LAUTECH Journal of Engineering and Technology (LAUJET)
Not a member yet
571 research outputs found
Sort by
INTERNET OF THINGS (IoT) BASED REMOTE SURVEILLANCE CAMERA FOR SUPERVISION OF EXAMINATIONS
No full textRemote surveillance camera is used for detecting and averting illegal or suspicious activities in cities, campuses, businesses places, large gathering and many other places. University examinations are faced with challenges of malpractices due to stress and inadequate number of human invigilators. The Internet of Things (IoT) based remote surveillance camera system was developed to monitor studentsβ conduct in examination hall using ESP32 CAM project development board with an on-board camera for video capturing. It was programed with the Future Technology Device International (FTDI), powered with 5v dc and the Ngrok application was developed and used to access the system output remotely on internet. The system was tested for surveillance from a remote distance over a local area network (LAN) and over the internet which yielded satisfactory results. Also when the captured image was fed into a trained face recognition model, the candidate was recognized by name and matriculation number. The conduct of examination can be effectively monitored in a wireless network over the local area network (LAN) and the wide area network (WAN) using the developed IoT based remote surveillance camera system for a closed supervision. This will help to detect and reduce all forms of malpractices in examination hall
INVESTIGATING THE EFFECT OF DOUBLE EXCLUSIVE OR OPERATION IN TRIPLE DATA ENCRYPTION ALGORITHM
Get PDFData encryption standard is an essential and efficient component to ensure the secure communication between the different entities by transferring information that only the authorized recipient can access. The assurance of the lack of access of unauthorized users to sensitive data is the most important challenges regarding data distribution in internet. The method employed involves the design of triple data encryption algorithms (TDEA) with double exclusive OR operation that uses three and two keys. These keys perform operation on data thrice more than more what data encryption does. The results obtained reveals that the triple data encryption algorithm with double exclusive OR (DXOR) execution speed was faster than triple data encryption algorithm without DXOR and it also consumes more memory to initialize the sub keys than the TDEA without DXOR. Also, the results obtained shows that for a file size of 1 MB, the average response time for data encryption algorithm (DEA) = 0.15s, TDEA (3KEYS) = 0.45s, TDEA (3KEYS) + DXOR = 0.31s, TDEA (2KEYS) = 0.31s and TDEA (2KEYS) + DXOR = 0.27s whereas for a file size of 15MB, the average response time for DEA = 2.13s, TDEA (3KEYS) = 6.51s, TDEA (3KEYS) + DXOR = 6.13s, TDEA (2KEYS) = 4.09s and TDEA (2KEYS) + DXOR = 3.62s. In conclusion, the effect of double exclusive OR operation in existing triple data encryption algorithm was investigated to improve the security and avalanche features of the conventional data encryption standards
PERFORMANCE EVALUATION OF MACHINE LEARNING ALGORITHMS FOR JUDICIAL PREDICTION SYSTEM
No full textArtificial Intelligence and Machine Learning techniques have been productively utilized to forecast judicial outcomes and analyze it. A Judicial Prediction System (JPS) is for forecasting the judicial results based on historical data, legal precedents, and other relevant factors, thereby providing judges and other law professionals the predictive insights into case outcomes. The purpose of the JPS is to educate the public by promoting transparency in the legal process and overcoming various factors negatively influencing the final judgment such as cognitive biases, judicial bottlenecks, emotions, and so on. This paper aims to find the most effective way for judicial outcome prediction to assist in time and judicial resource optimization. Four distinct algorithms: Support Vector Machine, Random Forest, Logistic Regression and K-Nearest Neighbor have been utilized to determine the appeal case outcomes at the Supreme Court of Nigeria (SCN). The dataset used in training the machine learning algorithms was obtained locally from a Supreme Court of Nigeria (SCN). The models were evaluated using precision, recall F1 score and accuracy. Results show that Random Forest provided the highest accuracy of 72%. However, future research should consider ensemble approach for judicial cases prediction.
