Dorin Moldovan

Tools for mapping ontologies to relational databases: A comparative evaluation

This paper presents an analysis of the state of the art solutions for mapping a relational database and an ontology by adding reasoning capabilities and offering the possibility to query the inferred information. We analyzed four approaches: Jena with D2RQ, Jena with R2RML, KAON2 and OWL API. In order to highlight the differences between the four approaches, we used a nutrition diagnostics related ontology for the definition of the concepts and of the rules, and a relational database for the storage of the individuals. As performance evaluation, we focused on the time required to map the relational database to the ontology, and the time required to retrieve the information that is inferred about the diagnostics of a number of people. The obtained results show that the best performance in both cases is given by KAON2.

Machine learning for sensor-based manufacturing processes

The increasing availability of relevant information, events and constraints in the environment of the modern factories due to deployment of IoT sensor technologies on the production line has led to an “explosion” in contextual big data. At the same time the advancements in the machine learning field from the last years opened new approaches for the analysis of the manufacturing processes datasets that are characterized by noisy data, a large number of features and an imbalanced classification of the samples. In this paper we investigate the applicability and the impact of machine learning techniques for managing production processes considering the data from a semiconductor manufacturing process (SECOM dataset). We have applied algorithms such as Boruta and MARS for the selection of the most relevant features and the Random Forest and the Gradient Boosted Trees for the samples classification. The results show better values for precision when the features are selected using Boruta and MARS rather than PCA and better values for accuracy when the data is unsampled and classified using Random Forest and Logistic Regression rather than Gradient Boosted Trees.

M2O: A library for using ontologies in software engineering

In this paper we propose an extensible framework over Jena and OWL API that maps complex Java data models onto semantic models based on some custom annotations in order to benefit from the advantages of ontologies in software engineering. Furthermore, it facilitates the implementation of basic CRUD operations for the domain classes and objects, also allowing the definition of new custom operations. We have performed tests on the Stanford Wine ontology, obtaining a code complexity reduction of up to 85% compared to the classical approaches using Jena or OWL API without noticeable performance reduction.

Spark-Based Classification Algorithms for Daily Living Activities

Dementia is an incurable disease that affects a large part of the population of elders and more than 21% of the elders suffering from dementia are exposed to polypharmacy. Moreover, dementia is very correlated with diabetes and high blood pressure. The medication adherence becomes a big challenge that can be approached by analyzing the daily activities of the patients and taking preventive or corrective measures. The weakest link in the pharmacy chain tends to be the patients, especially the patients with cognitive impairments. In this paper we analyze the feasibility of four classification algorithms from the machine learning library of Apache Spark for the prediction of the daily behavior pattern of the patients that suffer from dementia. The algorithms are tested on two datasets from literature that contain data collected from sensors. The best results are obtained when the Random Forest classification algorithm is applied.

Semantic data factory: A framework for using domain knowledge in software application development

This paper addresses the semantic gap between the domain knowledge and software application engineering by proposing a framework for mapping and integrating multiple heterogeneous data sources with application business logic by means of data semantic enrichment, aggregation, filtering and processing. Based on the main drawbacks identified in the current knowledge enhanced software application architectures, a generic framework for automating their development process is proposed. The framework reduces the implementation stage of complex applications to a simple task of editing a configuration file which can be performed even by the domain expert himself. Two use cases of the proposed framework are presented for developing semantically-enhanced applications. The first use case is described within the FP7 GEYSER research project in the context of energy-efficiency, while the second use-case is presented in the e-health context for generating applications over the Fitbit platform.

Particle Swarm Optimization Based Method forPersonalized Menu Recommendations

This paper presents a Particle Swarm Optimization (PSO) based method forgenerating healthy daily menu recommendations for elder. In order to apply the PSO method to the case of generating menu recommendations, we have redefined the concepts of particle, position and velocity of the particle, as well as the formulae for updating the position and velocity of the particle. Additionally, to evaluate the quality of a particle (i.e. a solution), we have used a fitness function that has four components: the closeness to a nutritionist dietary recommendation, a price component, a delivery time component, and a diversity component that estimates of how diverse a daily recommendation is. The method proposed has been tested on a set of different user profiles.

Diet Generator for Elders using Cat Swarm Optimization and Wolf Search

This paper addresses the problem of the generation of a recommendation of five healthy meals for the elders for an entire day by taking into consideration their nutritional constraints and their dietary restrictions. This problem is modeled as an optimization problem and is solved by using the Cat Swarm Optimization (CSO) and the Wolf Search (WS) algorithms. These two algorithms were integrated in an experimental prototype that allows the elders to order foods daily. Finally, a series of experiments were conducted in order to determine which algorithm leads to a combination of food packets that best matches the nutritional constraints imposed by the nutritionist and the older adult’s preferences for nutrition, price, time and aspect.

Hybrid Immune Based Method for Generating Healthy Meals for Older Adults

This paper presents a Hybrid Clonal Selection based method for generating healthy meals as starting from a given user request, a diet recommendation, and a set of food offers. The method proposed is based on a hybrid model, which consists of one core component and two hybridization components. The core component uses the CLONAG algorithm. One of the hybridization components is based on flower pollination, whereas the other utilizes tabu search and reinforcement learning. The flower pollination component is used for modifying the generated clones, while the tabu search and reinforcement learning component aims to improve the search capabilities of the core component by means of long-term and short-term memory structures. We integrated our method into an experimental prototype and we evaluated it on different older adult profiles.

SWAG: Semantic web application generator - a library for using ontologies as web services

This paper addresses the problem of integrating ontological knowledge bases into complex software applications by proposing a library for exposing ontology access and manipulation as web services. The proposed framework is an extension of our previous work, the M2O framework, and enhances it by integrating reasoning techniques and generating a web services layer for performing basic CRUD operations and inferred information retrieval over ontologies. The ontology access is provided by 3rd party APIs, such as Jena API for simple ontology access or D2RQ, in case of using ontologies mapped to relational databases for storing individuals. An object oriented layer is generated to intermediate the flow of information between the data sources and web services. The ontology, the reasoning rules and the database may be generated at runtime by using Java reflection techniques. The framework is used with the Diagnostic ontology to perform a set of experiments that illustrate the benefits of the proposed solution, such as code complexity reduction and reasoning capabilities.

Generating Healthy Menus for Older Adults Using a Hybrid Honey Bees Mating Optimization Approach

This paper models the problem of generating healthy menu recommendations for older adults as an optimization problem and proposes a hybrid Honey Bees Mating Optimization method for solving this problem. The method hybridizes the state of the art Honey Bees Mating Optimization meta-heuristic by injecting strategies inspired from Genetic Algorithms, Hill Climbing, Simulated Annealing, and Tabu Search into the steps that generate new solutions of the optimization problem. The method has been integrated in a food ordering system enabling older adults to order food daily. Experiments have been conducted on several hybridization configurations to identify the most appropriate hybridization that leads to the healthy menu recommendation that best satisfies the older adults diet recommended by the nutritionist, its culinary preferences and time and price constraints.