This paper reports an experimental study of welding of dissimilar materials between transparent Polymethylmethacrylate (PMMA) and stainless steel 304 sheets using a pulsed mode Nd:YAG laser. The process was carried out for two cases; laser transmission joining (LTJ) and conduction joining (CJ). The former is achieved when the joint is irradiated from the polymer side and the latter when the joint is irradiated from the opposite side (metal side). The light and process parameters represented by the peak power (Pp), pulse duration (τ), pulse repetition rate (PRR), scanning speed (ν) and pulse shape have a significant effect on the joint strength (Fb), joint bead width (b), joint quality and appearance. The optimum parameters were determined

Deep Learning Techniques For Skull Stripping of Brain MR Images

One of the diseases on a global scale that causes the main reasons of death is lung cancer. It is considered one of the most lethal diseases in life. Early detection and diagnosis are essential for lung cancer and will provide effective therapy and achieve better outcomes for patients; in recent years, algorithms of Deep Learning have demonstrated crucial promise for their use in medical imaging analysis, especially in lung cancer identification. This paper includes a comparison between a number of different Deep Learning techniques-based models using Computed Tomograph image datasets with traditional Convolution Neural Networks and SequeezeNet models using X-ray data for the automated diagnosis of lung cancer. Although the simple details p

Its well known that understanding human facial expressions is a key component in understanding emotions and finds broad applications in the field of human-computer interaction (HCI), has been a long-standing issue. In this paper, we shed light on the utilisation of a deep convolutional neural network (DCNN) for facial emotion recognition from videos using the TensorFlow machine-learning library from Google. This work was applied to ten emotions from the Amsterdam Dynamic Facial Expression Set-Bath Intensity Variations (ADFES-BIV) dataset and tested using two datasets.

The convolutional neural networks (CNN) are among the most utilized neural networks in various applications, including deep learning. In recent years, the continuing extension of CNN into increasingly complicated domains has made its training process more difficult. Thus, researchers adopted optimized hybrid algorithms to address this problem. In this work, a novel chaotic black hole algorithm-based approach was created for the training of CNN to optimize its performance via avoidance of entrapment in the local minima. The logistic chaotic map was used to initialize the population instead of using the uniform distribution. The proposed training algorithm was developed based on a specific benchmark problem for optical character recog