احمد عبد الرضا عباس الزاملي

Abstract: Face recognition is one of the most promising research area in the last decades. The SVM approach is one of the famous approaches in machine learning fields because it can determine the global optimum solutions with lesser number of training samples especially, complex non-linear challenges such as in face recognition applications. Though, there is an important issue that can affects the whole classification process which is picking the optimum parameters of SVM. Recently, Particle Swarm Optimization (PSO) is used to discover the optimal parameters of SVM and many versions of PSO are used for this purpose, like: PSO-SVM technique, opposition PSO and SVM which called (OPSO-SVM) technique and AAPSO-SVM technique which represents adaptive acceleration PSO and SVM. In this study, a new hybrid technique based on the combination of “Accelerated PSO” and “OPSO-SVM” is introduced for face recognition applications. The hybridization can improve the convergence speed in PSO in order to find the optimal parameters of SVM. In the feature extraction process, the PCA algorithm is used for that purpose and the resulted features are delivered to the proposed technique in order to classify the face images. Two human face datasets are used in the experimentation stage such as, SCface dataset and CASIA face dataset in order to validate the performance of the proposed technique. The comparison process for proposed technique with the other recent technique, like: PSO-SVM, OPSO-SVM and AAPSO-SVM is done as an assessment process. The proposed technique provided high accuracy for recognition when we compared it with the other techniques and it was robust in finding the optimal parameters of SVM.

Abstract: In order to hide the significant and secret message inside a cover object, Steganography is considered as one of the most used technique because of its strength. This paper presents a new steganography technique that it is difficult to discover or break by a third party. The ASCII Mapping Technique (AMT) is used to create an encoded table by mapping the text message and matching some bits with that of the cover image. The system saves the character parts matching and the location of which part of the pixels. Then change the related flag from zero to one the for matched locations so that they cannot be used again to strength the technique and make it more secure. The proposed technique was tested and showed low computational cost with effective performance to be used for multi-purpose applications.

ABSTRACT Hybrid intelligent system means a software system that utilizes a combination of different approaches and techniques from artificial intelligence subfields in order to optimize the target system. Field orient system FOS is a nonlinear device due to the saturation phenomenon, conventional FOS methods provide poor performance, and limited disturbance rejection capability and longer convergence time delay.to optimize the FOS. This paper describes a simple hybrid intelligent design of a “Fuzzy Inference system (FIS)” with PD (FIS-PD) intelligent that is suitable for real-time applications and uses novel output membership functions, which do not include overlap. This increases optimization of rate response convergence, allows for a significant reduction in computational problem, and lowers the execution time. Application of FIS-PD intelligent increases the quality factor of field orient system as results to optimize field oriented system FOS for saturated nonlinear drive in order to achieve high dynamic performance and wide operating range. The performance of the proposed optimization is validated via simulation and the simulation investigation has been carried out for the FOS in this paper. A relative comparison between the FOS and the proposed FIS-PD intelligent indicates that the proposed optimization method yields superior performance. Comparative tests with a conventional system are provided to confirm the effectiveness of the proposed technique.

Some cryptography algorithms mainly depend on prime numbers generated using certain algorithms such as RNG (Random Number Generator) and SRNG (Pseudorandom Number Generator). Those algorithms first generate random numbers, and then primes are chosen from these numbers after some tests such as isprime in Matlab. The objective of this work is to obtain the largest prime number through applying cubic spline interpolation that will be generate randomness pair of points and then select only the prime pair of points and choosing the corresponding Mersenne prime number to obtain the large size prime numbers. Therefore, this paper presents a novel method to generate random numbers using cubic spline interpolation to reduce periodicity. Then a prime number is chosen after isprime test; this prime is then extended to define a large Mersenne prime to be used in the RSA algorithm. Thus, this method will obtain the powerful keys which will used in encryption to increasing the secrecy of data. When applied this a new approach to generate key for RSA algorithm that depend on prime number. We increase the randomness of prime numbers and then obtain the large size of prime numbers which will be increase the level of security for the information.

Abstract Cryptography is the process of protecting sensitive information and making it unreadable to unwanted parties. Since all algorithms that perform this task depend on the process of finding a suitable key, the key generation is considered the soul of powerful encryption. The traditionally generated keys are long and random, hence are difficult to memorize, and we need a database to store the keys. To alleviate this limitation, we use biocryptography that is combined of biometrics and cryptography. Using Bio-Cryptography generated keys provides the necessary security through powerful encryption and decryption of data. This paper uses cubic spline to generate a cryptographic key through extracting the features from fingerprint. The approach is based on extracting the features generated by using Zernike Moment on a biometric, and then sending these features to a Cubic-Spline Interpolator to generate the keys. A key encryption will be generated for every person through extracting the features from his / her biometric (fingerprint) and then applying these features on the cubic spline interpolator to obtain some points. These interpolated points will be used as keys to encrypt the information by using a suitable encryption algorithm. The benefit presented by this approach is to ensure a high level of security to protect the information through generating secure keys ready to be used for unsecured channel. In this paper, we used fingerprints from Biometric Recognition Group - ATVS to examine the performance of this approach.