Search

We decomposed density functional theory charge densities of 53 nitroaromatic molecules into atom-centered electric multipoles using the distributed multipole analysis that provides a detailed picture of the molecular electronic structure. Three electric multipoles, ∑▒〖Q_0 (NO_2)〗 (the charge of the nitro groups), ∑▒〖Q_1 (NO_2)〗 (the total dipole, i.e., polarization, of the nitro groups), ∑▒〖Q_2 (C) 〗 (the total electron delocalization of the C ring atoms), and the number of explosophore groups (#NO_2) were selected as features for a comprehensive machine learning (ML) investigation. The target property was the impact sensitivity h_50 (cm) values quantified by drop-weight measurements. After a preliminary screening of 42 ML algorithms, four were selected based on the lowest root mean square errors: Extra Trees, Random Forests, Gradient Boosting, and AdaBoost. The predicted h_50 values of molecules having very different sensitivities for the four algorithms are in the range 19% - 28% compared to experimental data. The most important properties for predicting h_50 are the electron delocalization in the ring atoms and the polarization of the nitro groups with averaged weights of 39% and 35%, followed by the charge (16%) and number (10%) of nitro groups. A significant result is how the contribution of these properties to h_50 depends on its sensitivities: for the most sensitive explosives (h_50 up to ~ 50 cm), the four properties contribute to reducing h_50, and for intermediate ones (~ 50 cm ≲ h_50 ≲ 100 cm) #NO_2 and ∑▒〖Q_1 (NO_2)〗 contribute to increasing it and the other two properties to reducing it. For highly insensitive explosives (h_50≳ 200 cm), all four properties essentially contribute to increasing it. These results furnish a consistent molecular basis of the sensitivities of known explosives that also can be used for developing safer new ones.

O gerenciamento de riscos é um dos principais fatores atribuídos ao sucesso dos projetos porém, muitos não auferem os resultados esperados por falhas na etapa de planejamento. A utilização de ferramentas de quantificação de riscos usualmente é baixa e, devido à natureza singular dos projetos, torna-se difícil a utilização de dados históricos. Portanto, a consulta de um especialista é essencial para o planejamento de risco, embora tal opinião possa conter um alto grau de incerteza. Esse trabalho propõe uma metodologia que utiliza a Lógica Fuzzy e permite a estimação da probabilidade de ocorrência de riscos na análise quantitativa pelo levantamento de seus atributos, com base na opinião especializada, reduzindo a subjetividade. Por intermédio da sua aplicação em um estudo de caso, verifica-se que, em média, a probabilidade informada pelo especialista com base na sua experiência difere em 9,58% daquela encontrada pelo cálculo do valor através da extração dos atributos. O método mostra-se eficaz, portanto, na redução da subjetividade pois extrai e calcula fatores que pesam na escolha da probabilidade, melhorando a avaliação dos riscos.

Hammett's constants quantify the electron or electron acceptor power of a chemical group bonded to an aromatic ring. Their experimental values have been successfully used in a large variety of applications, but some of them may have inconsistent values or were not measured. For this reason, developing an accurate and consistent set of Hammett's values is paramount. In this work, we employed the machine learning (ML) regression algorithms Decision Tree Regressor, the neural network Multilayer Perceptron Regressor, and Lasso Lars IC in a cross-validation (CV) approach combined with quantum chemical calculations of atomic charges to estimate theoretically the new Hammett's constants for 90 chemical donor or acceptor groups by employing different types of quantum chemical atomic charges of the groups as input properties. New 219 sigma values, including previously unknown ones, are proposed for 90 chemical donor or acceptor groups by employing different types of quantum chemical atomic charges of the groups as input properties. The different substituent groups were bonded to benzene and meta- and para-substituted benzoic acid derivatives. Among the investigated atomic charge methods (Mulliken, Lwdin, Hirshfeld, and ChelpG), Hirshfeld's method showed the best regressions for most of the different kinds of sigma values. For each type of Hammett constant, linear expressions depending only on the atomic charges of the group were obtained. Correlation coefficients as high as 0.945, mean squared errors (MSE) as low as 0.004, and root mean square errors (RMSE) as low 0.062, were found. The ML approach, in most cases, showed very close predictions to the original experimental values, with the values from meta- and para-substituted benzoic acid derivatives showing the most accurate values. A new consistent set of Hammetts constants is presented, as well as simple equations for predicting new values for groups not included in the original set of 90.

