Contagem automatizada de veículos utilizando segmentação estatística

In this work was developed a program capable of performing automatic counting of vehicles on roads. The problem of counting vehicles is using expensive techniques for its realization, techniques which often involve manual counting or degradation of the pavement. The main motivation for this work was the importance that the vehicle counting represents to the Traffic Engineer, being essential to analyze the performance of the roads, allowing to measure the need for installation of traffic lights, roundabouts, access ways, among other means capable of ensuring a continuous flow and safe for vehicles. The main objective of this work was to apply a statistical segmentation technique recently developed, based on a nonparametric linear regression model, to solve the segmentation problem of the program counter. The development program was based on the creation of three major modules, one for the segmentation, another for the tracking and another for the recognition. For the development of the segmentation module, it was applied a statistical technique combined with the segmentation by background difference, in order to optimize the process. The tracking module was developed based on the use of Kalman filters and application of simple concepts of analytical geometry. To develop the recognition module, it was used Fourier descriptors and a neural network multilayer perceptron, trained by backpropagation. Besides the development of the modules, it was also developed a control logic capable of performing the interconnection among the modules, mainly based on a data structure called state. The analysis of the results was applied to the program counter and its component modules, and the individual analysis served as a means to establish the par ameter values of techniques used. The find result was positive, since the statistical segmentation technique proved to be very useful and the developed program was able to count the vehicles belonging to the three goal..

Desenvolvimento de uma rede neuro-fuzzy para a previsão da carga

Pós-graduação em Engenharia Elétrica - FEIS

Utilização de redes neurais artificiais aplicadas na discriminação de padrões de doenças florestais

Pós-graduação em Ciência Florestal - FCA

Solid-state compounds of 2-methoxybenzylidenepyruvate with some bivalent metal ions - Synthesis, characterization and thermal behavior studies

Solid-state M-2-MeO-BP compounds, where M represents bivalent Mn, Fe, Co, Ni, Cu, Zn and 2-MeO-BP is 2-methoxybenzylidenepyruvate have been synthesized. Simultaneous thermogravinietry-differential thermal analysis (TG-DTA), differential scanning calorimetry (DSC), X-ray powder diffractometry, infrared spectroscopy, elemental analysis and complexometry were used to characterize and to study the thermal stability and thermal decomposition of these compounds. The results led to information about the composition, dehydration, crystallinity and thermal decomposition of the isolated compounds.

Utilização dos parâmetros físico-químicos e redes neurais artificiais na identificação dos méis de abelhas (Apis mellifera L.) produzidos no verão e inverno na microrregião de Campos de Jordão, São Paulo

The objective of this work was to typify, through physicochemical parameters, honey from Campos do Jordão’s microrregion, and verify how samples are grouped in accordance with the climatic production seasonality (summer and winter). It were assessed 30 samples of honey from beekeepers located in the cities of Monteiro Lobato, Campos do Jordão, Santo Antonio do Pinhal e São Bento do Sapucaí-SP, regarding both periods of honey production (November to February; July to September, during 2007 and 2008; n = 30). Samples were submitted to physicochemical analysis of total acidity, pH, humidity, water activity, density, aminoacids, ashes, color and electrical conductivity, identifying physicochemical standards of honey samples from both periods of production. Next, we carried out a cluster analysis of data using k-means algorithm, which grouped the samples into two classes (summer and winter). Thus, there was a supervised training of an Artificial Neural Network (ANN) using backpropagation algorithm. According to the analysis, the knowledge gained through the ANN classified the samples with 80% accuracy. It was observed that the ANNs have proved an effective tool to group samples of honey of the region of Campos do Jordao according to their physicochemical characteristics, depending on the different production periods.

Modelagem da irradiação direta na incidência normal em Botucatu: aprendizado de máquina, estatístico e linke

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Informationsgehalt von ERS-1/-2 SAR-Daten zur Erfassung der Arteninventare und des Zustandes landwirtschaftlich genutzter Böden und Vegetation

