ABUAD Journal of Engineering Research and Development

Robotic Assistant for Object Recognition Using Convolutional Neural Network

2024-02-12T03:46:31+00:00

Visually impaired persons encounter certain challenges, which include access to information, environmental navigation, and obstacle detection. Navigating daily life becomes a big task with challenges relating to the search for misplaced personal items and being aware of objects in their environment to avoid collision. This necessitates the need for automated solutions to facilitate object recognition. While traditional methods like guide dogs, white canes, and Braille have offered valuable solutions, recent technological solutions, including smartphone-based recognition systems and portable cameras, have encountered limitations such as constraints relating to cultural-specific, device-specific, and lack of system autonomy. This study addressed and provided solutions to the limitations offered by recent solutions by introducing a Convolutional Neural Network (CNN) object recognition system integrated into a mobile robot designed to function as a robotic assistant for visually impaired persons. The robotic assistant is capable of moving around in a confined environment. It incorporates a Raspberry Pi with a camera programmed to recognize three objects: mobile phones, mice, and chairs. A Convolutional Neural Network model was trained for object recognition, with 30% of the images used for testing. The training was conducted using the Yolov3 model in Google Colab. Qualitative evaluation of the recognition system yielded a precision of 79%, recall of 96%, and accuracy of 80% for the Robotic Assistant. It also includes a Graphical User Interface where users can easily control the movement and speed of the robotic assistant. The developed robotic assistant significantly enhances autonomy and object recognition, promising substantial benefits in the daily navigation of visually impaired individuals.

Healthcare Waste Management: An Overview

2024-03-31T23:24:57+00:00

Healthcare waste (HCW) is a vital global issue that cannot be overlooked due to its threat to humans and the environment stemming from its infectious and hazardous nature. This study examines previous works undertaken on healthcare waste management (HCWM) practices around the world, notably the developing countries with a particular interest in segregation, collection, transportation, treatment, and disposal of HCW. This study draws attention to the environmental hazards arising from each stage of HCWM. Factors affecting HCWM practices have also been discussed. This study revealed evidence of poor HCWM practices in many developing countries. It also showed the impacts of human and non-human factors on HCWM practices. Proper documentation, sufficient budget, adequate supply of HCWM materials, frequent training of healthcare workers, and development of local manuals and guides are essential if a country is determined to achieve an efficient and sustainable HCWM system. Liquid HCW needs to be investigated as much as the solid HCW. Exploration of HCW minimization, reuse, and recycling opportunities is recommended for future research. The use of Modern-day technology such as Artificial Intelligence and geographic information system (GIS) has provided good results so far. However, they can be explored further for prediction, real-time monitoring, and reporting of HCW. The present study can be adopted as a guide in discussing issues about HCWM.

Mechanical Characterization and Dynamic Mechanical Analysis of Recycled Low Density Polyethylene Filled Unsaturated Polyester Composite

2024-04-05T15:21:00+00:00

Unsaturated polyester resin (UPR) is widely used as matrix in composite development; however, it has poor toughness property. To solve this problem, many researchers have used different tougheners to modify the resin, but the use of recycled low-density polyethylene (RLDPE) has not been explored. This work is aimed at modifying unsaturated polyester resin (UPR) with recycled low-density polyethylene (RLDPE) as a toughener and establishing the effects on the mechanical and dynamic mechanical performance of the RLDPE-filled polyester composite. Unsaturated polyester resin was modified with 1.18 mm RLDPE at different proportions of 1-4 wt%. Casting method was used for the production and the mechanical and dynamic mechanical analyses of the produced composite materials were carried out using ASTM standards. UPR modified with 1.5 wt% RLDPE exhibited the best impact than the un-modified UPR. The control (un-modified) sample had the highest flexural and tensile strength of 18 MPa and 14.02 MPa respectively which was about 26% and 25% higher than UPR modified with 1 wt% RLDPE. The Dynamic Mechanical Analysis (DMA) result showed that the composite does not depend strongly on the modifier loading as no regular pattern was observed for storage modulus, loss modulus and damping factor respectively.