Nos últimos anos, sistemas de reconhecimento automático de fala evoluíram de regras rígidas para modelos probabilísticos, graças ao avanço em redes neurais. No entanto, locutores podem estar expostos a ruídos, o que prejudica a transcrição da fala. Assim, este trabalho tem por objetivo avaliar a aplicação de redes neurais no reconhecimento automático de fala robusto a ruídos, mais especificamente, àqueles provenientes do maquinário da indústria do petróleo. Para atingir o objetivo, foi construída uma base de ruídos representativos, e, nos experimentos, o resultado da média do CER para os modelos desenvolvidos com o mesmo tipo de ruído foi de 0,421984, sendo a SNR do treino a mesma do teste, contra 0,522851 quando tais relações são diferentes.

Ad hoc teamwork is a research topic in multi-agent systems whereby an agent (the "ad hoc agent") must successfully collaborate with a set of unknown agents (the "teammates") without any prior coordination or communication protocol. However, research in ad hoc teamwork is predominantly focused on agent-only teams, but not in agent-human teams, which we believe is an exciting research avenue and has enormous application potential in human-robot teams. This paper will tap into this potential by proposing HOTSPOT, the first framework for ad hoc teamwork in human-robot teams. Our framework comprises two main modules, addressing the two key challenges in the interaction between a robot acting as the ad hoc agent and human teammates. First, a decision-theoretic module that is responsible for all task-related decision making (task identification, teammate identification, and planning). Second, a communication module that uses natural language processing in order to parse all communication between the robot and the human. To evaluate our framework, we use a task where a mobile robot and a human cooperatively collect objects in an open space, illustrating the main features of our framework in a real-world task.

espanolEste trabajo Contiene la solucion numerica de la ecuacion KdV usando el metodo de Petrov-Galerkin-Wavelet. Lo interesante es poder calcular las integrales Wavelets, usando Wavelets Biortogonales, las propiedades de simetria permiten que los calculos se reduzcan ostensiblemente. Aqui aplicaremos conceptos del analisis funcional y la teoria de distribuciones inmersos en el calculo de la derivada debil o derivada distribucional. Hasta obtener graficamente la solucion numerica y la solucion analitica de esta ecuacion muy usada en la parte de la tecnologia deondas y comunicaciones, como tambien en la reconstruccion de imagenes. Recientemente, los metodos de wavelet se aplican a la solucion numerica de ecuaciones diferenciales parciales, trabajos pioneros en esta direccion son las de Beylkin, Dahmen, Jaffard y Glowinski, entre otros. EnglishThis work contains the numerical solution of the KdV equation using the Petrov-Galerkin-Wavelet method. The interesting thing is to be able to calculate Wavelet integrals, using Biorthogonal Wavelets, the properties of symmetry allow the calculations to be significantly reduced. Here we will apply concepts of functional analysis and the theory of distributions immersed in the calculation of the weak derivative or distributional derivative. To obtain graphically the numerical solution and the analytical solution of this equation very used in the part of the wave and communications technology, as well as in the reconstruction of images. Recently, wavelet methods are applied to the numerical solution of partial differential equations, pioneering works in this direction are those of Beylkin, Dahmen, Jaffard and Glowinski, among others.

The study of Artificial Intelligence and, more specifically, Machine learning in games is of great interest to the gaming industry due to their wide application in several scenarios and their capabilities of simulating human behavior by non-playable characters. In online multiplayer scenarios, one of the greatest concerns is player disconnections and how to replace this player with a "good" replacement bot. In this work, we propose a machine learning based methodology to simulate the behavior of players that learns from their gaming history that generates more balance in the game. Our work uses Multi Layer Perceptron Neural Networks evaluated in a classic card game called Hearts, in order to emulate some previously defined behaviors. The results obtained in the experiments indicate that the proposed method has very good performance, since all generated models have managed to approach similar amount of victories when comparing to the behaviors that they were trained with. Through the evaluation of the results of 10,000 matches, with gameseeds of different matches used for training, the best result was for the model Shooter versus 3 Sheriffs getting 95.5% of the amount of wins compared to their particular bot. We also conclude that behavior learning is also clear on the difference of wins in all results depending on opponent skills, i.e., opponents who were difficult to win remain difficult to win in the simulated environment.