KEYWORDS: judicial prediction system, Machine Learning algorithms, model, case outcome
Brake pad Production and characterization of hybrid automobile brake pad produced from locally sourced materials
No full textA brake system is highly imperative for the safe control of an articulated automobile. One of the major components of the automobile system is brake pad which is currently imported into the Nigerian market. This study was aimed at producing brake pads from locally available materials to serve as an alternative to imported pads. Samples of brake pads were produced from a mixture of resin, kaolin, barium sulphate, steel fibre, fiberglass, silica, alumina, and graphite sourced from local markets. Three samples - A, B, and C β were moulded following the standard practice for brake pad production. The samples were characterized for microstructure, hardness, wear rate, ultimate tensile strength (UTS), and impact strength. The study established that the brake pad made from 16.3% resin, 13.8% kaolin, 32.6% barium sulphate, 6.5% steel fibre, 10.4% fiberglass, 6.8% silica, 9.2% alumina, and 4.4% graphite performed optimally with a hardness of 4.59 kg/m2. The optimal brake pad had its wear rate lower than other samples after 210 s of load application, an ultimate tensile strength of 3.60 MPa and impact strength of 0.028 J/mm. SEM image of the sample indicates homogenous distribution of the binders, filler and reinforcing materials. Compared to sample B, the conventional brake pad had a higher Brinell hardness value of 18,592 kg/m2. The results justified that the developed brake pads have sound tribological property as prominent characteristic. The study recommends the application of the optimally produced brake in automobiles for enhanced eco-user friendliness.
Keywords: Brake pad; Scan electron microscope; Binder; Energy dispersive x-ray; Local material
Effects of methylene blue as a mediator on pharmaceutical wastewater treatment and bioelectricity generation in a microbial fuel cell
Get PDFPharmaceutical wastewater (PWW) as an industrial wastewater presents a potential hazard to natural water systems. This wastewater contains organic matter, which is toxic to the various life forms of the system. PWW is one of the major health problems nowadays, not only for aquatic life but also for human beings and the environment. There are several methods such as filtration, advanced oxidation, coagulation and biological membranes been used for the treatment of PWW, however, all of these methods are limited in their results and applications. In this present study, Microbial Fuel Cells (MFCs) represent a new method for
treating wastewater, generating electricity, and reducing COD simultaneously. A novel H-type MFC connected with a graphite electrode has been designed for bioelectricity generation, COD reduction as well as PWW treatment. The treatment of PWW showed adequate bioelectricity generation such as Voltage, Current, and Power, of about 775 mV, 0.421 mA, and 583.70 mW at 100 ? respectively. The percentage of the COD removed ranged from 95.2-96.7% and 12-34% at the different process variables. This study established bioelectricity generation and bio-treatment of PWW
Affordable energy-saving switch control system for homes with disabled persons
No full textThe need for energy conservation has become increasingly urgent in today's world, especially as energy costs continue to rise and the demand for sustainable living grows. For persons with physical disabilities, simple tasks like turning light switches on and off can be challenging, resulting in higher energy usage, increased electricity bills, and increased physical strain. Existing solutions often prioritize energy efficiency but overlook affordability and accessibility, making them impractical for low-income households. To address these issues, this paper proposes an affordable automated energy-saving lighting switch control system using Arduino Uno, ultrasonic sensors for human presence detection, and a relay to control lighting. A person-counter mechanism ensures accurate operation based on room occupancy. Experimental results shows that the proposed system achieves 100% accuracy in detecting human presence in a room, effectively reducing energy consumption from 0.4 kWh to 0.2 kWh per day, which corresponds to 50% energy savings. Additionally, it is 42.41% less expensive than the most affordable system compared in the paper. These findings underscore the systemβs potential to offer an affordable, accessible, and energy-efficient solution that enhances the convenience and comfort of disabled persons while contributing to energy conservation efforts
Experimental Analysis of the Performance of Chippings, Stonedust, and Sand in the Production of durable Sandcrete Hollow Blocks
