Machine learning and small robot navigation

Developing successful navigation and mapping strategies is an essential part of autonomous robot research. However, hardware limitations often make for inaccurate systems. This project serves to investigate efficient alternatives to mapping an environment, by first creating a mobile robot, and then applying machine learning to the robot and controlling systems to increase the robustness of the robot system. My mapping system consists of a semi-autonomous robot drone in communication with a stationary Linux computer system. There are learning systems running on both the robot and the more powerful Linux system. The first stage of this project was devoted to designing and building an inexpensive robot. Utilizing my prior experience from independent studies in robotics, I designed a small mobile robot that was well suited for simple navigation and mapping research. When the major components of the robot base were designed, I began to implement my design. This involved physically constructing the base of the robot, as well as researching and acquiring components such as sensors. Implementing the more complex sensors became a time-consuming task, involving much research and assistance from a variety of sources. A concurrent stage of the project involved researching and experimenting with different types of machine learning systems. I finally settled on using neural networks as the machine learning system to incorporate into my project. Neural nets can be thought of as a structure of interconnected nodes, through which information filters. The type of neural net that I chose to use is a type that requires a known set of data that serves to train the net to produce the desired output. Neural nets are particularly well suited for use with robotic systems as they can handle cases that lie at the extreme edges of the training set, such as may be produced by "noisy" sensor data. Through experimenting with available neural net code, I became familiar with the code and its function, and modified it to be more generic and reusable for multiple applications of neural nets.

Prediction Of Hydrological Models’ Uncertainty By A Committee Of Machine Learning-Models

This study presents an approach to combine uncertainties of the hydrological model outputs predicted from a number of machine learning models. The machine learning based uncertainty prediction approach is very useful for estimation of hydrological models' uncertainty in particular hydro-metrological situation in real-time application [1]. In this approach the hydrological model realizations from Monte Carlo simulations are used to build different machine learning uncertainty models to predict uncertainty (quantiles of pdf) of the a deterministic output from hydrological model . Uncertainty models are trained using antecedent precipitation and streamflows as inputs. The trained models are then employed to predict the model output uncertainty which is specific for the new input data. We used three machine learning models namely artificial neural networks, model tree, locally weighted regression to predict output uncertainties. These three models produce similar verification results, which can be improved by merging their outputs dynamically. We propose an approach to form a committee of the three models to combine their outputs. The approach is applied to estimate uncertainty of streamflows simulation from a conceptual hydrological model in the Brue catchment in UK and the Bagmati catchment in Nepal. The verification results show that merged output is better than an individual model output. [1] D. L. Shrestha, N. Kayastha, and D. P. Solomatine, and R. Price. Encapsulation of parameteric uncertainty statistics by various predictive machine learning models: MLUE method, Journal of Hydroinformatic, in press, 2013.

O novo sistema de análise prévia dos atos de concentração e a questão do Gun-Jumping: traçando parâmetros para as empresas

Em 29 de maio de 2012 entrou em vigor a Lei nº 12.529/2011, que introduziu no Brasil o sistema de análise prévia dos atos de concentração. Nesse novo regime, as empresas deverão preservar as condições de concorrência entre si e não mais poderão consumar a operação antes de sua aprovação pelo Conselho Administrativo de Defesa Econômica (CADE), sob pena de violarem as regras do sistema de análise prévia das operações, i.e., praticarem gun-jumping ilegal. Contudo, nem a Nova Lei, nem o Novo Regimento Interno do CADE especificaram quais práticas implicariam a consumação da operação. Dessa forma, o presente trabalho buscou identificar parâmetros, através da experiência americana e europeia e da análise de acordos de preservação da reversibilidade da operação, que pudessem auxiliar as empresas a conduzirem suas atividades no momento que antecede a aprovação da operação.

An economic model of gun control

Guns stolen from law-abiding households provide the principal source of guns for criminals. The lethality of crime instruments increases with the availability of guns, so the gun market is subject to externalities that generate excessive ownership and inadequate spending on protective measures to deter gun theft. One motive for gun ownership is self defense, and the gun market is subject to coordination failure: the more guns purchased lawfully, the more will be stolen by criminals, so the greater the incentive for lawful . consumers to purchase guns for self defense. As a result, there may be multiple equilibria in the gun market and more than one equilibrium crime rate. We show that a simple refundable deposit for guns will internalize the externalities in the gun market and may cause large downward jumps in gun ownership, the lethality of crime instruments, and the social costs of crime.

Al-based anodic oxide films structure observation using field emission gun scanning electron microscopy

In the present work, the anodic oxide films of Al, Al-Cu 4.5% and Al-Si 6.5% alloys are formed using direct and pulse current. In the case of Al-Cu and Al-Si alloys, the electrolyte used contains sulfuric acid and oxalic acid, meanwhile for Al the electrolyte contains sulfuric acid only. Al-Cu alloy was submitted to a heat treatment in order to decrease the effect of inter metallic phase theta upon the anodic film structure. Fractured samples were observed using a field emission gun scanning electron microscope JSM-6330F at (LME)/Brazilian Synchrotron Light Laboratory (LNLS), Campinas, SP, Brazil. The oxide film images enable evaluation of the pore size and form with a resolution similar to the transmission electron microscope (TEM) resolution. It is also observed that the anodizing process using pulse current produces an irregular structure of pore walls, and by direct cur-rent it is produced a rectilinear pore wall. (c) 2005 Elsevier B.V. All rights reserved.

