Yaw Marfo Missah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yaw Marfo Missah has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Frimpong Twum
Department of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
5 shared publications - Emmanuel Ahene
Kwame Nkrumah University of Science and Technology
4 shared publications Najim Ussiph
4 shared publicationsTwum Frimpong
Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
3 shared publications- Frimpong Twum
Kwame Nkrumah University of Science and Technology
2 shared publications - Frimpong Twum
Kwame Nkrumah University of Science and Technology, Ghana
2 shared publications
Latest Publications
- Open Access
- 14 October 2026
- Published by Elsevier in SSRN Electronic Journal
MPACT: Multimodal Pulmonary Abnormality Classification with CNN-Transformer and Content-Aware Sampling
Pulmonary diseases continue to be among the largest causes of morbidity and mortality globally and are a significant strain on health care systems, particularly in low- and middle-income countries. Chest X-ray is a primary imaging modality, but image interpretation is not solely dependent on the image features, but on the report text combined with image interpretation. Current deep learning systems are mainly unimodal, and even the recent multimodal ones usually concatenate image and text features at shallow levels, failing to meaningfully influence their representation. In this work, we introduce MPACT, a multimodal method for classifying binary pulmonary abnormalities in pairs of radiographs and radiology reports. The proposed framework includes: (i) a parallel hybrid visual encoder designed to obtain the local texture and global structural patterns simultaneously, consisting of a custom CNN backbone and Swin Transformer branch; (ii) a domain-adapted BioBERT text encoder with handcrafted auxiliary clinical features extracted from the text of radiology reports; (iii) a bidirectional cross-modal attention fusion mechanism; (iv) a classification head that is activated by GELU and has a residual skip-connection branch; and (v) a content-aware weighted sampling strategy, which considers class imbalance and within-class clinical heterogeneity. Compared with four benchmark models, MPACT outperforms them in terms of accuracy (98.69%), precision (0.9888), specificity (0.9887), sensitivity (0.9851), F1-score (0.9870), and AUC-ROC (0.9987) on the Indiana University Chest X-Ray (IU-XRay) dataset for distinguishing between normal and abnormal cases. Each component of the architecture contributes uniquely, as confirmed by a systematic ablation study.
- 14 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMPACT: Multimodal Pulmonary Abnormality Classification with CNN-Transformer and Content-Aware Sampling
Pulmonary diseases continue to be among the largest causes of morbidity and mortality globally and are a significant strain on health care systems, particularly in low- and middle-income countries. Chest X-ray is a primary imaging modality, but image interpretation is not solely dependent on the image features, but on the report text combined with image interpretation. Current deep learning systems are mainly unimodal, and even the recent multimodal ones usually concatenate image and text features at shallow levels, failing to meaningfully influence their representation. In this work, we introduce MPACT, a multimodal method for classifying binary pulmonary abnormalities in pairs of radiographs and radiology reports. The proposed framework includes: (i) a parallel hybrid visual encoder designed to obtain the local texture and global structural patterns simultaneously, consisting of a custom CNN backbone and Swin Transformer branch; (ii) a domain-adapted BioBERT text encoder with handcrafted auxiliary clinical features extracted from the text of radiology reports; (iii) a bidirectional cross-modal attention fusion mechanism; (iv) a classification head that is activated by GELU and has a residual skip-connection branch; and (v) a content-aware weighted sampling strategy, which considers class imbalance and within-class clinical heterogeneity. Compared with four benchmark models, MPACT outperforms them in terms of accuracy (98.69%), precision (0.9888), specificity (0.9887), sensitivity (0.9851), F1-score (0.9870), and AUC-ROC (0.9987) on the Indiana University Chest X-Ray (IU-XRay) dataset for distinguishing between normal and abnormal cases. Each component of the architecture contributes uniquely, as confirmed by a systematic ablation study.
