International Journal on Artificial Intelligence Tools

This article presents a cost sensitive probabilistic contingent planning approach for automated semantic web service composition, under the assumptions that the execution of each web service incurs some cost; its alternative outcomes along with their probabilities of occurring are known in advance; and actions do not involve delete effects. The implemented planner, MAPPPA2, produces a contingent plan in the form of a decision tree, by integrating multiple alternative deterministic plans computed by solving a determinized version of the original problem. Both the generation of the alternative deterministic plans, as well as the merging process attempt to maximize the expected utility of the final contingent plan. The article presents evaluation results regarding the approach, based on three web service composition domains.

Oft-decried information overload is a serious problem that negatively impacts the comprehension of information in the digital age. Text summarization is a helpful process that can be used to alleviate this problem. With the aim of seeking a novel method to enhance the performance of multi-document summarization, this study proposes a novel approach to analyze the problem of multi-document summarization based on a mixture model, consisting of a contextual topic model from a Bayesian hierarchical topic modeling family for selecting candidate summary sentences, and a regression model in machine learning for generating the summary. By investigating hierarchical topics and their correlations with respect to the lexical co-occurrences of words, the proposed contextual topic model can determine the relevance of sentences more effectively, recognize latent topics, and arrange them hierarchically. The quantitative evaluation results from a practical application demonstrates that a system implementing this model can significantly improve the performance of summarization and make it comparable to state-of-the-art summarization systems.

Brazil is an agricultural nation whose process of spraying pesticides is mainly carried out by using aircrafts. However, the use of aircrafts with on-board pilots has often resulted in chemicals being sprayed outside the intended areas. The precision required for spraying on crop fields is often impaired by external factors, like changes in wind speed and direction. To address this problem, ensuring that the pesticides are sprayed accurately, this paper proposes the use of artificial neural networks (ANN) on programmable UAVs. For such, the UAV is programmed to spray chemicals on the target crop field considering dynamic context. To control the UAV ight route planning, we investigated several optimization techniques including Particle Swarm Optimization (PSO). We employ PSO to find near-optimal parameters for static environments and then train a neural network to interpolate PSO solutions in order to improve the UAV route in dynamic environments. Experimental results showed a gain in the spraying precision in dynamic environments when ANN and PSO were combined. We demonstrate the improvement in figures when compared against the exclusive use of PSO. This approach will be embedded in UAVs with programmable boards, such as Raspberry PIs or Beaglebones. The experimental results demonstrate that the proposed approach is feasible and can meet the demand for a fast response time needed by the UAV to adjust its route in a highly dynamic environment, while seeking to spray pesticides accurately.

In this work we propose a simulated annealing based search algorithm for optimal ramified or branched transportation route in $R^2$. The cost function of the transport network allows the system to merge small roads into larger highways, carry the goods together and separate them near the destination. As a result the transportation route has multiple branching-in and -out points, to some extent similar to nerve system of the tree leaf. The problem is known to be NP-complete even for finite set of branching points and metric spaces.

Data uncertainty in real-life problems is a current challenge in many areas, including Operations Research (OR) and Constraint Programming (CP). This is especially true given the continual and accelerating increase in the amount of data associated with real-life problems, to which Large Scale Combinatorial Optimization (LSCO) techniques may be applied. Although data uncertainty has been studied extensively in the literature, many approaches do not take into account the partial or complete lack of information about uncertainty in real-life settings. To meet this challenge, in this paper we present a strategy for extrapolating data from limited uncertain information to ensure a certain level of robustness in the solutions obtained. Our approach is motivated and evaluated with real-world applications of harvesting and supplying timber from forests to mills and the well known knapsack problem with uncertainty.

Among real-system applications of AI, the field of traffic simulation makes use of a wide range of techniques and algorithms. Especially, microscopic models of road traffic have been expanding for several years. Indeed, Multi-Agent Systems provide the capability of modeling the very diversity of individual behaviors. Several professional tools provide comprehensive sets of ready-made, accurate behaviors for several kinds of vehicles. The price in such tools is the difficulty to modify the nature of programmed behaviors, and the specialization in a single purpose, e.g. either studying resulting ows, or providing an immersive virtual reality environment. Thus, we advocate for a more exible approach for the design of multi-purpose tools for decision support. Especially, the use of geographical open databases offers the opportunity to design agent-based traffic simulators which can be continuously informed of changes in traffic conditions. Our proposal also makes decision support systems able to integrate environmental and behavioral modifications in a linear fashion, and to compare various scenarios built from different hypotheses in terms of actors, behaviors, environment and ows. We also describe here the prototype tool that has been implemented according to our design principles.