Development and Performance Evaluation of a Heart Disease Prediction Model Using Convolutional Neural Network

2024-03-31T23:26:58+00:00

Heart disease is a leading cause of mortality globally and its prevalence is increasing year after year. Recent statistics from the World Health Organization show that about 17.9 million individuals are embattled with heart diseases annually and people under the age of 70 account for one-third of these deaths. Hence, there is need to intensify research on early heart disease prediction and artificial intelligence-based heart disease prediction systems. Previous heart disease prediction systems using machine learning techniques are unable to manage large amount of data, resulting in poor prediction accuracy. Hence, this research employs Convolutional Neural Networks, a deep learning approach for prediction of heart diseases. The dataset for training and testing the model was obtained from a government owned hospital in Nigeria and Kaggle. The resulting system was evaluated using precision, recall, f1-score and accuracy metrics. The results obtained are: 0.94, 0.95, 0.95 and 0.95 for precision, recall, f1-score and accuracy respectively. This show that the CNN-based model responded very well to the prediction of heart diseases for both negative and positive classes. The results obtained were also compared to some selected machine-learning models like Random Forest, Naïve Bayes, KNN and Logistic Regression and results show that the developed model achieved a significant improvement over the methods considered. Therefore, convolutional neural network is more suitable for heart disease prediction than some state-of-the-art machine-learning models. The contribution to knowledge of this research is the use of Afrocentric dataset for heart disease prediction. Future research should consider increasing the data size for model training to achieve improved accuracy.

Unlocking the Power of Waste Cooking Oils for Sustainable Energy Production and Circular Economy: A Review

2024-03-31T23:28:08+00:00

In the pursuit for sustainable energy solutions, biodiesel has come to prominence as an alternative to petroleum-derived diesel. This review delves into cutting-edge developments in production of biodiesel, emphasizing use of waste cooking oils (WCOs) as an environmentally friendly raw material. Incorporating waste cooking oils (WCOs) into the biodiesel production process not only tackles environmental issues associated with improper disposal but also adheres to the principles of a circular economy. This manuscript covers various methods and technologies for converting WCOs into high-quality biodiesel, emphasizing economic viability and environmental benefits. It discusses the potential of WCO-derived biodiesel to meet stringent fuel standards and reduce greenhouse gas emissions. Significant progress has been made in using waste cooking oils to generate sustainable energy, aligning with broader initiatives focused on renewable energy and circular economy principles. In summary, the utilization of waste cooking oils for biodiesel production presents an opportunity to shift away from reliance on fossil fuels, thereby fostering circular economy practices and sustainability goals.

Detection of Incipient Faults in Power Transformers using Fuzzy Logic and Decision Tree Models Based on Dissolved Gas Analysis

2024-03-31T23:30:08+00:00

This paper proposes an integrated approach utilizing Fuzzy Logic and Decision Tree algorithms to diagnose early-stage faults in power transformers based on Dissolved Gas Analysis (DGA) test results of transformer insulation oil. Overcoming limitations in conventional methods such as Duval Triangle, Key Gas Analysis, Rogers Ratio, IEC Ratio, and Doernenburg Ratio, our Fuzzy Logic and Decision Tree models address issues like inaccurate diagnosis, inconsistent diagnosis, lack of decisions or out-of-code results, and time-intensive manual calculations for large DGA datasets. The Decision Tree algorithm, a machine learning technique is applied to categorize faults into thermal and electrical types. Trained with over 300 DGA samples from transformers with known faults, the models exhibit robust performance during testing with different datasets. Notably, the Duval Triangle decision tree model attains the highest accuracy among the ten developed models, achieving a 98% accuracy rate when tested with 50 samples with known faults. Moreover, Decision Tree models for KGA, Doernenburg, Rogers, and IEC also demonstrate substantial prediction accuracy at 92%, 86%, 92%, and 90% respectively underscoring the efficacy of artificial intelligence methods over traditional approaches.

Harnessing Abuja's Municipal Solid Waste as a Renewable Energy Source: Scanning Electron Microscopy Analysis

2024-03-31T23:30:55+00:00

A study of Abuja’s municipal solid waste (MSW) samples using the scanning electron microscopy analysis was undertaken in this work. In the face of the severe energy poverty being experienced in Nigeria which largely depends on diminishing fossil fuel resources coupled with the associated problem of greenhouse gas emission, the energy potential available in municipal solid wastes needs to be investigated. Using MSW as a fuel source for electric energy production will also positively impact on Abuja’s waste management. This present study requires the analysis of the MSW with aim of confirming that products of its incineration will not be hazardous to the environment. ASTM E 1508 procedures for utilizing the scanning electron microscope (SEM) were followed to identify elements that would be contained in the bottom ash of the incineration process of samples of Abuja’s municipal solid wastes obtained from selected districts of the city. Elemental composition of the bottom ash that will be formed from incineration of Abuja’s MSW was obtained by the use of energy dispersive x-ray analysis. The micrographs plotted indicate that silicon and iron are the principal elements present in the samples with values for silicon and iron being highest at 49.5 and 19.55%, respectively, for the sample from Dutse-Alhaji. The tests also show the presence of silver in the organic wastes generated in Abuja, while presence of sulphur is very minimal. The silicon levels present in Abuja’s municipal solid waste compare well with values for Nigerian coals which have percent silicon contents ranging from 39.0 – 49.4% (Enugu coal – 39.0%; Okaba – 44.8%; Maiganga – 49.4%). The test results also show that Abuja’s MSW samples had grain sizes ranging from 3.5 mm 16 mm. The results indicate Abuja’s MSW combustion rate will be lower than for pulverised coal which is known to have much lower grain size in the range of 75 μm to 106 μm and will need shredding before firing since grain size is a very critical determinant factor in solid fuel combustion rate and burn-out time. The tests conclusively show that Abuja’s MSW will be a more environmentally friendly fuel than coal because of its lower sulphur content.

