Browsing by Author "Iliyasu, Adamu Yau"

Now showing 1 - 5 of 5
  • Item
    Investigation of Optimal Components and Parameters of the Incremental PCA-based LSTM Network for Detection of EEG Epileptic Seizure Events
    (Faculty of Science, Gombe State University (GSU), Nigeria, 2023-12) Saminu, Sani; Jabire, Adamu Halilu; Aliyu, Hajar Abdulkarim; Yahaya, Suleiman Abimbola; Iliyasu, Adamu Yau; Ibitoye, Morufu Olusola; Xu, Guizhi
    Prediction of Epileptic seizures is highly imperative to improve the epileptic patient’s life. Epileptic seizures occur due to brain cells excessive abnormal activity that leads to unprovoked seizures and may occur without prior notice. Therefore, preventive measure that monitor and alert the possible occurrence of the seizures is paramount. Commercial and clinical available epileptic seizure computer aided detection system that utilized deep learning algorithms suffers from many challenges. These challenges ranges from low accuracy and precision, sensitive to artifacts and noise, among others. To enhance and increase the accuracy and optimal performance of these networks, this paper endeavor to investigate various optimization algorithm to optimized the network components and parameters in the developed incremental Principal Components Analysis based Long Short-Term Memory (Inc-PCA-LSTM) network for the detection and classification of Electroencephalograph (EEG) epileptic seizure signals based on the big data scenario. The model proved to be effective in the characterization of seven seizure events. The Adam, Elu, Orthogonal, and L1/L2 performed better than their counterparts in optimization functions, activation functions, initialization functions, and regularisation techniques respectively. The accuracy values of 97.5%, 97.5%, 98.4%, and 98.5% was obtained for each of the mentioned core components receptively.
  • Item
    Magnetoacoustic Tomography with Magnetic Induction: Multiphysics Imaging Approach_A Short Review
    (Ataturk University, Erzurum, Turkey, 2021) Saminu, Sani; Guizhi, Xu; Zhang, Shuai; Isselmou, Abd El Kader; Jabire, Adamu Halilu; Iliyasu, Adamu Yau
    Magnetoacoustic tomography with magnetic induction (MAT-MI) is one of the multiphysics imaging techniques that combines the principle of magnetic field excitation and acoustic vibration. It is a noninvasive imaging technique developed in order to achieve high electrical impedance contrast of biological tissue as well as high spatial resolution close to ultrasound imaging. The feasibility to reconstruct high spatial resolution conductivity images using MAT-MI method has been demonstrated by both computer simulation and experimental studies. This work reviews the summary of fundamental ideas of MAT-MI and major techniques developed in recent years. First, the physical mechanisms underlying MAT-MI imaging are described including the magnetic induction and Lorentz force induced acoustic wave propagation. Second, experimental setups and various imaging strategies for MAT-MI are reviewed. Finally, we give our opinions on existing challenges and future directions for MAT-MI research. With all the reported and future technical advancement, MAT-MI has the potential to become an important noninvasive modality for electrical conductivity imaging of biological tissue.
  • Item
    A Novel Computer Aided Detection System for Detection of Focal and Non-Focal EEG Signals using Optimized Deep Neural Network
    (IEEExplore, 2021-12) Saminu, Sani; Xu, Guizhi; Zhang, Shuai; Abd El Kader, Isselmou; Jabire, Adamu Halilu; Ahmed, Yusuf Kola; Aliyu, Hajara Abdulkarim; Adamu, Mohammed Jajere; Iliyasu, Adamu Yau; Umar, Faiza Ali
    Epilepsy is a neurological disorder affecting people of all ages. This disorder is reported to affect over 50 million people, with a majority residing in developing countries [1]. It is a sudden and unprovoked seizure that occurs due to an erratic change in the brains' electrical activity often accompanied by loss of consciousness, uncontrolled motions, jerking, and loss of memory [2] [3]. These inconvenient and undesirable effects undermine the quality of life of epilepsy patients as it's difficult for patients and doctors to predict when and where these seizures would occur. Therefore, it is highly imperative to develop an automated system for monitoring epileptic seizures and to assist clinicians in proper and efficient diagnosing of this disease [4] [5].
  • Item
    PERFORMANCE ANALYSIS OF TRANSMIT DIVERSITY CONFIGURATIONS BASED ON OSTBC ALAMOUTI’S EXTENSION
    (Department of Electrical Engineering, Ahmadu Bello University, Zaria, 2021-03) Saminu, Sani; Jabire, Adamu Halilu; Abdulkarim, Abubakar; Ahmed, Yusuf Kola; Iliyasu, Adamu Yau; Salisu, Sani; Karaye, Ibrahim Abdullahi; Ahmad, Isah Salim
    One of the diversity configurations is transmit diversity. It is employed to mitigate multipath fading channel in a time varying channels to improve wireless communication system and make it more reliable. This paper presents a review of diversity techniques and configurations with various signal processing techniques and space time coding system that are mostly employed, diversity combining schemes and analysis of diversity schemes is also exploited. We also proposed a robust space time coding scheme based on orthogonal design by extending the Alamouti’s space time block coding to a higher order diversity and evaluates its performance based on signal to noise ratio (SNR) and bit error rate (BER). The advantage of this transmit diversity is to simplify the hardware requirement by providing a cost effective solution in broadband wireless system with eliminating the need for adopting many antennas at the receiver side
  • Item
    PERFORMANCE OF CIRCULAR SPLIT RING RESONATOR IN WIDEBAND FREQUENCY RECONFIGURABLE METAMATERIAL ANTENNA
    (Department of Electrical Engineering, Ahmadu Bello University, Zaria, 2021-03) Iliyasu, Adamu Yau; Murtala, Aminu-Baba; Saminu, Sani; Bala, Bashir D; Jahun, Kabiru I; Umar, Faiza A; Hamid, Mohamas Rijal; Rahim, Mohamad Kamal A
    This paper presents the design of wideband frequency reconfigurable metamaterial antenna with circular split ring resonator (SRR). The design is based on SRR unit cell and series left-handed capacitance CL. Bandwidth enhancement was achieved by utilizing effect of CL, and gap capacitor of SRR unit cell. The wideband antenna was reconfigured by using Pin Diode switches. Computer Simulation Technology Software was used for simulation work. From the results obtained, antenna bandwidth covered (2.3-5.3) GHz, which is equivalent to 78% fractional bandwidth with gain of 2.5 dBi and 2.28 dBi for E and H plane respectively at center frequency 3.8 GHz. Two single bands which resonate at 2.4 GHz when only S3 is ON, and 5.2 GHz when only S2 is OFF. Then, dual band which resonates at 2.4 GHz and 5.2 GHz when all switches are OFF. From the result obtained, the antenna can be used for WLAN applications.