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

Big data analysis is essential for modern applications in areas such as healthcare, assistive technology, intelligent transportation, environment and climate monitoring. Traditional algorithms in data mining and machine learning do not scale well with data size. Mining and learning from big data need time and memory efficient techniques, albeit the cost of possible loss in accuracy. We have developed a data aggregation structure to summarize data with large number of instances and data generated from multiple data sources. Data are aggregated at multiple resolutions and resolution provides a trade-off between efficiency and accuracy. The structure is built once, updated incrementally, and serves as a common data input for multiple mining an

Different ANN architectures of MLP have been trained by BP and used to analyze Landsat TM images. Two different approaches have been applied for training: an ordinary approach (for one hidden layer M-H1-L & two hidden layers M-H1-H2-L) and one-against-all strategy (for one hidden layer (M-H1-1)xL, & two hidden layers (M-H1-H2-1)xL). Classification accuracy up to 90% has been achieved using one-against-all strategy with two hidden layers architecture. The performance of one-against-all approach is slightly better than the ordinary approach

  The great scientific progress has led to widespread Information as information accumulates in large databases is important in trying to revise and compile this vast amount of data and, where its purpose to extract hidden information or classified data under their relations with each other in order to take advantage of them for technical purposes.

      And work with data mining (DM) is appropriate in this area because of the importance of research in the (K-Means) algorithm for clustering data in fact applied with effect can be observed in variables by changing the sample size (n) and the number of clusters (K)

This research study Blur groups (Fuzzy Sets) which is the perception of the most modern in the application in various practical and theoretical areas and in various fields of life, was addressed to the fuzzy random variable whose value is not real, but the numbers Millbh because it expresses the mysterious phenomena or uncertain with measurements are not assertive. Fuzzy data were presented for binocular test and analysis of variance method of random Fuzzy variables , where this method depends on a number of assumptions, which is a problem that prevents the use of this method in the case of non-realized.

Theoretical and experimental investigations of the transient heat transfer parameters of constant heat flux source subjected to water flowing in the downward direction in closed channel are conducted. The power increase transient is ensured by step change increase in the heat source power. The theoretical investigation involved a mathematical modeling for axially symmetric, simultaneously developing laminar water flow in a vertical annulus. The mathematical model is based on one dimensional downward flow. The boundary conditions of the studied case are based on adiabatic outer wall, while the inner wall is subjected to a constant heat flux. The heat & mass balance equation derived for specified element of bulk water within the annulu

With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor se