Computer Engineering
Permanent URI for this collectionhttp://197.211.34.35:4000/handle/123456789/129
Computer Engineering
Browse
11 results
Search Results
Item Development of an Intelligent Evaporative Cooling System for Post-harvest Storage of Tomato(University of Ilorin, Nigeria, 2024-06-04) Isah, O.R., Adebayo S.E., Nuhu, B.K., Umar, B.U., Maliki, D., Abdullahi, I.M., Dogo, E.M, Olaniyi, O.M., & Agajo, JamesThis research developed an intelligent evaporative cooling system for post-harvest tomato preservation that adapts to its suitable temperature, humidity, and CO 2 states to store, preserve quality, and increase the shelf life of the fruits. This was accomplished through the use of transfer learning for fruit classification, the Internet of Things (IoT) for remote monitoring and shelf life tracking, and the integration of the evaporative cooling system with a CO 2 sensor, a temperature sensor, a humidity sensor, an Arduino Uno, and a Raspberry Pi 4b. The system can classify tomato fruit status as ripe or overripe with a prediction accuracy of 87.5% and a receiver operating characteristic (ROC) value of 88.89%. The developed evaporative cooling system extended the shelf life of ripe tomatoes from 5 to 14-17 days at 20℃ and 90% relative humidity and overripe tomatoes from 3 to 9-11 days at 18℃ and 95% relative humidity. These results emphasize the crucial function of evaporative cooling in fruit and vegetable storage, as it extends the shelf life of tomatoes by 180–200%, hence minimizing post-harvest loss as it also increases the farmers’ income, thereby contributing positively to the economy.Item Enhanced Adaptive Threshold Median Filter For Medical Image Filtering(OURNAL OF SCIENCE TECHNOLOGY AND EDUCATION, 2023-06-12) Adamu, M., Jiro, A.A., Abdul-Malik, U. TIn the field of medical image processing, mitigating the impact of noise is of paramount importance. Conventional median filters primarily target the elimination of medical image noise occurring as a single layer, characterized by a constant level of noise gray value. However, these filters encounter challenges when faced with images corrupted by noise that extends beyond a single layer. This study presents the Enhanced Adaptive Threshold Median Filter (EATMF) as a solution to naddress the aforementioned challenge. The proposed filter combines the Adaptive Median Filter (AMF) with thresholds (ATMF) and incorporates a Laplacian filter. By introducing changes in the thresholds, the EATMF achieves a balance between effectively removing both low and high density noise while preserving image quality. A comparative analysis between the EATMF and the ATMF is presented, accompanied by visual examples that showcase the performance of the newly introduced filter. The results demonstrate that the EATMF outperforms the ATMF in terms of Peak Signal-to-Noise Ratio (PSNR), indicating its superior noise reduction capabilities. This study highlights the significance of the EATMF in medical image processing, particularly in scenarios where images are corrupted by multi-layer noise. The proposed filter offers an enhanced approach to noise reduction, contributing to improved image quality and accuracy in medical diagnostics and analysis.Item Development of Animal Health Monitoring System based on Wireless Sensor Network(Journal of Contents Computing, 2022-12-10) Maliki, D., Ogunbase, E. F., Abdullahi, I. M., Aliyu, I., Oh, S., & Dauda, I. AClinical methods for tracking animal health are inadequate as they only include intermittent data which entail too much time and veterinarian knowledge expenditure in equipment. The animal health monitoring system which allocates equipment to be installed on the animal body does provide way of keeping the health of the animal in check. This project seeks to solve the problem of integration in system developed. Also, monitoring of psychological parameters has to be consistent (precision), accuracy and the response time of the system has to be low for a real time monitoring system. The project seeks to achieve a level of accuracy and precision to help diagnose the health situation of the animal. The system consists of two sensors (a temperature sensor, a heart rate sensor). For the implementation of the temperature node, esp 32 which has wifi capability was used while in the case of heart rate, Arduino Nano was interfaced alongside with esp32. The sensor nodes communicate with the sink node which serves as the display unit and also transmit the data to the cloud for real time monitoring. The precision and accuracy achieved by the ECG, modularity built into the system and the deep sleep energy-saving mechanism of the sensor nodes are achievement made by this work.Item Food Safety 4.0: The Future of Food Safety Leveraging Industry 4.0 Technologies(Springer, 2024) Dogo, E. M.; Bokaba, T.; Makun, H. A.; Aliyu, A.; Kparbong, P. B.The convergence of several factors, including population growth, scarce natural resources, climate change, globalization, sustainability, and advances in modern and emerging technologies, in addition to growing demand by consumers, retailers, regulators, and stakeholders to raise the level of food protection is increasingly driving the global food safety agenda. Industry 4.0 technologies are fast infusing