The real-time application research on the Fuzzy Logic Systems (FLSs) and Artificial Neural Networks (ANN) is vast and, in this paper, a technique for a photovoltaic failure analysis using the type 2 FLS and ANN is proposed. The method is proposed to build T2 FLS with a guaranteed value equal to or lower than T2 and ANN. Several explanations are conducted to illustrate the effectiveness of the methodologies. It is found that both the type 2 Fuzzy and ANN can be configured for productive actions in applications for a PV fault analysis, and choice is typically applied. The methods discussed in this paper lay the groundwork for developing FLSs and ANNs with durable characteristics that will be extremely useful in many functional applications. The result demonstrates that specific fault categories can be detected using the fault identification method, such as damaged PV modules and partial PV unit shades. The average detection performance is similar in both ANN and fuzzy techniques. In comparison, both systems evaluated show approximately the same performance during experiments. The architecture of the type 2 fuzzy logic system and ANN with radial basic function, including the roles of the output port and the rules for identifying the type of defect in the PV structure is slightly different.
Particle swarm optimization (PSO) is extensively used for real parameter optimization in diverse fields of study. This paper describes an application of PSO to the problem of designing a fractional-order proportional-integral-derivative (PI lambda D delta ) controller whose parameters comprise proportionality constant, integral constant, derivative constant, integral order (lambda) and derivative order (delta). The presence of five optimizable parameters makes the task of designing a PI iquest D iquest controller more challenging than conventional PID controller design. Our design method focuses on minimizing the integral time absolute error (ITAE) criterion. The digital realization of the deigned system utilizes the Tustin operator-based continued fraction expansion scheme. We carry out a simulation that illustrates the effectiveness of the proposed approach especially for realizing fractional-order plants. This paper also attempts to study the behavior of fractional PID controller vis-a-vis that of its integer-order counterpart and demonstrates the superiority of the former to the latter.
This novel work is aimed at the study of emotion recognition from gestures using Kinect sensor. The Kinect sensor along with Software Development Kit (SDK) generates the human skeleton represented by 3-dimensional coordinates corresponding to twenty body joints. Using the co-ordinates of eleven such joints from the upper body and the hands, a set of nine features based on the distances, accelerations and angles between the different joints have been extracted. These features are able to uniquely identify gestures corresponding to five basic human emotional states, namely, `Anger', `Fear', `Happiness', `Sadness' and `Relaxation'. The goal of the proposed system is to classify an emotion based on body gesture. A comparison of classification using binary decision tree, ensemble decision tree, k-nearest neighbour, support vector machine with radial basis function kernel and neural network classifier based on back-propagation learning is made, in terms of average classification accuracy and computation time. A high overall recognition rate of 90.83% is obtained from the ensemble decision tree.
Data security represents an essential task in the present day, in which chaotic models have an excellent role in designing modern cryptosystems. Here, a novel oscillator with chaotic dynamics is presented and its dynamical properties are investigated. Various properties of the oscillator, like equilibria, bifurcations, and Lyapunov exponents (LEs), are discussed. The designed system has a center point equilibrium and an interesting chaotic attractor. The existence of chaotic dynamics is proved by calculating Lyapunov exponents. The region of attraction for the chaotic attractor is investigated by plotting the basin of attraction. The oscillator has a chaotic attractor in which its basin is entangled with the center point. The complexity of the chaotic dynamic and its entangled basin of attraction make it a proper choice for image encryption. Using the effective properties of the chaotic oscillator, a method to construct pseudo-random numbers (PRNGs) is proposed, then utilizing the generated PRNG sequence for designing secure substitution boxes (S-boxes). Finally, a new image cryptosystem is presented using the proposed PRNG mechanism and the suggested S-box approach. The effectiveness of the suggested mechanisms is evaluated using several assessments, in which the outcomes show the characteristics of the presented mechanisms for reliable cryptographic applications.