Development of an IoT Based Water Quality Monitoring Device for Domestic Fish Ponds

2024-03-31T23:32:10+00:00

This study focuses on developing an affordable IoT-based water quality monitoring system for domestic fish ponds. The system aims to enable remote monitoring of critical water parameters, offering real-time data access through mobile or web interfaces. It includes an alert system to notify the pond owners of any significant changes in water quality, allowing swift corrective action. The initiative stems from challenges faced by aquaculture farmers due to insufficient knowledge about water pH levels. Understanding pH's importance, especially within the optimal range of 6.5-9.0 for fish culture, is crucial for success. Tests conducted on the system's performance in detecting various pH levels across different pond environments demonstrated its reliability in identifying low and normal pH levels. However, anomalies were observed in detecting higher pH levels, indicating potential sensitivity limitations that need further investigation for system refinement. While the system excelled in detecting low and normal pH levels accurately, improvements are required for detecting higher pH thresholds to ensure comprehensive monitoring across diverse water conditions. This enhancement is crucial for effective fish pond management and reducing losses for aquaculture farmers.

Reliability Analysis of a Typical 33kV Distribution Network Using MATLAB (A Case Study of Ile-Oluji 33kV Distribution Line)

2024-03-31T23:33:14+00:00

The significance of a dependable and sufficient electrical power supply in societal development cannot be overstated. The distribution of electrical power holds a crucial position in the power system chain, representing the final stage where it reaches consumers. At this phase, various types of losses, including technical loss and theft, among others are associated. The Ile-Oluji community is situated in Ondo State, a south-western part of Nigeria, A region which is host to federal, state, local and private institutions. This community grapples with inconsistent power supply experiencing intermittent trips without a clear originating cause from components in the Ile-Oluji injection substation and its feeder in Ondo. This study analyses the power distribution patterns in this locality focusing on three primary elements (transformer, switch gear and supply line) extracting data on; failures, outage time, numbers of customers and total hours for the year 2019 to 2022. Reliability indices were employed to assess its performance utilising the MATLAB software. Codes were crafted to extract these indices; Availability, Failure rates, Mean Time to Repair (MTTR), Mean Time Between failure (MTBF), System Average Interruption Duration Index (SAIDI), System Average Interruption Frequency Index (SAIFI), and Customer Average Interruption Duration Index (CAIDI). The results show that there is a strong relationship among the reliability indices. It is adduced that the lower the failure rate, the higher the availability of a system. It was concluded that the power system switchgear recorded the highest failure rate amongst the three elements with 0.037341 hrs/year followed by supply line with 0.022541 hrs/year and the transformer with 0.0148 hrs/year in 2022. In corollary, transformer has the highest availability of 0.94441 followed by supply line with 0.81681 and switchgear with 0.78004 in 2021, switchgear recorded the highest failure rates because it is responsible for executing both forced and planned outages.

Production and Characterization of Ackee Apple (Blighia sapida) Seeds and African Star Apple (Chrysophyllum albidum) Seeds Oil Mixtures and their Biodiesel

