Nasser M. Al-Zidi

Mr. Nasser M. Al-Zidi

Albaydha University, Albaydha, Yemen
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Qasem Al-TashiQasem Al-Tashi
Qasem Al-Tashi
EAEmelia Akashah P. Akhir
Emelia Akashah P. Akhir
SAsaid Jadid Abdulkadir
said Jadid Abdulkadir
Seyedali MirjaliliSeyedali Mirjalili
Seyedali Mirjalili
TATareq Alshami
Tareq Alshami
Nasser M. Al-ZidiNasser M. Al-Zidi
Nasser M. Al-Zidi
The accurate classification of reservoir recovery factor is dampened by irregularities such as noisy and high-dimensional features associated with the reservoir measurements or characterization. These irregularities, especially a larger number of features, make it difficult to perform accurate classification of reservoir recovery factor, as the generated reservoir features are usually heterogeneous. Consequently, it is imperative to select relevant reservoir features while preserving or amplifying reservoir recovery accuracy. This phenomenon can be treated as a multi-objective optimization problem, since there are two conflicting objectives: minimizing the number of measurements and preserving high recovery classification accuracy. In this study, wrapper-based multi-objective feature selection approaches are proposed to estimate the set of Pareto optimal solutions that represents the optimum trade-off between these two objectives. Specifically, three multi-objective optimization algorithms—Non-dominated Sorting Genetic Algorithm II (NSGA-II), Multi-Objective Grey Wolf Optimizer (MOGWO) and Multi-Objective Particle Swarm Optimization (MOPSO)—are investigated in selecting relevant features from the reservoir dataset. To the best of our knowledge, this is the first time multi-objective optimization has been used for reservoir recovery factor classification. The Artificial Neural Network (ANN) classification algorithm is used to evaluate the selected reservoir features. Findings from the experimental results show that the proposed MOGWO-ANN outperforms the other two approaches (MOPSO and NSGA-II) in terms of producing non-dominated solutions with a small subset of features and reduced classification error rate.

1 December 2021
Verified
Conference Paper
Closed access
MTMohammed Tawfik
Mohammed Tawfik
Nasser M. Al-ZidiNasser M. Al-Zidi
Nasser M. Al-Zidi
BABelal Alsellami
Belal Alsellami
AAAymen Muslih Al-Hejri
Aymen Muslih Al-Hejri
SNSunil Nimbhore
Sunil Nimbhore
Internet of Things (IoT) devices are expected to number about 3.5 billion by 2023.; a tremendous amount of Internet of Things (IoT) data that is generating (IoT) devices is estimated to exceed 79.4 zettabytes by 2025. Security challenges will become an increasingly significant issue, especially in smart homes that depend entirely on IoT devices. Due to the weak infrastructure of the IoT, it is vulnerable to various types of cyber-attacks. The most common IoT attacks are distributed denial of service (DDoS). Most traditional security solutions, like intrusion detection systems (IDS), cannot detect most attacks. Complexity is being hidden by a new paradigm that recently arose, called the software-defined system that is brings a significant change to the networking industry, a great solution for mitigation of attacks that can adopt deep learning technique to encounter cyber-attacks based on the attack behavior and by filtering normal and attack traffic by using well-defined rules. This paper proposed a system by suggesting middleware that can help mitigate or prevent various attacks on IoT on smart home environment. Machine learning has included in the middleware to provide automatic protection against cyber-attacks on IoT networks. A promising approach to protecting real-time, highly accurate attacks on SDN-managed IoT networks has been proposed. This middleware allows IoT devices to efficiently handle evolving security threats dynamically and adaptively without impacting the IoT devices.