Auf einer drei Anbauperioden umfassenden Ground Truth Datenbasis wird der Informationsgehalt multitemporaler ERS-1/-2 Synthetic Aperture Radar (SAR) Daten zur Erfassung der Arteninventare und des Zustandes landwirtschaftlich genutzter Böden und Vegetation in Agrarregionen Bayerns evaluiert.Dazu wird ein für Radardaten angepaßtes, multitemporales, auf landwirtschaftlichen Schlägen beruhendes Klassifizierungsverfahren ausgearbeitet, das auf bildstatistischen Parametern der ERS-Zeitreihen beruht. Als überwachte Klassifizierungsverfahren wird vergleichend der Maximum-Likelihood-Klassifikator und ein Neuronales-Backpropagation-Netz eingesetzt. Die auf Radarbildkanälen beruhenden Gesamtgenauigkeiten variieren zwischen 75 und 85%. Darüber hinaus wird gezeigt, daß die interferometrische Kohärenz und die Kombination mit Bildkanälen optischer Sensoren (Landsat-TM, SPOT-PAN und IRS-1C-PAN) zur Verbesserung der Klassifizierung beitragen. Gleichermaßen können die Klassifizierungsergebnisse durch eine vorgeschaltete Grobsegmentierung des Untersuchungsgebietes in naturräumlich homogene Raumeinheiten verbessert werden. Über die Landnutzungsklassifizierung hinaus, werden weitere bio- und bodenphysikalische Parameter aus den SAR-Daten anhand von Regressionsmodellen abgeleitet. Im Mittelpunkt stehen die Paramter oberflächennahen Bodenfeuchte vegetationsfreier/-armer Flächen sowie die Biomasse landwirtschaftlicher Kulturen. Die Ergebnisse zeigen, daß mit ERS-1/-2 SAR-Daten eine Messung der Bodenfeuchte möglich ist, wenn Informationen zur Bodenrauhigkeit vorliegen. Hinsichtlich der biophysikalischen Parameter sind signifikante Zusammenhänge zwischen der Frisch- bzw. Trockenmasse des Vegetationsbestandes verschiedener Getreide und dem Radarsignal nachweisbar. Die Biomasse-Informationen können zur Korrektur von Wachstumsmodellen genutzt werden und dazu beitragen, die Genauigkeit von Ertragsschätzungen zu steigern.

Classificazione di brani musicali mediante reti neuronali artificiali

L'informatica musicale è una disciplina in continua crescita che sta ottenendo risultati davvero interessanti con l'impiego di sistemi artificiali intelligenti, come le reti neuronali, che permettono di emulare capacità umane di ascolto e di esecuzione musicale. Di particolare interesse è l'ambito della codifica di informazioni musicali tramite formati simbolici, come il MIDI, che permette un'analisi di alto livello dei brani musicali e consente la realizzazione di applicazioni sorprendentemente innovative. Una delle più fruttifere applicazioni di questi nuovi strumenti di codifica riguarda la classificazione di file audio musicali. Questo elaborato si propone di esporre i fondamentali aspetti teorici che concernono la classificazione di brani musicali tramite reti neuronali artificiali e descrivere alcuni esperimenti di classificazione di file MIDI. La prima parte fornisce alcune conoscenze di base che permettono di leggere gli esperimenti presenti nella seconda sezione con una consapevolezza teorica più profonda. Il fine principale della prima parte è quello di sviluppare una comparazione da diversi punti di vista disciplinari tra le capacità di classificazione musicale umane e quelle artificiali. Si descrivono le reti neuronali artificiali come sistemi intelligenti ispirati alla struttura delle reti neurali biologiche, soffermandosi in particolare sulla rete Feedforward e sull'algoritmo di Backpropagation. Si esplora il concetto di percezione nell'ambito della psicologia cognitiva con maggiore attenzione alla percezione uditiva. Accennate le basi della psicoacustica, si passa ad una descrizione delle componenti strutturali prima del suono e poi della musica: la frequenza e l'ampiezza delle onde, le note e il timbro, l'armonia, la melodia ed il ritmo. Si parla anche delle illusioni sonore e della rielaborazione delle informazioni audio da parte del cervello umano. Si descrive poi l'ambito che interessa questa tesi da vicino: il MIR (Music Information Retrieval). Si analizzano i campi disciplinari a cui questa ricerca può portare vantaggi, ossia quelli commerciali, in cui i database musicali svolgono ruoli importanti, e quelli più speculativi ed accademici che studiano i comportamenti di sistemi intelligenti artificiali e biologici. Si descrivono i diversi metodi di classificazione musicale catalogabili in base al tipo di formato dei file audio in questione e al tipo di feature che si vogliono estrarre dai file stessi. Conclude la prima sezione di stampo teorico un capitolo dedicato al MIDI che racconta la storia del protocollo e ne descrive le istruzioni fondamentali nonchè la struttura dei midifile. La seconda parte ha come obbiettivo quello di descrivere gli esperimenti svolti che classificano file MIDI tramite reti neuronali mostrando nel dettaglio i risultati ottenuti e le difficoltà incontrate. Si coniuga una presentazione dei programmi utilizzati e degli eseguibili di interfaccia implementati con una descrizione generale della procedura degli esperimenti. L'obbiettivo comune di tutte le prove è l'addestramento di una rete neurale in modo che raggiunga il più alto livello possibile di apprendimento circa il riconoscimento di uno dei due compositori dei brani che le sono stati forniti come esempi.

