No abstract

No abstract

Particle Swarm is a heuristic technique based on collective behavior of birds. Several researches depicts that the PSO suffers from untimely convergence. To defeat the issue of untimely convergence in PSO several solutions are proposed to increase the performance in term of accuracy. This paper suggests a new hybrid mutation operator which used Chi-square and stable distribution. The hybrid mutation operator leads the swarm from local minima to global minima for better solution. To validate the new hybrid scheme, a 12 benchmark optimization functions are used in experiment and compared the result with pervious 6 variants of PSO, proposed variant achieved better results than previous 6 variants.

H.264/AVC video coding standard has achieved a significant improvement in coding efficiency over previous standards, such as, H.261, H.263 and MPEG-4, at the cost of computational complexity. This paper takes advantage of the macroblock (MB) level parallelism in H.264/AVC encoder and based upon this represents a scheme to implement the encoder for multi-core platform. According to this technique an encoding process of an MB is divided into several independent phases and each phase is executed on a separate processing core. Moreover to efficiently utilize the multi-core processors and to improve the encoder performance, the encoder is pipelined at MB level. The experimental results show that encoding rate of pipelined encoder as compare to sequential encoder is improved from 6 fps to 72 fps and from 2 fps to 32 fps for FD1 (720 × 480) and HD 720p (1280 × 720) resolutions, respectively. The implemented encoder can be used for multimedia applications like video conferencing, smart phones, high quality mobile digital video recorders, tablet computers, mobile digital TVs etc.

Nowadays, Face recognition and emotion detection are the most pop- ular area of research. In the past two decades, many applications related to facial emotions have been developed and different methods are used to detect human facial emotions. The goal of this research is to detect human facial emotions i.e. happy, sad, disgust, anger, fear, neutral, or surprise. In this paper, we proposed Haar Cascade classi- fier for face detection emotions detection. The Haar-like features have different types, the edge feature is used to detect edges around the object while the line and rectangle features are used to detect the slanted line of the object. The proposed technique recognizes facial emotions through deep-learning- convolutional neural networks based on FER2013. The FER2013 dataset contains 35887 entries of seven facial emotions and is categorized as 28709 training images, 3589 vali- dation images, and 3589 test images. The proposed method consists of six convolutional layers, three max-pooling layers, and four fully con- nected layers. The output layer is softmax is used to calculate the result from the convolutional neural networks. Through the experimental results, our proposed method achieved a validation accuracy of 65.59 %.