fuzzy inference system

The Water Lily Effect Algorithm, introduced in 2024, is inspired by the processes of pollination and movement on water lily leaves. It utilizes concepts of static and dynamic swarm intelligence, modeled through dragonfly movements, to enhance the algorithm's exploratory capabilities. Additionally, local pollination and water movement on lily leaves contribute to its extraction efficiency. However, the algorithm lacks a precise mechanism for managing key parameters during exploration and extraction, with dragonfly movements being randomly defined in all scenarios. This limitation reduces both the accuracy and convergence speed of the optimization process. This study proposes integrating a fuzzy inference system into the dragonfly movement mechanism to address these issues. By controlling the neighborhood radius, alignment, and cohesion movements, the algorithm achieves improved performance. When tested on 12 high-dimensional benchmark functions (50 dimensions), the fuzzy-enhanced Water Lily Algorithm showed a more than 49% improvement in convergence accuracy and over a 9% increase in convergence speed compared to the original algorithm.

Due to the separation of teachers and students in the online teaching system and not receiving the moods of learners and applying appropriate feedback, this study seeks to design an intelligent system that can first detect learners' emotions remotely and then suggest educational scenarios to the teacher. Increases positive emotions and reduces negative emotions in learners. This research was conducted in 1998. The study population is the tenth grade mathematics students of Farzanegan 7 High School in Tehran. The students were divided into 5 groups of 15 people, each of whom was exposed to one of the situations of happiness, anger, fear, despair and sadness, and their facial information was received and recorded through a webcam. Data analysis in this study was performed by data mining method by Clementine software. By comparing the change in the range of emotions recorded before the implementation of the training scenario and then by data mining method with the help of Cummins algorithm that first clustering and then classification The results show that after the implementation of educational scenarios, changes were made in the ranges and increased the mean of positive emotions and decreased the mean of negative emotions.

Predicting stock prices by data analysts have created a great business opportunity for a wide range of investors in the stock markets. But the fact is difficulte, because there are many affective economic factors in the stock markets that they are too dynamic and complex. In this paper, two models are designed and implemented to identify the complex relationship between 10 economic factors on the stock prices of companies operating in the Tehran stock market. First, a Mamdani Fuzzy Inference System (MFIS) is designed that the fuzzy rules set of its inference engine is found by the Particle Swarm Optimization Algorithm (PSO). Then a Deep Learning model consisting of 26 neurons is designed wiht 5 hidden layers. The designed models are implemented to predict the stock prices of nine companies operating on the Tehran Stock Exchange. The experimental results show that the designed deep learning model can obtain better results than the hybridization of MFIS-PSO, the neural network and SVM, although the interperative ability of the obtained patterns, more consistent behavior with much less variance, as well as higher convergence speed than other models can be mentioned as significant competitive advantages of the MFIS-PSO model.