h. mashayekhi

Finding an effective way to combine the base learners is an essential part of constructing a heterogeneous ensemble of classifiers. In this paper, we propose a framework for heterogeneous ensembles, which investigates using an artificial neural network to learn a nonlinear combination of the base classifiers. In the proposed framework, a set of heterogeneous classifiers are stacked to produce the first-level outputs. Then these outputs are augmented using several combination functions to construct the inputs of the second-level classifier. We conduct a set of extensive experiments on 121 datasets and compare the proposed method with other established and state-of-the-art heterogeneous methods. The results demonstrate that the proposed scheme outperforms many heterogeneous ensembles, and is superior compared to singly tuned classifiers. The proposed method is also compared to several homogeneous ensembles and performs notably better. Our findings suggest that the improvements are even more significant on larger datasets.

Understanding and analyzing spatial-temporal data changes is very important in various applications, including the protection and development of natural resources. In the past studies, Markov process and comparison-based methods were mainly used to predict the changes of vegetation indices, whose accuracy still needs improvement. Although time series analysis has been used to predict some indices, the method to extract these indices from remote sensing data and model their sequences with deep learning is rarely observed. In this article, a method for predicting changes in plant indices based on deep learning is presented. The research data includes Landsat satellite images from 2000 to 2018, related to four seasons in the north and east of Shahrood city in Semnan province. The time span of the extracted images makes it possible to predict changes in vegetation cover. Vegetation indices extracted from the data set are NDVI, SAVI and RVI. After performing atmospheric corrections on the images, the desired indicators are extracted and then the data is converted into a time series. Finally, the modeling of the sequence of these data is performed by the Short-Long-Term Memory (LSTM) network. The results of the experiments show that the deep network is able to predict future values with high accuracy. The amount of the model error without additional data is 0.03 for the NDVI index, 0.02 for the SAVI index, and 0.06 for the RVI index.

Bearings are one of the main components used in the drive-train of electrical machines. Early fault diagnosis and classification of bearing fault for maintenance of electromechanical system are very important. With progresses in measurement and digital systems, extensive range of real-time data can be available in electrical machines. Since fault diagnosis based on signal processing methods from extracted signals may not be possible due to different reasons such as noise level, natural frequencies of system, saturation of core,, severity of fault and load torque, deep learning methods have been considered in recent years. In this paper, time series deep learning method for condition monitoring of bearing in electrical machine for the purpose of detection and classification of fault is considered. Obtained results by means of proposed method have been compared with pervious techniques. Experimental results show that proposed deep learning method can detect and classify bearing fault with accuracy above 90%.

In this paper, a hierarchical Bayes model is introduced which models local word relationships in a language. The model can be considered as a language model. The proposed model does not suffer from sparseness because it does not rely on the exact word orders. However, the model does not completely ignore the word orders.  The proposed generative model assumes that each word is a distribution over words and the current word is generated from the distribution of one of its previous words located in a fixed-size window. Contrary to an n-gram model which is a distribution over word sequences and so takes the exact sequences of words into account, the proposed model considers ordered pairs of words which can occur at different distances in the subject text data. Because of this, the sparseness problem is not severe for the proposed model. The model is compared with and outperformed n-gram model according to its ability to model text data which is evaluated by perplexity.

The bases of children mental growth and social behavior are set in first years of childhood. Therefore in primary school textbooks, family health should be focused because of its high importance. The purpose of current study is studying how to present various kinds of family health in textbooks. The mentioned questions are as follows: * How much do the primary school textbooks contexts paid attention to family health elements (physical, environmental, mental)? The context of the texts and the applied pictures in textbooks of Farsi books from grade one to five have been studied quantitatively by using text analysis technique in this study. Here 3 elements of all kinds of health in family include: physical health, environmental health, mental health. In this study checklist has been used by applying elements classifying and descriptive statistics like frequency and percentage and concept analyzing have been used based on frequency, data and units. The statistical society of the research includes all Farsi books (grade one to five) of elementary school. In each educational grade in elementary school, there are two Farsi books by the name of "let's read" and "let's write ", so that in current study eight books were analyzed totally. In most educational grades, Farsi books are the same in size and the names of the chapters, though there are different in contexts of each grade.