Unmaned Aerial Systems (UAS) is a subject with great appeal, nowadays. Suitable applications for this kind of vehicles are countless. This work presents a study on scene matching (navigation with global positioning using image registration) in GPS denied environments. Usually, the problem is solved by fusing inertial data with other sources of displacement measurements like simultaneous localization and mapping or visual odometry. Although helpful, those methods establish a navigation system based on relative positioning, since they are limited to foreseeing displacements from previous states. Image registration can refresh the UAS position with georeferenced data, i.e., an absolute global position. This work reaches that goal through a detailed analysis of methods capable of extracting image information (e.g, edges or other invariant key points), enabling the registration process and consequently the estimation of position. Our results were quantified in terms of error estimation and time cost for computation. They have shown that good performance is achieved with a Convolutional Neural Network complemented with SURF approach.

This paper presents a real-time framework that combines depth data and infrared laser speckle pattern (ILSP) images, captured from a Kinect device, for static hand gesture recognition to interact with CAVE applications. At the startup of the system, background removal and hand position detection are performed using only the depth map. After that, tracking is started using the hand positions of the previous frames in order to seek for the hand centroid of the current one. The obtained point is used as a seed for a region growing algorithm to perform hand segmentation in the depth map. The result is a mask that will be used for hand segmentation in the ILSP frame sequence. Next, we apply motion restrictions for gesture spotting in order to mark each image as a `Gesture' or `Non-Gesture'. The ILSP counterparts of the frames labeled as "Gesture" are enhanced by using mask subtraction, contrast stretching, median filter, and histogram equalization. The result is used as the input for the feature extraction using a scale invariant feature transform algorithm (SIFT), bag-of-visual-words construction and classification through a multi-class support vector machine (SVM) classifier. Finally, we build a grammar based on the hand gesture classes to convert the classification results in control commands for the CAVE application. The performed tests and comparisons show that the implemented plugin is an efficient solution. We achieve state-of-the-art recognition accuracy as well as efficient object manipulation in a virtual scene visualized in the CAVE.

Statistics show that while large amounts of money are being invested in cybersecurity, the number of incidents continues to grow, with cyber attacks motivated by political and financial issues, many times funded by States as part of cyberwarfare. Although the general perception is that the occurrence of incidents is almost inevitable, the literature demonstrates that cybersecurity initiatives are often focused on prevention of incidents rather than its response, with many organizations often poorly prepared and ignoring key incident handling processes. Some initiatives were proposed in order to fill this gap, one of them being the VERIS framework, a "vocabulary for event recording and incident sharing." VERIS goal is to provide a basis for incident documentation, at the same time allowing the sharing of anonymized data to a community database, hence providing metrics for use within organizations or among external parties. As VERIS is a framework focused on information gathering and sharing, this work proposes the extension of the model from its original JSON representation to an OWL ontology, one of the main tools of the Semantic Web initiative, used for knowledge representation and strongly tied to the idea of information sharing. This work focus on the advantages of using such representation for incident handling.

Malware Analysis and Classification Systems use static and dynamic techniques, in conjunction with machine learning algorithms, to automate the task of identification and classification of malicious codes. Both techniques have weaknesses that allow the use of analysis evasion techniques, hampering the identification of malwares. In this work, we propose the unification of static and dynamic analysis, as a method of collecting data from malware that decreases the chance of success for such evasion techniques. From the data collected in the analysis phase, we use the C5.0 and Random Forest machine learning algorithms, implemented inside the FAMA framework, to perform the identification and classification of malwares into two classes and multiple categories. In our experiments, we showed that the accuracy of the unified analysis achieved an accuracy of 95.75% for the binary classification problem and an accuracy value of 93.02% for the multiple categorization problem. In all experiments, the unified analysis produced better results than those obtained by static and dynamic analyzes isolated.

