Machine vision and planning applied on assembby line of multiple products

This article describes the use of Artificial Intelligence (IA) techniques applied in cells of a manufacturing system. Machine Vision was used to identify pieces and their positions of two different products to be assembled in the same productive line. This information is given as input for an IA planner embedded in the manufacturing system. Therefore, initial and final states are sent automatically to the planner capable to generate assembly plans for a robotic cell, in real time.

Balancing Exploration and Exploitation: A New Algorithm for Active Machine Learning

Active machine learning algorithms are used when large numbers of unlabeled examples are available and getting labels for them is costly (e.g. requiring consulting a human expert). Many conventional active learning algorithms focus on refining the decision boundary, at the expense of exploring new regions that the current hypothesis misclassifies. We propose a new active learning algorithm that balances such exploration with refining of the decision boundary by dynamically adjusting the probability to explore at each step. Our experimental results demonstrate improved performance on data sets that require extensive exploration while remaining competitive on data sets that do not. Our algorithm also shows significant tolerance of noise.

SimSight: A Virtual Machine Based Dynamic Call Graph Generator

One problem with using component-based software development approach is that once software modules are reused over generations of products, they form legacy structures that can be challenging to understand, making validating these systems difficult. Therefore, tools and methodologies that enable engineers to see interactions of these software modules will enhance their ability to make these software systems more dependable. To address this need, we propose SimSight, a framework to capture dynamic call graphs in Simics, a widely adopted commercial full-system simulator. Simics is a software system that simulates complete computer systems. Thus, it performs nearly identical tasks to a real system but at a much lower speed while providing greater execution observability. We have implemented SimSight to generate dynamic call graphs of statically and dynamically linked functions in x86/Linux environment. A case study illustrates how we can use SimSight to identify sources of software errors. We then evaluate its performance using 12 integer programs from SPEC CPU2006 benchmark suite.

An ice machine adapted into an autonomous photovoltaic system without batteries using a variable-speed drive

The adaptation of a commercially available ice machine for autonomous photovoltaic operation without batteries is presented. In this adaptation a 1040 W(p) photovoltaic array directly feeds a variable-speed drive and a 24 V(dc) source. The drive runs an induction motor coupled by belt-and-pulley to an open reciprocating compressor, while the dc source supplies a solenoid valve and the control electronics. Motor speed and refrigerant evaporation pressure are set aiming at continuously matching system power demand to photovoltaic power availability. The resulting system is a simple integration of robust, standard, readily available parts. It produces 27 kg of ice in a clear-sky day and has ice production costs around US$0.30/kg. Although a few machine features might be specific to Brazil, its technical and economical guidelines are applicable elsewhere. Copyright (C); 2010 John Wiley & Sons, Ltd.

Gradients in N-cycling attributes along forestry and agricultural land-use systems are indicative of soil capacity for N supply

Indicators of soil quality associated with N-cycling were assessed under different land-use systems (native forest NAT, reforestation with Araucaria angustifolia or Pinus taeda and agricultural use AGR) to appraise the effects on the soil potential for N supply. The soil total N ranged from 2 to 4 g/kg (AGR and NAT, respectively), and the microbial biomass N ranged from 80 to 250 mg/kg, being higher in NAT and A. angustifolia, and lower in P. taeda and AGR sites. Activities of asparaginase (ca. 50200 mg NH4+-N/kg per h), glutaminase (ca. 200800 mg NH4+-N/kg per h) and urease (ca. 80200 mg NH4+-N/kg/h) were also more intense in the NAT and A. angustifolia-reforested soils, indicating greater capacity for N mineralization. The NAT and AGR soils showed the highest and the lowest ammonification rate, respectively (ca. 1 and 0.4 mg NH4+-N/kg per day), but the inverse for nitrification rate (ca. 12 and 26%), indicating a low capacity for N supply, in addition to higher risks of N losses in the AGR soil. A multivariate analysis indicated more similarity between NAT and A. angustifolia-reforested sites, whilst the AGR soil was different and associated with a higher nitrification rate. In general, reforestation with the native species A. angustifolia had less impact than reforestation with the exogenous species P. taeda, considering the soil capacity for N supply. However, AGR use caused more changes, generally decrease in indicators of N-cycling, showing a negative soil management effect on the sustainability of this agroecosystem.