Efeito da adição de óleos mineral e vegetal a acaricidas no controle do ácaro-da-leprose dos citros Brevipalpus phoenicis (Geijskes) (Acari: Tenuipalpide)

Com a finalidade de esclarecer os efeitos da adição de óleo vegetal e mineral aos acaricidas foi conduzido um ensaio de campo em 1994 no município de Viradouro, SP, utilizando-se de Assist, Triona e Natur'l Óleo, na dosagem de 500 mL por 100 litros de água, adicionados aos acaricidas: pyridaben nas formulações 200 CE e 750 PM, nas dosagens de 75 mL e 20 g; propargite 720 CE a 100 mL; óxido de fenbutatina 500 SC a 80 mL e cyhexatin 500 PM a 50 g. O delineamento estatístico adotado foi o de blocos casualizados. As aplicações foram feitas com pulverizador tipo pistola. Após a preparação da calda, foi determinado o pH. Empregou-se máquina de varredura e microscópio estereoscópico para as avaliações da população acarina. A adição de Natur'l Óleo pode afetar negativamente a eficiência do pyridaben 200 CE e 750 PM e cyhexatin 500 PM, no controle do ácaro-da-leprose. Triona e Assist não afetaram as eficiências dos acaricidas testados. Pelo índice de iodo, mediu-se o grau de insaturação das misturas dos acaricidas com Natur'l Óleo, concluindo-se que houve incorporação das moléculas dos acaricidas pelas ligações insaturadas do óleo; porém, isto não explica o diferente comportamento dos produtos no controle do ácaro da leprose dos citros.

Soil compaction by machine traffic and least limiting water range related to soybean yield

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Aquatic weed automatic classification using machine learning techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

HOW FAR do WE GET USING MACHINE LEARNING BLACK-BOXES?

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Safety illusion and error trap in a collectively-operated machine accident

Workplace accidents involving machines are relevant for their magnitude and their impacts on worker health. Despite consolidated critical statements, explanation centered on errors of operators remains predominant with industry professionals, hampering preventive measures and the improvement of production-system reliability. Several initiatives were adopted by enforcement agencies in partnership with universities to stimulate production and diffusion of analysis methodologies with a systemic approach. Starting from one accident case that occurred with a worker who operated a brake-clutch type mechanical press, the article explores cognitive aspects and the existence of traps in the operation of this machine. It deals with a large-sized press that, despite being endowed with a light curtain in areas of access to the pressing zone, did not meet legal requirements. The safety devices gave rise to an illusion of safety, permitting activation of the machine when a worker was still found within the operational zone. Preventive interventions must stimulate the tailoring of systems to the characteristics of workers, minimizing the creation of traps and encouraging safety policies and practices that replace judgments of behaviors that participate in accidents by analyses of reasons that lead workers to act in that manner.

A machine learning approach for genome-wide prediction of morbid and druggable human genes based on systems-level data

Background: The genome-wide identification of both morbid genes, i.e., those genes whose mutations cause hereditary human diseases, and druggable genes, i.e., genes coding for proteins whose modulation by small molecules elicits phenotypic effects, requires experimental approaches that are time-consuming and laborious. Thus, a computational approach which could accurately predict such genes on a genome-wide scale would be invaluable for accelerating the pace of discovery of causal relationships between genes and diseases as well as the determination of druggability of gene products.Results: In this paper we propose a machine learning-based computational approach to predict morbid and druggable genes on a genome-wide scale. For this purpose, we constructed a decision tree-based meta-classifier and trained it on datasets containing, for each morbid and druggable gene, network topological features, tissue expression profile and subcellular localization data as learning attributes. This meta-classifier correctly recovered 65% of known morbid genes with a precision of 66% and correctly recovered 78% of known druggable genes with a precision of 75%. It was than used to assign morbidity and druggability scores to genes not known to be morbid and druggable and we showed a good match between these scores and literature data. Finally, we generated decision trees by training the J48 algorithm on the morbidity and druggability datasets to discover cellular rules for morbidity and druggability and, among the rules, we found that the number of regulating transcription factors and plasma membrane localization are the most important factors to morbidity and druggability, respectively.Conclusions: We were able to demonstrate that network topological features along with tissue expression profile and subcellular localization can reliably predict human morbid and druggable genes on a genome-wide scale. Moreover, by constructing decision trees based on these data, we could discover cellular rules governing morbidity and druggability.

EIGENVALUES of FIBONACCI STOCHASTIC ADDING MACHINE

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)