Browsing by Author "Missah, Yaw Marfo"

Now showing 1 - 13 of 13
  • No Thumbnail Available
    Item
    A NovelComputerVisionModel forMedicinal Plant Identification Using Log-Gabor Filters and Deep Learning Algorithms
    (Computational Intelligence and Neuroscience, 2022) Oppong, Stephen Opku; Twum, Frimpong; Acquah-Hayfron, James Benjamin; Missah, Yaw Marfo
    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. is 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. e 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, Den-seNet201, 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. e 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.
  • No Thumbnail Available
    Item
    Agile neural expert system for managing basic education
    (Intelligent Systems with Applications, 2023-01-04) Inusah, Fuseini; Missah, Yaw Marfo; Najim, Ussiph; Twum, Frimpong; 0000-0001-9785-4464; 0000-0002-2926-681X; 0000-0002-6973-7495; 0000-0002-1869-7542
    Inadequate experts in managing resources at the lower level of education to enhance effective teaching and learning for quality education is a significant challenge in developing nations. Many basic schools lack basic educational resources such as sitting places and writing places for learners. Inadequate teaching and learning resources negatively affect the educational policies in a country. It is common to see the media projecting the challenges of a school lacking these resources. The use of an Expert System (ES) in Artificial Intelligence (AI) to assist in effective management is a necessity. In this paper, an agile neural expert system is proposed using differential equations with an initial value problem. The technique combines both rule-based and neural net works in handling the problem. The expertise of the Human Expert (HE) is used in a knowledge-based to assist in managing the resources in schools. This has been possible with the use of Data Mining (DM) techniques and modeling of projected population growth, affecting enrolment in schools and necessitating the provision of re sources to cater to the growing population. For efficiency and effectiveness in planning, provision, and management of the resources, smart notification has been embedded in the system to monitor the availability and provision of the resources by prompting the various actors in the requisition, verification, validation, and approval of resources to be supplied to schools. The system proves a higher efficiency demonstrating speed in decision-making, accuracy in decisions and ease to use.
  • No Thumbnail Available
    Item
    An enhanced RSA algorithm using Gaussian interpolation formula
    (Int. J. Computer Aided Engineering and Technology, 2022) Dawson, John Kwao; Twum, Frimpong; Missah, Yaw Marfo; Acquah-Hayfron, James Benjamin; Ayawli, Ben Beklisi Kwame; 0000-0002-7436-5550; 0000-0002-1869-7542; 0000-0002-2926-681X; 0000-0001-6935-9431; 0000-0002-1550-184X
    Data security is a crucial concern that ought to be managed to help protect vital data. Cryptography is one of the conventional approaches for securing data and is generally considered a fundamental data security component that provides privacy, integrity, confidentiality and authentication. In this paper, a hybrid data security algorithm is proposed by integrating traditional RSA and Gaussian interpolation formulas. The integration raises the security strength of RSA to the fifth degree. The Gaussian first forward interpolation is used to encrypt the ASCII values of the message after which the traditional RSA is used to encrypt and decrypt the message in the second and third levels. The last stage employs Gaussian backward interpolation to decrypt the data again. The integration helps to cater to the factorisation problem of the traditional RSA. Comparative analysis was performed using four different algorithms: RSA, SRNN, two-key pair algorithms and the proposed algorithm. It is proven that when the data size is small, the encryption and decryption times are lower for the proposed algorithm but higher when the data size is big.
  • No Thumbnail Available
    Item
    Cold Boot Attack on Encrypted Containers for Forensic Investigations
    (KSII Transactions On Internet And Information Systems,, 2022-09) Twum, Frimpong; Lagoh, Emmanuel Mawuli; Missah, Yaw Marfo; Najim, Ussiph; Ahene, Emmanuel; 0000-0002-1869-7542; 0000-0002-2926-681X; 0000-0002-6973-7495; 0000-0002-0810-1055
  • No Thumbnail Available
    Item
    Data Mining and Visualisation of Basic Educational Resources for Quality Education
    (International Journal of Engineering Trends and Technology, 2022-12) Inusah, Fuseini; Missah, Yaw Marfo; Najim, Ussiph; Twum, Frimpong; 0000-0001-9785-4464; 0000-0002-2926-681X; 0000-0002-6973-7495; 0000-0002-1869-7542
    With an increase in educational resources for the growing population, data for Basic Education (BE) is becoming larger, requiring technical data tools to analyze and interpret. This research uses classification and clustering techniques to analyze the data from public schools in Ghana to identify the challenges. Nine (9) data mining algorithms in rapid miner studio 9.10 were used for the analysis to know the most efficient algorithm suitable for the data. These are; Generalized Linear Module (GLM), Naïve Bayes (NB), Logistic Regression (LR), Deep Learning (DL), Decision Tree (DT), Fast Large Margins (FLM), Gradient Boosted Tree (GBT), Random Forest (RF), and Support Vector Machines (SVM). The performance of GBT was seen as more appropriate, and this algorithm's results were presented. Excerpts from the reports are also included in the form of qualitative data. A diagrammatic representation of the interoperability among levels of education for quality education has also been presented. A proposed Neural Network model has been designed for the challenges and solutions. The conclusions draw that addressing the challenges of BE requires educational policy stability and enforcement to maximize resources and minimize the challenges in schools at all levels of education.