into all fields of human endeavor including the food safety ecosystem, serving as catalysts for innovation and sustainability. However, there is no empirical evidence regarding the extent of their application and the level of acceptance within the food safety domain. This study explored the relationship between Industry 4.0 technologies and food safety by evaluating the applications of the Fourth Industrial Revolution technologies in addressing food safety challenges. The objectives are achieved using qualitative methodology and bibliometric analysis of content. Our analysis indicates that artificial intelligence, the Internet of Things, machine learning, and big data are prominent topics related to the 4IR and food safety, while blockchain and smart manufacturing are emerging topics.Item Combating Road Traffic Congestion with Big Data: A Bibliometric Review and Analysis of Scientific Research(Springer, 2021) Dogo, E.M.; Makaba, T.; Afolabi, O.J.; Ajibo, A.C.Road traffic congestion is one of the challenging problems confronting city dwellers globally. It is majorly caused by either one or a combination of recurrent congestion, nonrecurrent congestion, and pre congestion conditions in urban road networks. This chapter performs a bibliometric analysis and reviews the volume of literature linking big data with combating road traffic congestion between 2011 and 2020. The review employs a quantitative analysis of bibliometric science mapping tool to highlight features that affect knowledge accumulation. The chapter also reviews the intellectual structure of knowledge based on total publications and citations. The key scholars, documents, affiliations, regions, data, and algorithms that influenced the development of this research area are analyzed. The results of documents co-citation evaluation show that the key research clusters are salient elements linked with the development and deployment of connected and autonomous vehicles (CAVs) technology. These research clusters are traffic flow prediction, congestion and accidents alert systems, security and privacy mitigation, vehicle emission profiles, travel time estimation, optimization of vehicular routing, journey planning and congestion prediction, and travel and parking guidance. Finally, the chapter presents the way forward and future research direction for sustainable road traffic management in the context of smart city initiatives leveraging on big data.Item Toward Sustainable Domestication of Smart IoT Mobility Solutions for the Visually Impaired Persons in Africa(Springer, 2020) Salami, A.F.; Dogo, E.M.; Nwulu, N.I.; Paul, B.S.According to World Health Organization (WHO) estimates, Africa accounts for 10% of the global visually impaired persons (VIPs). This visual impairment burden is exacerbated by the shortage of specialist medical human resources, orientation and mobility specialists, and high cost of assessing primary eye care services. These render the majority of VIPs to rely heavily on human-assisted guides and ineffective navigation aids for their daily routines and movements. A viable technological solution that can fill this void and meet these mobility needs is the Internet of Things (IoT). This chapter provides an assessment of smart IoT mobility solutions pertinent to the African context. Furthermore, the barriers to the realization of technology domestication as well as growth catalysts are examined. Lastly, this chapter proffers technical recommendations for sustainable domestication of smart IoT mobility solutions for VIPs in Africa.Item Automatic Photovoltaic Solar Panel Dust Cleaning System(IGI Global, 2021) Shibane, N.; Nwulu, N.; Dogo, E. M.Renewable energy sources are currently regarded as viable options for stabilizing the energy crisis globally as well as addressing global warming challenges. Solar energy is the most promising and sustainable energy source as compared to other renewable energy sources such as coal, nuclear, wind, gas, and hydro energy. The increasing demand for solar panels should be reason enough to investigate ways in which we can increase their efficiency as much as possible. Dust, dirt, and bird dropping are major factors that can affect the performance of solar panel systems. This work presents the development of a solar panel cleaning system that automatically detects dust particles and cleans the solar panel to ensure the continues efficiency of the solar system is at an optimal level. The system comprises of five subsystems: dust sensing, water pumping, microcontroller, cleaning mechanism, and the power system. Tests carried out on the system shows its quick response to signals and effectiveness in cleaning the solar panel whenever dust particles are detected.Item Paillier Cryptosystem Based ChainNode for Secure Electronic Voting(Frontiers in Blockchain, 2022) Umar, B,U.; Olaniyi, O.M.; Olajide, D.O.; Dogo, E.M.Blockchain is a distributed and decentralized ledger of transactions that are linked together cryptographically leading to immutability and tamper-resistance, thereby ensuring the integrity of data. Due to the ability of blockchain to guarantee the integrity of data, it has found wide-range adoption in electronic voting (e-voting) systems in recent years, this is in a bid to prevent manipulation