to conduct an exploratory study on the use of generative AI in different case studies related to higher education. The methodology used for this study is based on the framework for the use of generative AI proposed by UNESCO. Using this framework, we establish a set of criteria. Then, we analyze real-life case studies in different types of academic activities. From there, we identify the strengths and weaknesses of its use in each case study. We then identify the limitations and challenges of generative AI by type of academic activity. Finally, we conclude with recommendations on ethical responsibilities, and the role of the professor in the learning process, among other aspects.

Early detection of anomalies in cattle growth is essential for ensuring animal welfare, improving productivity, and enabling timely management interventions in livestock farming. However, centralized machine learning solutions raise concerns about data privacy, ownership, and heterogeneity across farms. This paper proposes a federated learning (FL) framework for detecting anomalies in beef cattle fattening, which enables decentralized model training while preserving data confidentiality. The system employs deep neural networks trained locally on real and synthetic farm datasets, and aggregated via the Federated Averaging function. Two experimental scenarios were designed to evaluate the system under different variance conditions: (i) balanced variance across farms, and (ii) high variance concentrated in one farm. In Scenario 1, the global model achieved a Mean Absolute Error (MAE) of 2.53 kg and a coefficient of determination (R2) of 0.9974. In Scenario 2, where a single farm introduced significant variability, the global MAE increased to 2.96 kg, with an R2of 0.9884. The anomaly detection mechanism, based on a residual thresholding method using the 2σ rule, identified 399 anomalies 4.87% in the balanced scenario. Results demonstrate the feasibility of using FL in livestock settings for robust and privacy-preserving anomaly detection, and highlight the need for adaptive techniques to address inter-farm variability.

Feature engineering plays a main role in the construction of machine learning models. In particular, it consists of several processes, including feature selection, fusion, and generation. Specifically, feature selection is the process of choosing the most relevant features from a dataset to train a machine learning model, with the goal of improving model performance and reducing training time and model complexity.. In this work, we propose a new method of feature selection based on the LAMDA (Learning Algorithm for Multivariate Data Analysis) algorithm for the classification and clustering contexts. LAMDA calculates the membership degree of an individual to a class or cluster, considering the contribution of all its features/descriptors. Our approach uses this idea to determine the most relevant features of a class (with the highest membership degree), and from there, select those with the highest membership degree across all classes. For the classification, we use the LAMDA-HAD algorithm, and in the clustering, we use the LAMDA-RD algorithm. We have carried out different experiments with different datasets, and we have obtained satisfactory results. We observe that the features selected with our proposal have a significant impact on the performance of the classification and clustering models.

This paper presents ArSGam, a modular architecture designed to integrate gamification schemes into serious games aimed at cognitive-affective training. ArSGam focuses on the user's emotional, cognitive, motivational profile and learning style. The proposal seeks to move beyond traditional approaches in which game elements are added without clear justification while offering a structured framework that aligns pedagogical, motivational, and emotional objectives. We designed four modules, guiding the process from user profiling to the logical selection of game mechanics: 1) Contextual Analysis, 2) Recommendation, 3) Gamification Scheme Design, and 4) Gamification Integration. Particularly, the inclusion of the cognitive-affective model in the first module facilitated the identification of the emotional and cognitive aspects of the user. We used a case study conducted in the mining sector to validate the architecture's applicability, flexibility, and coherence. In addition, we developed a formal validation using an instrument adapted from the ISO/IEC 25010 standard, evaluating five key characteristics: functionality, usability, maintainability, compatibility, and portability. The evaluation resulted in a global quality score of Q = 47 with an average standard deviation of σ = 0.3, indicating high consistency and overall quality across the assessed characteristics. The results suggest that ArSGam enables the integration of gamification into serious games, thus enhancing educational processes across diverse contexts.