  • No Thumbnail Available
    Item
    Ensuring confidentiality and privacy of cloud data using a non-deterministic cryptographic scheme
    (PLOS One, 2023-02-09) Dawson, John Kwao; Twum, Frimpong; Hayfron-Acquah, James Benjamin; Missah, Yaw Marfo; 0000-0002-7436-5550; 0000-0002-1869-7542; 0000-0001-6935-9431; 0000-0002-2926-681X
    The amount of data generated by electronic systems through e-commerce, social networks, and data computation has risen. However, the security of data has always been a challenge.The problem is not with the quantity of data but how to secure the data by ensuring its confi dentiality and privacy. Though there are several research on cloud data security, this study proposes a security scheme with the lowest execution time. The approach employs a non linear time complexity to achieve data confidentiality and privacy. A symmetric algorithm dubbed the Non-Deterministic Cryptographic Scheme (NCS) is proposed to address the increased execution time of existing cryptographic schemes. NCS has linear time complex ity with a low and unpredicted trend of execution times. It achieves confidentiality and pri vacy of data on the cloud by converting the plaintext into Ciphertext with a small number of iterations thereby decreasing the execution time but with high security. The algorithm is based on Good Prime Numbers, Linear Congruential Generator (LGC), Sliding Window Algorithm (SWA), and XOR gate. For the implementation in C#, thirty different execution times were performed and their average was taken. A comparative analysis of the NCS was performed against AES, DES, and RSA algorithms based on key sizes of 128kb, 256kb, and 512kb using the dataset from Kaggle. The results showed the proposed NCS execution times were lower in comparison to AES, which had better execution time than DES with RSA having the longest. Contrary, to existing knowledge that execution time is relative to data size, the results obtained from the experiment indicated otherwise for the proposed NCS algorithm. With data sizes of 128kb, 256kb, and 512kb, the execution times in milliseconds were 38, 711, and 378 respectively. This validates the NCS as a Non-Deterministic Cryptographic Algorithm. The study findings hence are in support of the argument that data size does not determine the execution time of a cryptographic algorithm but rather the size of the security key.
  • No Thumbnail Available
    Item
    Evaluation of Conversational Agents: Understanding Culture, Context and Environment in Emotion Detection
    (IEEE Access, 2022-02) Teye, Martha T.; Missah, Yaw Marfo; Ahene, Emmanuel; Twum, Frimpong; 0000-0002-2370-4700; 0000-0002-2926-681X; 0000-0002-0810-1055; 0000-0002-1869-7542
    Valuable decisions and highly prioritized analysis now depend on applications such as facial biometrics, social media photo tagging, and human robots interactions. However, the ability to successfully deploy such applications is based on their efficiencies on tested use cases taking into consideration possible edge cases. Over the years, lots of generalized solutions have been implemented to mimic human emotions including sarcasm. However, factors such as geographical location or cultural difference have not been explored fully amidst its relevance in resolving ethical issues and improving conversational AI (Artificial Intelligence). In this paper, we seek to address the potential challenges in the usage of conversational AI within Black African society. We develop an emotion prediction model with accuracies ranging between 85% and 96%. Our model combines both speech and image data to detect the seven basic emotions with a focus on also identifying sarcasm. It uses 3-layers of the Convolutional Neural Network in addition to a new Audio-Frame Mean Expression (AFME) algorithm and focuses on model pre-processing and post processing stages. In the end, our proposed solution contributes to maintaining the credibility of an emotion recognition system in conversational AIs.
