Areej Alotaibi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Areej Alotaibi has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Duaa AlSaeed
King Saud University
2 shared publications - Alnashwan
Information Technology Department, College of Computer and Information Science, King Saud University, Saudi Arabia
1 shared publication - Lamya Albraheem
Information Technology Department, College of Computer and Information Sciences, King Saud University, Riyadh 145111, Saudi Arabia
1 shared publication - Malak Mashaabi
Department of Information Technology, College of Computer and Information Sciences, King Saud University, King Saud University
1 shared publication - Qudaih
Information Technology Department, College of Computer and Information Science, King Saud University, Saudi Arabia
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 3 January 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (1) , 99
Skin Cancer Detection Using Transfer Learning and Deep Attention Mechanisms
Background/Objectives: Early and accurate diagnosis of skin cancer improves survival rates; however, dermatologists often struggle with lesion detection due to similar pigmentation. Deep learning and transfer learning models have shown promise in diagnosing skin cancers through image processing. Integrating attention mechanisms (AMs) with deep learning has further enhanced the accuracy of medical image classification. While significant progress has been made, further research is needed to improve the detection accuracy. Previous studies have not explored the integration of attention mechanisms with the pre-trained Xception transfer learning model for binary classification of skin cancer. This study aims to investigate the impact of various attention mechanisms on the Xception model’s performance in detecting benign and malignant skin lesions. Methods: We conducted four experiments on the HAM10000 dataset. Three models integrated self-attention (SL), hard attention (HD), and soft attention (SF) mechanisms, while the fourth model used the standard Xception without attention mechanisms. Each mechanism analyzed features from the Xception model uniquely: self-attention examined the input relationships, hard-attention selected elements sparsely, and soft-attention distributed the focus probabilistically. Results: Integrating AMs into the Xception architecture effectively enhanced its performance. The accuracy of the Xception alone was 91.05%. With AMs, the accuracy increased to 94.11% using self-attention, 93.29% with soft attention, and 92.97% with hard attention. Moreover, the proposed models outperformed previous studies in terms of the recall metrics, which are crucial for medical investigations. Conclusions: These findings suggest that AMs can enhance performance in relation to complex medical imaging tasks, potentially supporting earlier diagnosis and improving treatment outcomes.
- 3 January 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (1) , 99
Top Cited PapersOpen AccessSkin Cancer Detection Using Transfer Learning and Deep Attention Mechanisms
Background/Objectives: Early and accurate diagnosis of skin cancer improves survival rates; however, dermatologists often struggle with lesion detection due to similar pigmentation. Deep learning and transfer learning models have shown promise in diagnosing skin cancers through image processing. Integrating attention mechanisms (AMs) with deep learning has further enhanced the accuracy of medical image classification. While significant progress has been made, further research is needed to improve the detection accuracy. Previous studies have not explored the integration of attention mechanisms with the pre-trained Xception transfer learning model for binary classification of skin cancer. This study aims to investigate the impact of various attention mechanisms on the Xception model’s performance in detecting benign and malignant skin lesions. Methods: We conducted four experiments on the HAM10000 dataset. Three models integrated self-attention (SL), hard attention (HD), and soft attention (SF) mechanisms, while the fourth model used the standard Xception without attention mechanisms. Each mechanism analyzed features from the Xception model uniquely: self-attention examined the input relationships, hard-attention selected elements sparsely, and soft-attention distributed the focus probabilistically. Results: Integrating AMs into the Xception architecture effectively enhanced its performance. The accuracy of the Xception alone was 91.05%. With AMs, the accuracy increased to 94.11% using self-attention, 93.29% with soft attention, and 92.97% with hard attention. Moreover, the proposed models outperformed previous studies in terms of the recall metrics, which are crucial for medical investigations. Conclusions: These findings suggest that AMs can enhance performance in relation to complex medical imaging tasks, potentially supporting earlier diagnosis and improving treatment outcomes.