Epidemiologists and social scientists have used the Network Scale-Up Method (NSUM) for over thirty years to estimate the size of a hidden sub-population within a social network. This method involves querying a subset of network nodes about the number of their neighbors belonging to the hidden sub-population. In general, NSUM assumes that the social network topology and the hidden sub-population distribution are well-behaved; hence, the NSUM estimate is close to the actual value. However, bounds on NSUM estimation errors have not been analytically proven. This paper provides analytical bounds on the error incurred by the two most popular NSUM estimators. These bounds assume that the queried nodes accurately provide their degree and the number of neighbors belonging to the hidden sub-population. Our key findings are twofold. First, we show that when an adversary designs the network and places the hidden sub-population, then the estimate can be a factor of Ω(√n) off from the real value (in a network with n nodes). Second, we also prove error bounds when the underlying network is randomly generated, showing that a small constant factor can be achieved with high probability using samples of logarithmic size O(log n). We present improved analytical bounds for Erdős-Rényi and Scale-Free networks. Our theoretical analysis is supported by an extensive set of numerical experiments designed to determine the effect of the sample size on the accuracy of the estimates in both synthetic and real networks.

Machine Learning algorithms are very sensitive to missing data, and their results depend on the way data is treated by the algorithms. In this work, we will understand missing data when a variable in a dataset is missing data but cannot be eliminated due to its relevance, or when some records of the dataset are missing the values of some of the variables. In general, these problems can be addressed during data preprocessing, for example, by removing variables with a lot of missing data. Now, our interest is to evaluate the robustness of the LAMDA (Learning Algorithm for Multivariable Data Analysis) algorithm to handle missing data at the variable level. A series of experiments will be carried out exposing the algorithm to cases with different percentages of missing variables, and the results obtained will be analyzed. In addition, the performance of the algorithm will be assessed compared to other machine learning algorithms in the context of classification and clustering problems. to carry out this study, several datasets are used. Multiple copies of each of them have been obtained, subjecting them to various transformations that allow us to study different case studies to test the effectiveness of the proposed algorithm.

A typical problem that is solved by supervised machine learning techniques is classification. There are many types of this problem, such as binary classification, multi-classification, and multi-labels. The development of techniques that perform well in different types of classification problems, and for datasets with many or few variables, or many or few data, remains a challenge. On the other hand, recent work indicates that machine learning can benefit from quantum computing in terms of reducing computational complexity and improving its performance. The purpose of this research is to analyze the use of Quantum Support Vector Machines (QSVM) for different types of classification problems. For this, several kernels (linear and Gaussian) are considered. In turn, a comparison is made with Random Forest. Also, a detailed analysis is carried out for the binary classification of coffee beans, obtaining a precision of 95% and an accuracy of 79%.

This study proposes a framework that leverages ML algorithms for the cybersecurity of telemedicine systems in the Department of Córdoba, Colombia, addressing challenges amplified by the COVID-19 pandemic. The framework emphasizes enhancing the processing capabilities and reliability in managing clinical information, particularly focusing on the RES. It integrates a PGaaS aligned with the OWASP guidelines, aiming to neutralize emerging threats using advanced IA models. The system incorporates data encryption, 2FA-based Access Control, continuous backups, code obfuscation, and watermarking, all supported by a suitable legal framework. These components are combined into a comprehensive monitoring and auditing scheme to ensure robust protection against intelligent intrusions and the compromise of medical data.

The concept of digital transformation involves exploiting digital technologies to generate new ways of doing things in organizations, including the creation of new processes, models, and services that produce value based on the digitization of data and processes. The application of digital technologies enables organizations to develop capabilities for innovation, automation, etc., utilizing both established and emerging technologies, including the widespread use of artificial intelligence. In this paper is proposed the implementation of a fuzzy cognitive map based on experts for the evaluation of the level of digital transformation in MSMEs (Micro, Small & Medium Enterprises). The main variables of digital transformation used to define our fuzzy cognitive map were classified into five types: i) Organization and Culture variables related to strategies, way of working, and ecosystems, ii) Customer variables related to services and digital channels and products, iii) Operations and Internal Processes variables related to supply chain, suppliers, business model, iv) Information Technologies variables related to innovation, digitization, data and analytic. Finally, the fifth type of variable is the target, which indicates the level of digital transformation of the organization. Our model managed to specify with 99.4% the level of digital transformation of the organization. Thus, our fuzzy cognitive map can predict and analyze the factors associated with digital transformation in MSMEs.

