Anytime Algorithms for Solving Possibilistic MDPs and Hybrid MDPs

The ability of an agent to make quick, rational decisions in an uncertain environment is paramount for its applicability in realistic settings. Markov Decision Processes (MDP) provide such a framework, but can only model uncertainty that can be expressed as probabilities. Possibilistic counterparts of MDPs allow to model imprecise beliefs, yet they cannot accurately represent probabilistic sources of uncertainty and they lack the efficient online solvers found in the probabilistic MDP community. In this paper we advance the state of the art in three important ways. Firstly, we propose the first online planner for possibilistic MDP by adapting the Monte-Carlo Tree Search (MCTS) algorithm. A key component is the development of efficient search structures to sample possibility distributions based on the DPY transformation as introduced by Dubois, Prade, and Yager. Secondly, we introduce a hybrid MDP model that allows us to express both possibilistic and probabilistic uncertainty, where the hybrid model is a proper extension of both probabilistic and possibilistic MDPs. Thirdly, we demonstrate that MCTS algorithms can readily be applied to solve such hybrid models.

Averaged Extended Tree Augmented Naive Classifier

This work presents a new general purpose classifier named Averaged Extended Tree Augmented Naive Bayes (AETAN), which is based on combining the advantageous characteristics of Extended Tree Augmented Naive Bayes (ETAN) and Averaged One-Dependence Estimator (AODE) classifiers. We describe the main properties of the approach and algorithms for learning it, along with an analysis of its computational time complexity. Empirical results with numerous data sets indicate that the new approach is superior to ETAN and AODE in terms of both zero-one classification accuracy and log loss. It also compares favourably against weighted AODE and hidden Naive Bayes. The learning phase of the new approach is slower than that of its competitors, while the time complexity for the testing phase is similar. Such characteristics suggest that the new classifier is ideal in scenarios where online learning is not required.

Learning Extended Tree Augmented Naive Structures

This work proposes an extended version of the well-known tree-augmented naive Bayes (TAN) classifier where the structure learning step is performed without requiring features to be connected to the class. Based on a modification of Edmonds' algorithm, our structure learning procedure explores a superset of the structures that are considered by TAN, yet achieves global optimality of the learning score function in a very efficient way (quadratic in the number of features, the same complexity as learning TANs). We enhance our procedure with a new score function that only takes into account arcs that are relevant to predict the class, as well as an optimization over the equivalent sample size during learning. These ideas may be useful for structure learning of Bayesian networks in general. A range of experiments shows that we obtain models with better prediction accuracy than naive Bayes and TAN, and comparable to the accuracy of the state-of-the-art classifier averaged one-dependence estimator (AODE). We release our implementation of ETAN so that it can be easily installed and run within Weka.

Learning Bounded Tree-Width Bayesian Networks via Sampling

Learning Bayesian networks with bounded tree-width has attracted much attention recently, because low tree-width allows exact inference to be performed efficiently. Some existing methods [12, 14] tackle the problem by using k-trees to learn the optimal Bayesian network with tree-width up to k. In this paper, we propose a sampling method to efficiently find representative k-trees by introducing an Informative score function to characterize the quality of a k-tree. The proposed algorithm can efficiently learn a Bayesian network with tree-width at most k. Experiment results indicate that our approach is comparable with exact methods, but is much more computationally efficient.

Automating fault tolerance in high-performance computational biological jobs using multi-agent approaches

Background: Large-scale biological jobs on high-performance computing systems require manual intervention if one or more computing cores on which they execute fail. This places not only a cost on the maintenance of the job, but also a cost on the time taken for reinstating the job and the risk of losing data and execution accomplished by the job before it failed. Approaches which can proactively detect computing core failures and take action to relocate the computing core's job onto reliable cores can make a significant step towards automating fault tolerance. Method: This paper describes an experimental investigation into the use of multi-agent approaches for fault tolerance. Two approaches are studied, the first at the job level and the second at the core level. The approaches are investigated for single core failure scenarios that can occur in the execution of parallel reduction algorithms on computer clusters. A third approach is proposed that incorporates multi-agent technology both at the job and core level. Experiments are pursued in the context of genome searching, a popular computational biology application. Result: The key conclusion is that the approaches proposed are feasible for automating fault tolerance in high-performance computing systems with minimal human intervention. In a typical experiment in which the fault tolerance is studied, centralised and decentralised checkpointing approaches on an average add 90% to the actual time for executing the job. On the other hand, in the same experiment the multi-agent approaches add only 10% to the overall execution time

