With the recent growth of Smart TV technology, the demand for unique and beneficial applications motivates the study of a unique gesture-based system for a smart TV-like environment. Combining movie recommendation, social media platform, call a friend application, weather updates, chatting app, and tourism platform into a single system regulated by natural-like gesture controller is proposed to allow the ease of use and natural interaction. Gesture recognition problem solving was designed through 24 gestures of 13 static and 11 dynamic gestures that suit to the environment. Dataset of a sequence of RGB and depth images were collected, preprocessed, and trained in the proposed deep learning architecture. Combination of three-dimensional Convolutional Neural Network (3DCNN) followed by Long Short-Term Memory (LSTM) model was used to extract the spatio-temporal features. At the end of the classification, Finite State Machine (FSM) communicates the model to control the class decision results based on application context. The result suggested the combination data of depth and RGB to hold 97.8% of accuracy rate on eight selected gestures, while the FSM has improved the recognition rate from 89% to 91% in a real-time performance.

No abstract

Video classification is an essential process for analyzing the pervasive semantic information of video content in computer vision. Traditional hand-crafted features are insufficient when classifying complex video information due to the similarity of visual contents with different illumination conditions. Prior studies of video classifications focused on the relationship between the standalone streams themselves. In this paper, by leveraging the effects of deep learning methodologies, we propose a two-stream neural network concept, named state-exchanging long short-term memory (SE-LSTM). With the model of spatial motion state-exchanging, the SE-LSTM can classify dynamic patterns of videos using appearance and motion features. The SE-LSTM extends the general purpose of LSTM by exchanging the information with previous cell states of both appearance and motion stream. We propose a novel two-stream model Dual-CNNSELSTM utilizing the SE-LSTM concept combined with a Convolutional Neural Network, and use various video datasets to validate the proposed architecture. The experimental results demonstrate that the performance of the proposed two-stream Dual-CNNSELSTM architecture significantly outperforms other datasets, achieving accuracies of 81.62%, 79.87%, and 69.86% with hand gestures, fireworks displays, and HMDB51 datasets, respectively. Furthermore, the overall results signify that the proposed model is most suited to static background dynamic patterns classifications.

No abstract

Abstract-Artificial Neural Network (ANN) approach is a fascinating mathematical tool, which can be used to simulate a wide variety of complex scientific and engineering problems. Due to its highly reliable prediction quality, the usage of it is growing rigorously and had already become an ultimate tool for various applications in the field of engineering. In this study an ANN technique was used to predict friction coefficient of roller burnishing AL6061 for two orientations which is parallel burnishing orientation (PB) and cross burnishing orientation (CB). The input parameters were defined by widths of roller curvature (7.5mm, 8mm and 8.5mm), burnishing speeds (110rpm, 230rpm, 330rpm and 490rpm), and burnishing forces (155.06N, 197.45N, 239.83N and 282.22N) while the output parameter was friction coefficient. 173 data was used for training the ANN and another 115 data was used to test the ANN. 60 different configurations of ANN was trained by using 6 different training algorithms. It was found that feed-forward back-propagation network with 15 neurons in hidden layer that was trained by Levenberg-Marquardt training algorithm gave the best result when compared to other training algorithms used. From the results it was found that the training performance and prediction performance was 0.000809 and 0.710 respectively. From this study, it became obvious that the selected ANN with the configuration and training algorithm proved to be the most suitable among the other ANN investigated for similar applications.Index Terms-Friction coefficient; neural network; roller burnishing AL6061.