Ali Al-Saegh

Ali Al-Saegh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ali Al-Saegh has a total of 9 co-authors. Here are the top co-authors by number of shared publications:

  • Jassim M. Abdul-Jabbar

    Computer Engineering Department, College of Engineering, University of Mosul, Mosul, Iraq

    2 shared publications
  • Shefa A. Dawwd

    Computer Engineering Department, College of Engineering, University of Mosul, Mosul, Iraq

    2 shared publications
  • Ahmed Mamoon Fadhil

    College of Engineering Computer Engineering Department

    1 shared publication
  • Amar Daood

    Computer Engineering Department, College of Engineering, University of Mosul, Mosul, Iraq

    1 shared publication
  • Mayada Faris Ghanim

    Computer Engineering Department University of Mosul 41001 Mosul Iraq

    1 shared publication
  • Mohammad H. Ismail

    Computer and Information Engineering Department, College of Electronics Engineering, Ninevah University, Mosul, Iraq

    1 shared publication

Latest Publications

  • Open Access

    Segmentation of Medical MRI Images Using Nested U-Net with Attention Mechanism and Fuzzy Pooling

    by Noor M. Basheer, Ali Al-Saegh

    Segmentation of medical images is a crucial step in the diagnosis and treatment of various diseases, particularly when analyzing magnetic resonance imaging (MRI) scans. Despite significant progress, accurate segmentation remains challenging due to the complexity of anatomical structures, ambiguous boundaries, and variations in image quality. This paper proposes an enhanced Nested U-Net structure that incorporates an attention mechanism and fuzzy pooling to improve retail performance. Nested U-Net benefits from extensive skip connections to capture multi-level contextual information, while the attention mechanism enhances the model's ability to focus on relevant features and noise suppression. In addition, we replace the traditional extreme pooling layers with fuzzy pooling, which enables the network to handle spatial ambiguity more effectively and produce more accurate and refined retail maps. Experimental results on publicly available MRI datasets show that the proposed model achieves remarkable improvements, with a 4.97% increase in the dice coefficient, a 2.76% improvement in accuracy, and a 4.25% increase in recall compared to enhanced U-Net structures. Furthermore, significant improvements have been observed in Hausdorff's distance measures.


  • Open Access

    Dual Optimization of Deep CNN for Motor Imagery EEG Tasks Classification

    by Ali Al-Saegh, Amar Daood, Mohammad H. Ismail

    The motor imagery (MI) electroencephalographic (EEG) signals are leveraged as control commands to numerus engineering applications, such as operating a wheelchair through thought alone. EEG signals are characterized by their non-stationary nature and high dimensionality, posing noteworthy challenges for building robust identification models with limited data samples. The renewed deep convolutional neural network (CNN) has been harnessed in various fields due to its ability to autonomously extract and select latent features addressing problems across various types of EEG signals. However, CNN architectures comprise a vast parameter and hyperparameter space. Normally, parameters are optimized via the back-propagation algorithm, while hyperparameters are adjusted through a lengthy trial-and-error process. This work mitigates the aforementioned problems by employing the genetic algorithm (GA) as an artificial intelligence optimization tool for optimizing crucial architectural hyperparameters including the number of convolution filters, size of filters, and dropout probability. Furthermore, the two parameters of cropping augmentation, used for boosting the EEG training samples, are also optimized by the GA. The proposed model in this paper (GACNN) that includes dual optimization, achieved both by the back-propagation algorithm and GA, has attained promising results in the analysis of MI EEG signals. Experiments are performed on the known brain-computer interface competition IV 2a dataset (BCIC IV 2a). GACNN has recorded an increment of about 17% in Cohen’s kappa coefficient and a decrement of about 30% in standard deviation (SD) in comparison to state-of-the-art studies.


  • Open Access

    Identifying a Suitable Signal Processing Technique for MI EEG Data

    by Ali Al-Saegh

    Motor imagery (MI) electroencephalography (EEG) technology is acquiring great attention from researchers due to its remarkable real-world applications. EEG signals inherit a high degree of non-stationarity, making their analysis not modest. Hence, choosing an appropriate signal processing approach becomes crucial. This comparative paper aims to identify a suitable signal processing method among famous approaches, namely short-time Fourier transform (STFT), continuous wavelet transform (CWT), and two variations of discrete wavelet transform maximal overlap DWT (MODWT) and MODWT multiresolution analysis (MODWTMRA). Different mother wavelet basis filters experimented with wavelet methods: Morse, Amor, Bump, Symlets, Daubechies, Coiflets, and Fejér-Korovkin. The different methods were tested on the classification of the right-hand and left-hand motor imagery tasks using the brain-computer interface (BCI) competition IV 2b dataset. A shallow convolutional neural network containing a single convolution layer was first trained and then used for classification. The experimental outcomes verified that MI EEG signals can be better analyzed and recognized using the maximal overlap-based signal processing methods. The classification accuracy proved that MODWT and MODWTMRA with the Symlets wavelet outperformed the other methods.


