Controlling the rate of insulin injection is very important in diabetic patients who are equipped with an insulin pump. The challenges of proper insulin injection into the body can be exacerbated by the presence of uncertainties (due to different physiological differences in individuals) and the different daily activities of each person. Insulin control has also become more complex due to the delayed effect of carbohydrate entry on the body's blood sugar levels, and may lead to dangerous conditions of hyperglycemia or hypoglycemia. In this paper, the aim is to reduce the effect of inherent uncertainties in the patient. The patient model is based on the Hurca mathematical model. General type 2 fuzzy controllers with alpha cuts are proposed. A neural network system with a linear regression model is used to predict blood sugar levels in the following hours. Also the adjustment of a number of controlling parameters has been done using genetic algorithm. To investigate the controlling behavior, several disturbances in the model and the entry of carbohydrates into the closed-loop system have been considered. The simulation results show that the proposed controller can control blood sugar under different conditions. The designed controller also prevents the occurrence of two dangerous states of hyperglycemia and hypoglycemia. تفاصيل المقالة

The most common way of communication between humans is the use of speech signals, which also includes the person's emotional states. Bionic wavelet transform entropy has been considered in this study for speaker-independent and context-independent emotion detection from speech. Bionic wavelet Transform decomposition, using wavelet type Morlet, is used after preprocessing and Shannon entropy in its nodes is calculated for feature selection. In addition, prosodic features such as the first four formants, jitter or pitch deviation amplitude, and shimmer or energy variation amplitude besides MFCC features are applied to complete the feature vector. Support Vector Machine (SVM) is used to classify multi-class samples of emotions. 46 different utterances of a single sentence from the Berlin emotional speech dataset are selected to be analyzed. The emotions that have been considered are sadness, happiness, fear, boredom, anger, and normal emotional state. Experimental results show that proposed features can improve emotional state detection accuracy in the multi-class situation. تفاصيل المقالة