Machine learning (ML) models enable exploration of vast structural space faster than the traditional methods, such as finite element method (FEM). This makes ML suitable for stochastic fracture problems in brittle porous materials. In this work, fully convolutional networks (FCNs) were trained to predict stress and concentration factor distributions two-dimensional isotropic elastic materials w...

Precise recognition of emotion from speech signals aids in enhancing human–computer interaction (HCI). The performance a (SER) system depends on the derived features signals. However, selecting optimal set feature representations remains most challenging task SER because effectiveness varies with emotions. Most studies extract hidden local ignoring global long-term contextual existing suffers l...

Abstract Full convolution neural network (FCN) based on an encoder-decoder structure has become a standard in the semantic segmentation domain. Encoder-decoder architecture is effective means to get finer-grained performance. Encoders constantly extract multilevel features, and then use decoders gradually introduce low-level features into high-level features. Context information critical for ac...

Semantic segmentation is challenging as it requires both object-level information and pixel-level accuracy. Recently, FCN-based systems gained great improvement in this area. Unlike classification networks, combining features of different layers plays an important role in these dense prediction models, as these features contains information of different levels. A number of models have been prop...

Let c be a constant and (e1, f1), (e2, f2), . . . , (ecn, fcn) be a sequence of ordered pairs of edges from the complete graph Kn chosen uniformly and independently at random. We prove that there exists a constant c2 such that if c > c2 then whp every graph which contains at least one edge from each ordered pair (ei, fi) has a component of size Ω(n) and if c < c2 then whp there is a graph conta...

Modulation signal classification in communication systems can be considered a pattern recognition problem. Earlier works have focused on several feature extraction approaches such as fractal feature, constellation reconstruction, etc. The recent advent of deep learning (DL) models makes it possible to proficiently classify the modulation signals. In this view, study designs chaotic oppositional...

This paper presents a time- and cost-efficient method for the management of construction demolition (C&amp;D) debris at sites, jobsites, illegal C&amp;D waste dumping sites. The developed integrates various drone, deep learning, geographic information system (GIS) technologies, including drone scanning, 3D reconstruction with structure from motion (SfM), image segmentation fully convolutional n...

Signs of functional loss due to the deterioration structures are primarily identified from cracks occurring on surface structures, and continuous monitoring structural is essential for socially important structures. Recently, many crack technologies have been developed with development deep-learning artificial intelligence (AI). In this study, stacking ensemble learning was applied predict more...

Void fraction is one of the key parameters for gas-liquid study and detection nuclear power system state. Based on fully convolutional neural network (FCN) high-speed photography, an indirect void measure approach flow boiling condition in narrow channels developed this paper. Deep learning technique applied to extract image features can better realize identification gas liquid phase complicate...