Search

Phosphorylation is the most important and studied post-translational modification (PTM), which plays a crucial role in protein function studies and experimental design. Many significant studies have been performed to predict phosphorylation sites using various machine-learning methods. Recently, several studies have claimed that deep learning-based methods are the best way to predict the phosphorylation sites because deep learning as an advanced machine learning method can automatically detect complex representations of phosphorylation patterns from raw sequences and thus offers a powerful tool to improve phosphorylation site prediction. In this study, we report DF-Phos, a new phosphosite predictor based on the Deep Forest to predict phosphorylation sites. In DF-Phos, the feature vector taken from the CkSAApair method is as input for a Deep Forest framework for predicting phosphorylation sites. The results of 10-fold cross-validation show that the Deep Forest method has the highest performance among other available methods. We implemented a Python program of DF-Phos, which is freely available for non-commercial use at https://github.com/zahiriz/DF-Phos Moreover, users can use it for various PTM predictions. [ABSTRACT FROM AUTHOR]

Recently, deep learning (DL)-based methods have attracted increasing attention for hyperspectral images (HSIs) classification. However, the complex structure and limited number of labelled training samples of HSIs negatively affect the performance of DL models. In this paper, a spectral-spatial classification method is proposed based on the combination of local and global spatial information, including extended multi-attribute profiles and multiscale Gabor features, with sparse stacked autoencoder (GEAE). GEAE stacks the spatial and spectral information to form the fused features. Also, GEAE generates virtual samples using weighted average of available samples for expanding the training set so that many parameters of DL network can be learned optimally in limited labelled samples situations. Therefore, the similarity between samples is determined with distance metric learning to overcome the problems of Euclidean distance-based similarity metrics. The experimental results on three HSIs datasets demonstrate the effectiveness of the GEAE in comparison to some existing classification methods. [ABSTRACT FROM AUTHOR]

In this paper, a hand-crafted spectral-spatial feature extraction (SEA-FE) method for classification of hyperspectral images (HSIs) is proposed to improve the classification performance, especially in the limited labelled training samples. Usually, spatial information (SPI) is extracted from the neighborhood of each pixel. To overcome the shortcoming of the traditional method, i.e., fixed square window (SW), superpixel analysis is used to construct the neighborhood regions. Also, to reduce the problems of selection the optimal superpixel size, multiscale framework is applied where each superpixel is known as a feature map (FM). Then, SEA-FE combines the FMs together to exploit the spatial structure by calculating the covariance map (CM) as feature coding strategy (FCS). The CMs are mapped from manifold space (MS) to Euclidean space (ES) to serve as direct input for classical learning methods. The experimental results on three HSI datasets demonstrate the effectiveness of the SEA-FE compared to several FE methods. [ABSTRACT FROM AUTHOR]

Nowadays, the approach of integrating low-cost inertial navigation system and satellite data is common due to accuracy and reliability matters. Self-reliance, high data set rates and rotational data presentation, in comparison to gradual reduced accuracy in inertial navigation systems, low data set rates, lack of rotational data presentation, and disruption or outage in the receipt of GNSS data has popularized the approach while Kalman filter integration methods face limitations such as model dependency, the need for prior knowledge, linearization, and most importantly, the inefficiency at GNSS signals outage. This paper aims to present a reliable intelligent online integration method that keeps functioning at signal interruption or outage. The results of GMDH neural network simulations and its comparison with the conventional Kalman filter method and MLP and RBF neural networks show that the former can be used in online navigation operations and for the inevitable conditions of GNSS data unavailability due to high speed and capability in estimating and correcting INS errors (because of having a simple structure and removing inactive neurons, through an effective learning method). [ABSTRACT FROM AUTHOR]

Because of limited labeled samples, semisupervised learning (SSL) methods have attracted much attention for classification of hyperspectral images (HSIs). Graph-based methods that treat data samples as nodes in a graph are very popular classes of SSL in the HSI data analysis. However, constructing a graph that can well capture the essential data structure is critical for these classes of SSL methods. A graph construction method based on low-rank representation (LRR) is proposed. Since LRR only captures the global structure of data, it cannot provide an informative graph for graph-based SSL tasks. To increase the effectiveness of the LRR-based graph, the local structure information is incorporated into the objective function of LRR as an additional penalty term. The proposed low-rank and local linear graph (LRLLG) takes the global and local structure into account, hence it provides a more generative and discriminative graph. Experimental results on two well-known data sets demonstrate that LRLLG outperforms the traditional graph construction methods in label propagation and graph-based SSL methods for HSIs. ® 2018 SPIEand IS&T [DOI: 10.1117/1.JEI.27.6.063002] [ABSTRACT FROM AUTHOR]

Diabetes is a serious disease during which the body's production and use of insulin is impaired, causing glucose concentration level to increase in the bloodstream. The blood glucose dynamics is described using the Bergman minimal model. In this paper, higher-order sliding mode control techniques, in specific prescribed convergence law, super-twisting control algorithm, is used to robustly stabilize the glucose concentration level of a diabetic patient in presence of the parameter variations and meal disturbance. Intelligent systems have appeared in many technical areas, such as consumer electronics, robotics and industrial control systems. Many of these intelligent systems are based on fuzzy control strategies which describe complex systems mathematical model in terms of linguistic rules. By advent of these methods, new techniques have appeared from which fuzzy logic been applied extensively in medical systems. This paper surveys the utilization of fuzzy logic control. Based on this method, fuzzy logic controller is designed to tackle a control problem of the resulting highly nonlinear plant. It was shown also that the proposed schemes can perform well in simulation experiments. Finally the obtained results from these two methods, are verified based on comparison via digital computer simulation by MATLAB. [ABSTRACT FROM AUTHOR]

Since the search process of the particle swarm optimization (PSO) technique is non-linear and very complicated, it is hard if not impossible, to mathematically model the search process and dynamically adjust the PSO parameters. Thus, already some fuzzy systems proposed to control the important structural parameters of basic PSO. However, in those researches no effort were reported for optimizing the structural parameters of the designed fuzzy controller. In this paper, a new algorithm called Fuzzy Optimum PSO (FOPSO) has been introduced. FOPSO utilizes two optimized fuzzy systems for optimal controlling the main parameters of basic PSO. Extensive experimental results on many benchmark functions with different dimensions show that the powerfulness and effectiveness of the proposed FOPSO outperforms other versions of PSO. [ABSTRACT FROM AUTHOR]