Search

Neural network algorithms are gradually applied to the field of chemical informatics. In this paper, the neural network models are used to predict the properties of compounds based on Molecular Information. We predict the aqueous solubility of compounds, and evaluate the prediction results of the Neural Networks including CNN, RNN, DNN, SNN. The performance of the models in predicting the solubility is able to meet or exceed the predicted effect of the method based on the molecular structure (ESOL). DNN model performance is of more accuracy, and RNN performance is of better stability. This method can directly avoid complex molecular structure characterisation, and provide a convenient and flexible way to predict properties of compounds. [ABSTRACT FROM AUTHOR]

This paper presents the detailed evaluation and classification of Surface Electromyogram (SEMG) signals at different upper arm muscles for different operations. After acquiring the data from selected locations, interpretation of signals was done for the estimation of parameters using simulated algorithm. First, different types of arm operations were analysed; then statistical techniques were implemented for investigating muscle force relationships in terms of amplitude estimation. The classification (Artificial Neural Network) based results have been presented for detecting different pre-defined arm motions in order to discriminate SEMG signals. The outcome of research indicates that a neural network classifier performs best with an average classification rate of 92.50%. Finally, the result also inferred the operations which were observed to be easy for arm recognition and the study is a step forward to develop powerful, flexible and efficient prosthetic designs. [ABSTRACT FROM AUTHOR]

The basic idea of a cartogram is to distort a geographical map by substituting the geographic area of a region by some other variable of interest. The objective is to rescale each region according to the value of the variable of interest while keeping the map, as much as possible, recognizable. There are several algorithms for building cartograms. None of these methods has proved to be universally better than any other, since the trade-offs made to get the correct distortion vary. In this paper we present a new method for building cartograms, based on self-organizing neural networks (Kohonen's self-organizing maps or SOM). The proposed method is widely available and is easy to carry out, and yet has several appealing properties, such as easy parallelization, making up a good tool for geographic data presentation and analysis. We present a series of tests on different problems, comparing the new algorithm with existing ones. We conclude that it is competitive and, in some circumstances, can perform better then existing algorithms. [ABSTRACT FROM AUTHOR]

The paper deals with collision free path-planning for industrial robotic manipulators A new efficient approach is proposed that is based on the topologically ordered neural network model. This model describes harmonic potential field of the robot configuration space, sampled by the non-regular grid. The developed path-planning algorithm takes into account highly-irregular shape of the obstacles of welding and assembling robotic cells, and provides reduced number of collision checking. The stability of the topologically ordered neural network is investigated. The algorithm has been successfully applied to the off-line programming of a robotic manufacturing cell for the automotive industry. [ABSTRACT FROM AUTHOR]

A common problem in a packet radio network (PRN) environment is to construct a multicasting network from a single source to a set of remote destinations which minimizes the number of transmissions. This problem is known to be NP-complete, thus computing an optimal solution may be infeasible for sizable networks. This paper provides two alternative solutions to this problem. The first is a heuristic algorithm which iteratively builds a spanning tree from the destinations to the source. A second solution, included for comparative purposes, is based on the Hopfield neural network whose dynamics are governed by a motion equation and a set of constraints. Both solutions are tested on a variety of instances against an optimal algorithm. Results show the approaches form good solutions (the number of transmissions is within about 3% of the optimum) and run in a fraction of the time required to form the optimal solution. [ABSTRACT FROM AUTHOR]

This paper makes a comparative assessment of three popular maximum power point tracking (MPPT) algorithms used in photovoltaic power generation. A 120 Wp PV module is taken as reference for the study that is connected to a suitable resistive load by a boost converter. Two profiles of variation of solar insolation at fixed temperature and varying temperature at fixed solar insolation are taken to test the tracking efficiency of three MPPT algorithms based on the perturb and observe (P&O), Fuzzy logic, and Neural Network techniques. MATLAB/SIMULINK simulation software is used for assessment, and the results indicate that the fuzzy logic-based tracker presents better tracking effectiveness to variations in both solar insolation and temperature profiles when compared to P&O technique and Neural Network-based technique. [ABSTRACT FROM AUTHOR]