Browsing by Author "Gyening, Rose-Mary Owusuaa Mensah"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    A NOVEL SOIL MOISTURE, TEMPERATURE AND HUMIDITY MEASURING SYSTEM- AN IOT APPROACH
    (Journal of Theoretical and Applied Information Technology, 2021-03) AKPALU, 1 LARRY ELIKPLIM KODJO; Gyening, Rose-Mary Owusuaa Mensah; YAKUBU, OSMAN; 0000-0002-8087-5207
    The world is currently experiencing a rapid population growth resulting in increased food demand. To avoid the risk of famine in especially low-income countries, effective and efficient agricultural practices that will enhance food production at a lower cost is desired. For effective food production, soil quality is very important. There should be improved techniques to determine precise soil moisture, humidity, and temperature measurement to guide farmers to be efficient. In Sub-Saharan African countries such as Ghana, farmers use conventional methods to check how good the soil is for cultivating crops; they examine the soil with their bare hands. This approach has proven to be ineffective as it requires significant amount of human effort. To address this challenge, an IoT based soil moisture, humidity, and temperature measurement system is proposed. It consists of a moisture probe to determine the moisture percentage of the soil, a temperature and humidity sensor for measuring the temperature and humidity of the soil, and a Wi-Fi module for transmitting the data to a data repository for analysis. A prototype is developed based on a conceptual framework which is tested under live conditions. Based on ideal parameters for the cultivation of certain crops which are stored in the data repository, and the live data captured by the sensors, the farmers are alerted electronically on the most suitable crops to plant. The system was tested in five different locations and based on the data gathered, it recommended the products that are suitable for cultivation in a particular field. The proposed system outperformed other referenced models in identifying soil suitability for the cultivation of crops. The system was able to recommend suitable crops for planting based on data on soil parameters, a feature that made it novel.
  • No Thumbnail Available
    Item
    An improved man-in-the-middle (MITM) attack detections using convolutional neural networks
    (Multidiciplainary Science Journal, 2024-08) Iddrisu, Mohammed; Takyi, Kate; Gyening, Rose-Mary Owusuaa Mensah; Peasah, Kwame Ofosuhene; Banning, Linda Amoako; Agyemang, Kwabena Owusu; 0000-0002-8087-5207
    The increasing reliance on digital communication networks has made information security a critical concern for individuals, organizations, and governments worldwide. Man-in-the-middle (MITM) attacks are significant, prevalent, and damaging concerning cyber-attacks. Detecting MitM attacks is complex due to their stealthy nature and the sophisticated methods employed by attackers. There is the need for researchers to address this issue using current and novel methods like artificial intelligence. In this paper, an improved MitM attack detection approach using the Convolutional Neural Network (CNN) deep learning algorithm is developed, resulting in an overall detection accuracy of 0.986%. The results confirms that the proposed model is very efficient in comparision to other proposed solutions by other authors.
  • No Thumbnail Available
    Item
    Cocoa beans classification using enhanced image feature extraction techniques and a regularized Artificial Neural Network model
    (Elseviere, 2023-07) Opoku, Eric; Gyening, Rose-Mary Owusuaa Mensah; Appiah, Obed; Takyi, Kate; Appiahene, Peter; 0000-0002-8087-5207
    Cut-Test technique employs visual inspection of interior coloration, compartmentalization, and defects of beans for effective classification of cocoa beans. However, due to its subjective nature and natural variations in visual perception, it is intrinsically limited, resulting in disparities in verdicts, imprecision, discordance, and time-consuming and labor-intensive classification procedures. Machine Learning (ML) techniques have been proposed to address these challenges with significant results, but there is still a need for improvement. In this paper, we propose a color and texture extraction technique for image representation, as well as a generalized, less complex Neural Network model, to help improve the performance of machine classification of Cut-Test cocoa beans. A total of 1400 beans were classified into 14 grades. Experimental results on the equal cocoa cut-test dataset, which is the standard publicly available cut-test dataset, show that the novel extraction method combined with the developed Artificial Neural Networks provides a more homogeneous classification rate for all grades, obtaining 85.36%, 85%, 83%, and 83% for accuracy, precision, recall, and F1 measure, respectively. The proposed model outperforms other ML models, such as Support Vector Machines, Decision Trees, Random Forests, and Naïve Bayes, on the same dataset. Additionally, the proposed ANN model demonstrates relatively better generalization when compared with earlier work by Santos on the same dataset. The proposed techniques in this work are robust on the cut-test dataset and can serve as an accurate Computer-Aided Diagnostic tool for cocoa bean classification.