Heuristic methods for the single machine scheduling problem with different ready times and a common due date

The single machine scheduling problem with a common due date and non-identical ready times for the jobs is examined in this work. Performance is measured by the minimization of the weighted sum of earliness and tardiness penalties of the jobs. Since this problem is NP-hard, the application of constructive heuristics that exploit specific characteristics of the problem to improve their performance is investigated. The proposed approaches are examined through a computational comparative study on a set of 280 benchmark test problems with up to 1000 jobs.

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.

Using Machine Learning Classifiers to Assist Healthcare-Related Decisions: Classification of Electronic Patient Records

Surveillance Levels (SLs) are categories for medical patients (used in Brazil) that represent different types of medical recommendations. SLs are defined according to risk factors and the medical and developmental history of patients. Each SL is associated with specific educational and clinical measures. The objective of the present paper was to verify computer-aided, automatic assignment of SLs. The present paper proposes a computer-aided approach for automatic recommendation of SLs. The approach is based on the classification of information from patient electronic records. For this purpose, a software architecture composed of three layers was developed. The architecture is formed by a classification layer that includes a linguistic module and machine learning classification modules. The classification layer allows for the use of different classification methods, including the use of preprocessed, normalized language data drawn from the linguistic module. We report the verification and validation of the software architecture in a Brazilian pediatric healthcare institution. The results indicate that selection of attributes can have a great effect on the performance of the system. Nonetheless, our automatic recommendation of surveillance level can still benefit from improvements in processing procedures when the linguistic module is applied prior to classification. Results from our efforts can be applied to different types of medical systems. The results of systems supported by the framework presented in this paper may be used by healthcare and governmental institutions to improve healthcare services in terms of establishing preventive measures and alerting authorities about the possibility of an epidemic.

Can neuroimaging be used as a support to diagnosis of borderline personality disorder? An approach based on computational neuroanatomy and machine learning

Several recent studies in literature have identified brain morphological alterations associated to Borderline Personality Disorder (BPD) patients. These findings are reported by studies based on voxel-based-morphometry analysis of structural MRI data, comparing mean gray-matter concentration between groups of BPD patients and healthy controls. On the other hand, mean differences between groups are not informative about the discriminative value of neuroimaging data to predict the group of individual subjects. In this paper, we go beyond mean differences analyses, and explore to what extent individual BPD patients can be differentiated from controls (25 subjects in each group), using a combination of automated-morphometric tools for regional cortical thickness/volumetric estimation and Support Vector Machine classifier. The approach included a feature selection step in order to identify the regions containing most discriminative information. The accuracy of this classifier was evaluated using the leave-one-subject-out procedure. The brain regions indicated as containing relevant information to discriminate groups were the orbitofrontal, rostral anterior cingulate, posterior cingulate, middle temporal cortices, among others. These areas, which are distinctively involved in emotional and affect regulation of BPD patients, were the most informative regions to achieve both sensitivity and specificity values of 80% in SVM classification. The findings suggest that this new methodology can add clinical and potential diagnostic value to neuroimaging of psychiatric disorders. (C) 2012 Elsevier Ltd. All rights reserved.

Estimación de la potencia eólica en una zona mediante el apoyo de estaciones meteorológicas de referencia y el empleo de técnicas estadísticas no paramétricas, funcionales y de machine learning: aplicación a las islas Canarias

Programa de doctorado: Tecnología industrial

Automatic (data-based) learning of expressive indicators for machine failure detection : a proposal

Máster Universitario en Sistemas Inteligentes y Aplicaciones Numéricas en Ingeniería (SIANI)

Predizione dell'effetto delle mutazioni sulla variazione della stabilita' proteica con metodi di "machine-learning".

