Computer Engineering
Permanent URI for this collectionhttp://197.211.34.35:4000/handle/123456789/64
Computer Engineering
Browse
17 results
Search Results
Item Deploying A Standalone Facial and Emotion Recognition Classroom Management System on Resource-Constrained.(Izmir Turkiye, 2024-12-20) Abdullahi, I.M., Maliki, D., Abdulqudus, A., Abraham, S.A, & Ibrahim, M.In recent times, it has been proven in most industries that deep learning can play a huge part in the development and automation of processes otherwise performed manually by humans alone. The trend however has encountered more of a shift and tend towards transfer learning where standalone systems can be built on weights that have been extensively trained to be use-case agnostic. This project seeks to address the problem of student truancy. The methodology applied is a combination of a deep learning use-case agnostic weight embedding obtained from a popular network called Face net. Recognition is performed by computing facial distances using the weight embedding. Also addressed is the common reliance on internet for functionality present in most modern-day systems by deploying all the resources necessary on a resource-constrained development board. Emotions during class are also analyzed to improve classroom experience which will be displayed on a web application dashboard powered by artificial intelligence back-end. The results obtained show an above average recognition rate of 0.63 with emotional recognition accuracy of 0.72. The implications of these results are that accurate attendance can be taken in an organization with minor increments to the system such as increased computational capabilities.Item Towards The Development of An Intelligent Evaporative Cooling System for Post-Harvest Storage of Selected Fruits(Federal University of Technology, Minna, 2024-12-03) Isah, O.R., Adebayo S.E., Nuhu, B.K., Umar, B.U., Maliki, DPoor management of post-harvest storage of fruits and vegetables has led to enormous food wastage and economic loss globally. Refrigerating systems have been adopted over the years to avert these losses; however, installing them is expensive and can cause chilling injury and moisture loss to the fruits and vegetables when they go below 20℃ temperature. An evaporative cooling system has recently been widely used to preserve fruits and vegetables because it’s cheap to implement, especially for small-scale farmers. This system reduces the temperature and increases the air humidity in their chamber by removing latent heat from the evaporated water when exposed to sunlight. The existing evaporative system has been efficient in preserving the quality of fruits and vegetables as well as extending their shelf-life; however, they lacked automated operation and control mechanisms, intelligent mechanisms capable of identifying the physical state of the fruits, adaptive control techniques for the storage and remote monitoring, feedback scheme of the system for use by the farmers. The abovementioned limitations have prevented the system from achieving optimal performance in preserving fruits. Hence, this research aims to develop a multi-chamber evaporative cooling preservative system for post-harvest storage of fruits. In the first step, Tomato images were collected and trained with the MobileNetV2 model, achieving accuracy, precision and recall of 88%, 89% and 88% respectively. Overall, the model performs well, however, fine- tuning the model or using more training data could help improve its performance furtherItem A Joint Optimization Scheme for Enhanced Breast Cancer Diagnosis using Particle Swarm Optimization (PSO) and Binary Particle Swarm Optimization (BPSO)(International Conference of the Faculty of Science, 2025-01-14) Ahmed, Y.E., Abdullahi, I.M., Maliki, D., & Akogbe, M. AOne of the leading diseases globally is cancer and breast cancer is not exempted. The objective of the WHO Global Breast Cancer Initiative (GBCI) is to reduce global breast cancer mortality by 2.5% per year, thereby averting 2.5 million breast cancer deaths globally between 2020 and 2040. The three pillars toward achieving these objectives are: health promotion for early detection; timely diagnosis; and comprehensive breast cancer management. In this study we propose an early and comprehensive detection technique in combating breast cancer diagnosis by combining the strength of both PSO (Particle Swarm Optimization) and BPSO (Binary Particle Swarm Optimization) to achieve optimal solution. The results obtained indicated the superiority of the Hybrid PSO-BPSO model in detection over an existing solution by achieving an accuracy of 98.82% on both the WBCD and WDBC datasets.Item Investigating the Thresholding Effect and Fingerprint Transformation Using Cross-Correlation Similarity Matching(Faculty of Science Lafiya, 2025-01-12) Garuba