Bachelor's

Sep 1, 2002 - Jul 1, 2006

software engineering techniques

master

Nov 11, 2015 - Jul 10, 2015

computer engineering

Design and implementation of image based object recognition

Jan 3, 2020

Journal Periodicals of Engineering and Natural Sciences

publisher sazeen taha abdulrazzaq

Issue 1

Volume 8

The aim of this paper is to design and implement image based object recognition. This represents more of a challenge when speaking of advance object recognition systems. A practical example of this issue is the recognition of objects in images. This is a task that humans can perform very well, but convolutional neural network systems don’t struggle to perform. AlexNet pre-trained model was used for the training the dataset because of it trouble-free architecture on very large scale dataset “Cifar-10” using R2019a Matlab. The dataset was split with the ratio of 70% for training and 30% for the testing part. This has prompted convolutional neural network to start experimenting with networks architectures as well as new algorithms to train them. This research paper presents an approach to train networks such as to improve their robustness to the recognition of object images on R2019a Matlab. This training strategy is then evaluated for designed AlexNet network architecture. The result of the study was that the training algorithm could improve robustness to different image recognition at the expense of an increase in performance for the performance of images of objects (i.e. Dog, Frog, Deer, Automobile, Airplane etc.) with high accuracy of recognition. When the advantages of different types of architectures were evaluated, it was found that accuracy of all object recognition were around 98% based on the image. It followed the findings from classical object recognition that feed-forward neural networks could perform as well their high accuracy of recognition.

Read Publication

A novel steganography approach for audio files

Apr 24, 2020

Journal SN Computer Science

publisher sazeen taha abdulrazzaq

DOI https://doi.org/10.1007/s42979-020-0080-2

Issue 97

Volume 1

We present a novel robust and secure steganography technique to hide images into audio files aiming at increasing the carrier medium capacity. The audio files are in the standard WAV format, which is based on the LSB algorithm, while images are compressed by the GMPR technique which is based on the Discrete Cosine Transform and high-frequency minimization encoding algorithm. The method involves compression–encryption of an image file by the GMPR technique followed by hiding it into audio data by appropriate bit substitution. The maximum number of bits without significant effect on audio signal for LSB audio steganography is 6 LSBs. The encrypted image bits are hidden into variable and multiple LSB layers in the proposed method. Experimental results from observed listening tests show that there is no significant difference between the stego-audio reconstructed from the novel technique and the original signal. A performance evaluation has been carried out according to quality measurement criteria of signal-to-noise ratio and peak signal-to-noise ratio.

Read Publication

Improvement of cellular network capacity via array gain in MIMO

May 1, 2020

Journal Journal of Xidian University

publisher sazeen taha abdulrazzaq

Issue 14

Volume 5

The size of mobile networks varies significantly and can thus be enhanced by the use of an array gain or through the use of spatial multiplexing that can be accomplished by the use of Massive MIMO. Coherent interference that is caused by pilot contamination is associated with the creation of a finite capacity limitation. The limitation is profound when the number of antennae tends towards infinity. This study will use a simplistic channel model in combination with suboptimal precoding schemes. The technique will also apply a large-scale fading variation over the array which will increase the channel capacity regardless of the number of antennae. The method will allow an infinite increase in the number of antennae in a cellular network. The results in this study can also hold when the contaminating channel covariance matrices and the user of the network are curve arbitrarily tending towards linearly independent that has become the common case. The method will also be applied for the diagonals of the covariance matrices which should also be linearly independent.

Read Publication

Decentralized security and data integrity of blockchain using deep learning techniques

Sep 3, 2020

Journal Periodicals of Engineering and Natural Sciences

publisher sazeen taha abdulrazzaq

Issue 3

Volume 8

Since the introduction of blockchain, cryptocurrencies have become very attractive as an alternative digital payment method and a highly speculative investment. With the rise in computational power and the growth of available data, the artificial intelligence concept of deep neural networks had a surge of popularity over the last years as well. With the introduction of the long short-term memory (LSTM) architecture, neural networks became more efficient in understanding long-term dependencies in data such as time series. In this research paper, we combine these two topics, by using LSTM networks to make a prognosis of decentralized blockchain security. In particular, we test if LSTM based neural networks can produce profitable trading signals for different blockchains. We experiment with different preprocessing techniques and different targets, both for security regression and trading signal classification. We evaluate LSTM based networks. As data for training we use historical security data in one-minute intervals from August 2019 to August 2020. We measure the performance of the models via back testing, where we simulate trading on historic data not used for training based on the model’s predictions. We analyze that performance and compare it with the buy and hold strategy. The simulation is carried out on bullish, bearish and stagnating time periods. In the evaluation, we find the best performing target and pinpoint two preprocessing combinations that are most suitable for this task. We conclude that the CNN LSTM hybrid is capable of profitably forecasting trading signals for securing blockchain, outperforming the buy and hold strategy by roughly 30%, while the performance was better. The LTSM method used by current system for encrypting passwords is efficient enough to mitigate modern attacks like man in the middle attack (MITM) and DDOS attack with 95.85% accuracy

Read Publication