Dhurgham Ali Mohammed Alhasani

Deep learning techniques has illuminated the way ahead for large scale development on various sectors of human live. Medical applications were amongst those developments. Deep learning is used for mining knowledge that related to diseases so that, disease can be recognized in more effective ways. A large record of thyroid illness taken from hospital; cases are intensively investigated with aim of thyroid disorder detection. In this paper, Long Short Term Memory (LSTM) neural network is deployed for thyroid illness prediction. A 5000 cases were used to train the model and the model is calibrated using a bunch of performance metrics. The results are compared with those obtained by other tools such as Recurrent neural network (RNN) and Linear Vector Quantization (LVQ) algorithm. Accuracy of prediction in LSTM model is outperformed over the others.

Handwriting character recognition involves a high degree of variability and imprecision. For that, the main factor to judge the recognition accuracy is the technique that is used to extract the features. This paper developed a novel method for handwritten Arabic characters by combining the Density-Based Clustering method with statistical and morphological features. The first stage in recognition of handwritten character image has been done by binarization the image then applies noise removal techniques. The Density-Based Algorithm used to categorize and find any shape of clusters based on pixel information positions. This technique divided the image into characters. Each character will be decomposing into four regions from the centroid followed by feature extraction. These features include vertical and horizontal projections, upper and lower profile, rectangularity and orientation. The results of the present process will transfer to the Neural Network (NN) stage which generates a high level of correctness and accuracy by training. The testing results compared with two of state-of-art researches. The total accuracy of this proposed work observes a better recognition of characters.

and AAPSO are the most recently developed face recognition techniques, in order to optimize the parameters of SVM. However, in order to increase the optimization, a combination between OPSO and AAPSO techniques has been proposed in this paper. The proposed technique is called Adaptive-Opposition particle swarm optimization (AOPSO). In AOPSO, the random values in the initial generation of the population in PSO is solved by OPSO and the randomization fixed values in the velocity coefficient is solved using AAPSO in the same time. Then, the proposed algorithm is used with support vector machine to find the optimal parameters of SVM. The performance of the proposed AOPSO method has been validated with two face images datasets, YALE and CASIA datasets. In the proposed method, we have initially performed feature extraction, followed by the recognition of the extracted features. In the recognition process, the extracted features have been employed for SVM training and testing. During the training and testing, the SVM parameters have been optimized with the AOPSO technique. The comparative analysis has demonstrated that, the AOPSOSVM proposed in this study has outperformed the existing PSO-SVM technique.

In this paper, a novel non-linear system identification procedure is established using the structures of the artificial immune system AIS. The high order nonlinear system has many difficulties such as need high computation time, slow response, and has more oscillation with high steady state error. In order to resolve these problems, a simplified method for AIS combined with immediate feedback mechanism is suggested to optimize the system's parameters simultaneously. To confirm and validate the effectiveness of the proposed algorithm, a simulation example on high order nonlinear system based on AIS was studied. This intelligent algorithm realized robustness system with high efficiency by optimizing the complex high order non-linear systems. The simulation results show that the recognized immune models are robust to noise of the system dynamics. The algorithms are naturally modelled after the immune system's characteristics for solving the system problem and optimizing the output signals.

OPSO and AAPSO are the most recently developed face recognition techniques, in order to optimize the parameters of SVM. However, in order to increase the optimization, a combination between OPSO and AAPSO techniques has been proposed in this paper. The proposed technique is called Adaptive-Opposition particle swarm optimization (AOPSO). In AOPSO, the random values in the initial generation of the population in PSO is solved by OPSO and the randomization fixed values in the velocity coefficient is solved using AAPSO in the same time. Then, the proposed algorithm is used with support vector machine to find the optimal parameters of SVM. The performance of the proposed AOPSO method has been validated with two face images datasets, YALE and CASIA datasets. In the proposed method, we have initially performed feature extraction, followed by the recognition of the extracted features. In the recognition process, the extracted features have been employed for SVM and testing. During the training and testing, the SVM parameters have been optimized with the AOPSO technique. The comparative analysis has demonstrated that, the AOPSOSVM proposed in this study has outperformed the existing PSO-SVM technique.

In this paper we have worked to provide facility to the client which gets proof of integrity of the data which he wishes to store in the cloud storage. By doing this client can get advantage with respect to the cost and efforts. The Purpose of our scheme is to reduce computational and storage overhead at the user side and as well as reduce overhead of the cloud storage server. Our scheme is also reduce network bandwidth consumption Cloud computing is an important application for storage of data in the cloud. Cloud computing platform avoid the Burdon of local data storage and also reduce maintaince cost. In cloud storage data is move to a remotely located cloud server on which user does not have any control. Cloud faithfully stores the data and return back to the owner whenever is needed, but there is no guarantee that the data store in the cloud is secure or not modify by cloud. In this paper we provide a scheme which gives an assurance of data integrity in the cloud storage in which the owner of the data can check the correctness of his data in the cloud. This proof can be agreeing upon by both cloud and the client and can be incorporated in the service level agreement. This scheme ensures that the storage at the client side is minimal which will be useful for the thin client and small scale company.