Modularità: Dai sistemi biologici ai sistemi artificiali

I sistemi di intelligenza artificiale vengono spesso messi a confronto con gli aspetti biologici riguardanti il cervello umano. L’interesse per la modularità è in continua crescita, che sta portando a risultati davvero interessanti attraverso l’utilizzo di sistemi artificiali intelligenti, come le reti neuronali. Molte reti, sia biologiche sia artificiali sono organizzate in moduli, i quali rappresentano cluster densi di parti interconnesse fra loro all’interno di una rete complessa. Nel campo dell’ingegneria, si usano design modulari per spiegare come una macchina è costituita da parti separate. Lo studio della struttura e delle funzioni di organismi/processi complessi si basa implicitamente su un principio di organizzazione modulare, vale a dire si dà per acquisito il fatto che siano modulari, cioè composti da parti con forma e/o funzioni diverse. Questo elaborato si propone di esporre gli aspetti fondamentali riguardanti la modularità di reti neuronali, le sue origini evolutive, le condizioni necessarie o sufficienti che favoriscono l’emergere dei moduli e relativi vantaggi. Il primo capitolo fornisce alcune conoscenze di base che permettono di leggere gli esperimenti delle parti successive con consapevolezza teorica più profonda. Si descrivono reti neuronali artificiali come sistemi intelligenti ispirati alla struttura di reti neurali biologiche, soffermandosi in particolare sulla rete feed-forward, sull’algoritmo di backpropagation e su modelli di reti neurali modulari. Il secondo capitolo offre una visione delle origini evolutive della modularità e dei meccanismi evolutivi riguardanti sistemi biologici, una classificazione dei vati tipi di modularità, esplorando il concetto di modularità nell’ambito della psicologia cognitiva. Si analizzano i campi disciplinari a cui questa ricerca di modularità può portare vantaggi. Dal terzo capitolo che inizia a costituire il corpo centrale dell’elaborato, si dà importanza alla modularità nei sistemi computazionali, illustrando alcuni casi di studio e relativi metodi presenti in letteratura e fornendo anche una misura quantitativa della modularità. Si esaminano le varie possibilità di evoluzione della modularità: spontanea, da specializzazione, duplicazione, task-dependent, ecc. passando a emulare l’evoluzione di sistemi neurali modulari con applicazione al noto modello “What-Where” e a vari modelli con caratteristiche diverse. Si elencano i vantaggi che la modularità produce, soffermandosi sull’algoritmo di apprendimento, sugli ambienti che favoriscono l’evoluzione della modularità con una serie di confronti fra i vari tipi, statici e dinamici. In ultimo, come il vantaggio di avere connessioni corte possa portare a sviluppare modularità. L’obiettivo comune è l’emergere della modularità in sistemi neuronali artificiali, che sono usati per applicazioni in numerosi ambiti tecnologici.

THE RESONATE-AND-FIRE NEURON: TIME DEPENDENT AND FREQUENCY SELECTIVE NEURONS IN NEURAL NETWORKS

The means through which the nervous system perceives its environment is one of the most fascinating questions in contemporary science. Our endeavors to comprehend the principles of neural science provide an instance of how biological processes may inspire novel methods in mathematical modeling and engineering. The application ofmathematical models towards understanding neural signals and systems represents a vibrant field of research that has spanned over half a century. During this period, multiple approaches to neuronal modeling have been adopted, and each approach is adept at elucidating a specific aspect of nervous system function. Thus while bio-physical models have strived to comprehend the dynamics of actual physical processes occurring within a nerve cell, the phenomenological approach has conceived models that relate the ionic properties of nerve cells to transitions in neural activity. Further-more, the field of neural networks has endeavored to explore how distributed parallel processing systems may become capable of storing memory. Through this project, we strive to explore how some of the insights gained from biophysical neuronal modeling may be incorporated within the field of neural net-works. We specifically study the capabilities of a simple neural model, the Resonate-and-Fire (RAF) neuron, whose derivation is inspired by biophysical neural modeling. While reflecting further biological plausibility, the RAF neuron is also analytically tractable, and thus may be implemented within neural networks. In the following thesis, we provide a brief overview of the different approaches that have been adopted towards comprehending the properties of nerve cells, along with the framework under which our specific neuron model relates to the field of neuronal modeling. Subsequently, we explore some of the time-dependent neurocomputational capabilities of the RAF neuron, and we utilize the model to classify logic gates, and solve the classic XOR problem. Finally we explore how the resonate-and-fire neuron may be implemented within neural networks, and how such a network could be adapted through the temporal backpropagation algorithm.

Development of dendritic tonic GABAergic inhibition regulates excitability and plasticity in CA1 pyramidal neurons

Synaptic plasticity rules change during development: while hippocampal synapses can be potentiated by a single action potential pairing protocol in young neurons, mature neurons require burst firing to induce synaptic potentiation. An essential component for spike timing-dependent plasticity is the backpropagating action potential (BAP). BAP along the dendrites can be modulated by morphology and ion channel composition, both of which change during late postnatal development. However it is unclear whether these dendritic changes can explain the developmental changes in synaptic plasticity induction rules. Here, we show that tonic GABAergic inhibition regulates dendritic action potential backpropagation in adolescent but not pre-adolescent CA1 pyramidal neurons. These developmental changes in tonic inhibition also altered the induction threshold for spike timing-dependent plasticity in adolescent neurons. This GABAergic regulatory effect upon backpropagation is restricted to distal regions of apical dendrites (>200 μm) and mediated by α5-containing GABA(A) receptors. Direct dendritic recordings demonstrate α5-mediated tonic GABA(A) currents in adolescent neurons which can modulate backpropagating action potentials. These developmental modulations in dendritic excitability could not be explained by concurrent changes in dendritic morphology. To explain our data, model simulations propose a distally-increasing or localized distal expression of dendritic α5 tonic inhibition in mature neurons. Overall, our results demonstrate that dendritic integration and plasticity in more mature dendrites are significantly altered by tonic α5 inhibition in a dendritic region-specific and developmentally-regulated manner.

Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients

Objective The main purpose of this research is the novel use of artificial metaplasticity on multilayer perceptron (AMMLP) as a data mining tool for prediction the outcome of patients with acquired brain injury (ABI) after cognitive rehabilitation. The final goal aims at increasing knowledge in the field of rehabilitation theory based on cognitive affectation. Methods and materials The data set used in this study contains records belonging to 123 ABI patients with moderate to severe cognitive affectation (according to Glasgow Coma Scale) that underwent rehabilitation at Institut Guttmann Neurorehabilitation Hospital (IG) using the tele-rehabilitation platform PREVIRNEC©. The variables included in the analysis comprise the neuropsychological initial evaluation of the patient (cognitive affectation profile), the results of the rehabilitation tasks performed by the patient in PREVIRNEC© and the outcome of the patient after a 3–5 months treatment. To achieve the treatment outcome prediction, we apply and compare three different data mining techniques: the AMMLP model, a backpropagation neural network (BPNN) and a C4.5 decision tree. Results The prediction performance of the models was measured by ten-fold cross validation and several architectures were tested. The results obtained by the AMMLP model are clearly superior, with an average predictive performance of 91.56%. BPNN and C4.5 models have a prediction average accuracy of 80.18% and 89.91% respectively. The best single AMMLP model provided a specificity of 92.38%, a sensitivity of 91.76% and a prediction accuracy of 92.07%. Conclusions The proposed prediction model presented in this study allows to increase the knowledge about the contributing factors of an ABI patient recovery and to estimate treatment efficacy in individual patients. The ability to predict treatment outcomes may provide new insights toward improving effectiveness and creating personalized therapeutic interventions based on clinical evidence.