2024-03-31T23:34:14+00:00

This paper focused on the characterization of oils and biodiesels derived from Ackee apple seeds and African star apple seeds obtained from local markets. The oils from individual seeds and their mixtures at varying ratios were characterised for relative density, free fatty acid, acid, iodine, and saponification, which yielded 0.91 g/cm³, 1.06 mg-KOH/g, 2.12 mg-KOH/g, 38.36mg-iodine/100g, and 195.74 mg-KOH/g of ackee seed oil, respectively. And 0.89 g/cm³, 2.105 mg-KOH/g, 4.2 mg-KOH/g, 52.49 mg-iodine/100 g, and 227.7 mg-KOH/g of African star apple seed oil, respectively. The highest relative density of 0.9064 g/cm³ and free fatty acid of 3.73 mg-KOH/g were achieved from the mixture of ackee apple and African star apple seeds’ oils at 80 and 20%, respectively, while the highest saponification of 221.264 mg-KOH/g and iodine of 49.66 mg-iodine/100 g were obtained from the oil mixture of 20 and 80%, respectively. Also, the oils extracted from the seeds, were subjected to a transesterification process to produce biodiesel. 144°C flash point, 206°C fire point, and 2.8°C cloud point were obtained from the biodiesel of the oil mixture of 20 and 80%, respectively. Further analysis of the mixtures showed low volatility and high resistance to fire due to their high flash and fire points. The highest value recorded for the flash point is lower when compared with some other seed oils flash points; however this value is higher than the standard flash point for biodiesels .Highest boiling point of 64°C was attained at an oil mixture ratio of 60 and 40%, respectively. This value is too low compared to the normal boiling point range of 315-350°C for biodiesels, and the high acid values recoded for the mixtures make the oils inedible. The oils, however, have advantages over other edible seed oils as they will serve as valuable ingredients in the soap-making industries since they are not competing with food resources

Modelling and Simulation of Co-Gasification of Chlorella Vulgaris and High-density Polyethylene Using Aspen Plus

2024-03-31T23:35:04+00:00

A technical innovation that holds promise for producing renewable fuel and decreasing waste disposal is the production of syngas from the co-gasification of waste materials and biomass. In this present study, a new simulation model for co-gasifying high-density polyethylene (HDPE) and microalgae using Aspen plus V10 was built. Several operating parameters, including operating temperature, air equivalence ratio (ER), biomass blending ratio, steam-to-biomass ratio (S/B), and air/steam ratio, were investigated for their influence on the yield and composition of H₂, CO, CO₂, and CH₄. Results indicated that these operating parameters had significant impacts on the gaseous products. High gasifier temperatures (1000°C) for the co-gasification process favored the formation of H₂ and CO and increased their yields. Also, the yield of H₂ significantly decreased when the value of the equivalence ratio was increased. According to simulation results, increasing the steam-to-biomass ratio favored the synthesis of H₂ and CO up to a point. In addition, waste plastic (HDPE) in the feedstock should be kept at a minimum to favor the production of hydrogen-rich gas. The findings show that the model results agree with previous experimental studies. This research study has proven the air-steam co-gasification of microalgae and HDPE as a suitable process for the production of syngas rich in hydrogen.

Influence of Extraction Temperature on the Quality of Neem Seed Oil: Preliminary Investigation

2024-03-31T23:35:47+00:00

The storage of neem oil for a long time before usage comes along with challenge of quality retain ability of the oil; and the extraction methods can affect the quality of neem seed oil. This research work compared the mechanical expression method to the solvent extraction method to find a better method that will give high-grade neem oil for long-term storage. A plant with a capacity of 50 kg/day of neem seed kernel was used to extract oil from neem seed using ethanol as extraction solvent. The increase of extraction temperature from 20 ^oC (mechanically expressed) to 78 ^oC leads to decrease of iodine value from 62.70 to 60.10 gI2/100 g; increase of acid value from 3.4 to 4.2 mg KOH/g and increase of saponification value from 158.74 to 210.18 mgKOH/g. The Fames standard method was used for the GC – MS analysis and the percentage composition of the polyunsaturated components in the 20 ^oC (mechanically expressed), 50 ^oC, 55 ^oC, 60 ^oC and 78 ^oC oils were 21.58, 6.33, 3.09, 1.83 and 0.21% respectively. The changed of extraction temperature from 20 ^oC to 78 ^oC brings about reduction of polyunsaturated components from 21.58% to 0.21%. The increase of extraction temperature leads to conversion of unsaturated components to saturated components due to auto – oxidation process. This is clearly seen as the extraction temperature increased from 20 ^oC to 78 ^oC, the percentage composition of the saturated components increased from 22.40% to 43.70% and the polyunsaturated component decreased from 20.47% to 0%. The fatty acid composition associated with the 78 ^oC oil are: Oleic acid, 46.61%; Stearic acid, 11.83%; Palmitic acid, 16.54%; 11 – Octadecenoic acid, 3.58%; Cis – Vaccenic acid, 5.90%; Cyclopropaneoctanal, 11.19%; Squalene, 0.21% and Trimethylsilyl – di(timethylsiloxy) – silane, 4.14%. The functional groups identified in the 78 ^oC oil were C – H, C = O, C – C and C – O. Based on the lowest iodine value, lowest percentage composition of the polyunsaturated component value and high percentage composition of saturated component, the neem oil obtained at 78 ^oC from the miscella is considered as the high grade neem oil because it is less reactive due to lowest percentage composition of polyunsaturated and can be stored for long time before usage. Furthermore, the results from this work will assist manufacturers in selecting the extraction temperature for particular application of the neem seed oil. The extracted oil is recommended for soap production due to its high saponification value.

