A Road Following Approach Using Artificial Neural Networks Combinations

Navigation is a broad topic that has been receiving considerable attention from the mobile robotic community over the years. In order to execute autonomous driving in outdoor urban environments it is necessary to identify parts of the terrain that can be traversed and parts that should be avoided. This paper describes an analyses of terrain identification based on different visual information using a MLP artificial neural network and combining responses of many classifiers. Experimental tests using a vehicle and a video camera have been conducted in real scenarios to evaluate the proposed approach.

Ground-state energy of a classical artificial molecule

We study the ground-state energy of a classical artificial molecule formed by two-dimensional clusters (artificial atoms) of N/2 charged particles separated by a distance d. For the small molecules of N = 2 and 4, we obtain analytical expressions for this energy. For the larger ones, we calculate the ground-state energy using molecular dynamics simulation for N up to 128. From our numerical results, we are able to find out a function to approximate the ground-state energy of the molecules covering the range from atoms to molecules for any inter-atom distance d and for particle number from N = 8 to 128 within a difference less than one percent from the MD data.

The Mobility of Chondroitin Sulfate in Articular and Artificial Cartilage Characterized by (13)C Magic-Angle Spinning NMR Spectroscopy

We have studied the molecular dynamics of one of the major macromolecules in articular cartilage, chondroitin sulfate. Applying (13)C high-resolution magic-angle spinning NMR techniques, the NMR signals of all rigid macromolecules in cartilage can be suppressed, allowing the exclusive detection of the highly mobile chondroitin sulfate. The technique is also used to detect the chondroitin sulfate in artificial tissue-engineered cartilage. The tissue-engineered material that is based on matrix producing chondrocytes cultured in a collagen gel should provide properties as close as possible to those of the natural cartilage. Nuclear relaxation times of the chondroitin sulfate were determined for both tissues. Although T(1) relaxation times are rather similar, the T(2) relaxation in tissue-engineered cartilage is significantly shorter. This suggests that the motions of chondroitin sulfate in data:rat and artificial cartilage different. The nuclear relaxation times of chondroitin sulfate in natural and tissue-engineered cartilage were modeled using a broad distribution function for the motional correlation times. Although the description of the microscopic molecular dynamics of the chondroitin sulfate in natural and artificial cartilage required the identical broad distribution functions for the correlation times of motion, significant differences in the correlation times of motion that are extracted from the model indicate that the artificial tissue does not fully meet the standards of the natural ideal. This could also be confirmed by macroscopic biomechanical elasticity measurements. Nevertheless, these results suggest that NMR is a useful tool for the investigation of the quality of artificially engineered tissue. (C) 2010 Wiley Periodicals, Inc. Biopolymers 93: 520-532, 2010.

Artificial Neural Networks and the Study of the Psychoactivity of Cannabinoid Compounds

Cannabinoid compounds have widely been employed because of its medicinal and psychotropic properties. These compounds are isolated from Cannabis sativa (or marijuana) and are used in several medical treatments, such as glaucoma, nausea associated to chemotherapy, pain and many other situations. More recently, its use as appetite stimulant has been indicated in patients with cachexia or AIDS. In this work, the influence of several molecular descriptors on the psychoactivity of 50 cannabinoid compounds is analyzed aiming one obtain a model able to predict the psychoactivity of new cannabinoids. For this purpose, initially, the selection of descriptors was carried out using the Fisher`s weight, the correlation matrix among the calculated variables and principal component analysis. From these analyses, the following descriptors have been considered more relevant: E(LUMO) (energy of the lowest unoccupied molecular orbital), Log P (logarithm of the partition coefficient), VC4 (volume of the substituent at the C4 position) and LP1 (Lovasz-Pelikan index, a molecular branching index). To follow, two neural network models were used to construct a more adequate model for classifying new cannabinoid compounds. The first model employed was multi-layer perceptrons, with algorithm back-propagation, and the second model used was the Kohonen network. The results obtained from both networks were compared and showed that both techniques presented a high percentage of correctness to discriminate psychoactive and psychoinactive compounds. However, the Kohonen network was superior to multi-layer perceptrons.