- Open Access
- 26 November 2024
- Published by MDPI AG in Preprints.org
Skin Cancer Detection Using Transfer Learning and Deep Attention Mechanisms
Early and accurate diagnosis of skin cancer improves survival rates; however, dermatologists often struggle with lesion detection due to similar pigmentation. Deep learning and transfer learning models have shown promise in diagnosing skin cancers through image processing. Integrating Attention Mechanisms (AMs) with deep learning have further enhanced the accuracy of medical image classification. While significant progress has been made, further research is needed to im-prove detection accuracy. Previous studies have not explored the integration of attention mechanisms with the pre-trained Xception transfer learning model for binary classification of skin cancer. This study investigates the impact of various attention mechanisms on the Xception model's performance in detecting benign and malignant skin lesions. Using the HAM10000 dermatoscopic image dataset, four experiments were conducted. Three models incorporated self-attention (SL), hard-attention (HD), and soft-attention (SF), respectively, while the fourth model used standard Xception without AMs. Results demonstrated the effectiveness of AMs, with models incorporating self, soft, and hard attention mechanisms achieving accuracies of 94.11%, 93.29%, and 92.97%, respectively, compared to 91.05% for the baseline model, representing a 3% improvement. Both self-attention and soft-attention models outperformed previous studies on recall metrics, which are crucial for medical investigations. These findings suggest that AMs can enhance performance on complex medical imaging tasks, potentially supporting earlier diagnosis and improving treatment outcomes.
- 26 November 2024
- Published by MDPI AG in Preprints.org
Open AccessSkin Cancer Detection Using Transfer Learning and Deep Attention Mechanisms
Early and accurate diagnosis of skin cancer improves survival rates; however, dermatologists often struggle with lesion detection due to similar pigmentation. Deep learning and transfer learning models have shown promise in diagnosing skin cancers through image processing. Integrating Attention Mechanisms (AMs) with deep learning have further enhanced the accuracy of medical image classification. While significant progress has been made, further research is needed to im-prove detection accuracy. Previous studies have not explored the integration of attention mechanisms with the pre-trained Xception transfer learning model for binary classification of skin cancer. This study investigates the impact of various attention mechanisms on the Xception model's performance in detecting benign and malignant skin lesions. Using the HAM10000 dermatoscopic image dataset, four experiments were conducted. Three models incorporated self-attention (SL), hard-attention (HD), and soft-attention (SF), respectively, while the fourth model used standard Xception without AMs. Results demonstrated the effectiveness of AMs, with models incorporating self, soft, and hard attention mechanisms achieving accuracies of 94.11%, 93.29%, and 92.97%, respectively, compared to 91.05% for the baseline model, representing a 3% improvement. Both self-attention and soft-attention models outperformed previous studies on recall metrics, which are crucial for medical investigations. These findings suggest that AMs can enhance performance on complex medical imaging tasks, potentially supporting earlier diagnosis and improving treatment outcomes.
- Open Access
- 16 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 179-188
IoT Based Accident Prevention System using Machine Learning techniques
The likelihood of car accidents increases during extreme weather conditions, such as fog, winds, snow, rain, etc. While it may not be possible to prevent all such accidents, their incidence can be reduced by taking proper measures. Therefore, an intelligent accident-avoidance system is necessary to predict the severity of accidents based on weather and road conditions. This research paper suggests three machine learning (ML) methods for an Internet of Things (IoT)-based accident severity prediction system. The methods are Random Forest, LightGBM, and XGBoost.The aim is to predict the severity of car accidents based on various weather features using a machine learning model. However, considering the previous work, we observed that the size of datasets is frequently minimal, and some of the research discusses the influence of the weather on the number of accidents. Therefore, we used the Countrywide Traffic Accident Dataset, which covers 2.8 million vehicle accidents in the United States from 2016 to 2021. In conclusion, our methodology appears to be efficient in predicting the severity of car accidents. Among the three methods, LightGBM achieved the highest prediction accuracy (72%), precision (70%), recall (70%), F1-scores (70%), and area curve (AUC) (0.86) of the receiver operating characteristic (ROC) curve.
- 16 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 179-188
Open AccessIoT Based Accident Prevention System using Machine Learning techniques
The likelihood of car accidents increases during extreme weather conditions, such as fog, winds, snow, rain, etc. While it may not be possible to prevent all such accidents, their incidence can be reduced by taking proper measures. Therefore, an intelligent accident-avoidance system is necessary to predict the severity of accidents based on weather and road conditions. This research paper suggests three machine learning (ML) methods for an Internet of Things (IoT)-based accident severity prediction system. The methods are Random Forest, LightGBM, and XGBoost.The aim is to predict the severity of car accidents based on various weather features using a machine learning model. However, considering the previous work, we observed that the size of datasets is frequently minimal, and some of the research discusses the influence of the weather on the number of accidents. Therefore, we used the Countrywide Traffic Accident Dataset, which covers 2.8 million vehicle accidents in the United States from 2016 to 2021. In conclusion, our methodology appears to be efficient in predicting the severity of car accidents. Among the three methods, LightGBM achieved the highest prediction accuracy (72%), precision (70%), recall (70%), F1-scores (70%), and area curve (AUC) (0.86) of the receiver operating characteristic (ROC) curve.