- 19 July 2025
- Published by Elsevier in Computers & Security
- Vol. 157
Hybrid framework of differential privacy and secure multi-party computation for privacy-preserving entity resolution
- 19 July 2025
- Published by Elsevier in Computers & Security
- Vol. 157
Hybrid framework of differential privacy and secure multi-party computation for privacy-preserving entity resolution
- Open Access
- 12 February 2024
- Published by River Publishers in Journal of Cyber Security and Mobility
- p. 265-282
Cryptographic Solutions for Data Security in Cloud Computing:
Due to the recent explosion in the amount of data being created by various social media platforms, e-commerce websites, and other businesses, a paradigm shift from on-site data centers to the cloud is required. Concerns about privacy and secrecy have been a major obstacle to the mainstream adoption of cloud computing. The best approach to protect the confidentiality and privacy of cloud data is by using cryptographic techniques. Researchers have developed several cryptographic algorithms, but they all have lengthy, linear, predictable, memory-intensive execution times. The performance of the CPU, memory, run-time trend, and throughput of the three cryptographic schemes: Enhanced RSA (ERSA), Non-Deterministic Cryptographic Scheme (NCS), and Enhanced Homomorphic Scheme (EHS) are compared using RAsys. The experiment’s results demonstrated that NCS and EHS produced non-linear and non-deterministic run times. Again, NCS and EHS produced the lowest throughput and memory consumption for text and numeric data types when data sizes of 5n*102(KB(∈1,2,4,10,20,40) were processed. However, ERSA produced a run-time trend that was deterministic, linear, and predictable
- 12 February 2024
- Published by River Publishers in Journal of Cyber Security and Mobility
- p. 265-282
Open AccessCryptographic Solutions for Data Security in Cloud Computing:
Due to the recent explosion in the amount of data being created by various social media platforms, e-commerce websites, and other businesses, a paradigm shift from on-site data centers to the cloud is required. Concerns about privacy and secrecy have been a major obstacle to the mainstream adoption of cloud computing. The best approach to protect the confidentiality and privacy of cloud data is by using cryptographic techniques. Researchers have developed several cryptographic algorithms, but they all have lengthy, linear, predictable, memory-intensive execution times. The performance of the CPU, memory, run-time trend, and throughput of the three cryptographic schemes: Enhanced RSA (ERSA), Non-Deterministic Cryptographic Scheme (NCS), and Enhanced Homomorphic Scheme (EHS) are compared using RAsys. The experiment’s results demonstrated that NCS and EHS produced non-linear and non-deterministic run times. Again, NCS and EHS produced the lowest throughput and memory consumption for text and numeric data types when data sizes of 5n*102(KB(∈1,2,4,10,20,40) were processed. However, ERSA produced a run-time trend that was deterministic, linear, and predictable
- 26 December 2022
- Published by Springer Nature in SN Computer Science
- Vol. 4 (2) , 1-29
Reseed Skipping of Linear Congruential Generator for Multi-level Image Steganography Security of Financial Data
- 26 December 2022
- Published by Springer Nature in SN Computer Science
- Vol. 4 (2) , 1-29
Reseed Skipping of Linear Congruential Generator for Multi-level Image Steganography Security of Financial Data
- 25 December 2022
- Published by Seventh Sense Research Group Journals in International Journal of Engineering Trends and Technology
- Vol. 70 (12) , 296-307
Data Mining and Visualisation of Basic Educational Resources for Quality Education
Data Mining and Visualisation of Basic Educational Resources for Quality Education
- 25 December 2022
- Published by Seventh Sense Research Group Journals in International Journal of Engineering Trends and Technology
- Vol. 70 (12) , 296-307
Data Mining and Visualisation of Basic Educational Resources for Quality Education
Data Mining and Visualisation of Basic Educational Resources for Quality Education
- Open Access
- 7 November 2022
- Published by Slovenian Association Informatika in Informatica
- Vol. 46 (8)
Ensuring Privacy and Confidentiality of Data on the Cloud Using an Enhanced Homomorphism Scheme
Cloud computing is one of the widest phenomena embraced in information technology. This result from numerous advantages associated with it making many organizations and individuals offload their data to the cloud. Encryption schemes restrict access to data from unauthorized clients, helping attain confidentiality and privacy. The modification of the ciphertext of clients’ data on the cloud demand downloading, deciphering, editing, and finally uploading back to the cloud by sharing their private key with the cloud service provider making it tedious. The application of homomorphism, allows computation to be performed on ciphertext with no decipher activity which helps to avoid the surfacing of sensitive client data stored on the cloud. In this paper, an Enhanced Homomorphism Scheme (EHS) is proposed based on Good Prime Numbers (GPN), Linear Congruential Generator (LCG), Fixed Sliding Window Algorithm (FSWA), and Gentry’s homomorphism scheme. A dataset from the Kaggle database was used to test the proposed algorithm. A variety of tests were conducted using the proposed algorithm such as the Uniqueness of ciphertext, addition and multiplication property of full homomorphism, and the execution times using 2^n (n ∈ 2,3,4,5) data sizes. A comparison of the execution time of the proposed EHS was conducted with the New Fully Homomorphism Scheme (NFHS), and the Enhanced Homomorphism Encryption Scheme (EHES). From the comparison, the proposed EHS algorithm had the lowest encryption time when a data size of 24kb was executed but with a higher decryption time of 567.6667 ± 96.38911when a data size of 8kb was used. On the other hand, with a data size of 32kb, EHES had the highest decryption time of 1274ms with the proposed EHS having the lowest decryption time of 551.2222 ± 82.68746 indicating a decryption percentage decrease of 56.73%. This confirms that execution times are dependent on the size of the encryption key but not on data size.