Evaluation and Multi-Objective Optimisation of Cutting Parameters in Turning of AISI 1020 Mild Steel using Formulated Cutting Fluid

2024-04-12T07:15:06+00:00

Input parameter like the cutting fluid is one of the requirements for minimal surface roughness, cutting temperature, tool wear and optimal material removal rate coupled with improved machinability and productivity. The evaluation of the optimal factors of surface roughness, material removal rate, cutting temperature and tool wear in the turning of AISI Mild Steel with the use of eco-friendly fluids. Concerns has been raise globally about the non - biodegradability and non-recyclability of the conventional fluids in the research space. This prompted the research interest in replacing the mineral oil based fluids with eco-friendly cutting fluid such as castor seed oil based cutting fluid (CBCF). The locally sourced castor seed oil was investigated for its physiochemical properties as well as its fatty acid composition (FAC). The cutting fluid was formulated using ratio 1:9 of oil with additives to distilled water and then characterized. In turning of AISI 1020 Mild Steel, the evaluation of surface roughness, material removal rate, cutting temperature and tool wear under the CBCF compared to the mineral oil based cutting fluid (MBCF) were carried out using Taguchi experimental design and Grey Relational Analysis (GRA) for multi-response optimization. The formulated cutting fluid showed pH value of 8.47, viscosity of 0.830 mm²/s, good resistance to corrosion, good stability and milkfish in colour. From the GRA, the multi-response optimal factor combination under the CBCF is (1250 rev/min) spindle speed, (0.6 mm/rev) feed rate and (1.0 mm) depth of cut, all at level 3 while under the MBCF, it also shows (1250 rev/min) spindle speed, (0.6 mm/rev) feed rate and (1.0 mm) depth of cut all at level 3. The parameters from Taguchi and GRA results are in agreement with results from other vegetable oil based fluids and this study also contributes and improves the science of machining.

Design and Construction of Voice Controlled Home Automation using Arduino

2024-04-12T07:18:20+00:00

System automation has been widely researched in the twenty-first century due to its essential role in daily life. The fundamental advantage of an automated system is its ability to reduce human stress and minimize errors. Over the past few years, there has been a swift shift from traditional switches to switches equipped with remote controls. Currently, the presence of conventional wall switches distributed around the house poses challenges in terms of use, especially for individuals who are elderly or have physical disabilities. Due to technological advancements, mobile smartphones are now affordable for all individuals. Android devices are becoming equipped with applications that aid in multiple ways. Another new technology is the Google speech recognition APIs, which enable voice-based system command and control. This study demonstrates the implementation of voice-controlled home automation using the Arduino Uno microcontroller. Users of this system will be able to exercise full authority over every domestic device through spoken commands. The control circuit consists of an Arduino Uno microcontroller that receives and interprets voice commands from an Android smartphone equipped with the corresponding application. While the Bluetooth module shares signal data after establishing a wireless link between the microcontroller and the smartphone, the relay regulates device switching.

Predictive Modeling for Cardiovascular Disease in Patients Based on Demographic and Biometric Data

2024-04-13T12:22:39+00:00

Cardiovascular disease (CVD) remains the leading global cause of death, highlighting the urgent need for accurate risk assessment and prediction tools. Machine learning (ML) has emerged as a promising approach for CVD risk prediction, offering the potential to capture complex relationships between clinical and biometric data and patient outcomes. This study explores the application of support vector machines (SVMs), ensemble learning, and artificial neural networks (NNs) for predictive modeling of CVD in patients. The study utilizes a comprehensive dataset comprising demographic and biometric data of patients, including age, gender, blood pressure, cholesterol levels, and body mass index, features. SVMs, ensemble learning, and NNs are employed to construct predictive models based on these data. The performance of each model is evaluated using metrics such as accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC). The results demonstrate that all three models achieve accuracy performance in predicting CVD events, with AUC values ranging from 0.85 to 0.92. Ensemble learning exhibits the highest overall accuracy, while SVM and ANN demonstrate strengths in specific aspects of prediction. The study concludes that Machine learning algorithms, particularly ensemble learning, hold significant promise for improving CVD risk assessment. The integration of ML-based predictive models into demographic practice can facilitate early intervention, personalized treatment strategies, and improved patient outcomes.