O.R., Abdullahi, I.M., Dogo, E.M., & Maliki, DOne of the leading diseases globally is cancer and breast cancer is not exempted. The objective of the WHO Global Breast Cancer Initiative (GBCI) is to reduce global breast cancer mortality by 2.5% per year, thereby averting 2.5 million breast cancer deaths globally between 2020 and 2040. The three pillars toward achieving these objectives are: health promotion for early detection; timely diagnosis; and comprehensive breast cancer management. In this study we propose an early and comprehensive detection technique in combating breast cancer diagnosis by combining the strength of both PSO (Particle Swarm Optimization) and BPSO (Binary Particle Swarm Optimization) to achieve optimal solution. The results obtained indicated the superiority of the Hybrid PSO-BPSO model in detection over an existing solution by achieving an accuracy of 98.82% on both the WBCD and WDBC datasets.Item Software Failures: A Review of Causes and Solutions.(JOURNAL OF SCIECNCE TECHNOLOGY AND EDUCATION, 2021-04-17) Dauda, I. A., Nuhu, B. K., Abubakar, J., Abdullahi, I. M., & Maliki, D.Software failure occurs when the developed software swerves from the expected behaviours or could not execute the task it was developed to perform. Software failures could lead to different degrees of harm to organizations or individual businesses, which include but not limited to financial losses, embarrassments and damage to organizations’ reputations. This study reviewed and analyzed several related works in this domain and put more lights on the factors that make software either fail or become inoperative. From the various analyses, it is discovered that failures occur due to schedule pressure, deficient requirements, lack of technical skill set, unrealistic requirements and lack of discrete allocation of tasks. It is therefore imperative to the new and existing organizations to understand these causes and devise a realistic measure to ensure their software perform adequately.Item Systematic Literature Review of Deep Learning models for Computer Vision Applications: Deployment Challenges in Nigeria(JOURNAL OF SCIENCE TECHNOLOGY AND EDUCATION, 2023-09-05) Abdullahi, I. M., Siyaka, H.O., Alhaji, G.S., Maliki, D., DaudaDeep learning has gained attention recently. Since its adoption, deep learning has provided state-of-the-art solutions to lots of standing computational problems. One of the areas it has gained unequaled success is computer vision. The success of deep learning is not limited to computer vision only, it has also recorded unmatchable success in areas like natural language processing and speech recognition. With the advent of big data, the use and importance of deep learning can only continue to grow. One downside of this algorithm is its computational requirements: large datasets and high-end computing devices. In this paper, we provide an overview of recent deep learning models for computer vision, and we also highlighted the challenges faced by developing countries in adopting these technologies. No review has covered the challenges faced by Nigeria in deploying this technology. Some of the challenges highlighted include manual data collection and lack of adequate cloud storage services. Inadequate infrastructures such as power and network facilities, and finally, lack of adequate funding of the sector. It was recommended that local cloud services be established to encourage local data storage and reduce storage cost. Also, adequate investment for power and network availability should be made. Finally, there should be enough budget allocation to IT sector that will encourage technocrat and experts to develop and fully harness the benefit of the technology.Item A Smart Real-time Attendance System using Smart Data Filtering and Selection Techniques(2024-04-09) Ibrahim M. A., Maliki, D., I. A. Dauda, A. Y. Ogaji, S. YakubuCooperate organizations, firms, companies, and educational institutions in Nigeria and the whole world are concerned about attendance of students and employees as the case may be, student overall performance is affected by it. In order to provide solutions for attendance management systems, a variety of techniques and technologies were used in the development of the attendance systems. However, most of these systems lack the flexibility of use and appropriate resource management. This paper presents the development of a smart real-time attendance system that uses smart data filtering and selection techniques to parse user-defined attendance instructions, optimize performance, and improve efficiency and flexibility. This system also employs a multi-factor approach in terms of security engaging the use of RFID technology and fingerprint biometrics to manage attendance records. Also, the system uses a wireless (Wi-Fi) communication approach for real-time communication. The performance