MCTS (Monte Carlo Tree Search) is a well-known and efficient process to cover and evaluate a large range of states for combinatorial problems. We choose to study MCTS for the Computer Go problem, which is one of the most challenging problem in the field of Artificial Intelligence. For this game, a single combinatorial approach does not always lead to a reliable evaluation of the game states. In order to enhance MCTS ability to tackle such problems, one can benefit from game specific knowledge in order to increase the accuracy of the game state evaluation. Such a knowledge is not easy to acquire. It is the result of a constructivist learning mechanism based on the experience of the player. That is why we explore the idea to endow the MCTS with a process inspired by constructivist learning, to self-acquire knowledge from playing experience. In this paper, we propose a complementary process for MCTS called BHRF (Background History Reply Forest), which allows to memorize efficient patterns in order to promote their use through the MCTS process. Our experimental results lead to promising results and underline how self-acquired data can be useful for MCTS based algorithms.

Extreme Learning Machine (ELM) is a recently proposed algorithm, efficient and fast for learning the parameters of single layer neural structures. One of the main problems of this algorithm is to choose the optimal architecture for a given problem solution. To solve this limitation several solutions have been proposed in the literature, including the regularization of the structure. However, to the best of our knowledge, there are no works where such adjustment is applied to classification problems in the presence of a non-linearity in the output; all published works tackle modelling or regression problems. Our proposal has been applied to a series of standard databases for the evaluation of machine learning techniques. Results obtained in terms of classification success rate and training time, are compared to the original ELM, to the well known Least Square Support Vector Machine (LS-SVM) algorithm and with two other methods based on the ELM regularization: Optimally Pruned Extreme Learning Machine (OP-ELM) and Bayesian Extreme Learning Machine (BELM). The obtained results clearly demonstrate the usefulness of the proposed method and its superiority over a classical approach.

Personal authentication systems based on biometrics have given rise to new problems and challenges related to the protection of personal data, issues of less concern in traditional authentication systems. The irrevocability of biometric templates makes biometric systems very vulnerable to several attacks. In this paper we present a new approach for biometric template protection. Our objective is to build a non-invertible transformation, based on random projection, which meets the requirements of revocability, diversity, security and performance. In this context, we use the chaotic behavior of logistic map to build the projection vectors using a methodology that makes the construction of the projection matrix depend on the biometric template and its identity. The proposed approach has been evaluated and compared with Biohashing and BioPhasor using a rigorous security analysis. Our extensive experimental results using several databases (e.g., face, finger-knuckle and iris), show that the proposed technique has the ability to preserve and increase the performance of protected systems. Moreover, it is demonstrated that the security of the proposed approach is sufficiently robust to possible attacks keeping an acceptable balance between discrimination, diversity and non-invertibility.

In data mining, classification rule learning extracts the knowledge in the representation of IF_THEN rule which is comprehensive and readable. It is a challenging problem due to the complexity of data sets. Various meta-heuristic machine learning algorithms are proposed for rule learning. Cooperative rule learning is the discovery process of all classification rules with a single run concurrently. In this paper, a novel cooperative rule learning algorithm, called CoABCMiner, based on Artificial Bee Colony is introduced. The proposed algorithm handles the training data set and discovers the classification model containing the rule list. Token competition, new updating strategy used in onlooker and employed phases, and new scout bee mechanism are proposed in CoABCMiner to achieve cooperative learning of different rules belonging to different classes. We compared the results of CoABCMiner with several state-of-the-art algorithms using 14 benchmark data sets. Non parametric statistical tests, such as Friedman test, post hoc test, and contrast estimation based on medians are performed. Nonparametric tests determine the similarity of control algorithm among other algorithms on multiple problems. Sensitivity analysis of CoABCMiner is conducted. It is concluded that CoABCMiner can be used to discover classification rules for the data sets used in experiments, efficiently.

A proposal for intelligent retrieval in the biodiversity domain is described. It applies natural language processing to integrate linguistic and domain knowledge in a mathematical model for information management, formalizing the notion of semantic similarity in different degrees. The goal is to provide computational tools to identify, extract and relate not only data but also scientific notions, even if the information available to start the process is not complete. The use of conceptual graphs as a basis for interpretation makes it possible to avoid the use of classic ontologies, whose start-up requires costly generation and maintenance protocols and also unnecessarily overload the accessing task for inexpert users. We exploit the automatic generation of these structures from raw texts through graphical and natural language interaction, at the same time providing a solid logical and linguistic foundation to sustain the curation of databases.