Mohammed Hassan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammed Hassan has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Mohamed Hamada
Software Engineering Lab, University of Aizu, Fukushima 965-8580, Japan
15 shared publications - Aminu Musa
Department of Computer Science, Federal University Dutse, Dutse 720211, Nigeria
4 shared publications - Habeebah Adamu Kakudi
Department of Computer Science, Bayero University, Kano 700006, Nigeria
3 shared publications - Jesse Jeremiah Tanimu
Department of computer Science, Bayero Unoiversity Kano, Kano Nigeria
3 shared publications - Saratu Yusuf Ilu
Department of Software Engineering, Bayero University, Kano. Nigeria
3 shared publications - Lawan Abdullahi Yusuf
Faculty of Science, department of Computer Science, National Open University of Nigeria. Abuja, Nigeria
2 shared publications
Latest Publications
- Open Access
- 15 October 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 113
A New Glaucoma Detection Method Using a Swin Transformer and Image Segmentation
This study develops and evaluates an advanced automated system for glaucoma detection using deep learning techniques, addressing the limitations of traditional diagnostic methods that rely heavily on ophthalmologists’ expertise, often leading to inconsistencies and delays. By merging five publicly available datasets—ODIR-5K, ACRIMA, RIM-ONE, ORIGA, and REFUGE—into a comprehensive dataset, the research ensures robust model training and evaluation. The SegFormer model is employed for effective image segmentation, overcoming the feature discrimination challenges of traditional convolutional neural networks. The segmented images are then classified using the Swin Transformer, which efficiently handles high-resolution images with reduced computational complexity. The combined SegFormer and Swin Transformer model demonstrates superior performance, achieving 97.8% accuracy, 97.5% precision, 98.29% recall, and a 98.33% F1-score. This approach not only outperforms standalone models but also surpasses other state-of-the-art CNNs, highlighting the significant potential of deep learning in enhancing glaucoma detection and improving diagnostic accuracy.
- 15 October 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 113
Open AccessA New Glaucoma Detection Method Using a Swin Transformer and Image Segmentation
This study develops and evaluates an advanced automated system for glaucoma detection using deep learning techniques, addressing the limitations of traditional diagnostic methods that rely heavily on ophthalmologists’ expertise, often leading to inconsistencies and delays. By merging five publicly available datasets—ODIR-5K, ACRIMA, RIM-ONE, ORIGA, and REFUGE—into a comprehensive dataset, the research ensures robust model training and evaluation. The SegFormer model is employed for effective image segmentation, overcoming the feature discrimination challenges of traditional convolutional neural networks. The segmented images are then classified using the Swin Transformer, which efficiently handles high-resolution images with reduced computational complexity. The combined SegFormer and Swin Transformer model demonstrates superior performance, achieving 97.8% accuracy, 97.5% precision, 98.29% recall, and a 98.33% F1-score. This approach not only outperforms standalone models but also surpasses other state-of-the-art CNNs, highlighting the significant potential of deep learning in enhancing glaucoma detection and improving diagnostic accuracy.
- Open Access
- 26 August 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 107 (1) , 21
A Deep Convolutional Neural Network-Based Model for Aspect and Polarity Classification in Hausa Movie Reviews
Aspect-based sentiment analysis (ABSA) plays a pivotal role in understanding the nuances of sentiment expressed in text, particularly in the context of diverse languages and cultures. This paper presents a novel deep convolutional neural network (CNN)-based model tailored for aspect and polarity classification in Hausa movie reviews, as Hausa is an underrepresented language with limited resources and presence in sentiment analysis research. One of the primary implications of this work is the creation of a comprehensive Hausa ABSA dataset, which addresses a significant gap in the availability of resources for sentiment analysis in underrepresented languages. This dataset fosters a more inclusive sentiment analysis landscape and advances research in languages with limited resources. The collected dataset was first preprocessed using Sci-Kit Learn to perform TF-IDF transformation for extracting feature word vector weights. Aspect-level feature ontology words within the analyzed text were derived, and the sentiment of the reviewed texts was manually annotated. The proposed model combines convolutional neural networks (CNNs) with an attention mechanism to aid aspect word prediction. The model utilizes sentences from the corpus and feature words as vector inputs to enhance prediction accuracy. The proposed model leverages the advantages of the convolutional and attention layers to extract contextual information and sentiment polarities from Hausa movie reviews. The performance demonstrates the applicability of such models to underrepresented languages. With 91% accuracy on aspect term extraction and 92% on sentiment polarity classification, the model excels in aspect identification and sentiment analysis, offering insights into specific aspects of interest and their associated sentiments. The proposed model outperformed traditional machine models in both aspect word and polarity prediction. Through the creation of the Hausa ABSA dataset and the development of an effective model, this study makes significant advances in ABSA research. It has wide-ranging implications for the sentiment analysis field in the context of underrepresented languages.