Learning Bayesian Networks with Bounded Tree-Width via Guided Search

Bounding the tree-width of a Bayesian network can reduce the chance of overfitting, and allows exact inference to be performed efficiently. Several existing algorithms tackle the problem of learning bounded tree-width Bayesian networks by learning from k-trees as super-structures, but they do not scale to large domains and/or large tree-width. We propose a guided search algorithm to find k-trees with maximum Informative scores, which is a measure of quality for the k-tree in yielding good Bayesian networks. The algorithm achieves close to optimal performance compared to exact solutions in small domains, and can discover better networks than existing approximate methods can in large domains. It also provides an optimal elimination order of variables that guarantees small complexity for later runs of exact inference. Comparisons with well-known approaches in terms of learning and inference accuracy illustrate its capabilities.

Bioassays against pinewood nematode: assessment of a suitable dilution agent and screening for bioactive essential oils

Acetone was investigated and found to be an appropriate alternative to Triton X-100 as a solvent of essential oils in bioassays aimed to investigate their effects on pinewood nematode (Bursaphelenchus xylophilus) mortality. Therefore it was used as dilution agent to screen the effectiveness of fifty two essential oils against this pest. Thirteen essential oils were highly effective, resulting in more than 90% pinewood nematode mortality at 2 mg/mL, with six of them resulting in 100% mortality. LC100 values ranged between 0.50 mg/mL and 0.83 mg/mL for the essential oils of Origanum vulgare and Satureja montana, respectively. Essential oils were submitted to gas chromatography and gas chromatography-mass spectrometry analysis and their chemical composition established. Data from essential oils with 100% mortality at 2 mg/mL and other essential oils previously found to have LC100 ≤ 2 mg/mL was combined, their chemical profiles investigated by correspondences analysis plus automatic classification.

Pine wilt disease: a worldwide threat to forest ecosystems

The pinewood nematode (PWN), Bursaphelenchus xylophilus, the causal agent of pine wilt disease (PWD), is a serious pest and pathogen of forest tree species, in particular among the genus Pinus. It was first reported from Japan in the beginning of the XXth century, where it became the major ecological catastrophe of pine forests, with losses reaching over 2 million m3/ year in the 1980s. It has since then spread to other Asian countries such as China, Taiwan and Korea, causing serious losses and economic damage. In 1999, the PWN was first detected in the European Union (EU), in Portugal, and immmediately prompted several government (national and EU) actions to assess the extent of the nematode’s presence, and to contain B. xylophilus and its insect vector (Monochamus galloprovincialis) to an area with a 30km radius in the Setúbal Peninsula, 20 km south of Lisbon. International wood trade, with its political as well as economic ramifications, has been seriously jeopardized. The origin of the population of PWN found in Portugal remains elusive. Several hypotheses may be considered regarding pathway analysis, basically from two general origins: North America or the Far East (Japan or China). World trade of wood products such as timber, wooden crates, palettes, etc… play an important role in the potential dissemination of the pinewood nematode. In fact, human activities involving the movement of wood products may be considered the single most important factor in spreading of the PWN. Despite the dedicated and concerted actions of government agencies, this disease continues to spread. Very recently (2006), in Portugal, forestry and phytosanitary authorities (DGRF and DGPC) have announced a new strategy for the control and ultimately the erradication of the nematode, under the coordination of the national program for the control of the pinewood nematode (PROLUNP). Research regarding the bioecology of the nematode and insect as well as new detection methods, e.g., involving real-time PCR, has progressed since 1999. International agreements (GATT, WTO) and sharing of scientific information is of paramount importance to effectively control the nematode and its vector, and thus protect our forest ecosystems and forest economy.

