saif aljumaili

Dr. saif aljumaili

altinbas university

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
20 August 2024 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
AAAthar Alazzawı
Athar Alazzawı
SAsaif aljumaili
saif aljumaili
ADAdil Deniz Duru
Adil Deniz Duru
OUOsman Nuri Uçan
Osman Nuri Uçan
OBOğuz Bayat
Oğuz Bayat
Ivan Miguel PiresIvan Miguel Pires
Ivan Miguel Pires
Schizophrenia is a severe mental disorder that impairs a person’s mental, social, and emotional faculties gradually. Detection in the early stages with an accurate diagnosis is crucial to remedying the patients. This study proposed a new method to classify schizophrenia disease in the rest state based on neurologic signals achieved from the brain by electroencephalography (EEG). The datasets used consisted of 28 subjects, 14 for each group, which are schizophrenia and healthy control. The data was collected from the scalps with 19 EEG channels using a 250 Hz frequency. Due to the brain signal variation, we have decomposed the EEG signals into five sub-bands using a band-pass filter, ensuring the best signal clarity and eliminating artifacts. This work was performed with several scenarios: First, traditional techniques were applied. Secondly, augmented data (additive white Gaussian noise and stretched signals) were utilized. Additionally, we assessed Minimum Redundancy Maximum Relevance (MRMR) as the features reduction method. All these data scenarios are applied with three different window sizes (epochs): 1, 2, and 5 s, utilizing six algorithms to extract features: Fast Fourier Transform (FFT), Approximate Entropy (ApEn), Log Energy entropy (LogEn), Shannon Entropy (ShnEn), and kurtosis. The L2-normalization method was applied to the derived features, positively affecting the results. In terms of classification, we applied four algorithms: K-nearest neighbor (KNN), support vector machine (SVM), quadratic discriminant analysis (QDA), and ensemble classifier (EC). From all the scenarios, our evaluation showed that SVM had remarkable results in all evaluation metrics with LogEn features utilizing a 1-s window size, impacting the diagnosis of Schizophrenia disease. This indicates that an accurate diagnosis of schizophrenia can be achieved through the right features and classification model selection. Finally, we contrasted our results to recently published works using the same and a different dataset, where our method showed a notable improvement.

30 April 2023 in Traitement du Signal
Verified
Journal Article
Closed access
AAAthar Al-Azzawi
Athar Al-Azzawi
SAsaif aljumaili
saif aljumaili
ADAdil Deniz Duru
Adil Deniz Duru
DDDilek Göksel Duru
Dilek Göksel Duru
OUOsman Nuri Uçan
Osman Nuri Uçan

8 July 2025 in Dentomaxillofacial Radiology
Verified
Journal Article
Closed access
HYHasret Yuce
Hasret Yuce
GAGozde Acıkgoz
Gozde Acıkgoz
SAsaif aljumaili
saif aljumaili
OUOsman Nuri Ucan
Osman Nuri Ucan
GULFEM OZLU UCANGULFEM OZLU UCAN
GULFEM OZLU UCAN
KDKadriye Ayça Dere
Kadriye Ayça Dere
Objectives: To reduce the problems arising from the inability to identify dental implant brands, this study aims to classify various dental implant brands using deep learning algorithms on panoramic radiographs. Methods: Images of 4 different dental implant systems (NucleOSS, Medentika, Nobel, and Implance) were used from a total of 5375 cropped panoramic radiographs. To enhance image clarity and reduce blurriness, the contrast limited adaptive histogram equalization filter was applied. GoogleNet, ResNet-18, VGG16, and ShuffleNet deep learning algorithms were utilized to classify the 4 different dental implant systems. To evaluate the classification performance of the algorithms, Receiver Operating Characteristic (ROC) curves and confusion matrices were generated. Based on these confusion matrices, accuracy, precision, sensitivity, and F1 score were calculated. The Z-test was used to compare the performance metrics across different algorithms. Results: The accuracy rates of the deep learning algorithms were obtained as 96.00% for GoogleNet, 84.40% for ResNet-18, 98.90% for VGG16, and 84.80% for ShuffleNet. A statistically significant difference was found between the accuracy rate of the VGG16 algorithm and those of GoogleNet, ShuffleNet, and ResNet-18 (P < .001, P < .001, and P < .001, respectively). Conclusions: With the achievement of high accuracy rates, deep learning algorithms are considered a valuable and powerful method for identifying dental implant brands.

1 January 2023 in AURUM Journal of Engineering Systems and Architecture
Verified
Journal Article
Open access
PDF file
SAsaif aljumaili
saif aljumaili
Over the last few decades, neuroimaging, particularly magnetic resonance imaging (MRI), has played a significant sessional part in studying brain functions and diseases. MRI images, combined with unique ML approaches and developed tools during these years, have opened up new opportunities for diagnosing neurological illnesses. However, due to the apparent symptoms that are similar to each other, brain illnesses are regarded as difficult to precisely detect. This research examines a newly developed algorithm (ParkinsonNet) to classify Parkinson's disorder into two unique classes which are Control (healthy) and Parkinson's (PD), this method is one of the deep learning approaches, Convolutional neural networks (CNN). CNN is one way that may be used to classify a range of brain illnesses such as Parkinson's. We employed a freshly constructed CNN technique from scratch, and we got 97.9% accuracy which is considered outstanding compared with recently published articles using the same dataset

7 October 2025 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
NBNameer Baht
Nameer Baht
EDEnrique Dominguez
Enrique Dominguez
SAsaif aljumaili
saif aljumaili
The sustainability of coffee production is a concern for many coffee-producing countries. Indeed, the conservation of the production of coffee needs to detect disease and infection in the early stages, to provide the ability to control and remedy. Coffee is one of the most consumed daily beverages, so it is considered one of the most important plant crops that affect the economy of the country that produces it. Thus, implementing systems for disease detection that do not require expert consultation can streamline production processes. In this paper, we proposed an efficient and rapid system utilizing cost-effective devices for detecting coffee leaf diseases to support farmers without the need for specialized expertise, leveraging deep learning models. Our technique involves several types of artificial intelligence (AI) models used, which include proposed new models using convolutional neural networks (CNN1, CNN2), and prompt transfer learning (VGG16, ResNet50, and EfficientNet), as well as applied machine learning supervised classifier with hybrid approaches (support vector machine (SVM) and Random Forest (RF)). In terms of training, the proposed model was fed with large datasets that contain five classes, with a total number of images exceeding 50,000 images, while the testing utilized a separate dataset. Finally, the results showed high performance across all evaluation metrics. CNN1 obviously distinguished that it has the superior accuracy compared to the other models, with a 99% value. In conclusion, the proposed framework has the capability to be applied, and it will deliver on-hand support to farmers.

17 December 2024 in International Journal of Communication Systems
Verified
Journal Article
Closed access
SASalam Alyassri
Salam Alyassri
MIMuhammad Ilyas
Muhammad Ilyas
MAMustafa S. Aljumaily
Mustafa S. Aljumaily
SAsaif aljumaili
saif aljumaili
ADAdil Deniz Duru
Adil Deniz Duru