The solution of the modal equation of a planar optical waveguide is a cumbersome job and usually incident angle of successful modes is determined by a graphical solution. In this research work, we applied two computational intelligence methods: Particle Swarm Optimization (PSO) and Genetic algorithm (GA) in a segment-wise approach to solving the modal equation of the tangent function. The motivation for employing Computational Intelligence (CI) lies in its ability to optimize functions without requiring high-level mathematics or complex statistical models, as opposed to traditional analytical methods. This strategic use of computational intelligence significantly reduces the overall computational cost, more nature inspired and probabilistic, providing an efficient alternative. Particularly for functions with complex solutions, the utilization of computational intelligence or soft computing methods becomes imperative to obtain an approximate solution compared to classical numerical optimization methods like Newton-Raphson, bisection etc. that generally deterministic and aim to find the exact optimal solution. In terms of using probability (a core component of chosen algorithm’s searching mechanism) we can incorporate distributions that will enhance the performance. Therefore, while classical root-finding methods are computationally simpler for isolated cases, the use of PSO and GA is motivated by their global search capability, robustness to initialization, and ease of automation, which are advantageous in generalized or large-scale modal solution frameworks. The outcomes derived from both methods (PSO and GA) are meticulously compared with the results obtained through the traditional graphical solution. We have found accuracy of 99.95% for PSO and 99.87% for GA. Notably, the findings reveal a close correlation between the computational intelligence approaches and the graphical method offering a promising avenue for advancing the field with a more computationally feasible approach.

One of the key aspects of 5G networks is the implementation of massive MIMO (Multiple Input Multiple Output) technology combined with adaptive beamforming. This study explores the use of a linear array antenna to manage and reduce unwanted signals such as jamming, interference, and noise, while also boosting the signal strength towards the intended user or device. The main challenge lay in optimizing the weights of the antenna elements, which was tackled by employing adaptive algorithms like LCMV (Linearly Constrained Minimum Variance) and RLS (Recursive Least Squares). To simplify the optimization process, two soft computing techniques—Particle Swarm Optimization (PSO) and Genetic Algorithm (GA)—were utilized. The performance of the beamforming weights and radiation patterns was assessed in terms of minimizing unwanted signals and maximizing the desired signal. To check how well the proposed methods work, some commonly used algorithms like MVDR (Minimum Variance Distortionless Response) and LCMV are also applied. The outcomes were compared to those from other algorithms. A Differential Beamforming method is applied to examine how effectively the system can focus the signal in the target direction while minimizing unwanted interference from other directions. Additionally, the fminsearch algorithm, which is a basic local search method, is used to compare how well it can adjust the beamforming weights compared to the more advanced global optimization techniques. The results indicate that PSO and GA produce highly similar performance levels.

The electrical load forecasting plays a vital role on the economy of a country in context of fuel saving, working hours of employee and depreciation cost of equipment of power generating station.  In this paper, we use several machine learning techniques relevant to fuzzy system to forecast the demand of electrical load on short-term basis. Here, we consider temperature, humidity, wind speed, types of day such as working day or holiday, barometric pressure as the parameters, which govern the demand of electrical load. To cope with the variables and the power demand, the previous data of Bangladesh Power Development Board (BPDB) and Bangladesh Space Research and Remote Sensing Organization (SPARRSO) were taken for training purpose and then data of current day was used as the test data. For each of the weather parameter several membership functions (MFs) were used as the fuzzy input and then Takagi-Sugeno, Mamdani rule, FCM + Mamdani and ANFIS were applied to acquire the output as the demand of load. The average percentage of error as the difference between forecasted demand and actual demand of test data was found 1.675% for Takagi-Sugeno, 1.91% for Mamdani (centroid), 2.56% for FCM + Mamdani and 3.62% for ANFIS, which were found superior to some previous research works.

Recently data clustering algorithm under machine learning are used in ‘real-life data’ to segregate them based on the outcome of a phenomenon. In this paper, diabetes is detected from pathological data of 768 patients using four clustering algorithms: Fuzzy C-Means (FCM), K-means clustering, Fuzzy Inference system (FIS) and Support Vector Machine (SVM). Our main objective is to make binary classification on the data table in a sense that presence or absence of diabetes of a patient. We combined the four machine learning algorithms based on entropy-based probability to enhance accuracy of detection. Before applying combining scheme, we reduce the size of variables applying multiple linear regression (MLR) on the table then logistic regression is again applied on the resultant data to keep the outlier within a narrow range. Finally, entropy based combining scheme with some modification is applied on the four ML algorithms and we got the accuracy of detection about 94% from the combining technique.