Viral diseases such as dengue and COVID-19 constitute a public health problem due to high morbidity and mortality rates when diagnosis is not rapid and appropriate. The difficulties in the diagnostic process of these diseases lie in the variability of the clinical manifestations and the similarity with other viral diseases such as Zika and chikungunya. The implementation of computer-aided approaches can support medical professionals to support and improve decision making. In this article, we propose two medical decision support systems for severity prediction in dengue and COVID-19. The proposed systems use fuzzy cognitive maps for prediction and federated learning to increase the feature space, sample size, and ensure data privacy and security. The models were evaluated using dengue and COVID-19 datasets, and the results showed good performance in predicting severity and classifying patients. The implementation of the proposed systems in real clinical settings would be useful for the diagnosis of viral diseases such as dengue and COVID-19.

Model-Driven Engineering can play a crucial role in developing serious training games. Model-Driven Engineering benefits the creation of serious games by offering a structured software modeling approach, resulting in enhanced productivity, quality, and maintainability of the game software. These models can then be used to automatically generate code and other artifacts, significantly reducing development time and improving efficiency. We propose a metamodel that describes users' cognitive and affective dimensions during a serious game, utilizing a set of classes that define the relationships between them based on a theoretical framework of cognitive functions and emotions. We employed the Eclipse Modeling Framework to transform a primary model of the problem domain into a metamodel. We then combine the cognitive and affective dimensions of the model and formalize it into a generic metamodel for cognitive-affective training of users using serious games. Finally, we illustrate our approach with an example of instantiation of the model metamodel. We concluded with the importance of Model-Driven Engineering in serious game development.

In this work, an Automated Ontology Generator System (AOGS) is developed to autonomously create and populated ontologies based on the linked data paradigm. AOGS generates context-specific ontologies and populates these with information extracted from various linked data sources and pre-existing ontologies. AOGS allows reducing the time and effort required to create an ontology, ensuring consistency and accuracy in the ontology, and that domain experts to focus on higher-level tasks such as ontology refinement and evaluation. MEDAWEDE methodology is used to develop AOGS, which is then applied to create ontologies for COVID-19 and Energy. The quality of these ontologies is evaluated using precision, recall and f-measure metrics, which yield values between 0.9 and 0.7. The ontologies are also validated using Competence Questions, Consistency, and Quality Validation methods, all of which show good results.

A growing trend in information technology is not just reacting to changes, but anticipating them as much as possible. This paradigm is the base of modern applications, such as recommendation systems, the context-aware applications, among others. Anticipatory systems extend the idea to the communication systems, by studying patterns and periodicity in human behavior and network dynamic, to optimize the network performance. Particularly, for context-awareness applications is very important to extract autonomously contextual information. This work proposes a set of autonomic cycles of data analysis tasks to provide context awareness using the network traffic data, which gives information about the behavior of the traffic flow in a given context. This information about the network (links, users, type of traffic, etc.) is used to extract useful knowledge about the context using data analysis tasks.

Cattle breeding has been one of the most important industrial sectors in the world, since it is related to food security and the survival of the human race. Cattle diagnostics is a fundamental procedure for cattle breeders because it allows them to make strategic decisions, such as timely treatment in case of any abnormality (e.g., weight gain in herds, in their paddocks). This article aims to present a system to diagnose weight loss or gain in cattle under a rotational grazing scheme, considering the health status of the animal and the pasture. The diagnostic system is based on a fuzzy classifier that uses fuzzy logic to define the rules that characterize the diagnostic process, and fuzzy reasoning to determine the current situation given an input. In addition, the fuzzy classifier optimizes the rules using genetic algorithms, which modify the membership functions, providing a more accurate system for diagnosis. We tested our proposal with experimental cases, with promising results. The accuracy metrics have high values, indicating a low error rate in terms of false positives. In general, the values of the quality metrics are very good, with an accuracy close to 100% and an Area Under the Curve close to 1.