The Pine Wood Nematode: a personal view

The first report of the disease (“pine wilt disease”) associated with the pinewood nematode, goes back to 1905, when Yano reported an unusual decline of pines from Nagasaki. For a long time thereafter, the cause of he disease was sought, but without success. Because of the large number of insect species that were usually seen around and on infected trees, it had always been assumed that the causal agent would prove to be one of these. However, in 1971, Kiyohara and Tokushike found a nematode of the genus Bursaphelenchus in infected trees. The nematode found was multiplied on fungal culture, inoculated into healthy trees and then re-isolated from the resulting wilted trees. The subsequent published reports were impressive: this Bursaphelenchus species could kill fully-grown trees within a few months in the warmer areas of Japan, and could destroy complete forests of susceptible pine species within a few years. Pinus densiflora, P. thunbergii und P. luchuensis were particularly affected. In 1972, Mamiya and Kiyohara described the new species of nematode extracted from the wood of diseased pines; it was a named Bursaphelenchus lignicolus. Since 1975, the species has spread to the north of Japan, with the exception of the most northerly prefectures. In 1977, the loss of wood in the west of the country reached 80%. Probably as a result of unusually high summer temperatures and reduced rainfall in the years 1978 and 1979, the losses were more than 2 million m3 per year. From the beginning, B. lignicolus was always considered by Japanese scientists to be an exotic pest. But where did it come from? That this nematode could also cause damage in the USA became clear in 1979 when B. lignicolus was isolated in great numbers from wood of a 39 year-old pine tree (Pinus nigra) in Missouri which had suddenly died after the colour of its needles changed to a reddish-brown colour (Dropkin und Foudin, 2 1979). In 1981, B. lignicolus was synonymised by Nickle et al. with B. xylophilus which had been found for the first time in the USA as far back as 1929, and reported by Steiner and Buhrer in 1934. It had originally been named Aphelenchoides xylophilus, the wood-inhabiting Aphelenchoides but was recognised by Nickle, in 1970,to belong in the genus Bursaphelenchus. Its common name in the USA was the "pine wood nematode" (PWN. After its detection in Missouri, it became known that B. xylophilus was widespread throughout the USA and Canada. It occurred there on native species of conifers where, as a rule, it did not show the symptoms of pine wilt disease unless susceptible species were stressed eg., by high temperature. This fact was an illuminating piece of evidence that North America could be the homeland of PWN. Dwinell (1993) later reported the presence of B. xylophilus in Mexico. The main vector of the PWN in Japan was shown to be the long-horned beetle Monochamus alternatus, belonging to the family Cerambycidae. This beetle lays its eggs in dead or dying trees where the developing larvae then feed in the cambium layer. It was already known in Japan in the 19th century but in the 1930s, it was said to be present in most areas of Japan, but was generally uncommon. However, with the spread of the pine wilt disease, and the resulting increase of weakened trees that could act as breeding sites for beetles, the populations of Monochamus spp. increased significantly In North America, other Monochamus species transmit PWN, and the main vector is M. carolinensis. In Japan, there are also other, less efficient vectors in the genus Monochamus. Possibly, all Monochamus species that breed in conifers can transmit the PWN. The occasional transmission by less efficient species of Monochamus or by some of the many other beetle genera in the bark or wood is of little significance. In Europe, M. galloprovincialis and M. sutor transmits the closely related species B. mucronatus. Some speculate that these two insect species are “standing by” and waiting for the arrival of B. xylophilus. In 1982, the nematode was detected and China. It was first found in dead pines near the Zhongshan Monument of Nanjing (CHENG et. al. 1983); 265 trees were then killed by pine wilt disease. Despite great efforts at eradication in China, the nematode spread further and pine wilt disease has been 3 reported from parts of the provinces of Jiangsu, Anhui, Guangdong, Shandong, Zhejiang and Hubei (YANG, 2003). In 1986, the spread of the PWN to Taiwan was discovered and in 1989, the nematode was reported to be present in the Republic of Korea where it had first been detected in Pinus thunbergii and P. densiflora. It was though to have been introduced with packing material from Japan. PWN was advancing. In 1984, B. xylophilus was found in wood chips imported into Finland from the USA and Canada, and this was the impetus to establish phytosanitary measures to prevent any possible spread into Europe. Finland prohibited the import of coniferous wood chips from these sources, and the other Nordic countries soon followed suit. EPPO (the European and Mediterranean Plant Protection Organization) made a recommendation to its member countries in 1986 to refuse wood imports from infested countries. With its Directive of 1989 (77/93 EEC), the European Community (later called the European Union or EU) recognised the potential danger of B. xylophilus for European forests and imposed restrictions on imports into the Europe. PWN was placed on the quarantine list of the EU and also of other European countries. Later, in 1991, a dispensation was allowed by the Commission of the EU(92/13 EEC) for coniferous wood from North America provided that certain specified requirements were fulfilled that would prevent introduction.