- 26 August 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 107 (1) , 21
Open AccessA Deep Convolutional Neural Network-Based Model for Aspect and Polarity Classification in Hausa Movie Reviews
Aspect-based sentiment analysis (ABSA) plays a pivotal role in understanding the nuances of sentiment expressed in text, particularly in the context of diverse languages and cultures. This paper presents a novel deep convolutional neural network (CNN)-based model tailored for aspect and polarity classification in Hausa movie reviews, as Hausa is an underrepresented language with limited resources and presence in sentiment analysis research. One of the primary implications of this work is the creation of a comprehensive Hausa ABSA dataset, which addresses a significant gap in the availability of resources for sentiment analysis in underrepresented languages. This dataset fosters a more inclusive sentiment analysis landscape and advances research in languages with limited resources. The collected dataset was first preprocessed using Sci-Kit Learn to perform TF-IDF transformation for extracting feature word vector weights. Aspect-level feature ontology words within the analyzed text were derived, and the sentiment of the reviewed texts was manually annotated. The proposed model combines convolutional neural networks (CNNs) with an attention mechanism to aid aspect word prediction. The model utilizes sentences from the corpus and feature words as vector inputs to enhance prediction accuracy. The proposed model leverages the advantages of the convolutional and attention layers to extract contextual information and sentiment polarities from Hausa movie reviews. The performance demonstrates the applicability of such models to underrepresented languages. With 91% accuracy on aspect term extraction and 92% on sentiment polarity classification, the model excels in aspect identification and sentiment analysis, offering insights into specific aspects of interest and their associated sentiments. The proposed model outperformed traditional machine models in both aspect word and polarity prediction. Through the creation of the Hausa ABSA dataset and the development of an effective model, this study makes significant advances in ABSA research. It has wide-ranging implications for the sentiment analysis field in the context of underrepresented languages.
- Open Access
- 22 August 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 107 (1) , 16
FairCXRnet: A Multi-Task Learning Model for Domain Adaptation in Chest X-Ray Classification for Low Resource Settings
Medical imaging analysis plays a pivotal role in modern healthcare, with physicians relying heavily on radiologists for disease diagnosis. However, many hospitals face a shortage of radiologists, leading to long queues at radiology centers and delays in diagnosis. Advances in artificial intelligence (AI) have made it possible for AI models to analyze medical images and provide insights similar to those of radiologists. Despite their successes, these models face significant challenges that hinder widespread adoption. One major issue is the inability of AI models to generalize data from new populations, as performance tends to degrade when evaluated on datasets with different or shifted distributions, a problem known as domain shift. Additionally, the large size of these models requires substantial computational resources for training and deployment. In this study, we address these challenges by investigating domain shifts using ChestXray-14 and a Nigerian chest X-ray dataset. We propose a multi-task learning (MTL) approach that jointly trains the model on both datasets for two tasks, classification and segmentation, to minimize the domain gap. Furthermore, we replace traditional convolutional layers in the backbone model (Densenet-201) architecture with depthwise separable convolutions, reducing the model’s number of parameters and computational requirements. Our proposed model demonstrated remarkable improvements in both accuracy and AUC, achieving 93% accuracy and 96% AUC when tested across both datasets, significantly outperforming traditional transfer learning methods.
