Search

Emotion recognition from human speech is essential to understand the convoluted human nature. For any machine to accurately decipher the intended message in the speech, it must understand the emotion of spoken words. Emotions control the modulations in the speech, and these modulations may even change the context. Through this paper, we aim to propose a system which can efficiently detect the emotions from speech. The domain of emotion recognition from human speech is very complex due to highly overlapping regions of emotions, and it sometimes becomes very difficult to distinguish between two emotions just based on voice. Such ambiguity in the label assignment is responsible for low classification accuracy in existing systems. In the proposed system, we have worked on finding both the suitable feature set as well as the classifier. The proposed system achieved 29.74% increase in classification accuracy in comparison with the baseline human accuracy on the primary dataset, i.e. ‘CREMA-D’. Further, we have validated on other standard datasets such as ‘EmoDB’, ‘RAVDESS’, and ‘SAVEE’. ‘EmoDB’ is a German language dataset, while the other two are English language datasets, which is in line with the language-independent nature of our system. When compared to the current state of the art in this domain on these datasets, the proposed system gives better accuracies for most of the cases, and for some cases, it gives comparable accuracies to baseline models or existing published work.

This paper focuses on developing an adaptive weighted whale optimization algorithm that helps avoid the getting trap at local minima during the convergence. The adaptive weight during each iteration of the algorithm also helps achieve optimal solutions during exploration and exploitation. Further, various adaptive weights, including the chaotic consequences and traditional algorithm, are executed on multiple benchmark functions. The statistical results determined in terms of mean, best and standard deviation depict that the proposed adaptive weighted algorithm performs a higher level than conventional and chaotic weighted algorithms. The results also highlighted that the developed technique showed preferable performance for most minor functions than the traditional technique on achieving the worst global minima.

This paper focuses on developing an adaptation algorithm for hypotrochoid spiral dynamic optimization using linear adaptive spiral radius and angle by dynamically varying the value for each iteration based on the fitness function value. The adaptive algorithm will help obtain the optimal search point compared to fixed radius and angle in conventional methods. The spiral radius and angle effect show that the spiral movement with a negative radius will boost the process of escaping from converging at local optima. The statistical results on various benchmark functions show that the proposed optimization has performed better than spiral dynamic, adaptive spiral dynamic, and hypotrochoid spiral dynamic algorithms.

The principal focus of this paper is to develop a prediction model to predict the turbidity of beach waves. The prediction model is developed using a nonlinear autoregressive neural network model using three input parameters: water temperature, wave height, and wave period. The beach wave turbidity is predicted without installing any additional sensors. The performance of the developed model is evaluated on three beaches in Chicago Park’s district. The proposed model performance showed better tracking ability for all the three considered beaches. The R2 and mean square errors MSE also confirm the best prediction model’s performance for both training and testing.

This paper focuses on developing a prediction model to predict heart stroke using the parameters, namely, age, hypertension, previous heart disease status, average body glucose level, BMI, and smoking status. The prediction model is developed using a support vector machine (SVM) algorithm. Further, the SVM algorithm with various decision boundaries like linear, quadratic, and cubic are also produced. The performance prediction results show that the linear and quadratic SVM has performed better in predicting the heart stoke with greater accuracy values. This is true for both the male and female databases during training and testing.

This paper focuses on developing a weather prediction model to predict temperature and humidity. Further, a classification model is also extended to predict the weather condition using the expected model’s output. The proposed hybrid model can predict the temperature and humidity and forecast future weather conditions. The prediction and classification models are created using neural networks and k-nearest neighbors, respectively. The prediction model’s results have shown the best ability for both the output variables (temperature and humidity) with R2 values close to one and MSE values close to zero. Further, the classification model’s results also showed better execution in classifying the weather conditions with the highest accuracy values.

The objective of this research is to devise a cognitive behavioral therapy system or a Therapy Chatbot capable of catering to the health and informative needs of a user. Also, the key focus is on the therapy element which detects the level of depression in a particular individual. With the increasing stress in day to day life, every individual is prone to depression and the consequences of depression are disastrous, therefore this study revolves around helping people against depression using technology. Since depression has been the major cause of suicide among people, hence, an attempt to lessen the chances of depression and thereby suicide has been made. This study is intended to target 300 million people worldwide. The system not only detects the level of depression in an individual but also suggests remedies to lower the level of depression in an individual. Apart from this, the system caters to the informative needs of the user by helping him make a search for name, place, things, check weather conditions etc. This study uses python as the base language which can be integrated with android so as to serve as a messaging platform so that it can target a larger audience. It is designed in such a way that it can emulate a psychotherapist.