Num contexto de crescente dependência dos sistemas computacionais e da Internet, as instituições têm investido cada vez mais recursos para garantir a Segurança da Informação. Apesar dos inúmeros esforços, os incidentes continuam crescendo em frequência [CERT.br 2017] e gravidade, evidenciando a necessidade de processos mais eficientes de resposta a incidentes. Uma das ameaças em franca expansão são os Crypto Ransomwares. Este trabalho realiza um estudo de caso do WannaCry – um ransomware bastante peculiar que causou pânico no início de 2017 – com o objetivo de identificar oportunidades de melhoria nos sistemas e processos de resposta a incidentes.

The cybernetic environment is hostile. An infinitude of gadgets with access to fast networks and the massive use of social networks considerably raised the number of vectors of malware propagation. Deep Learning models achieved great results in many different areas, including security-related tasks, such as static and dynamic malware analysis. This paper details a deep learning approach to the problem of malware classification using only the disassembled artifact's code as input. We show competitive performance when comparing to other solutions that use a higher degree of knowledge.

We present Entropy Guided Transformation Learning models for three Portuguese Language Processing tasks: Part-of-Speech Tagging, Noun Phrase Chunking and Named Entity Recognition. For Part-of-Speech Tagging, we separately use the Mac-Morpho Corpus and the Tycho Brahe Corpus. For Noun Phrase Chunking, we use the SNR-CLIC Corpus. For Named Entity Recognition, we separately use three corpora: HAREM, MiniHAREM and LearnNEC06. For each one of the tasks, the ETL modeling phase is quick and simple. ETL only requires the training set and no handcrafted templates. ETL also simplifies the incorporation of new input features, such as capitalization information, which are sucessfully used in the ETL based systems. Using the ETL approach, we obtain state-of-the-art competitive performance in all six corpora-based tasks. These results indicate that ETL is a suitable approach for the construction of Portuguese corpus-based systems.

Transformation Based Learning (TBL) is a Machine Learning technique frequently used in some Natural Language Processing (NLP) tasks. TBL uses rule templates to identify error-correcting patterns. A critical requirement in TBL is the availability of a problem domain expert to build these rule templates. In this work, we propose an evolutionary approach based on Genetic Algorithms to automatically implement the template generation process. Additionally, we report our findings on five experiments with useful NLP tasks. We observe that our approach provides template sets with a mean loss of performance of 0.5% when compared to human built templates

A transformada de Burrows-Wheeler, baseada na ordenação de contextos, transforma uma seqüência de caracteres em uma nova seqüência mais facilmente comprimida por um algoritmo que explore grandes seqüências de repetições de caracteres. Aliado a recodificação do MoverParaFrente e seguida de uma codificação para os inteiros gerados, eles formam uma nova família de compressores, que possuem excelentes taxas de compressão, com boas performances nos tempos de compressão e descompressão. Este trabalho examina detalhadamente essa transformada, suas variações e algumas alternativas para os algoritmos utilizados em conjunto com ela. Como resultado final, apresentamos uma combinação de estratégias que produz taxas de compressão para texto melhores do que as oferecidas pelas implementações até aqui disponíveis. The Burrows-Wheeler Transform, based on sorting of contexts, transforms a sequence of characters into a new sequence easier to compress by an algorithm that exploits long sequences of repeted characters. Combined with the coding provided by the MoveToFront Algorithm and followed by a codification for the generated integers, they propose a new family of compressors, that achieve excellent compression rates with good time performances in compression and decompression. This work examines detaildedly this transform, its variations and some alternatives for the algorithms used together with it. As a final result, we present a combination of strategies that producescompression rates for text data that are better than those offered by implementations available nowadays.

The authentication of users on a Virtual Learning Environment (VLE) is, in general, punctual and intrusive, occurring when the user connects to the environment, by typing his password. Such approach allows, after the initial login, that unauthenticated users take the role of authenticated users and perform tasks in the environment, causing, among other things, distortions in the perception about the academic performance of students. The objective of this work is, thus, to propose a mechanism to execute periodic and non-intrusive authentications of users in VLEs. The proposed mechanism uses machine learning techniques to build recognition models based on the keystroke dynamics of users and it is also independent of the used VLE. A prototype of the proposed mechanism, integrated with Moodle, was implemented and applied to a postgraduate course with seventeen users. The recognition models generated by the prototype in the case study showed a performance above 92% of accuracy, which is a positive indication about the viability of the utilization of the proposed mechanism.