Diego de Siqueira Braga

The Game of Trust: Using Behavioral Experiment as a Tool to Assess and Collect Trust-Related Data

Trust is one of the most important dimensions in developing and maintaining business relationships. However, due to the difficult to collect trust-related data from industry, given its concerns surrounding privacy and trade secret protection, it still very problematic to investigate it. Motivated by the growing interest in behavioral research in the field of operations and supply chain management, and by the lack of supply chain trust-related datasets, the authors of this paper proposed and designed a novel trust behavioral experiment. Utilizing concepts of gamification and serious games, the experiment is capable of gathering information regarding individuals’ behavior during procurement, information exchange, and ordering decisions considering trust relations in the context of supply chains.

An evaluation of forecasting methods for anticipating spare parts demand

In the planning process of a supply chain, demand forecast have an important role in planning process of a company. The forecasts have to be as accurate as possible in order to allow the optimization of production, avoiding extra stocking costs or lost sales. In the case of spare parts, the challenge arises as the demand presents intermittent behavior. Nowadays, many forecast techniques, namely ARIMA models and Crostons method, are used to forecast spare parts demand. Alternatively to statistical methods, artificial neural networks (ANNs) are also powerful tools for solving non linear complex problems. Recurrent neural networks, such as the reservoir computing (RC), present an architecture that allows modeling of dynamic behavior, making it a strong candidate for solving the spare parts demand forecast problem. This work proposes a performance evaluation of artificial neural networks (feed-forward and recurrent) for spare parts demand forecasting, including also a comprehensive comparison of best achieving techniques, such as Crostons and the ARIMA method. The evaluation performed here may help an organization to decide which technique suits better its needs for forecasting the spare parts demand. The experiments show that neural networks out perform the statistical methods in three out of four data sets tested.

An aspect-oriented domain-specific language for modeling multi-agent systems in social simulations

Aspect-oriented programming (AOP) is a programming paradigm which aims to increase modularity by allowing the separation of cross-cutting concerns. This paper presents the definition and characteristics of the domain-specific language, aspect-oriented, AspectNetLogo and its compiler, the AspectNetLogoCompiler and show the use of this system in a multi-agent system in social simulation. This system allows the definition of the elements of the agents in the NetLogo environment in an isolated way and simplify the implementation of social simulations.

MusicOWL: the music score ontology

Managing and analyzing music scores content is a known issue for digital libraries. Despite their inarguable complexity, these contents are often ignored by digital libraries, where music scores are mostly treated as simple digital images. This paper reports on the development and application of MusicOWL, an ontology to formally describe music scores contents for western music. Unlike other efforts on the subject, MusicOWL provides a comprehensive vocabulary for annotating music scores, which covers important music-related information, such as melodies, dynamics, and tonalities. We also report on the Linked Music Score dataset creation, including all necessary steps from scanned music scores to RDF triples, and how this linked music score data enables users to search for music scores by using handy queries, thus translating the needs of many music professionals, data curators and online learners. Additionally, we introduce and analyze the search engine WWU Music Score Portal, which uses the approach proposed in this work to improve music scores discovery and support online learning of music.

Combining Behavioral Experiments and Agent-based Social Simulation to Support Trust-aware Decision-making in Supply Chains

Trust is seen as one of the most important dimensions in developing and maintaining fruitful business relationships and has deep impact on the decision-making process in the supply chain planning. Despite its importance, very limited research has been done in the trust-aware decision-making field. This paper aims to experimentally examine how trust can be assessed over different dimensions and then be used to support decision-making in order to reduce the Bullwhip Effect, which is one of the biggest efficiency problems shown by supply chains of highly interconnected organizations. As industry is generally reluctant to provide data due to privacy concerns and trade secret protection, the authors of this paper, designed and conducted a web-based trust behavioral experiment. The data collected was used to evaluate the proposed trust mechanism through an Agent-Based Social Simulation. The results revealed that it is possible to infer trust relationships from behavioral experiments and historical based data, and use these relationships to influence the procurement, ordering and information sharing process. Although additional research is still necessary, the preliminary results revealed that the use of computational trust mechanisms can be helpful to lower the Bullwhip Effect.

A Novel Serious Game for Trust-Related Data Collection in Supply Chains

Trust is considered an essential factor to develop and maintain business and supply chain relationships. However, it is hard to investigate its mechanisms due to the lack of supply chain trust-related datasets. This lack forces researchers to use artificially and often self-generated datasets which limit the validity of results and comparability with different approaches. Striving for the generation of less artificial trust datasets, this paper presents a novel serious game to gather trust information in a B2B supply chain setting.

Automated scalable modeling for population microsimulations

The propagation of diseases within the population is an ever-reappearing hot topic in news stories. Mutations of known diseases repeatedly infected large portions of the population. In order to support the select appropriate mechanisms to help taming the spread of an epidemic, several simulation approaches have been developed to forecast the propagation behavior of diseases. Agent-based micro simulations promise to create the most detailed and accurate forecasts, but require a high modeling effort. In this paper we propose an approach to lessen this modeling effort by introducing a method that automatically creates agents for representing groups within the population based on multiple data sources (e.g. census data, vaccinations records, etc.). Our approach also facilitates combining these heterogeneous data with geographic information systems as well as dealing with incomplete data for enabling automatic and scalable creation of epidemics models for different simulation purposes in epidemiology. Two test cases were used to assess the proposition.

The use of multimodal interaction for supporting the production of location-based information

Despite the increasingly volume of location-based information systems, it is a common practice to develop these technological resources aiming for the usage by professional content providers. Non-experts users appear as an important alternative of impartial contributions in this scenario. In this manner, multimodal interaction - particularly, gestures recognition and voice commands - can open further opportunities for support the usage by common users. This paper therefore aims to analyze the contributions on the use of multimodal interaction for supporting the production of location-based information. Its research methodology is based on a conceptual framework as well as usability analysis with real users. The results revealed that non-experts users often take a while before becoming confident with new kinds of interaction. It also shown that voice commands were rather more useful than gestures according to the users. Furthermore, even with long years of research in the field, technological resources still need improvements for the speech and gesture recognitions, mainly due to the idiosyncrasies presented on this interaction. Although additional research is still necessary in this area, it can be concluded that multimodal interactions have a great potential for supporting the production of location-based information.

Indicação de Rotas com Base na Sazonalidade e no Perfil do Turista Utilizando Técnicas de Computação Evolucionária

This article presents a study on genetic algorithm s applied to a combinatorial problem, where the sea rch space is very large, with the aim of generating tourist rout es. The routes are based on the preferences of tour ists (i.e. elements that he wishes to be present in cities the route generated) in addition to considering the period of the year when tourists plan to travel.

Application of the Fish School Search for the Supply Chain Network Planning Problem

The Fish School Search (FSS) is a recently proposed meta-heuristic, which is inspired by the collective behavior of fish schools during their search for food. This optimization technique has been showing promising results when applied to benchmarking problems. Moreover, the FSS has been especially designed to tackle complex problems, especially ones with large search spaces like they are found in the area of Supply Chain Management. As such, the Supply Chain Network Planning (SCNP) problem was chosen as an NP-hard optimization problem to evaluate the applicability of the FSS in this problem domain. Additionally, other state-of-the-art meta-heuristics used for optimization problems (Particle Swarm Optimization and Differential Evolution), as well as a stateof-the art mathematical optimization technique were applied to solve the same planning problem in order to determine the relative performance of the FSS algorithm for this class of problems. Keywords—Fish School Search, Meta-heuristics, Computational Intelligence, Supply Chain Management, Supply Chain Network Planning, Bio-inspired Methods