Integrated pest management (IPM) seeks to minimize the environmental impact of pesticide application. IPM is based on two important aspects —prevention and monitoring of diseases and insect pests— which today are being assisted by sensing and artificial-intelligence (AI). Particularly, AI helps to identify, monitor, control and make decisions about pests in crops. In this paper, we present a comparison among five machine-learning models to classify the population of the boll weevil in cotton into three classes: low, medium and high. Weather data (average daily rainfall, humidity and temperature) were used to classify the population of the boll weevil in the department of Córdoba, Colombia. The results showed that XGBoost obtained the highest accuracy (88%). Results showed that it is possible to classify boll-weevil populations using weather data.

In a smart environment like the smart grids, it is necessary to have knowledge models that allow solving emerging problems. However, large datasets are required to automatically create these models, which in the vast majority of cases are not available. Therefore, in these environments is essential to have a data generator for each context. In this paper, we propose a synthetic data generation system based on the variational autoencoder (VAE) technique and linked data paradigm, to create larger datasets from small datasets acting as samples. Specifically, a Linked Data-based dataset extractor is proposed, which allows obtaining samples of data in a particular context. Then, a VAE is trained with these samples of data available in a specific context, to learn the latent distribution that characterizes the dataset, allowing the production of new records that are similar to those of the original dataset. Finally, several case studies in the field of energy management are carried out. In one of them, the process that follows our approach is described in detail; and then, another 3 more are considered to evaluate its ability to automate the data generation process for smart energy management. The results show how our synthetic data generation system can be used to obtain synthetic datasets in different energy contexts.

The difficulty in finding the most suitable recommendation algorithm for all requests is a common challenge in the recommendation system context, regardless of the domain. Although the combination of multiple techniques in a hybrid approach is often a good solution, the majority of implementations follow a static hybridization scheme, which does not consider the available data, the user specificities at a given time, or the changing environment. Thus, another challenge is the definition of adaptive hybrid recommenders that are capable to adjust the combination of the recommendation algorithms based on the properties of the dynamic inputs. For that purpose, it is necessary to define meta-features that contain information to effectively differentiate recommendation algorithm behaviors over time, and capture how properties of the user/items are related to their performance. This work studies these meta-features in order to analyze their characteristics, relevance, behavior, redundancy and their abilities to represent the system dynamics over time. The paper presents several experiments that can be used as a meta-feature’s evaluation guide, and briefly propose its utilization in a hybrid fuzzy system for recommendation.

In Machine Learning (ML), there is a lot of research that seek to automate specific processes carried out by data scientists in the generation of knowledge models (predictive, classification, clustering, etc.); however, an open problem is to find mechanisms that allow conferring the ability of self-learning. Thus, a meta-learning mechanism is required to allow ML techniques to self-adapt in order to improve their performance in problem solving, and even in some cases, to induce the learning algorithm itself. In this context, our research defines a meta-learning architecture using Linked Data (LD) for the automatic generation of knowledge models. Specifically, this intelligent architecture is formed by the layers of Knowledge Sources, Meta-Knowledge and Knowledge Modelling, to unify all processes to guarantee a Meta-Learning process. The Knowledge Sources layer is responsible for providing semantic knowledge about the processes of generation of knowledge models; the Meta-Knowledge layer is responsible for controlling the different processes and strategies for the automatic generation of knowledge models; and finally, the Knowledge Modelling layer is responsible for executing ML tasks defined by the Meta-Knowledge layer, among which are the tasks of feature engineering, ML algorithm configuration, model building, among others. Additionally, this article presents a case study to analyze the behavior of the different layers of the architecture, to generate knowledge models. Thus, the main contribution of this research is the definition of a Meta-Learning architecture for ML techniques, which takes advantage of the semantic information described as LD when generating the knowledge models. The preliminary results are very encouraging.

In this work is proposed a parameter adaptive system for emerging serious games, which allows the emerging of properties in a game, in order to adapt it to the educational context in which it is being used. Previous articles have proposed an engine for emerging serious games based on the ant colony optimization algorithm, which allows the initial emergence of a serious game. In this paper, another component of the game adaptive sub-system of the engine is specified, which allows its dynamic adaptation while the game is running, in this case, in order to adapt its properties to the educational context-domain. Particularly, the property emergence system is based on the use of cultural algorithms, which establishes a learning process to modify its parameters. This system is tested in the context of a smart classroom.

