Volume 13 (2017): Edizione 1 (December 2017)

The problem of classifying diversely distorted objects is considered. The classifier is a 2-layer perceptron capable of classifying greater amounts of objects in a unit of time. This is an advantage of the 2-layer perceptron over more complex neural networks like the neocognitron, the convolutional neural network, and the deep learning neural networks. Distortion types are scaling, turning, and shifting. The object model is a monochrome 60 × 80 image of the enlarged English alphabet capital letter. Consequently, there are 26 classes of 4800-featured objects. Training sets have a parameter, which is the ratio of the pixel-to-scale-turn-shift standard deviations, which allows controlling normally distributed feature distortion. An optimal ratio is found, at which the performance of the 2-layer perceptron is still unsatisfactory. Then, the best classifier is further trained with additional 438 passes of training sets by increasing the training smoothness tenfold. This aids in decreasing the ultimate classification error percentage from 35.23 % down to 12.92 %. However, the expected practicable distortions are smaller, so the percentage corresponding to them becomes just 1.64 %, which means that only one object out of 61 is misclassified. Such a solution scheme is directly applied to other classification problems, where the number of features is a thousand or a few thousands by a few tens of classes.

This study presents a well-developed optimization methodology based on the dynamic inertia weight Artificial Bee Colony algorithm (ABC) to design an optimal PID controller for a robotic arm manipulator. The dynamical analysis of robotic arm manipulators investigates a coupling relation between the joint torques applied by the actuators and the position and acceleration of the robot arm. An optimal PID control law is obtained from the proposed (ABC) algorithm and applied to the robotic system. The designed controller optimizes the trajectory of the robot’s end effector for a time-variant input and makes the robot robust in the presence of external disturbance.

The aim of the investigation presented in this paper was to develop a software-based assistant for the protein analysis workflow. The prior characterization of the unknown protein in two-dimensional electrophoresis gel images is performed according to the molecular weight and isoelectric point of each protein spot estimated from the gel image before further sequence analysis by mass spectrometry. The paper presents a method for automatic and robust identification of the protein standard band in a two-dimensional gel image. In addition, the method introduces the identification of the positions of the markers, prepared by using pre-selected proteins with known molecular mass. The robustness of the method was achieved by using special validation rules in the proposed original algorithms. In addition, a self-organizing map-based decision support algorithm is proposed, which takes Gabor coefficients as image features and searches for the differences in preselected vertical image bars. The experimental investigation proved the good performance of the new algorithms included into the proposed method. The detection of the protein standard markers works without modification of algorithm parameters on two-dimensional gel images obtained by using different staining and destaining procedures, which results in different average levels of intensity in the images.

A conventional MIMO system is designed consisting of 4 antenna elements at both the receiver and transmitter ends. Different kinds of signal detection techniques, namely, zero forcing (ZF), minimum mean square error (MMSE) and beamforming (BF), are used at the receiver end for signal detection. The performance of the system is analyzed by calculating BER vs SNR for each of the above techniques separately. The present work has been thoroughly analyzed and implemented using MATLAB. On the basis of the results obtained, it is summarized that as the values of SNR increase, BER decreases for ZF and MMSE and it almost vanishes to zero even for low SNR values if BF is used. Although ZF and MMSE are suitable for designing a conventional MIMO system with 4 antenna elements, it becomes too difficult for a large number of antenna elements due to its complexity of calculating the inverse of a (N × N) matrix. Based on the results analyzed so far, it is concluded that beamforming (BF) is a suitable technique for designing a system that has a large number of antenna elements at the base station. A further improved system with enhanced performance regarding lower BER for even smaller values of SNR is designed in the present study, consisting of 8 antennas at the base station. The results obtained are enthusiasm-provoking and encouraging for further studies to develop a concept for next-generation wireless communication systems with an optimum design.

The choice of the spreading sequence for asynchronous direct-sequence code-division multiple-access (DS-CDMA) systems plays a crucial role for the mitigation of multiple-access interference. Considering the rich dynamics of chaotic sequences, their use for spreading allows overcoming the limitations of the classical spreading sequences. However, to ensure low cross-correlation between the sequences, careful selection must be performed. This paper presents a novel exhaustive search algorithm, which allows finding sets of chaotic spreading sequences of required length with a particularly low mutual cross-correlation. The efficiency of the search is verified by simulations, which show a significant advantage compared to non-selected chaotic sequences. Moreover, the impact of sequence length on the efficiency of the selection is studied.