of the system was mainly evaluated in terms of throughput, latency, and accuracy showing an average delay of 3 seconds per student, 21.95Mbps average throughput, and zero percent false acceptance.Item Recent advances in smart kitchen automation technologies: Principles, approaches, and challenges(Journal of Engineering Science, 2022-09-22) Umar, B. U., Olayemi, O. M., Dauda I. A., Maliki D., & Okoro P. KThe Internet of Things (IoT) is a growing network of physical devices that are connected to various types of sensors and can share data with the aid of internet connectivity,. Safety is an important consideration when designing a house, town, smart kitchen, etc., and it continues to play an important role in today’s world. In general, the kitchen is regarded as one of the most crucial tasks in our everyday lives, making it imperative to equip this vital intense particles in the environment, or fire outbursts. Gas leaks in the kitchen can be dangerous and deadly, resulting in fires if they go unchecked. For smart kitchens, various systems have been built to combat gas leaks and fire outbreaks. However, despite their high precision, these systems each have their own set of flaws that have severely restricted their implementations. The start-of-the-art in gas leakage, fire, and smoke detection in a smart kitchen is discussed in this paper. Different methods of gas leakage and fire detection are also addressed, along with their strengths and weaknesses, as well as products available in the market today.Item Performance Evaluation of Sun Tracking Control Systems using IMC and PID Controllers(4th International Engineering Conference (IEC 2022) Federal University of Technology, Minna, Nigeria, 2022) Madaki, I. D.; Folorunso, T. A.; Bala, J. A.; Adedigba, A. P.; Dogo, E. M.The inadequate supply of electricity for illumination has made many industries, organizations, and households resort to alternative energy sources, one of which includes solar energy. In comparison to other renewable sources of energy, the idea of employing photovoltaic panels for solar energy conversion into electrical energy remains a widespread choice. However, the amount of power a solar panel can produce is reduced due to the sun's constant shift in angle with respect to the earth. In this work, we evaluate the performance response of the STS using the transient response, Integral Absolute Error (IAE) and Integral Square Error (ISE) of the IMC and PID controller using MATLAB. The results obtained shows that, the PID outperforms the IMC in terms of IAE, ISE and Rise time, while the IMC outperforms the PID in terms of Settling time and system overshoot.Item Accessing Imbalance Learning Using Dynamic Selection Approach in Water Quality Anomaly Detection(MDPI, 2021) Dogo, E. M.; Nwulu, N. I.; Twala, B.; Aigbavboa, C.Automatic anomaly detection monitoring plays a vital role in water utilities’ distribution systems to reduce the risk posed by unclean water to consumers. One of the major problems with anomaly detection is imbalanced datasets. Dynamic selection techniques combined with ensemble models have proven to be effective for imbalanced datasets classification tasks. In this paper, water quality anomaly detection is formulated as a classification problem in the presences of class imbalance. To tackle this problem, considering the asymmetry dataset distribution between the majority and minority classes, the performance of sixteen previously proposed single and static ensemble classification methods embedded with resampling strategies are first optimised and compared. After that, six dynamic selection techniques, namely, Modified Class Rank (Rank), Local Class Accuracy (LCA), Overall-Local Accuracy (OLA), K-Nearest Oracles Eliminate (KNORA-E), K-Nearest Oracles Union (KNORA-U) and Meta-Learning for Dynamic Ensemble Selection (META-DES) in combination with homogeneous and heterogeneous ensemble models and three SMOTE-based resampling algorithms (SMOTE, SMOTE+ENN and SMOTE+Tomek Links), and one missing data method (missForest) are proposed and evaluated. A binary real-world drinking-water quality anomaly detection dataset is utilised to evaluate the models. The experimental results obtained reveal all the models benefitting from the combined optimisation of both the classifiers and resampling methods. Considering the three performance measures (balanced accuracy, F-score and G-mean), the result also shows that the dynamic classifier selection (DCS) techniques, in particular, the missForest+SMOTE+RANK and missForest+SMOTE+OLA models based on homogeneous ensemble-bagging with decision tree as the base classifier, exhibited better performances in terms of balanced accuracy and G-mean, while the Bg+mF+SMENN+LCA model based on homogeneous ensemble-bagging with random forest has a better overall F1-measure in comparison to the other models.