A serious emerging games engine (SEGE) must make explicit the possibility of emergence in a serious game (SG), from the coordinated handling of game plot, adapted to the specific educational context where it is being developed. In previous articles a SEGE based on the ant colony optimization algorithm (ACO) has been proposed, which allows the initial emergence of a SG. In the present work the adaptive plot system (APS) is specified, which allows the emergence of plot in a serious game emerging (SGE), and is based on an ACO that changes the plot in the game, according to the theme that is being given in a smart classroom SaCI (Salón de Clase Inteligente, for its acronym in Spanish),). The APS performs the management of a set of game plot that may be of interest in a context-educational domain, in such a way to adapt the SGE initially conceived to the subject taught in the SaCI, in order to make the appropriate SGE emerge Pedagogical process in progress. Additionally, this paper analyzes the behavior of APS in a case study, showing very encouraging results as SEGE.

In this paper, we study the emergent behaviors in a multi-robot system. The multi-robot system uses a model for decision making that is composed of three levels: one individual, one collective, and another for the knowledge and learning management. In particular, the individual level, the base of the emergent behavior of the system, is composed of a module of perception/interpretation, an executing module and a behavioral module that has an emotional component, a reactive component, a cognitive component and a social component. In this paper, we analyze the robot performance, in order to produce an emergent behavior in the system. We present an example of an emergent scenario, and study its instantiation in our multi-robot architecture.

The merging procedures of two ontologies are mostly related to the enrichment of one of the input ontologies, i.e. the knowledge of the aligned concepts from one ontology are copied into the other ontology. As a consequence, the resulting new ontology extends the original knowledge of the base ontology, but the unaligned concepts of the other ontology are not considered in the new extended ontology. On the other hand, there are experts-aided semi-automatic approaches to accomplish the task of including the knowledge that is left out from the resulting merged ontology and debugging the possible concept redundancy. With the aim of facing the posed necessity of including all the knowledge of the ontologies to be merged without redundancy, this article proposes an automatic approach for merging ontologies, which is based on semantic similarity measures and exhaustive searching along of the closest concepts. The authors' approach was compared to other merging algorithms, and good results are obtained in terms of completeness, relationships and properties, without creating redundancy.

This paper presents the architecture of a Reflective Middleware for Acoustic Management that will improve the interaction between users and agents in Intelligent Environments, using the Multiagent System paradigm. The middleware manages the acoustic services, from the identification and recognition of the acoustic signals, until the interpretation, processing and analysis of them. In this paper are detailed the architecture bases, the middleware components, and case studies where this Middleware can be used. Acoustic signals and vibrations will generate the connection between agents, but it will also include the sounds that are provided by the users of the Intelligent Environment, making it an interactive and immersive experience.

This paper presents a semantic personalized recommender system for biomedical ontologies. To do this, we design and implement a semantic repository of biomedical ontologies, containing metadata associated with each biomedical ontology. The knowledge stored in the metadata of the semantic repository is used for the recommender system, in order to give prioritized recommendations of the different biomedical ontologies that meet certain search criteria. The proposed recommender also considers hybridization, considering the calibration of the impact generated by two aspects: customization (adaptability) for each user, and the quality evaluation of each ontology to recommend.

This article presents a Model of an Adaptive Learning Object (MOAA) for virtual environments from a definition of Adaptive Learning Object, and a proposition of extension of the LOM standard to specify the adaptation metadata. The MASINA methodology and the UML diagrams are used to describe it. The model specifies modularly and independently two categories of rules, of adaptation and conversion, giving it versatility and flexibility to perform different types of adaptation to the learning objects, incorporating or removing rules in each category.

Technological advances such as miniaturization of sensors, mobile devices and increased computational capabilities have given way to Context Aware Applications (ACC), which constantly monitor and change depending on the context. These applications require a variety of features and services, particularly on the management of context. When applications/services lack part or some of these services, they must be consumed from other suppliers who can provide them via a middleware. In addition, due to the changes undergone by the context mean that such services consumed by the ACC must be dynamic; and due to the amount of data involved to define the context, it may require more computation capacity than that provided by a mobile device. For these reason it is necessary the use of the Cloud. In this way, to support these requirements is proposed CARMiCLOC (Context Awareness in Reflective Middleware Cloud Computing), a web-service based middleware, which can behave as a SaaS (Software as a Service) or as a PaaS (Platform as a Service).