- 22 August 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 107 (1) , 16
Open AccessFairCXRnet: A Multi-Task Learning Model for Domain Adaptation in Chest X-Ray Classification for Low Resource Settings
Medical imaging analysis plays a pivotal role in modern healthcare, with physicians relying heavily on radiologists for disease diagnosis. However, many hospitals face a shortage of radiologists, leading to long queues at radiology centers and delays in diagnosis. Advances in artificial intelligence (AI) have made it possible for AI models to analyze medical images and provide insights similar to those of radiologists. Despite their successes, these models face significant challenges that hinder widespread adoption. One major issue is the inability of AI models to generalize data from new populations, as performance tends to degrade when evaluated on datasets with different or shifted distributions, a problem known as domain shift. Additionally, the large size of these models requires substantial computational resources for training and deployment. In this study, we address these challenges by investigating domain shifts using ChestXray-14 and a Nigerian chest X-ray dataset. We propose a multi-task learning (MTL) approach that jointly trains the model on both datasets for two tasks, classification and segmentation, to minimize the domain gap. Furthermore, we replace traditional convolutional layers in the backbone model (Densenet-201) architecture with depthwise separable convolutions, reducing the model’s number of parameters and computational requirements. Our proposed model demonstrated remarkable improvements in both accuracy and AUC, achieving 93% accuracy and 96% AUC when tested across both datasets, significantly outperforming traditional transfer learning methods.
- Open Access
- 28 May 2024
- Published by MDPI AG in Engineering Proceedings
- Vol. 56 (1) , 338
Enhanced Driver Drowsiness Detection Model Using Multi-Level Features Fusion and a Long-Short-Term Recurrent Neural Network
Drowsiness driving poses a significant risk to road safety, necessitating effective drowsiness detection models. Most of the prior research has primarily relied on composite facial-based features, mainly focusing on the mouth and/or eye states, to identify drowsiness status. However, these models tend to overlook crucial information from input signals, resulting in suboptimal detection accuracy. Moreover, the absence of suitable algorithms and techniques for extracting other essential facial features, such as the eyebrow and nostril, further impacts the accuracy of drowsiness detection. To address these limitations, this study introduces an innovative algorithm and a technique for extracting drowsiness-related information from the eyebrow and nostril regions. Additionally, we propose a method, leveraging four composite facial-based drowsiness features; eyebrow, nostril, eye, and mouth states as inputs to a Convolutional Neural Network (CNN). A novel multilevel feature fusion method is employed to effectively combine the deep representations of these drowsiness-related features. The final step involves employing a Long-short-term memory (LSTM) recurrent neural network to classify the drowsiness status of drivers. Our proposed model is rigorously evaluated using the National Tsing Hua University drowsy driver detection (NTHU-DDD) video dataset. The experimental results demonstrate an impressive accuracy in different scenarios, and the accuracy result reached 0.973, showcasing the effectiveness of our approach in enhancing drowsiness detection accuracy and promoting road safety.
- 28 May 2024
- Published by MDPI AG in Engineering Proceedings
- Vol. 56 (1) , 338
Open AccessEnhanced Driver Drowsiness Detection Model Using Multi-Level Features Fusion and a Long-Short-Term Recurrent Neural Network
Drowsiness driving poses a significant risk to road safety, necessitating effective drowsiness detection models. Most of the prior research has primarily relied on composite facial-based features, mainly focusing on the mouth and/or eye states, to identify drowsiness status. However, these models tend to overlook crucial information from input signals, resulting in suboptimal detection accuracy. Moreover, the absence of suitable algorithms and techniques for extracting other essential facial features, such as the eyebrow and nostril, further impacts the accuracy of drowsiness detection. To address these limitations, this study introduces an innovative algorithm and a technique for extracting drowsiness-related information from the eyebrow and nostril regions. Additionally, we propose a method, leveraging four composite facial-based drowsiness features; eyebrow, nostril, eye, and mouth states as inputs to a Convolutional Neural Network (CNN). A novel multilevel feature fusion method is employed to effectively combine the deep representations of these drowsiness-related features. The final step involves employing a Long-short-term memory (LSTM) recurrent neural network to classify the drowsiness status of drivers. Our proposed model is rigorously evaluated using the National Tsing Hua University drowsy driver detection (NTHU-DDD) video dataset. The experimental results demonstrate an impressive accuracy in different scenarios, and the accuracy result reached 0.973, showcasing the effectiveness of our approach in enhancing drowsiness detection accuracy and promoting road safety.