Transformación del espacio cinemático Laban para la evaluación del movimiento

Este proyecto tiene como objetivo la implementación de un sistema capaz de analizar el movimiento corporal a partir de unos puntos cinemáticos. Estos puntos cinemáticos se obtienen con un programa previo y se captan con la cámara kinect. Para ello el primer paso es realizar un estudio sobre las técnicas y conocimientos existentes relacionados con el movimiento de las personas. Se sabe que Rudolph Laban fue uno de sus mayores exponentes y gracias a sus observaciones se establece una relación entre la personalidad, el estado anímico y la forma de moverse de un individuo. Laban acuñó el término esfuerzo, que hace referencia al modo en que se administra la energía que genera el movimiento y de qué manera se modula en las secuencias, es una manera de describir la intención de las expresiones internas. El esfuerzo se divide en 4 categorías: peso, espacio, tiempo y flujo, y cada una de estas categorías tiene una polaridad denominada elemento de esfuerzo. Con estos 8 elementos de esfuerzo un movimiento queda caracterizado. Para poder cuantificar los citados elementos de esfuerzo se buscan movimientos que representen a alguno de ellos. Los movimientos se graban con la cámara kinect y se guardan sus valores en un archivo csv. Para el procesado de estos datos se establece que el sistema más adecuado es una red neuronal debido a su flexibilidad y capacidad a la hora de procesar entradas no lineales. Para la implementación de la misma se requiere un amplio estudio que incluye: topologías, funciones de activación, tipos de aprendizaje, algoritmos de entrenamiento entre otros. Se decide que la red tenga dos capas ocultas, para mejor procesado de los datos, que sea estática, siga un proceso de cálculo hacia delante (Feedforward) y el algoritmo por el que se rija su aprendizaje sea el de retropropagación (Backpropagation) En una red estática las entradas han de ser valores fijos, es decir, no pueden variar en el tiempo por lo que habrá que implementar un programa intermedio que haga una media aritmética de los valores. Una segunda prueba con la misma red trata de comprobar si sería capaz de reconocer movimientos que estuvieran caracterizados por más de un elemento de esfuerzo. Para ello se vuelven a grabar los movimientos, esta vez en parejas de dos, y el resto del proceso es igual. ABSTRACT. The aim of this project is the implementation of a system able to analyze body movement from cinematic data. This cinematic data was obtained with a previous program. The first step is carrying out a study about the techniques and knowledge existing nowadays related to people movement. It is known that Rudolf Laban was one the greatest exponents of this field and thanks to his observations a relation between personality, mood and the way the person moves was made. Laban coined the term effort, that refers to the way energy generated from a movement is managed and how it is modulated in the sequence, this is a method of describing the inner intention of the person. The effort is divided into 4 categories: weight, space, time and flow, and each of these categories have 2 polarities named elements of effort. These 8 elements typify a movement. We look for movements that are made of these elements so we can quantify them. The movements are recorded with the kinect camera and saved in a csv file. In order to process this data a neural network is chosen owe to its flexibility and capability of processing non-linear inputs. For its implementation it is required a wide study regarding: topology, activation functions, different types of learning methods and training algorithms among others. The neural network for this project will have 2 hidden layers, it will be static and follow a feedforward process ruled by backpropagation. In a static net the inputs must be fixed, this means they cannot vary in time, so we will have to implement an intermediate program to calculate the average of our data. A second test for our net will be checking its ability to recognize more than one effort element in just one movement. In order to do this all the movements are recorded again but this time in pairs, the rest of the process remains the same.

Neural control of a batch distillation

The purpose of the work reported here was to investigate the application of neural control to a common industrial process. The chosen problem was the control of a batch distillation. In the first phase towards deployment, a complex software simulation of the process was controlled. Initially, the plant was modelled with a neural emulator. The neural emulator was used to train a neural controller using the backpropagation through time algorithm. A high accuracy was achieved with the emulator after a large number of training epochs. The controller converged more rapidly, but its performance varied more widely over its operating range. However, the controlled system was relatively robust to changes in ambient conditions.

Neural networks for perpetual grouping

A number of researchers have investigated the application of neural networks to visual recognition, with much of the emphasis placed on exploiting the network's ability to generalise. However, despite the benefits of such an approach it is not at all obvious how networks can be developed which are capable of recognising objects subject to changes in rotation, translation and viewpoint. In this study, we suggest that a possible solution to this problem can be found by studying aspects of visual psychology and in particular, perceptual organisation. For example, it appears that grouping together lines based upon perceptually significant features can facilitate viewpoint independent recognition. The work presented here identifies simple grouping measures based on parallelism and connectivity and shows how it is possible to train multi-layer perceptrons (MLPs) to detect and determine the perceptual significance of any group presented. In this way, it is shown how MLPs which are trained via backpropagation to perform individual grouping tasks, can be brought together into a novel, large scale network capable of determining the perceptual significance of the whole input pattern. Finally the applicability of such significance values for recognition is investigated and results indicate that both the NILP and the Kohonen Feature Map can be trained to recognise simple shapes described in terms of perceptual significances. This study has also provided an opportunity to investigate aspects of the backpropagation algorithm, particularly the ability to generalise. In this study we report the results of various generalisation tests. In applying the backpropagation algorithm to certain problems, we found that there was a deficiency in performance with the standard learning algorithm. An improvement in performance could however, be obtained when suitable modifications were made to the algorithm. The modifications and consequent results are reported here.