  • No Thumbnail Available
    Item
    Implementation of a Data Protection Model dubbed Harricent_RSECC
    ((IJACSA) International Journal of Advanced Computer Science and Applications, 2022) Twum, Frimpong; Amankona, Vincent; Missah, Yaw Marfo; Najim, Ussiph; Opoku, Michael; 0000-0002-1869-7542; 0000-0001-8658-7575; 0000-0002-2926-681X; 0000-0002-6973-7495
    Every organization subsists on data, which is a quintessential resource. Quite a number of studies have been carried out relative to procedures that can be deployed to enhance data protection. However, available literature indicates most authors have focused on either encryption or encoding schemes to provide data security. The ability to integrate these techniques and leverage on their strengths to achieve a robust data protection is the pivot of this study. As a result, a data protection model, dubbed Harricent_RSECC has been designed and implemented to achieve the study’s objective through the utilization of Elliptic Curve Cryptography (ECC) and Reed Solomon (RS) codes. The model consists of five components, namely: message identification, generator module, data encoding, data encryption and data signature. The result is the generation of the Reed Solomon codewords; cipher texts; and generated hash values which are utilized to detect and correct corrupt data; obfuscates data; and sign data respectively, during transmission or storage. The contribution of this paper is the ability to combine encoding and encryption schemes to enhance data protection to ensure confidentiality, authenticity, integrity, and non-repudiation.
  • No Thumbnail Available
    Item
    Integrating expert system in managing basic education: A survey in Ghana
    (International Journal of Information Management Data Insights, 2023-03-13) Inusah, Fuseini; Missah, Yaw Marfo; Najim, Ussiph; Twum, Frimpong; 0000-0001-9785-4464; 0000-0002-2926-681X; 0000-0002-6973-7495; 0000-0002-1869-7542
    Management of basic education in developing countries like Ghana is a major challenge as resources are not ad equately available for effective teaching and learning in schools. Careful planning and prediction using available data is also a major challenge as there are inaccuracies and inconsistencies in the available data. An investigation into the use of an Expert System for easy management of the resources is carried out in this research to know the level of readiness to accept an ES to assist in management. Stakeholders of education are contacted to solicit their views. With 216 districts for managing education in the country, a minimum of 3 participants were selected from each district to constitute a sample for the survey. In all 648 participants data were analyzed. The unstructured interview was also conducted using 9 members of an executive position in management. A thematic analysis was done on the responses and presented in diagrammatic form. The Acceptance Model for Educational Expert System (AMEES) is also presented. The results showed the majority of respondents agree with the use of an Expert System (ES) to assist in managing basic education. The use of data mining techniques to filter the data in an ES and help in easy prediction for decision-making accuracy is a necessity.
  • No Thumbnail Available
    Item
    Predicting Bank Operational Efficiency Using Machine Learning Algorithm: Comparative Study of Decision Tree, Random Forest, and Neural Networks
    (Advances in Fuzzy Systems, 2020) Appiahene, Peter; Missah, Yaw Marfo; Najim, Ussiph; 0000-0002-6098-4537; 0000-0002-2926-681X; 0000-0002-6973-7495
    %e financial crisis that hit Ghana from 2015 to 2018 has raised various issues with respect to the efficiency of banks and the safety of depositors’ in the banking industry. As part of measures to improve the banking sector and also restore customers’ confidence,efficiency and performance analysis in the banking industry has become a hot issue. %is is because stakeholders have to detect the underlying causes of inefficiencies within the banking industry. Nonparametric methods such as Data Envelopment Analysis (DEA) have been suggested in the literature as a good measure of banks’ efficiency and performance. Machine learning algorithms have also been viewed as a good tool to estimate various nonparametric and nonlinear problems. %is paper presents a combined DEA with three machine learning approaches in evaluating bank efficiency and performance using 444 Ghanaian bank branches, Decision Making Units (DMUs). %e results were compared with the corresponding efficiency ratings obtained from the DEA. Finally, the prediction accuracies of the three machine learning algorithm models were compared. %e results suggested that the decision tree (DT) and its C5.0 algorithm provided the best predictive model. It had 100% accuracy in predicting the 134 holdout sample dataset (30% banks) and a P value of 0.00. %e DT was followed closely by random forest algorithm with a predictive accuracy of 98.5% and a P value of 0.00 and finally the neural network (86.6% accuracy) with a P value 0.66. %e study concluded that banks in Ghana can use the result of this study to predict their respective efficiencies. All experiments were performed within a simulation environment and conducted in R studio using R codes.