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3220 (1) , 030002
A regularized CNN approach for detecting cervical cancer
This study delved into leveraging deep learning techniques to classify different types of cervical cancer images, recognizing the disease’s prevalence and criti This study delved into leveraging deep learning techniques to classify different types of cervical cancer images, recognizing the disease’s prevalence and criti
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3220 (1) , 030002
A regularized CNN approach for detecting cervical cancer
This study delved into leveraging deep learning techniques to classify different types of cervical cancer images, recognizing the disease’s prevalence and criti This study delved into leveraging deep learning techniques to classify different types of cervical cancer images, recognizing the disease’s prevalence and criti
- Open Access
- 2 November 2023
- Published by MDPI AG in Engineering Proceedings
- Vol. 56 (1) , 318
A Lightweight Deep Learning Model for Identifying Weeds in Corn and Soybean Using Quantization
Deep learning models are applied in precision agriculture for site-specific weed management by identifying weeds in farmlands. Unfortunately, because deep learning models are usually large, they are rarely adopted in resource-constrained devices (like edge devices) used in precision agriculture. In this study, we propose a lightweight deep learning model for detecting weeds in corn and soybean plants. We used transfer learning to train an InceptionnetV3 model for the task. The dataset used consists of a total of 13,177 samples of corn, soybean, and weeds. The InceptionV3 model, whose size is 183.34 MB, achieved a classification accuracy of 97%. We then applied the quantization technique to reduce the size of the model. The quantized model was reduced to a size of 23.38 MB, achieving an accuracy of 87%. The results show that quantization can reduce the size of a deep learning model while maintaining a reasonable amount of performance.
- 2 November 2023
- Published by MDPI AG in Engineering Proceedings
- Vol. 56 (1) , 318
Open AccessA Lightweight Deep Learning Model for Identifying Weeds in Corn and Soybean Using Quantization
Deep learning models are applied in precision agriculture for site-specific weed management by identifying weeds in farmlands. Unfortunately, because deep learning models are usually large, they are rarely adopted in resource-constrained devices (like edge devices) used in precision agriculture. In this study, we propose a lightweight deep learning model for detecting weeds in corn and soybean plants. We used transfer learning to train an InceptionnetV3 model for the task. The dataset used consists of a total of 13,177 samples of corn, soybean, and weeds. The InceptionV3 model, whose size is 183.34 MB, achieved a classification accuracy of 97%. We then applied the quantization technique to reduce the size of the model. The quantized model was reduced to a size of 23.38 MB, achieving an accuracy of 87%. The results show that quantization can reduce the size of a deep learning model while maintaining a reasonable amount of performance.
- Open Access
- 24 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (23) , 11996
State-of-the-Art Survey on Deep Learning-Based Recommender Systems for E-Learning
Recommender systems (RSs) are increasingly recognized as intelligent software for predicting users’ opinions on specific items. Various RSs have been developed in different domains, such as e-commerce, e-government, e-resource services, e-business, e-library, e-tourism, and e-learning, to make excellent user recommendations. In e-learning technology, RSs are designed to support and improve the learning practices of a student or an organization. This survey aims to examine the different works of literature on RSs that corroborate e-learning and classify and provide statistics of the reviewed articles based on their recommendation goals, recommendation techniques used, the target user, and the application platforms. The survey makes a prominent contribution to the e-learning RSs field by providing an overview of current research and traditional and nontraditional recommendation techniques to provide different recommendations for future e-learning. One of the most significant findings to emerge from this survey is that a substantial number of works followed either deep learning or context-aware recommendation techniques, which are considered more efficient than any traditional methods. Finally, we provided comprehensive observations from the quantitative assessment of publications, which can guide and support researchers in understanding the current development for potential future trends and the direction of deep learning-based RSs in e-learning.