  • No Thumbnail Available
    Item
    Deep learning based capsule networks for breast cancer classification using ultrasound images
    (SyncSci Publisher, 2024-08) Afrifa, Stephen; Varadarajan, Vijayakumar; Zhang, Tao; Appiahene, Peter; Gyamf, Daniel; Gyening, Rose-Mary Owusuaa Mensah; Mensah, Jacob; Berchie, Samuel Opoku; 0000-0002-8087-5207
    Abstract: Purposes: Breast cancer (BC) is a disease in which the breast cells multiply uncon trolled. Breast cancer is one of the most often diagnosed malignancies in women worldwide. Early identification of breast cancer is critical for limiting the impact on affected people’s health conditions. The influence of technology and artificial intelligence approaches (AI) in the health industry is tremendous as technology advances. Deep learning (DL) techniques are used in this study to classify breast lumps. Materials and Methods: The study makes use of two distinct breast ultrasound images (BUSI) with binary and multiclass classification. To assist the models in understanding the data, the datasets are exposed to numerous preprocessing and hyperparameter approaches. With data imbalance being a key difficulty in health analysis, due to the likelihood of not having a condition exceeding that of having the disease, this study applies a cutoff stage to impact the decision threshold in the datasets data augmentation procedures. The capsule neural network (CapsNet), Gabor capsule network (GCN), and convolutional neural network (CNN) are the DL models used to train the various datasets. Results: The findings showed that the CapsNet earned the maximum accuracy value of 93.62% while training the multiclass data, while the GCN achieved the highest model accuracy of 97.08% when training the binary data. The models were also evaluated using a variety of performance assessment parameters, which yielded consistent results across all datasets. Conclusion: The study provides a non-invasive approach to detect breast cancer; and enables stakeholders, medical practitioners, and health research enthusiasts a fresh view into the analysis of breast cancer detection with DL techniques to make educated judgements.
  • No Thumbnail Available
    Item
    Enhancing institutional policies and frameworks for E learning: A case study of the Kwame Nkrumah University of Science and Technology, Kumasi, Ghana.
    (Uniteted States International Africa, 2024) Ewusi-Mensah, Nana; Logah, Courage Julius; Gyening, Rose-Mary Owusuaa Mensah; 0000-0002-8087-5207
    The onset of Covid-19 has made learning online an important component of tertiary-level education. However, for the Kwame Nkrumah University of Science and Technology (KNUST), the challenge has been the lack of a clear policy guiding teaching and learning within online environments. Instructors seem to be unclear about which standards/policies are expected of them when delivering instructions in online settings, and learners are equally unsure of the ethics and responsibilities that come with online learning. This research thus sets out to address this problem by developing frameworks for the institutionalization of a codified E-learning policy for KNUST to guide/regulate online teaching and learning. The research adopted a convergent parallel design in which qualitative and quantitative approaches were used. Three key institutional E-Learning innovators and 73 lecturers from different Departments and Colleges of KNUST were conveniently and purposefully sampled to interview schedules and survey questionnaires for data collection. Audio-recorded interviews were transcribed and coded. Furthermore, a focused group discussion was conducted with seven level 400 students. The quantitative data was analysed using descriptive statistical methods (including standard deviations, percentages, means, and graphs where appropriate). From our preliminary qualitative results, participants agreed that existing policies and infrastructure in KNUST are inadequate and do not fully address online teaching and learning needs. In terms of policy recommendations, while teaching staff are concerned about and advocate for policies that regulate learners’ ethical behavior within online learning spaces; learners are interested in policies that regulate the ethical behavior of learners and those that specify standards of teaching for facilitators. Some learners emphasized the need for policies to include adequate support staff for each online learning activity to ensure that both learners and facilitators uphold the standards. Seventy percent of the respondents indicated the need for designed institutional sanctions for student misconduct during online teaching and learning engagements. Again, more than 50% of respondents indicated the need for specific and clearer ethical and copyright guidelines for online teaching and learning as well as clearer instructions regarding student behavior within online teaching environments. The findings that emerge from this research seek to make specific recommendations to address the barriers that hinder effective teaching and learning in online environments. The authors hereby recommend that government institutions such as the Ghana Tertiary Education Commission should strongly encourage stakeholder discussions for a nationwide E-learning policy from which tertiary institutions could use as a springboard in drafting policies/guidelines, policy audit, and conducting a needs assessment.