Search

The signal analysis helps us derive useful knowledge from biological processes to analyze, describe, and understand their origin mechanisms. However, biomedical signals are not immune and have time-consuming statistics. The major challenges of signal analysis of sportsperson are reliability and accuracy. Sports psychology uses psychological skills to discuss the optimum success and well-being of sports athletes, the developmental and social dimensions of the sport and sports facilities, and structural problems. The signal detection tool is used to detect the best combination of long-term practice predictors for active, sedentary adults’ signal. This paper proposed the wearable assisted signal detection method (WASDM) to find the sportspersons’ behavior signal analysis. This method performs an IoT based heart rate monitoring using a wearable device named intelligent bracelet mounted on the sportsperson to track the variations in his/her human heart rate. The wearable signal detector method analysis the heart rate abnormality and predicts health status, followed by an alarm to the physician and the respective personnel while performing activity session. In this research, various machine learning algorithms have been tried to perform signal analysis and prediction and compared their results to suggest the best in this application scenario. Finally, the experimental analysis shows better outcomes for the sportspersons’ psychological behavior signal analysis than the conventional methods.

In this correspondence, we present an accurate Magnetic Resonance (MR) image Super-Resolution (SR) method that uses a Very Deep Residual network (VDR-net) in the training phase. By applying 2D Stationary Wavelet Transform (SWT), we decompose each Low Resolution (LR)-High Resolution (HR) example image pair into its low-frequency and high-frequency subbands. These LR-HR subbands are used to train the VDR-net through the input and output channels. The trained parameters are then used to generate residual subbands of a given LR test image. The obtained residuals are added with their LR subbands to produce the SR subbands. Finally, we attempt to maintain the intrinsic structure of images by implementing the Gaussian edge-preservation step on the SR subbands. Our extensive experimental results show that the proposed MR-SR method outperforms the existing methods in terms of four different objective metrics and subjective quality.

In this article, a simple controller design with the fractional order calculations applies to unstable cascade processes with a significant time delay. Series cascade control system consists of two loops in which the inner loop is designed using the IMC principle based on the synthesis method. The primary controller is designed with the FOPI-FOPD controller to ensure stable and satisfactory closed-loop performances for the unstable processes. For the primary controller, five tuning parameters are involved, which tuned using the centroid of the convex stability region method. Different examples are given to illustrate the superiority of the proposed design over some existing designs. Results obtained from simulation reveals that with the proposed control design, enhanced closed-loop control performances are obtained for nominal and perturbed conditions.

Model parameter estimation and controller tuning of the nonlinear clarification process are primary issues in the sugar industry. This paper proposes a Lagrangian-based state transition algorithm (LSTA) for controlling the clarification process and identifying the model parameters. First, the standard system identification procedure is used to estimate the model parameters for the clarifier. Then, the LSTA is used to enhance the accuracy of the identified system parameters. Once a suitable model is obtained, the proposed LSTA is used to fine-tune the optimal controller parameters off-line. We choose two types of evolutionary algorithms for comparison to show the efficacy of the proposed design. The results of the simulations indicate that the proposed controller achieves optimum transient and tracking performance in all cases. For fast convergence and the ability to provide the global optimum when estimating the modeling and controller parameters, the LSTA performance was found to be superior to that of the other algorithms.

The paper proposes a new optimization algorithm that is extremely robust in solving mathematical and engineering problems. The algorithm combines the deterministic nature of classical methods of optimization and global converging characteristics of meta-heuristic algorithms. Common traits of nature-inspired algorithms like randomness and tuning parameters (other than population size) are eliminated. The proposed algorithm is tested with mathematical benchmark functions and compared to other popular optimization algorithms. The results show that the proposed algorithm is superior in terms of robustness and problem solving capabilities to other algorithms. The paradigm is also applied to an engineering problem to prove its practicality. It is applied to find the optimal location of multi-type FACTS devices in a power system and tested in the IEEE 39 bus system and UPSEB 75 bus system. Results show better performance over other standard algorithms in terms of voltage stability, real power loss and sizing and cost of FACTS devices.

The combination and convergence of energy-intensive industries developed by ecological factors based on energy clusters is discussed in this paper. Here, a few models for the prediction of greenhouse effects are used as a single type of modeling. In this model, the solar panel system is included as a measure of the greenhouse effect, Commitment Unit (CU) formulations are changed with flouted logic because solar integrations and other unknown variables are intermittent. In general, the greenhouse model with natural ventilation temperature prediction is incomplete, in which the resulting fluid logical CU problem can be solved with an evolutionary algorithm based on the definition and the theory of quantum calculation. This paper proposes a Fuzzy Model-Based Quantum Greenhouse Evolutionary Ventilation Algorithm (FM-BSQGEVA) which helps to minimize the CU problem. The QGEVA is updated to include a hierarchy-group-oriented scheme to tackle the non-linear nature of the issue and its multifaceted nature. The QGEVA is further developed to support a new binary differential operator and several genetic algorithm operators with a redefined rotational angle look-up. The chances that such operators are used on separate solutions are affected by stating the membership function based on their related fitness. The fitness function is calculated through a combination of the penalty function, objective function and the added fluid function. The models built can be used to regulate and control natural ventilation in greenhouse effects. This finding shows that an energy-intensive industrial cluster's environmental chain of the industry has improved eco-efficiency.

The parameter estimation optimisation with constraints for the nonlinear complex system requires a serious of computation. This paper introduced a novel constrained optimisation method named Lagrangian-based state transition algorithm (LSTA) to solve problems in distributed cloud computing environment. LSTA with the physical constraints involved in solving the problems which occurs while the conventional techniques are used. In LSTA, the updating of the result to an optimisation problem with constraints known as, a state transition. The Lagrangian multiplier is used as a constraint for state transition process to estimate the drying process system effectively. The experiments are conducted in the cloud computing environment and simulated results validated the proposed LSTA methodology for parameter estimation. This method is a promising way for system identification due to its searching competency, enduring performance considering physical limitations and quick convergence.