Evaluation of the in vitro biological activities of extracts from carob tree and mediterranean oaks

Dissertação mest., Engenharia Biológica, Universidade do Algarve, 2009

Methylamine as true template and TEAOH as purifying agent: unexpected roles of current organic additives in the hydrothermal synthesis of microporous aluminophosphates

Methylamine (MA), TEA+ and water were shown to play a concerted role during the synthesis of two new aluminophosphates IST-1 and IST-2. Both structures start to nucleate after the dramatic change of the gel composition due to preliminary interactions between TEA+ cations.

Chemical and microbial changes during the natural fermentation of strawberry tree (Arbutus unedo L.) fruits

Aguardente de medronho is the name given in Portugal to a spirit made from the fermented fruit of Arbutus unedo (strawberry tree), a plant grown in the Mediterranean region. In order to gain a better understanding of the fermentation process, as it is performed in the farms, a natural fermentation with wild microbiota was carried out during 36 days, and some physicochemical and microbiological parameters were studied. The microbial parameters analyzed were total viable, lactic and acetic acids bacteria, and yeast counts. The physicochemical parameters monitored were sugars, minerals, ethanol, organic acids and pH. Yeasts were the main responsible for the fermentation of the fruits, as the lactic and acetic acids bacteria are absent. As the fermentation progressed, the sugars increased during the first 2 days and gradually decreased along the fermentation period. Maintaining the good quality of the product could contribute to the preservation and valorization of traditional resources that are of great importance to prevent their disappearance.

Entomofauna associated with the olive tree in southern Portugal

Since 2004 several studies have been carried out in order to identify the main insect species that usually inhabiting the olive ecosystem. The field trials have taken place in two olive groves, one situated in Olhão and the other one in Loulé, both in Algarve and also under Integrated Pest Management (IPM). The sampling techniques used differ according to their purpose (sticky traps, pheromone traps, pitfall traps and samples of aerial parts of the trees such as inflorescences, leaves, fruits and branches). Results showed that the main insect pests of olive tree in southern Portugal were the olive fruit fly Bactrocera oleae Gmelin (Diptera: Tephritidae) and the olive moth Prays oleae Bernard (Lepidoptera: Hyponeumetidae). Other insect pests were also found in our olive groves namely the olive psyllid Euphyllura olivina Costa (Homoptera: Psyllidae), the olive dark beetle Phloeotribus scarabaeoides Bernard (Coleoptera: Curculionidae), the mediterranean black scale Saissetia oleae (Olivier) (Homoptera: Coccidae) and the olive thrip Liothripes oleae Costa (Thysanoptera: Phlaeothripidae). Concerning the auxiliary insects that were found in our olives groves they belong to the following orders and families: Diptera (Syrphidae), Coleoptera (Carabidae, Coccinelidae and Staphylinidae), Hemiptera (Anthocoridae and Miridae), Neuroptera (Chrysopidae) and Hymenoptera (Braconidae, Encyrtidae, Eulophidae, Formicidae and Trichogrammatidae).