Networks Of Multilayer Perceptron Type Research Articles

Comparison of edge computing methods in Internet of Things architectures for efficient estimation of indoor environmental parameters with Machine Learning

The large increase in the number of Internet of Things (IoT) devices have revolutionised the way data is processed, which added to the current trend from cloud to edge computing has resulted in the need for efficient and reliable data processing near the data sources using energy-efficient devices. Two methods based on low-cost edge-IoT architectures are proposed to implement lightweight Machine Learning (ML) models that estimate indoor environmental quality (IEQ) parameters, such as Artificial Neural Networks of Multilayer Perceptron type. Their implementation is based on centralised and distributed parallel IoT architectures, connected via wireless, which share commercial off-the-self modules for data acquisition and sensing, such as sensors for temperature, humidity, illuminance, CO2, and other gases. The centralised method uses a Graphics Processing Unit and the Message Queuing Telemetry Transport protocol, but the distributed method utilises low-performance ARM-based devices and the Message Passing Interface protocol. Although multiple IEQ parameters are measured, the training and testing of ML models is accomplished with experiments focused on small temperature and illuminance datasets to reduce data processing load, obtained from sudden spikes, square profiles and sawteeth test cases. The results show a high estimation performance with F-score and Accuracy values close to 0.95, and an almost theorical Speedup with a reduction in power consumption close to 37% in the distributed parallel approach. In addition, similar or slightly better performance is achieved compared to equivalent IoT architectures from related research, but error reduction of 35–76% is accomplished with an adequate balance between performance and energy efficiency.

Neural Image Analysis and Electron Microscopy to Detect and Describe Selected Quality Factors of Fruit and Vegetable Spray-Dried Powders-Case Study: Chokeberry Powder.

The study concentrates on researching possibilities of using computer image analysis and neural modeling in order to assess selected quality discriminants of spray-dried chokeberry powder. The aim of the paper is the quality identification of chokeberry powders on account of their highest dying power, the highest bioactivity, as well as technologically satisfying looseness of the powder. The article presents neural models with vision techniques backed up by devices such as digital cameras, as well as an electron microscope. The reduction in size of input variables with PCA has an influence on improving the processes of learning data sets, thus increasing the effectiveness of identifying chokeberry fruit powders included in digital pictures, which is shown in the results of the conducted research. The effectiveness of image recognition is presented by classifying abilities, as well as low Root Mean Square Error (RMSE), for which the best results are achieved with a typology of network type Multi-Layer Perceptron (MLP). The selected networks type MLP are characterized by the highest degree of classification at 0.99 and RMSE at 0.11 at most at the same time.

New Segmentation Method for Analytical Recognition of Arabic Handwriting Using a Neural-Markovian Method

A new hybrid system of off-line analytical recognition of Arabic handwriting combining a neural network type multi-layer perceptron (MLP) and hidden Markov models (HMM) is presented. We propose a way to cooperate HMM and MLP neural network in a probabilistic architecture taking advantage of both tools dedicated to the recognition of Arabic literal amounts. This description is based on statistical and structural characteristics extraction of the significant character of the handwritten Arabic words, which can be used in the MLP classification module to estimate probabilities used as the observations to perform a recognition by the HMM. The originality of our approach is based on the segmentation into characters taking into account diacritics with the characters that match them. The experiments show the convergence of the global system, even with a random initialization of the neural network. Keywords - Recognition of Arabic handwriting, hidden Markov models, fast K-means, Arabic literal amounts, multi-layer perceptron. * E-mail: khaoula_1190@hotmail.com

New Segmentation Method for Analytical Recognition of Arabic Handwriting Using a Neural-Markovian Method

A new hybrid system of off-line analytical recognition of Arabic handwriting combining a neural network type multi-layer perceptron (MLP) and hidden Markov models (HMM) is presented. We propose a way to cooperate HMM and MLP neural network in a probabilistic architecture taking advantage of both tools dedicated to the recognition of Arabic literal amounts. This description is based on statistical and structural characteristics extraction of the significant character of the handwritten Arabic words, which can be used in the MLP classification module to estimate probabilities used as the observations to perform a recognition by the HMM. The originality of our approach is based on the segmentation into characters taking into account diacritics with the characters that match them. The experiments show the convergence of the global system, even with a random initialization of the neural network.Keywords - Recognition of Arabic handwriting, hidden Markov models, fast K-means, Arabic literal amounts, multi-layer perceptron. * E-mail: khaoula_1190@hotmail.com

Automation in accession classification of Brazilian Capsicum germplasm through artificial neural networks

Germplasm classification by species requires specific knowledge on/of the culture of interest. Therefore, efforts aimed at automation of this process are necessary for the efficient management of collections. Automation of germplasm classification through artificial neural networks may be a viable and less laborious strategy. The aims of this study were to verify the classification potential of Capsicum accessions regarding/ the species based on morphological descriptors and artificial neural networks, and to establish the most important descriptors and the best network architecture for this purpose. Five hundred and sixty-four plants from 47 Brazilian Capsicum accessions were evaluated. Neural networks of multilayer perceptron type were used in order to automate the species identification through 17 morphological descriptors. Six network architectures were evaluated, and the number of neurons in the hidden layer ranged from 1 to 6. The relative importance of morphological descriptors in the classification process was established by Garson's method. Corolla color, corolla spot color, calyx annular constriction, fruit shape at pedicel attachment, and fruit color at mature stage were the most important descriptors. The network architecture with 6 neurons in the hidden layer is the most appropriate in this study. The possibility of classifying Capsicum plants regarding/ the species through artificial neural networks with 100 % accuracy was verified.