- 7 November 2022
- Published by Slovenian Association Informatika in Informatica
- Vol. 46 (8)
Open AccessEnsuring Privacy and Confidentiality of Data on the Cloud Using an Enhanced Homomorphism Scheme
Cloud computing is one of the widest phenomena embraced in information technology. This result from numerous advantages associated with it making many organizations and individuals offload their data to the cloud. Encryption schemes restrict access to data from unauthorized clients, helping attain confidentiality and privacy. The modification of the ciphertext of clients’ data on the cloud demand downloading, deciphering, editing, and finally uploading back to the cloud by sharing their private key with the cloud service provider making it tedious. The application of homomorphism, allows computation to be performed on ciphertext with no decipher activity which helps to avoid the surfacing of sensitive client data stored on the cloud. In this paper, an Enhanced Homomorphism Scheme (EHS) is proposed based on Good Prime Numbers (GPN), Linear Congruential Generator (LCG), Fixed Sliding Window Algorithm (FSWA), and Gentry’s homomorphism scheme. A dataset from the Kaggle database was used to test the proposed algorithm. A variety of tests were conducted using the proposed algorithm such as the Uniqueness of ciphertext, addition and multiplication property of full homomorphism, and the execution times using 2^n (n ∈ 2,3,4,5) data sizes. A comparison of the execution time of the proposed EHS was conducted with the New Fully Homomorphism Scheme (NFHS), and the Enhanced Homomorphism Encryption Scheme (EHES). From the comparison, the proposed EHS algorithm had the lowest encryption time when a data size of 24kb was executed but with a higher decryption time of 567.6667 ± 96.38911when a data size of 8kb was used. On the other hand, with a data size of 32kb, EHES had the highest decryption time of 1274ms with the proposed EHS having the lowest decryption time of 551.2222 ± 82.68746 indicating a decryption percentage decrease of 56.73%. This confirms that execution times are dependent on the size of the encryption key but not on data size.
- 30 September 2022
- Published by Korean Society for Internet Information (KSII) in KSII Transactions on Internet and Information Systems
- Vol. 16 (9) , 3068-3086
Cold Boot Attack on Encrypted Containers for Forensic Investigations
KSII Transactions on Internet and Information Systems TIIS Paper Details
- 30 September 2022
- Published by Korean Society for Internet Information (KSII) in KSII Transactions on Internet and Information Systems
- Vol. 16 (9) , 3068-3086
Cold Boot Attack on Encrypted Containers for Forensic Investigations
KSII Transactions on Internet and Information Systems TIIS Paper Details
- Open Access
- 27 September 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-21
A Novel Computer Vision Model for Medicinal Plant Identification Using Log-Gabor Filters and Deep Learning Algorithms
Computer vision is the science that enables computers and machines to see and perceive image content on a semantic level. It combines concepts, techniques, and ideas from various fields such as digital image processing, pattern matching, artificial intelligence, and computer graphics. A computer vision system is designed to model the human visual system on a functional basis as closely as possible. Deep learning and Convolutional Neural Networks (CNNs) in particular which are biologically inspired have significantly contributed to computer vision studies. This research develops a computer vision system that uses CNNs and handcrafted filters from Log-Gabor filters to identify medicinal plants based on their leaf textural features in an ensemble manner. The system was tested on a dataset developed from the Centre of Plant Medicine Research, Ghana (MyDataset) consisting of forty-nine (49) plant species. Using the concept of transfer learning, ten pretrained networks including Alexnet, GoogLeNet, DenseNet201, Inceptionv3, Mobilenetv2, Restnet18, Resnet50, Resnet101, vgg16, and vgg19 were used as feature extractors. The DenseNet201 architecture resulted with the best outcome of 87% accuracy and GoogLeNet with 79% preforming the worse averaged across six supervised learning algorithms. The proposed model (OTAMNet), created by fusing a Log-Gabor layer into the transition layers of the DenseNet201 architecture achieved 98% accuracy when tested on MyDataset. OTAMNet was tested on other benchmark datasets; Flavia, Swedish Leaf, MD2020, and the Folio dataset. The Flavia dataset achieved 99%, Swedish Leaf 100%, MD2020 99%, and the Folio dataset 97%. A false-positive rate of less than 0.1% was achieved in all cases.