  • No Thumbnail Available
    Item
    Rainfall Prediction Using Machine Learning Algorithms for the Various Ecological Zones of Ghana
    (IEEE Access, 2022) Appiah-Badu, Nana Kofi Ahoi; Missah, Yaw Marfo; Amekudzi, Leonard K.; Najim, Ussiph; Twum, Frimpong; Ahene, Emmanuell; 0000-0002-3029-4498; 0000-0002-2186-3425; 0000-0002-2926-681X; 0000-0002-6973-7495; 0000-0002-1869-7542; 0000-0002-0810-1055
    Accurate rainfall prediction has become very complicated in recent times due to climate change and variability. The efficiency of classification algorithms in rainfall prediction has flourished. The study contributes to using various classification algorithms for rainfall prediction in the different ecological zones of Ghana. The classification algorithms include Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGB) and K-Nearest Neighbour (KNN). The dataset, consisting of various climatic attributes, was sourced from the Ghana Meteorological Agency spanning 1980 – 2019. The performance of the classification algorithms was examined based on precision, recall, f1-score, accuracy and execution time with various training and testing data ratios. On all three training and testing ratios: 70:30, 80:20 and 90:10, RF, XGB and MLP performed well, whereas KNN performed least across all zones. In terms of the execution time of the models, Decision Tree is consistently portrayed as the fastest, whereas MLP used the most run time.
  • No Thumbnail Available
    Item
    Rainfall Prediction Using Machine Learning Algorithms for the Various Ecological Zones of Ghana
    (IEEE Access, 2022-12) Appiah-Badu, Nana Kofi Ahoi; Missah, Yaw Marfo; Amekudzi, Leonard K.; Ussiph, Najim; Frimpong, Twum; Ahene, Emmanuel; 0000-0002-3029-4498; 0000-0002-2926-681X; 0000-0002-2186-3425; 0000-0002-6973-7495; 0000-0002-1869-7542; 0000-0002-0810-1055
    Accurate rainfall prediction has become very complicated in recent times due to climate change and variability. The efficiency of classification algorithms in rainfall prediction has flourished. The study contributes to using various classification algorithms for rainfall prediction in the different ecological zones of Ghana. The classification algorithms include Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGB) and K-Nearest Neighbour (KNN). The dataset, consisting of various climatic attributes, was sourced from the Ghana Meteorological Agency spanning 1980 – 2019. The performance of the classification algorithms was examined based on precision, recall, f1-score, accuracy and execution time with various training and testing data ratios. On all three training and testing ratios: 70:30, 80:20 and 90:10, RF, XGB and MLP performed well, whereas KNN performed least across all zones. In terms of the execution time of the models, Decision Tree is consistently portrayed as the fastest, whereas MLP used the most run time.
  • No Thumbnail Available
    Item
    Reconnoitering Security Algorithms Performance in the Cloud: Systematic Literature Review based on the Prisma Archetype
    (Journal of Theoretical and Applied Information Technology, 2023-03-31) Dawson, John Kwao; Twum, Frimpong; Hayfron-Acquah, James Benjamin; Missah, Yaw Marfo; 0000-0002-7436-5550; 0000-0002-1869-7542; 0000-0001-6935-9431; 0000-0002-2926-681X
    Industries and academia have embraced cloud computing for their day-to-day activities. A lot of studies have been done to unpin variants of cryptographic algorithms used to secure the cloud. This survey aims to unravel recent studies of the most employed cryptographic scheme used to secure the cloud, the type of cryptographic algorithms used, the execution time trend of the cryptographic algorithms (Linear time / Non-Linear time), the aims of these cryptographic algorithms, and identify some of the security concerns in cloud computing. The study considered published studies from 2015 to 2022 from well-known databases such as Taylor and Francis, Scopus, Research Gate, Web of Science, IEEE Xplore, Science Direct, Hindawi, Google Scholar, and ACM. A total of 72 published articles were considered to respond to the various specific objectives using the Prisma framework. The systematic literature review has revealed the usage of encryption schemes as the most employed cryptographic approach and data security and cloud security as the most researched security challenge. The security challenges that were identified are data integrity and preservation, intrusion detection, and privacy and confidentiality. It has been revealed that from 2015 to 2022, 90% of encryption algorithms depict linear time complexity. The systematic literature review has proven little usage of symmetric stream cipher algorithms to ensure the privacy and confidentiality of cloud data.