ANALYSIS & STUDY OF AI TECHNIQUES FORAUTOMATIC CONDITION MONITORING OFRAILWAY TRACK INFRASTRUCTURE : Artificial Intelligence Techniques

Since the last decade the problem of surface inspection has been receiving great attention from the scientific community, the quality control and the maintenance of products are key points in several industrial applications.The railway associations spent much money to check the railway infrastructure. The railway infrastructure is a particular field in which the periodical surface inspection can help the operator to prevent critical situations. The maintenance and monitoring of this infrastructure is an important aspect for railway association.That is why the surface inspection of railway also makes importance to the railroad authority to investigate track components, identify problems and finding out the way that how to solve these problems. In railway industry, usually the problems find in railway sleepers, overhead, fastener, rail head, switching and crossing and in ballast section as well. In this thesis work, I have reviewed some research papers based on AI techniques together with NDT techniques which are able to collect data from the test object without making any damage. The research works which I have reviewed and demonstrated that by adopting the AI based system, it is almost possible to solve all the problems and this system is very much reliable and efficient for diagnose problems of this transportation domain. I have reviewed solutions provided by different companies based on AI techniques, their products and reviewed some white papers provided by some of those companies. AI based techniques likemachine vision, stereo vision, laser based techniques and neural network are used in most cases to solve the problems which are performed by the railway engineers.The problems in railway handled by the AI based techniques performed by NDT approach which is a very broad, interdisciplinary field that plays a critical role in assuring that structural components and systems perform their function in a reliable and cost effective fashion. The NDT approach ensures the uniformity, quality and serviceability of materials without causing any damage of that materials is being tested. This testing methods use some way to test product like, Visual and Optical testing, Radiography, Magnetic particle testing, Ultrasonic testing, Penetrate testing, electro mechanic testing and acoustic emission testing etc. The inspection procedure has done periodically because of better maintenance. This inspection procedure done by the railway engineers manually with the aid of AI based techniques.The main idea of thesis work is to demonstrate how the problems can be reduced of thistransportation area based on the works done by different researchers and companies. And I have also provided some ideas and comments according to those works and trying to provide some proposal to use better inspection method where it is needed.The scope of this thesis work is automatic interpretation of data from NDT, with the goal of detecting flaws accurately and efficiently. AI techniques such as neural networks, machine vision, knowledge-based systems and fuzzy logic were applied to a wide spectrum of problems in this area. Another scope is to provide an insight into possible research methods concerning railway sleeper, fastener, ballast and overhead inspection by automatic interpretation of data.In this thesis work, I have discussed about problems which are arise in railway sleepers,fastener, and overhead and ballasted track. For this reason I have reviewed some research papers related with these areas and demonstrated how their systems works and the results of those systems. After all the demonstrations were taking place of the advantages of using AI techniques in contrast with those manual systems exist previously.This work aims to summarize the findings of a large number of research papers deploying artificial intelligence (AI) techniques for the automatic interpretation of data from nondestructive testing (NDT). Problems in rail transport domain are mainly discussed in this work. The overall work of this paper goes to the inspection of railway sleepers, fastener, ballast and overhead.

Evolution of artificial defects during shape rolling

Very often defects are present in rolled products. For wire rods, defects are very deleterious since the wire rods are generally used directly in various applications. For this reason, the market nowadays requires wire rods to be completely defect-free. Any wire with defects must be rejected as scrap which is very costly for the production mill. Thus, it is very important to study the formation and evolution of defects during wire rod rolling in order to better understand and minimize the problem, at the same time improving quality of the wire rods and reducing production costs. The present work is focused on the evolution of artificial defects during rolling. Longitudinal surface defects are studied during shape rolling of an AISI M2 high speed steel and a longitudinal central inner defect is studied in an AISI 304L austenitic stainless steel during ultra-high-speed wire rod rolling. Experimental studies are carried out by rolling short rods prepared with arteficial defects. The evolution of the defects is characterised and compared to numerical analyses. The comparison shows that surface defects generally reduce quicker in the experiments than predicted by the simulations whereas a good agreement is generally obtained for the central defect.