- 27 September 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-21
Open AccessA Novel Computer Vision Model for Medicinal Plant Identification Using Log-Gabor Filters and Deep Learning Algorithms
Computer vision is the science that enables computers and machines to see and perceive image content on a semantic level. It combines concepts, techniques, and ideas from various fields such as digital image processing, pattern matching, artificial intelligence, and computer graphics. A computer vision system is designed to model the human visual system on a functional basis as closely as possible. Deep learning and Convolutional Neural Networks (CNNs) in particular which are biologically inspired have significantly contributed to computer vision studies. This research develops a computer vision system that uses CNNs and handcrafted filters from Log-Gabor filters to identify medicinal plants based on their leaf textural features in an ensemble manner. The system was tested on a dataset developed from the Centre of Plant Medicine Research, Ghana (MyDataset) consisting of forty-nine (49) plant species. Using the concept of transfer learning, ten pretrained networks including Alexnet, GoogLeNet, DenseNet201, Inceptionv3, Mobilenetv2, Restnet18, Resnet50, Resnet101, vgg16, and vgg19 were used as feature extractors. The DenseNet201 architecture resulted with the best outcome of 87% accuracy and GoogLeNet with 79% preforming the worse averaged across six supervised learning algorithms. The proposed model (OTAMNet), created by fusing a Log-Gabor layer into the transition layers of the DenseNet201 architecture achieved 98% accuracy when tested on MyDataset. OTAMNet was tested on other benchmark datasets; Flavia, Swedish Leaf, MD2020, and the Folio dataset. The Flavia dataset achieved 99%, Swedish Leaf 100%, MD2020 99%, and the Folio dataset 97%. A false-positive rate of less than 0.1% was achieved in all cases.
- Open Access
- 5 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 83204-83220
Textural Analysis for Medicinal Plants Identification Using Log Gabor Filters
Texture plays a crucial role in computer vision, providing valuable information about image regions. Log Gabor filters that mimic the human eye’s visual cortex are used as feature extractors to identify medicinal plants based on the leaf textural features. This method was tested on a dataset developed from the Centre of Plant Medicine Research, Ghana, consisting of forty-nine (49) plant species as well as the Flavia and Swedish Leaf datasets, which are benchmark datasets. The Log Gabor filter outperformed the Gabor filters, which have been extensively used in this area when tested on nine supervised classifiers (K-Nearest Neighbour, Support Vector Machine, Naïve Bayes, Logistic Regression, Decision tree, Random Forest, Multilayer Perceptron, Gradient Boosting and Stochastic Gradient Descent) with 10-fold cross-validation. The Support Vector Machine and Multilayer Perceptron were the best performing classifiers for both Log Gabor filter and Gabor filter in terms of accuracy, precision, true positive rate, F1 score and false positive rate. The Log Gabor filter’s highest accuracy was 79% for Mydatastet, 97% for Flavia, and 98% for the Swedish Leaf dataset whiles the Gabor filter’s highest accuracy was 66% for Mydatastet, 92% for Flavia and 96% for the Swedish Leaf dataset.
- 5 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 83204-83220
Open AccessTextural Analysis for Medicinal Plants Identification Using Log Gabor Filters
Texture plays a crucial role in computer vision, providing valuable information about image regions. Log Gabor filters that mimic the human eye’s visual cortex are used as feature extractors to identify medicinal plants based on the leaf textural features. This method was tested on a dataset developed from the Centre of Plant Medicine Research, Ghana, consisting of forty-nine (49) plant species as well as the Flavia and Swedish Leaf datasets, which are benchmark datasets. The Log Gabor filter outperformed the Gabor filters, which have been extensively used in this area when tested on nine supervised classifiers (K-Nearest Neighbour, Support Vector Machine, Naïve Bayes, Logistic Regression, Decision tree, Random Forest, Multilayer Perceptron, Gradient Boosting and Stochastic Gradient Descent) with 10-fold cross-validation. The Support Vector Machine and Multilayer Perceptron were the best performing classifiers for both Log Gabor filter and Gabor filter in terms of accuracy, precision, true positive rate, F1 score and false positive rate. The Log Gabor filter’s highest accuracy was 79% for Mydatastet, 97% for Flavia, and 98% for the Swedish Leaf dataset whiles the Gabor filter’s highest accuracy was 66% for Mydatastet, 92% for Flavia and 96% for the Swedish Leaf dataset.
- Open Access
- 8 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 35900
Corrections to “Evaluation of Conversational Agents: Understanding Culture, Context and Environment in Emotion Detection”
In the above article [1] , one author was omitted from the author list. This is a correction to include Auxane Boch as a coauthor to this published work.
- 8 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 35900
Open AccessCorrections to “Evaluation of Conversational Agents: Understanding Culture, Context and Environment in Emotion Detection”
In the above article [1] , one author was omitted from the author list. This is a correction to include Auxane Boch as a coauthor to this published work.