Get PDFSand is one of the most important building elements used to make sandcrete blocks. River sand is rapidly vanishing from river beds as a result of over-exploitation and because the mechanical properties of sandcrete blocks have a significant impact on the longevity of structures made of them, the goal of this study was to explore if using different materials instead of river sand in the production process may boost the strength of hollow sandcrete blocks. Conventional block moulding machine was used to make several units of sandcrete hollow blocks (450 X 225 X 150 mm) for three different categories of blocks containing stonedust, chippings, and sand. Stonedust is used to replace 100 percent of the sand in category A, 50 percent stonedust plus 50 percent chippings in category B, and 40 percent stonedust, 40 percent chippings, and 20 percent sand in category C. The blocks were made with a cement ratio of 1:6. There were 90 blocks cast in all, with the compressive strength and additional tests performed at 7, 14, 21, and 28 days. SigmaPlot 14.0 was used to conduct the statistical analysis of the result. The compressive strengths of hollow sandcrete block samples made from stonedust and chipping were found to be the highest with 6.67N/mm2 which is higher than those of other samples. The results reported for all of the samples are higher than the Nigerian Industrial Standard (NIS), demonstrating that utilizing these materials to partially or completely replace sand increases block compressive strength
Implementation of smart wheelchair with obstacle avoidance
Get PDFThe primary goal of this work is to develop a dependable and efficient solution for maintaining optimal mobility in wheelchair systems. The aim is to enhance functionality and reduce the userβs physical effort required to move the wheelchair wheels. The proposed system integrates advanced sensing technology, intelligent control algorithms, and robust hardware components to manage the wheelchair, detect obstacles, and eliminate the need for external assistance. This wheelchair employs joystick control and halts when the system senses an obstacle. The system enhances user autonomy by providing ease of control and ensures safety by detecting and avoiding obstacles. Motor speeds are adjusted based on joystick input, and the motor direction (forward, backward, left, right) is determined accordingly. An ultrasonic sensor measures obstacle distance, and if an obstacle is detected (distance <= 20cm), both motors stop, and a warning buzzer activates for 1 second. If no obstacle is detected, the warning buzzer turns off, and motor speeds are adjusted based on joystick input. The system effectively demonstrated obstacle avoidance by changing direction when a command was issued away from the obstacle. The outcomes of this study contribute valuable insights to the field of wheelchairs, specifically in the realm of obstacle avoidance.
 
Enhanced multimodal biometric access control system using chicken swarm optimization and self-organizing feature maps: a study on ear and iris recognition
Get PDFAccess control systems are crucial for securing sensitive data and system components by allowing authorized access while blocking unauthorized entities. Traditional unimodal biometric systems, make use of a single physiological or behavioral trait, have limitations such as susceptibility to spoofing and environmental constraints, leading to reduced reliability. This study explores an enhanced multimodal biometric access control system that combines ear and iris traits using an enhanced Self-Organizing Feature Map (SOFM) algorithm improved with Chicken Swarm Optimization (CSO). The system's performance is evaluated against traditional SOFM, with a focus on recognition accuracy and processing time.
The data used to train the classifier for this study were collected from 190 individuals, encompassing a total of 2,280 images of iris, and ear traits. Preprocessing involved cropping, resizing, and grayscale conversion using histogram equalization. Feature extraction utilized Local Binary Patterns (LBP), followed by feature fusion at the feature level to create an integrated feature set. The enhanced SOFM algorithm was then applied for classification, with the CSO technique optimizing the learning rate and weight parameters for improved performance.
At different thresholds, the CSO-SOFM classifier outperformed the standard SOFM classifier using metrics such as Sensitivity, Specificity, Precision, Accuracy and Recognition time
EXTRACTION AND ANALYSIS OF PHOENIX DACTYLIFERA L. (DATE SEED) OIL
Get PDFThe research work aimed to extract oil from Phoenix dactylifera (Date Seed), known for its potential nutraceutical and biodiesel applications. Using n-hexane Soxhlet extraction, oil yields were determined as 30.8% for dust samples and 26.5% for lump samples. Physicochemical analysis showed moisture content at 6.77%, acid value at 1.083 mgKOH/g, and saponification value at 189 mgKOH/g, with specific gravity of 0.9016 and density of 0.9177 g/cm3 for both samples. Fourier Transform Infrared Spectroscopy (FTIR) identified 23 peaks in dust sample oil and 17 in lump sample oil, indicating functional groups such as OH, C-H, C=C, C=O, and N-H. Gas Chromatography Mass Spectrometry (GC-MS) revealed dominant fatty acids Caprylic acid, Capric acid, Palmitic acid, and Oleic acid beneficial for brain health. Date palm seed oil's practical implications include soap manufacturing, washing agents, and biodiesel production. The research underscores the potential of date seed oil as a versatile resource with both industrial and health benefits