This work aims to evaluate the use of Learning Analitycs (LA) in Higher Education; students, and attributes such as: profile, interactions in a virtual learning environment learning - for this use business intelligence paradigm in order to explore and exploit the data from one of the actors in the educational process is analyzed, test scores, among others, which will contribute to their educational success. In particular, this paper tries to answer the following specific objectives: To identify factors that influence the decision of a college student distance learning to abandon their studies and get the profile of potentially susceptible students from their university studies. To meet this purpose we define two analysis tasks learning and use a business intelligence methodology to implement it.

This paper presents a prototype of a semantic personalized recommender system for a repository of preserved web files. To do this, we design and implement a semantic repository of preserved web files, containing metadata associated with each preserved site. The knowledge stored in the metadata of the semantic repository is used for the recommender system, in order to give prioritized recommendations of the different preserved web files (or web heritage) that meet certain search criteria. The proposed recommender also considers semantic associations, in order to recommend not only the websites matched to the search criteria, but also semantically related.

This paper describes how to semantically enrich clusters from signaling pathways networks. The study is divided into two phases, the first is the detection of clusters in signaling pathways networks, after getting these clusters, they are passed to an extraction process of centrality within each one, so the second phase can enrich them semantically. The centrality chosen for the case study is the measure of closeness to other nodes, and it is who is enriched semantically in each cluster. The selected case study is the signaling pathway of TGF-β, and the central nodes found were enriched with the Gene Ontology.

A major endeavor of ecology is to understand the emergence of complexity. This task requires the integration of knowledge and theories, moving from physical to social sciences. We use genetic programming to develop mathematical relationships between ecological emergence and variables such as self-organization, homeostasis, autopoiesis and complexity. These variables were initially formalized on the basis of information theory. The emergence models found were applied and tested with a case study involving an arctic lake and a tropical lake. In these lakes, the variables of limiting nutrients, biomass and physico-chemical components were taken into account for the automated generation of the model equations. The results show that the model follows in the dynamics of the aquatic ecological components selected accurately. In this context, ecological emergence can be calculated and studied.

This article specific a management system of the learning cloud, based on the ODA (Ontology Driven Architecture) and SOA (Service Oriented Architecture) paradigms, of the educational online platform defined for the Career in Computer Science and Informatics in the University of the Andes in Mérida. This platform consists of three clouds: Formation Cloud, composed of the graph in which is defined the curricular profiles that a student can take to get a degree/diploma; Knowledge Sources Cloud, where learning objects and online courses appear as sources of knowledge to meet the learning units defined in curricular graph; and finally, the Learning Cloud, where the paradigms, strategies and learning tools appear, so she brings learning mechanisms necessary for the formation of the student.

An Ambient Intelligence (AmI) requires a conceptual definition of its components, its devices must handle a common semantic for reasoning about context and specific application domains. Ontology is an ideal tool for the semantic characterization of AmI. In that sense, update and evolution of each ontology should be in the same moment when information changes in the environment and the application domain also. Context information can provide specific data on a new object in the environment, to characterize and to classify it within the ontology. For this reason, we propose an "Emergent Ontology” based on an Ant Colony Optimization algorithm to overcome the need for an emergent and dynamic semantic for an AmI. This proposal emergent ontology is structured according to three ontologies to evolve in real time: context ontology, another associated with AmI's components, and the last one, about conceptual model of a particular domain.

This paper describes the steps for achieving data processing in a methodological context, which take part of a methodology previously proposed by the authors for developing Data Mining (DM) applications, called "Methodology for the development of data mining applications based on organizational analysis". The methodology has three main phases: Knowledge of the Organization, Preparation and treatment of data, and finally, development of the DM application. We will focus on the second phase. The main contribution of this proposal is the design of a methodological framework of the second phase based on the paradigm of Data Science (DS), in order to get what we have called “Vista Minable Operacional” (VMO) from the “Vista Minable Conceptual” (VMC). The VMO built is used in the third phase. This methodological framework has been applied in two different cases of study, oil and public health.

