In recent years hand geometric dependent biometric system has shown to be the quite acceptable biometric trait and suitable for security applications. It has been recognized as an effective means of authenticating identity in a variety of commercial applications as a result of better hardware and improved algorithms. This paper purpose a hand recognition system that extract 21 features for the right hand to identify and authorize persons. The system has two main parts, the first contain the data collection, explains the basic pre-processing required and how hand geometry characteristics like fingers length, width, coordinates of the base of the fingers, and palm width are extracted to derive the features used for discrimination, While the second part include the training and testing of three artificial neural networks to perform the recognition. After features extraction, the system uses three kinds of artificial neural networks in performing the recognition process, which are feed forward back propagation NN, Elman NN, and the cascade forward neural network NN. The proposed system shows that the Recognition Rate RR for the neural networks after testing were 95%, 92%, 88% respectively.

The face-recognition system is among the most effective pattern recognition and image analysis techniques. This technique has met great attention from academic and industrial fields because of its extensive use in detecting the identity of individuals for monitoring systems, security and many other practical fields. In this paper, an effective method of face recognition was proposed. Ten person's faces images were selected from ORL dataset, for each person (42) image with total of (420) images as dataset. Features are extracted using principle component analysis PCA to reduce the dimensionality of the face images. Four models where created, the first one was trained using feed forward back propagation learning (FFBBL) with 40 features, the second was trained using 50 features with FFBBL, the third and fourth models were trained using the same features but using Elman neural network. For each person (24) image used as training set for the neural networks, while the remaining images used as testing set. The results showed that the proposed method was effective and highly accurate. FFBBL give accuracy of (98.33, 98.80) with (40, 50) features respectively, while Elman gives (98.33, 95.14) for with (40, 50) features respectively.

In recent years, different encryption lightweight algorithms have been suggested to protect the security of data transferred across the IoT network. The symmetric key ciphers play a significant role in the security of devices, in particular block ciphers. the RECTANGLE algorithm amongst the current lightweight algorithms. Rectangle algorithm does have good encryption efficacy but the characteristics of confusion and diffusion that a cipher needed are lacking from this algorithm. Therefore, by improving the algorithm confusion and diffusion properties, we expanded Rectangle utilizing a 3D cipher and modified the key scheduling algorithm. To assess if these two algorithms are random or not, randomness analysis was done by using the NIST Statistical Test Suite. To create 100 samples for each algorithm, nine distinct data categories were used. These algorithms created ciphertext blocks, which were then concatenated to form a binary sequence. NIST tests carried out under 1% significance level. According to the results of the comparison study, the proposed algorithm's randomness analysis results are gave 27.48% better results than the original algorithm.

No abstract