  • CutCat: An augmentation method for EEG classification

    by Ali Al-Saegh, Shefa A. Dawwd, Jassim M. Abdul-Jabbar


  • Open Access

    Real-Time Signature Recognition Using Neural Network

    by Ahmed Mamoon Fadhil, Mayada Faris, Ali Al-Saegh, Mohammad Mohammad

    The human signature is an important biometric feature that is used to identify human identity. It is essential in preventing falsification of documents in numerous financial, legal, and other commercial settings. The computerized system enters many aspects of our life, security is one of them, continues developing in computer vision and artificial network leads researcher to develop computerized signature recognition. This paper proposed a real-time algorithm for signature recognition. It is based on client and server operation.in which, client agent captures a signature and sends it to the server through the network. The server receives data and performs processing on it. Processing algorithm is based on weightless neural network. It is chosen for its simplicity and few numbers of sample required for training. The algorithm is tested and evaluated and show the ability to process 4.7 images per second.

  • Top Cited Papers

    Deep learning for motor imagery EEG-based classification: A review

    by Ali Al-Saegh, Shefa A. Dawwd, Jassim M. Abdul-Jabbar


  • Comparison of Complex-Valued Independent Component Analysis Algorithms for EEG Data

    by Ali Al-Saegh

    Independent Component Analysis (ICA) has been successfully applied to a variety of problems, from speaker identification and image processing to functional magnetic resonance imaging (fMRI) of the brain. In particular, it has been applied to analyze EEG data in order to estimate the sources form the measurements. However, it soon became clear that for EEG signals the solutions found by ICA often depends on the particular ICA algorithm, and that the solutions may not always have a physiologically plausible interpretation. Therefore, nowadays many researchers are using ICA largely for artifact detection and removal from EEG, but not for the actual analysis of signals from cortical sources. However, a recent modification of an ICA algorithm has been applied successfully to EEG signals from the resting state. The key idea was to perform a particular preprocessing and then apply a complexvalued ICA algorithm. In this paper, we consider multiple complex-valued ICA algorithms and compare their performance on real-world resting state EEG data. Such a comparison is problematic because the way of mixing the original sources (the “ground truth”) is not known. We address this by developing proper measures to compare the results from multiple algorithms. The comparisons consider the ability of an algorithm to find interesting independent sources, i.e. those related to brain activity and not to artifact activity. The performance of locating a dipole for each separated independent component is considered in the comparison as well. Our results suggest that when using complex-valued ICA algorithms on preprocessed signals the resting state EEG activity can be analyzed in terms of physiological properties. This reestablishes the suitability of ICA for EEG analysis beyond the detection and removal of artifacts with real-valued ICA applied to the signals in the time-domain.


  • Open Access

    RAM-Based Neural Network Parallel Implementation on a Reconfigurable Platform and Its Application for Handwritten Digits Recognition

    by Shefa A. Dawwd, Ali Al-Saegh

    Artificial neural networks (ANNs) are widely used in different areas of nowadays applications. Many challenges are imposed on the practical implementation of ANNs. Some of them are: the number of samples required to train the network; the number of adders, multipliers, nonlinear transfer functions, storage elements; and the speed of calculations in either training phase or recall phase. In this paper, the RAM-based neural network is investigated. No weights, adders, multipliers, transfer functions are required to implement it neither in hardware nor in software, but at a cost of large RAM utilization. In addition, a small number of samples are required for training. However, in hardware implementation, a large size of memory is required to train it.The network is implemented on the FPGA platform. The Stratix IV GX FPGA development board, which is provided on large on board RAM, is used. A considerable speedup of 237is achievedin either training or recalling phases. A comparable error rate of 7.6 is achieved when MNIST (Mixed National Institute of Standards and Technology) database are used to train the network on handwritten digit recognition.