- 24 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (23) , 11996
Open AccessState-of-the-Art Survey on Deep Learning-Based Recommender Systems for E-Learning
Recommender systems (RSs) are increasingly recognized as intelligent software for predicting users’ opinions on specific items. Various RSs have been developed in different domains, such as e-commerce, e-government, e-resource services, e-business, e-library, e-tourism, and e-learning, to make excellent user recommendations. In e-learning technology, RSs are designed to support and improve the learning practices of a student or an organization. This survey aims to examine the different works of literature on RSs that corroborate e-learning and classify and provide statistics of the reviewed articles based on their recommendation goals, recommendation techniques used, the target user, and the application platforms. The survey makes a prominent contribution to the e-learning RSs field by providing an overview of current research and traditional and nontraditional recommendation techniques to provide different recommendations for future e-learning. One of the most significant findings to emerge from this survey is that a substantial number of works followed either deep learning or context-aware recommendation techniques, which are considered more efficient than any traditional methods. Finally, we provided comprehensive observations from the quantitative assessment of publications, which can guide and support researchers in understanding the current development for potential future trends and the direction of deep learning-based RSs in e-learning.
- Open Access
- 13 May 2022
- Published by EDP Sciences in SHS Web of Conferences
- Vol. 139, 03010
Investigating the Usefulness of Metric-based Prediction Method for Spreadsheet Fault Detection
The ability to predict whether a specific section of a spreadsheet is faulty or not is frequently required for the development of spreadsheet functionality. Although errors in such spreadsheets are common and can have serious consequences, today’s spreadsheet creation and management tools offer weak capabilities for defect detection, localization, and fixing. In this thesis, we proposed a method for predicting faults in spreadsheet formulas that can detect faults in non-formula cells by combining a catalog of spreadsheet metrics with modern machine learning algorithms. An examination of the individual metrics in the catalog reveals that they are suited to detecting data where a formula is expected to have flaws. In this framework, Recall Score of 99% was achieved and performance was compared with that of Melford. The result of the experiment reveals that the proposed framework outperforms Melford framework.
- 13 May 2022
- Published by EDP Sciences in SHS Web of Conferences
- Vol. 139, 03010
Open AccessInvestigating the Usefulness of Metric-based Prediction Method for Spreadsheet Fault Detection
The ability to predict whether a specific section of a spreadsheet is faulty or not is frequently required for the development of spreadsheet functionality. Although errors in such spreadsheets are common and can have serious consequences, today’s spreadsheet creation and management tools offer weak capabilities for defect detection, localization, and fixing. In this thesis, we proposed a method for predicting faults in spreadsheet formulas that can detect faults in non-formula cells by combining a catalog of spreadsheet metrics with modern machine learning algorithms. An examination of the individual metrics in the catalog reveals that they are suited to detecting data where a formula is expected to have flaws. In this framework, Recall Score of 99% was achieved and performance was compared with that of Melford. The result of the experiment reveals that the proposed framework outperforms Melford framework.
- Open Access
- 13 May 2022
- Published by EDP Sciences in SHS Web of Conferences
- Vol. 139, 03002
A Theoretical Framework Towards Building a Lightweight Model for Pothole Detection using Knowledge Distillation Approach
Despite recent advances in deep learning, the rise of edge devices, and the exponential growth of Internet of Things (IoT) connected devices undermine the performance of deep learning models. It is clear that the future of computing is moving to edge devices. Autonomous vehicles and self-driving cars have leveraged the power of computer vision, especially object detection to navigate through traffic safely. Nevertheless, to be able to drive on all types of roads, these new vehicles have to be equipped with a road anomaly detection system, which strikes the need for small deep learning models of detecting road anomalies that can be deployed on these vehicles for safer driving experience. However, the current deep learning models are not practical on embedded devices due to the heavy resource requirements of the models, as such cannot be deployed on embedded devices. This paper proposes a theoretical approach to building a lightweight model from a cumbersome pothole detection model that is suitable on edge devices using knowledge distillation. It presents the theoretical approach of knowledge distillation, why it is a better technique of model compression compared to the rest. It shows that a cumbersome model can be made lightweight without sacrificing accuracy and with a reduced time complexity and faster training time.