20 January 2022
Verified
Conference Paper
Closed access
MTMohammed Tawfik
Mohammed Tawfik
SNSunil Nimbhore
Sunil Nimbhore
Nasser M. Al-ZidiNasser M. Al-Zidi
Nasser M. Al-Zidi
ZAZeyad A. T. Ahmed
Zeyad A. T. Ahmed
Ali Mansour AlmadaniAli Mansour Almadani
Ali Mansour Almadani
This research paper proposed a smart system based on deep learning to detect COVID-19 patient's using the cough sound. The deep neural networks are used to distinguish between different types of cough COVID-19 positive or negative coughs. The proposed system is segmented into three stages: Audio pre-processing by noise reduction, segmentation, feature extraction, classification, and model deployment. Eight features have been extracted from 1635 sound subjects: 573 COVID-19 positive and 1062 negative coughs. The feature's extracted data have trained using two models; first model Cough detection based on ANN used to distinguish if there is cough or not, the second model to detect the covid-19 using Convolutional Neural Network. The overall accuracy for both models is 98.1% for the Cough model and 98.5% for the Covid-19 model. The models were compiled after deployment to work together as a web service based on flask. Cough model receives cough sound from the mobile app or web interface and discriminates if there is cough then passe it coivd1-9 model that will analyze if cough is positive or negative. and send the result back to the mobile app.

16 November 2022
Verified
Book Chapter
Closed access
PDF file
MTMohammed Tawfik
Mohammed Tawfik
Nasser M. Al-ZidiNasser M. Al-Zidi
Nasser M. Al-Zidi
IFIbraheam Fathail
Ibraheam Fathail
SNSunil Nimbhore
Sunil Nimbhore

1 December 2021
Verified
Conference Paper
Closed access
Nasser M. Al-ZidiNasser M. Al-Zidi
Nasser M. Al-Zidi
MTMohammed Tawfik
Mohammed Tawfik
AAAymen Muslih Al-Hejri
Aymen Muslih Al-Hejri
IFIbraheam Fathail
Ibraheam Fathail
TATalal A. Aldhaheri
Talal A. Aldhaheri
QAQasem Al-Tashi
Qasem Al-Tashi
Patient monitoring has become one of the most popular studies and is of interest to many researchers worldwide due to the development and growth of healthcare technologies. People in rural areas face multiple diseases and issues due to distance, lack of doctors, and lack of medical treatment for patients. One of the best solutions to these issues is remote patient monitoring. This paper proposes a real-time remote patient monitoring system based on the Internet of Things that can monitor the basic vital signs of the patient, such as body temperature, heartbeat rate, and blood pressure. The core of the system is a wearable device consisting of a microcontroller, a Wi-Fi module, and sensors. Sensors are used to capture patient's vital signs, and the data captured by the sensors is transmitted to the cloud database via a Wi-Fi module. The doctor can real-time monitor the patient via an Android-based smartphone application or retrieve previously recorded data via a website. Moreover, the system will send a notification to the doctor application if any of the vital signs exceed the predefined threshold value. Thus, the real-time remote patient monitoring system helps in the early detection of critical condition and contributes to saving people's lives.

18 January 2024
Verified
Conference Paper
Closed access
Nasser M. Al-ZidiNasser M. Al-Zidi
Nasser M. Al-Zidi
DVD. Vasumathi
D. Vasumathi
Prostate cancer (PCa) ranks second among the most common cancers in men globally, with a staggering 1.4 million new cases estimated in 2020. Due to the increasing number of cases of this type of cancer, the detection and classification of PCa is one of the challenges for early treatment and increasing human survival chances. In recent years, several studies focused on identifying PCa. In the detection and classification of prostate cancer (PCa), magnetic resonance imaging (MRI) assumes a crucial role. Machine learning (ML) and Deep Learning (DL) can accurately and rapidly analyze MRI images and could provide better standardization and consistency in detecting PCa. This review summarizes studies that used ML and DL techniques on prostate MRI and focused on PCa detection and classification. The studies reviewed varied in performing prostate organ segmentation and approximation, prostate lesion characterization, and prostate lesion detection and segmentation. Derived from the good outcomes observed in the analysis of these studies, despite the difficulties and the presence of unsolved problems, it was concluded that the techniques based on ML and DL are adequate and promising for the detection and classification of PCa.