Современные методы и подходы обработки информации по урожайности яровой пшеницы

The productivity of spring wheat crops is the result of a complex interaction of many different factors. Construction of mathematical models, using modern methods and approaches, make it possible to explore and optimize the conditions of the environment in relation to the genetic program of a particular culture and thus increase crop productivity. We used the monitoring results of wheat yield for 32 years and eight major independent factors, affecting it: humidity, the effective temperature during the growing season, rainfall, vegetation period, gluten content, the weight of a thousand grains, grain weight from one ear, straw length. The factor analysis was used previously to improve the efficiency of the model. The use of this analysis led to reveal a latent correlation between factors, and group the data, thereby reducing the dimension of the problem. We obtain four main components (MC), corresponding a linear combination of factor loadings and factors, that describe the 83% of output factor dispersion. A part of dispersion, explained by MC1, is approximately 37%; MC2 - 21%, MC - 13% MC4 - 12%. Further investigation is to build and compare two mathematical models. The first classical model is deal with the construction of the regression equation and the second is a neural network research model, based on neural networks of multilayer perceptron type with one input, one output, and one hidden layer. The four major components are used as input parameters of the model. The models were tested on the input set and checked for adequacy of using Fisher’s exact test. As a result, both models showed good results, but more similar to the original data were the results of the neural network model.

Multi Temporal SAR Image Analysis using NSCT Fusion and Supervised Classifier for Change Detection

The project presents change detection approach for synthetic aperture radar (SAR) images based on an image fusion and supervised classifier system. The image fusion technique will be introduced to generate a difference image by using complementary information from a mean-ratio image and a log-ratio image. NSCT (Non- subsampled contourlet transform) fusion rules based on an average operator and minimum local area gradient are chosen to fuse the contourlet coefficients for a low-frequency band and a high-frequency band respectively, to restrain the background information and to enhance the information of changed regions in the fused difference image. For the remote sensing images, differencing(subtraction operator) and ratioing (ratio operator) are well-known techniques for producing a difference image. In differencing, changes are measured by subtracting the intensity values pixel by pixel between the considered couple of temporal images. In ratioing, changes are obtained by applying a pixel-by-pixel ratio operator to the considered couple of temporal images. In the case of SAR images, the ratio operator is typically used instead of the subtraction operator since the image differencing technique is not adapted to the statistics of SAR images. An artificial neural network type multi-layer perceptron or back propagation with feed forward network will be proposed for classifying changed and unchanged regions in the fused difference image. This classifier comes under supervised segmentation which is worked based on training cum classification. The results will be proven that ratioing generates better difference image for change detection, using supervised classifier segmentation approach and efficiency of this algorithm will be exhibited by sensitivity and correlation evaluation.

Condições de Acesso às Pessoas com Deficiência em Instituições de Ensino Enfermagem: Utilização de Redes Neurais Artificiais como Suporte à Decisão

Objective: To investigate the conditions of accessibility in three undergraduate nursing institutions in the city of Joao Pessoa. Material and Methods: This was an exploratory, descriptive and inferential study using artificial neural network systems such as Multilayer Perceptron (MLP). The sample consisted of students with disabilities and other academics from three undergraduate nursing courses in the city of Joao Pessoa, in the period between August 2008 and June 2009. For empirical data collection, it was used a structured questionnaire comprising socioeconomic data, accessibility and inclusion policies. Results: Access conditions for people with disabilities was considered “weak” (69.96%), presenting percentage of accuracy satisfactory (86.0987%) and significant statistic Kappa (approximately 0.7), showed by the artificial neural network type Multilayer Perceptron. Conclusion: The accessibility conditions of nursing students in the scenarios investigated were considered weak with significant predictors when artificial neural network systems were used as support for decision making. DESCRIPTORS: Education, Nursing. Higher Education Institutions. Decision Support Techniques.

Multinodal Load Forecasting in Power Electric Systems Using a Neural Network with Radial Basis Function

In this paper we present the results of the use of a methodology for multinodal load forecasting through an artificial neural network-type Multilayer Perceptron, making use of radial basis functions as activation function and the Backpropagation algorithm, as an algorithm to train the network. This methodology allows you to make the prediction at various points in power system, considering different types of consumers (residential, commercial, industrial) of the electric grid, is applied to the problem short-term electric load forecasting (24 hours ahead). We use a database (Centralised Dataset - CDS) provided by the Electricity Commission de New Zealand to this work.

Method for the selection of inputs and structure of feedforward neural networks

Feedforward neural networks of multi-layer perceptron type can be used as nonlinear black-box models in data-mining tasks. Common problems encountered are how to select relevant inputs from a large set of variables that potentially affect the outputs to be modeled, as well as high levels of noise in the data sets. In order to avoid over-fitting of the resulting model, the input dimension and/or the number of hidden nodes have to be restricted. This paper presents a systematic method that can guide the selection of both input variables and a sparse connectivity of the lower layer of connections in feedforward neural networks of multi-layer perceptron type with one layer of hidden nonlinear units and a single linear output node. The algorithm is illustrated on three benchmark problems.

Adaptive comb-filtering using neural networks

Neural networks of multi-layer perceptron type perform well as adaptive comb-filters for PAL and NTSC color decoding. They are optimized by learning algorithms. Sampled encoded and original images serve as training patterns.