- 13 May 2022
- Published by EDP Sciences in SHS Web of Conferences
- Vol. 139, 03002
Open AccessA Theoretical Framework Towards Building a Lightweight Model for Pothole Detection using Knowledge Distillation Approach
Despite recent advances in deep learning, the rise of edge devices, and the exponential growth of Internet of Things (IoT) connected devices undermine the performance of deep learning models. It is clear that the future of computing is moving to edge devices. Autonomous vehicles and self-driving cars have leveraged the power of computer vision, especially object detection to navigate through traffic safely. Nevertheless, to be able to drive on all types of roads, these new vehicles have to be equipped with a road anomaly detection system, which strikes the need for small deep learning models of detecting road anomalies that can be deployed on these vehicles for safer driving experience. However, the current deep learning models are not practical on embedded devices due to the heavy resource requirements of the models, as such cannot be deployed on embedded devices. This paper proposes a theoretical approach to building a lightweight model from a cumbersome pothole detection model that is suitable on edge devices using knowledge distillation. It presents the theoretical approach of knowledge distillation, why it is a better technique of model compression compared to the rest. It shows that a cumbersome model can be made lightweight without sacrificing accuracy and with a reduced time complexity and faster training time.
- Open Access
- 26 April 2022
- Published by MDPI AG in Journal of Low Power Electronics and Applications
- Vol. 12 (2) , 24
Low-Power Deep Learning Model for Plant Disease Detection for Smart-Hydroponics Using Knowledge Distillation Techniques
Recent advances in computing allows researchers to propose the automation of hydroponic systems to boost efficiency and reduce manpower demands, hence increasing agricultural produce and profit. A completely automated hydroponic system should be equipped with tools capable of detecting plant diseases in real-time. Despite the availability of deep-learning-based plant disease detection models, the existing models are not designed for an embedded system environment, and the models cannot realistically be deployed on resource-constrained IoT devices such as raspberry pi or a smartphone. Some of the drawbacks of the existing models are the following: high computational resource requirements, high power consumption, dissipates energy rapidly, and occupies large storage space due to large complex structure. Therefore, in this paper, we proposed a low-power deep learning model for plant disease detection using knowledge distillation techniques. The proposed low-power model has a simple network structure of a shallow neural network. The parameters of the model were also reduced by more than 90%. This reduces its computational requirements as well as its power consumption. The proposed low-power model has a maximum power consumption of 6.22 w, which is significantly lower compared to the existing models, and achieved a detection accuracy of 99.4%.
- 26 April 2022
- Published by MDPI AG in Journal of Low Power Electronics and Applications
- Vol. 12 (2) , 24
Open AccessLow-Power Deep Learning Model for Plant Disease Detection for Smart-Hydroponics Using Knowledge Distillation Techniques
Recent advances in computing allows researchers to propose the automation of hydroponic systems to boost efficiency and reduce manpower demands, hence increasing agricultural produce and profit. A completely automated hydroponic system should be equipped with tools capable of detecting plant diseases in real-time. Despite the availability of deep-learning-based plant disease detection models, the existing models are not designed for an embedded system environment, and the models cannot realistically be deployed on resource-constrained IoT devices such as raspberry pi or a smartphone. Some of the drawbacks of the existing models are the following: high computational resource requirements, high power consumption, dissipates energy rapidly, and occupies large storage space due to large complex structure. Therefore, in this paper, we proposed a low-power deep learning model for plant disease detection using knowledge distillation techniques. The proposed low-power model has a simple network structure of a shallow neural network. The parameters of the model were also reduced by more than 90%. This reduces its computational requirements as well as its power consumption. The proposed low-power model has a maximum power consumption of 6.22 w, which is significantly lower compared to the existing models, and achieved a detection accuracy of 99.4%.