Outdoor performance of forest seedlings pre-cultivated under artificial lights : effects of the light spectra used for pre-cultivation on the future establishment and development

Forest nurseries are essential for producing good quality seedlings, thus being a key element in the reforestation process. With increasing climate change awareness, nursery managers are looking for new tools that can help reduce the effects of their operations on the environment. The ZEPHYR project, funded by the European Commission under the Seventh Framework Programme (FP7), has the objective of finding new alternatives for nurseries by developing innovative zero-impact technologies for forest plant production. Due to their direct relationship to the energy consumption of the nurseries, one of the main elements addressed are the grow lights used for the pre-cultivation. New LED luminaires with a light spectrum tailored to the seedlings’ needs are being studied and compared against the traditional fluorescent lamps. Seedlings of Picea abies and Pinus sylvestris were grown under five different light spectra (one fluorescent and 4 LED) during 5 weeks with a photoperiod of 16 hours at 100 μmol∙m-2∙s-1 and 60% humidity. In order to evaluate if these seedlings were able cope with real field stress conditions, a forest field trial was also designed. The terrain chosen was a typical planting site in mid-Sweden after clear-cutting. Two vegetation periods after the outplanting, the seedlings that were pre-cultivated under the LED lamps have performed at least as well as those that were grown under fluorescent lights. These results show that there is a good  potential for lightning substitution in forestry nurseries.

NDVI With Artificial Neural Networks For SRTM Elevation Model Improvement – Hydrological Model Application

Digital elevation model (DEM) plays a substantial role in hydrological study, from understanding the catchment characteristics, setting up a hydrological model to mapping the flood risk in the region. Depending on the nature of study and its objectives, high resolution and reliable DEM is often desired to set up a sound hydrological model. However, such source of good DEM is not always available and it is generally high-priced. Obtained through radar based remote sensing, Shuttle Radar Topography Mission (SRTM) is a publicly available DEM with resolution of 92m outside US. It is a great source of DEM where no surveyed DEM is available. However, apart from the coarse resolution, SRTM suffers from inaccuracy especially on area with dense vegetation coverage due to the limitation of radar signals not penetrating through canopy. This will lead to the improper setup of the model as well as the erroneous mapping of flood risk. This paper attempts on improving SRTM dataset, using Normalised Difference Vegetation Index (NDVI), derived from Visible Red and Near Infra-Red band obtained from Landsat with resolution of 30m, and Artificial Neural Networks (ANN). The assessment of the improvement and the applicability of this method in hydrology would be highlighted and discussed.

Aplicação de técnicas de descobrimento de conhecimento em bases de dados e de inteligência artificial em avaliação de imóveis

A comparação de dados de mercado é o método mais empregado em avaliação de imóveis. Este método fundamenta-se na coleta, análise e modelagem de dados do mercado imobiliário. Porém os dados freqüentemente contêm erros e imprecisões, além das dificuldades de seleção de casos e atributos relevantes, problemas que em geral são solucionados subjetivamente. Os modelos hedônicos de preços têm sido empregados, associados com a análise de regressão múltipla, mas existem alguns problemas que afetam a precisão das estimativas. Esta Tese investigou a utilização de técnicas alternativas para desenvolver as funções de preparação dos dados e desenvolvimento de modelos preditivos, explorando as áreas de descobrimento de conhecimento e inteligência artificial. Foi proposta uma nova abordagem para as avaliações, consistindo da formação de uma base de dados, ampla e previamente preparada, com a aplicação de um conjunto de técnicas para seleção de casos e para geração de modelos preditivos. Na fase de preparação dos dados foram utilizados as técnicas de regressão e redes neurais para a seleção de informação relevante, e o algoritmo de vizinhança próxima para estimação de valores para dados com erros ou omissões. O desenvolvimento de modelos preditivos incluiu as técnicas de regressão com superficies de resposta, modelos aditivos generalizados ajustados com algoritmos genéticos, regras extraídas de redes neurais usando lógica difusa e sistemas de regras difusas obtidos com algoritmos genéticos, os quais foram comparados com a abordagem tradicional de regressão múltipla Esta abordagem foi testada através do desenvolvimento de um estudo empírico, utilizando dados fornecidos pela Prefeitura Municipal de Porto Alegre. Foram desenvolvidos três formatos de avaliação, com modelos para análise de mercado, avaliação em massa e avaliação individual. Os resultados indicaram o aperfeiçoamento da base de dados na fase de preparação e o equilíbrio das técnicas preditivas, com um pequeno incremento de precisão, em relação à regressão múltipla.Os modelos foram similares, em termos de formato e precisão, com o melhor desempenho sendo atingido com os sistemas de regras difusas.