of votes. However, due to the distributed nature of the blockchain, opportunities arise for privacy intrusion of the data being secured. The translation of this privacy flaw in blockchain to e-voting systems is the possibility of violation of the privacy of the electorates. Consequently, in a bid to achieve integrity and privacy of votes in e-voting, this study presents the use of an open-source blockchain system, coupled with a privacy-oriented cryptosystem known as the Paillier cryptosystem, towards addressing the privacy concerns of the blockchain. The performance of the system was evaluated and a transaction throughput of 1424 tps was obtained for ten thousand simulated ballot transactions. Further evaluation was carried out on the system, by increasing the number of system transactions. This showed that the mining time of the blockchain increased by an average factor of 0.18 s for every thousand increases in the number of transactions. Also, the response time of the system to a range of user actions was evaluated over an increasing number of voters. Results obtained showed that the response time of the system for vote casting operations increased by an average of 0.33 min per thousand voters while for vote tallying there was an increase in response time by an average of 0.848 min per thousand voters. The scientific value of this study is the development of an integrity and privacy-preserving e-voting system consisting of an open-source nodechain coupled with a privacy-oriented cryptosystem known as the Paillier cryptosystem following the security requirements of e-voting systems. The proposed system addresses the issue of integrity in e-voting while still maintaining the privacy of the electorates.Item On the Relative Impact of Optimizers on Convolutional Neural Networks with Varying Depth and Width for Image Classification(MDPI, 2022) Dogo, E. M.; Afolabi, O. J.; Twala, B.The continued increase in computing resources is one key factor that is allowing deep learning researchers to scale, design and train new and complex convolutional neural network (CNN) architectures in terms of varying width, depth, or both width and depth to improve performance for a variety of problems. The contributions of this study include an uncovering of how different optimization algorithms impact CNN architectural setups with variations in width, depth, and both width/depth. Specifically in this study, three different CNN architectural setups in combination with nine different optimization algorithms—namely SGD vanilla, with momentum, and with Nesterov momentum, RMSProp, ADAM, ADAGrad, ADADelta, ADAMax, and NADAM—are trained and evaluated using three publicly available benchmark image classification datasets. Through extensive experimentation, we analyze the output predictions of the different optimizers with the CNN architectures using accuracy, convergence speed, and loss function as performance metrics. Findings based on the overall results obtained across the three image classification datasets show that ADAM and NADAM achieved superior performances with wider and deeper/wider setups, respectively, while ADADelta was the worst performer, especially with the deeper CNN architectural setup.Item A Sensor-Based Data Acquisition System for Soil Parameters to Determine Suitable Crops(2023) Abisoye, B. O.; Dogo, E. M.; Umar, B. U.; Mamman, I. Z.Soil parameters monitoring is significant in sustainable crop and food production. The standard strategy of soil parameters monitoring in developing and underdeveloped nations uses manual labor, resulting in wrong decisions in soil management. Inaccurate measurements due to sensor miscalibration or low sensor quality can lead to incorrect soil management decisions and negatively impact crop yield and environmental sustainability. Due to the mentioned challenges, this work aims to develop a Sensor-based Data Acquisition System for Soil Parameters that will enable users to observe various soil parameters like temperature, humidity, water level and soil pH. The system was developed using the combination of hardware and software components. The hardware component comprises of sensory and processing parts. The study calibrates sensors using known pH, moisture, and temperature values for specific crops to grow in Nigeria. The system will aid farmers in determining suitable crops for their farmland and increasing crop yield. The system collects data through a network of sensors installed in the soil and wirelessly transmits the data to a cloud-based server. The collected data is then analyzed and visualized in through a web-based dashboard, providing farmers with information about the state of their soil. The performance evaluation of the system was carried out using response time and accuracy. The average response time of the system was 4 seconds, and the percentage error for temperature and humidity readings when compared to weather forecast readings were 8.20% and 5.08%, respectively. The results show that the proposed system can provide accurate and reliable measurements of soil parameters and can be easily deployed and operated by small-scale farmers. Using this system can result in improved crop yields, reduced wastage, and better overall efficiency in agricultural operations.