La tesi consiste nell’implementare un software in grado a predire la variazione della stabilità di una proteina sottoposta ad una mutazione. Il predittore implementato fa utilizzo di tecniche di Machine-Learning ed, in particolare, di SVM. In particolare, riguarda l’analisi delle prestazioni di un predittore, precedentemente implementato, sotto opportune variazioni dei parametri di input e relativamente all’utilizzo di nuova informazione rispetto a quella utilizzata dal predittore basilare.

Machine learning methods for prediction of disulphide bonding states of cysteine residues in proteins

The goal of this thesis work is to develop a computational method based on machine learning techniques for predicting disulfide-bonding states of cysteine residues in proteins, which is a sub-problem of a bigger and yet unsolved problem of protein structure prediction. Improvement in the prediction of disulfide bonding states of cysteine residues will help in putting a constraint in the three dimensional (3D) space of the respective protein structure, and thus will eventually help in the prediction of 3D structure of proteins. Results of this work will have direct implications in site-directed mutational studies of proteins, proteins engineering and the problem of protein folding. We have used a combination of Artificial Neural Network (ANN) and Hidden Markov Model (HMM), the so-called Hidden Neural Network (HNN) as a machine learning technique to develop our prediction method. By using different global and local features of proteins (specifically profiles, parity of cysteine residues, average cysteine conservation, correlated mutation, sub-cellular localization, and signal peptide) as inputs and considering Eukaryotes and Prokaryotes separately we have reached to a remarkable accuracy of 94% on cysteine basis for both Eukaryotic and Prokaryotic datasets, and an accuracy of 90% and 93% on protein basis for Eukaryotic dataset and Prokaryotic dataset respectively. These accuracies are best so far ever reached by any existing prediction methods, and thus our prediction method has outperformed all the previously developed approaches and therefore is more reliable. Most interesting part of this thesis work is the differences in the prediction performances of Eukaryotes and Prokaryotes at the basic level of input coding when ‘profile’ information was given as input to our prediction method. And one of the reasons for this we discover is the difference in the amino acid composition of the local environment of bonded and free cysteine residues in Eukaryotes and Prokaryotes. Eukaryotic bonded cysteine examples have a ‘symmetric-cysteine-rich’ environment, where as Prokaryotic bonded examples lack it.

Machine-learning methods for structure prediction of β-barrel membrane proteins

Different types of proteins exist with diverse functions that are essential for living organisms. An important class of proteins is represented by transmembrane proteins which are specifically designed to be inserted into biological membranes and devised to perform very important functions in the cell such as cell communication and active transport across the membrane. Transmembrane β-barrels (TMBBs) are a sub-class of membrane proteins largely under-represented in structure databases because of the extreme difficulty in experimental structure determination. For this reason, computational tools that are able to predict the structure of TMBBs are needed. In this thesis, two computational problems related to TMBBs were addressed: the detection of TMBBs in large datasets of proteins and the prediction of the topology of TMBB proteins. Firstly, a method for TMBB detection was presented based on a novel neural network framework for variable-length sequence classification. The proposed approach was validated on a non-redundant dataset of proteins. Furthermore, we carried-out genome-wide detection using the entire Escherichia coli proteome. In both experiments, the method significantly outperformed other existing state-of-the-art approaches, reaching very high PPV (92%) and MCC (0.82). Secondly, a method was also introduced for TMBB topology prediction. The proposed approach is based on grammatical modelling and probabilistic discriminative models for sequence data labeling. The method was evaluated using a newly generated dataset of 38 TMBB proteins obtained from high-resolution data in the PDB. Results have shown that the model is able to correctly predict topologies of 25 out of 38 protein chains in the dataset. When tested on previously released datasets, the performances of the proposed approach were measured as comparable or superior to the current state-of-the-art of TMBB topology prediction.