In this paper we describe the design and implementation of a library (based on pthreads and C + +) to use explicit parallelism thread-level speculation. The library consists of several models proposed for speculation, guaranteeing sequential consistency: decision structures speculation (where the branches are executed in parallel to the previous section), loops speculation (where all iterations are run in parallel), critical sections speculation, and speculation by cooperating threads. The library was evaluated through case studies taken from SPEC CPU 2000, allowing acceleration of about 1.5 x for a multicore architecture (four cores) with coarse-grained multithreaded.

Motifs are useful in biology to highlight the nucleotides/amino-acids that are involved in structure, function, regulation and evolution, or to infer homology between genes/proteins. PROSITE is a strategy to model protein motifs as Regular Expressions and Position Frequency Matrices. Multiple tools have been proposed to discover biological motifs, but not for the case of the motifs comparison problem, which is NP-Complete due to flexibility and independence at each position. In this paper we present a formal model to compare two protein motifs based on the Genetic Programming to generate the population of sequences derived from every regular expression under comparison and on a Neural Network Backpropagation to calculate a motif similarity score as fitness function. Additionally, we present a fusion formal method for two similar motifs based on the Ant Colony Optimization technique. The comparison and fusion method was tested using amyloid protein motifs.

This paper proposes a methodology to identify the feasibility of applying Data Mining techniques (DM) in an organization (institutions or enterprises). This methodology can be applied when there are different sources of data and knowledge, and their interactions are not well identified or defined. The methodology consists of five phases defined to know and characterize the enterprise processes, its its relationships, its actors, and sources of knowledge and data. As a final result, the methodology defines the problems of the institution/company that can be improved with DM tasks MD. The methodology selects the processes of interest based on prioritization, and identifies DM tasks to perform, from the present and expected future scenarios. The utilization of this proposition is illustrated in two different types of organization, health and petroleum.

In this work we detail the design of the Interpretative Ontology used by the Dynamic Semantic Ontological Framework (MODS) proposed in [1]. We also present its use for the characterization of continuous production processes as proposed in [2], specifically for the supervision and diagnosis domain. Thus, with this ontology we can query in natural language on the Semantic Web using MODS, in the domain of supervision and diagnosis.

This paper aims to evaluate the learning model for coordination schemes in multiagent systems (MAS) based on Cultural Algorithms. The model is applied to a case of study in industrial automation, related to the Agents-based System for Fault Management System. The instantiation occurs on the conversations that are defining in the MAS's coordination model, which are characterized by type of conversation that have been previously defined. A conversation can have sub-conversations, and in this case the sub-conversations are characterized by a particular type of conversation. Additionally in these conversations can occur some type of conflict, that can be solved by using different coordination mechanisms existing in the literature. For this, it is developed a model based on cultural algorithms, which is used by the MAS as a learning way in the process to determine which coordination mechanism is more suitable for a given conversation and a given scenario. The results show that the obtained model through this learning guides the MAS to determine which mechanism is better suited for a given conversation.

The chronicles paradigm has been used to determine fault in dynamic systems, allow modeling the temporal relationships between observable events to describe the patterns of behavior of the system. The chronicle recognition mechanisms used until now are semi-centralized approaches, which consist of a central component that is responsible for making the final inference about the fault diagnosis of the system, based on the information collected from local diagnosers. This model has difficulty when is implemented for monitoring very large systems. This paper proposes a fault diagnosis system based on distributed chronicles. For that, we need to extend both, the definition of the chronicles as its recognition mechanism, so that they are fully distributed. This paper presents these extensions, and then describes the fault diagnosis system based on distributed chronicles proposed, and an example of its use in SOA applications.

This paper proposes a system of automatic code generation for MASINA (Multiagent Systems in Automation). MASINA is a methodology for specifying Multi-agent systems. The code generator takes MASINA models as input, and from them generates code for each one of the agents of the Multiagent System under construction. The code generation system SISGECOMA, as we call it, is composed of several agents: one that is interface with the user and captures all the information provided by him through MASINA models, another agent performs the verification and validation of the information, finally, another agent generates the Multiagents System.