LAUTECH Journal of Engineering and Technology (LAUJET)
Not a member yet
571 research outputs found
Sort by
Sentiment Analysis of Movie Reviews using Word Embeddings and Machine Learning Techniques
Get PDFIn this study, sentiment analysis of movie reviews was carried out using word embeddings and machine learning techniques. Sentiment analysis, as an opinion mining technique, involves using feature extraction methods to understand the opinions and emotions expressed in text—particularly in domains such as movie reviews, where public sentiment plays a strong role in shaping consumer decisions. For sentiment analysis to be effective, text must be converted into a form that a computer can process. This involves transforming words or documents into vectors using word embedding techniques. Common techniques include Bag of Words, TF-IDF, and Word2Vec. In this study, TF-IDF and Bidirectional Encoder Representations from Transformers (BERT) were selected to compare their effectiveness in analyzing sentiment in movie reviews. The research used the IMDb dataset, which is widely recognized and commonly used in text mining tasks. Various machine learning models were applied, including Support Vector Machine (SVM), XGBoost, and Long Short-Term Memory (LSTM). Results showed that the combination of TF-IDF and SVM produced the highest accuracy, outperforming more complex models such as BERT with LSTM. The findings suggest that simpler word embedding techniques, when paired with effective classifiers, can give strong performance in sentiment analysis
Development of an android-based energy meter reading with load control monitoring
Get PDFThis paper discusses the design and implementation of an Android-based energy meter reading system with load control capabilities. The system leverages modern communication technologies for real-time energy monitoring and management, featuring automatic meter reading, remote load control, and a user-friendly interface via a smartphone application. Integrating voltage and current sensors, a relay module, and an LCD display with the ESP32 microcontroller, the system demonstrates high accuracy and reliability in energy measurement and control. Testing reveals accurate data collection, effective real-time visualization, and reliable load management. The use of Android technology and IoT platforms addresses traditional metering inefficiencies, offering significant improvements in energy management and potential cost savings. The system's robust design and user-friendly interface support its potential for broader adoption and more sustainable energy practices
Development of a modified fuzzy logic-based system in decongesting traffic at road junctions: Development of a modified fuzzy logic-based system in decongesting traffic at road junctions
No full textTraffic congestion at road junctions is a growing concern in urban areas, significantly impacting travel time, fuel consumption, and environmental pollution. As cities expand and vehicle ownership increases, traditional traffic management systems struggle to handle the rising volume of vehicles, leading to frequent bottlenecks at key intersections. Existing traffic decongestion methods, such as fuzzy-based algorithms, suffer from design complexity and tuning inaccuracy. To address these limitations, this work proposes a modified fuzzy logic-based algorithm integrated with the Spider Wasp Optimization (SWO) algorithm for efficient traffic decongestion at road junctions. Traffic parameters including vehicle arrival rate, queue length, and waiting time were generated using a MATLAB R2023a-based stochastic traffic simulation model. These inputs fed into a fuzzy logic controller that determined adaptive green signal durations for each lane. The SWO algorithm, modeled on the predatory and resource allocation behavior of spider wasps, was employed to optimize the fuzzy rule weights and membership function parameters. System performance was evaluated using queue length, average vehicle delay, throughput, signal timing efficiency, green time utilization, and intersection delay index as performance metrics. Comparative simulation results demonstrated that the proposed hybrid SWO-fuzzy system outperformed the standalone fuzzy logic controller by reducing congestion, improving signal utilization efficiency, and enhancing traffic flow stability. The developed model exhibited adaptive capability to varying traffic scenarios without human intervention, thereby improving road safety, reducing fuel consumption, and enhancing commuter experience
Physico-mechanical properties, tribological behaviour and metallurgical characteristics of aluminium metal matrix composites reinforced with agricultural residues: A Review: Physico-mechanical properties, tribological behaviour and metallurgical characteristics of aluminium metal matrix composites reinforced with agricultural residues: A Review
No full textAluminium Metal Matrix Composites (AMMCs) that are reinforced with agricultural residues (such as rice husk ash, coconut shell ash, sugarcane bagasse ash, maize/corn-cob ash, palm kernel and shell ash) have garnered increasing attention as environmentally friendly, low-cost, and lightweight alternatives to traditional ceramic reinforcements. This review gathers recent findings on (1) physico-mechanical properties (tensile strength, hardness, ductility, density), (2) tribological behaviour (wear rate, friction coefficient, wear mechanisms), and (3) metallurgical characteristics (microstructure, interfacial bonding, phase formation, porosity) of agro-reinforced AMMCs. The review describes common synthesis methods (stir casting and powder metallurgy), emphasises critical microstructure–property correlations, pinpoints persistent challenges (particle agglomeration, inadequate wettability, porosity, variable pre-treatment) and optimisation process. Key fabrication techniques are briefly outlined, and future research directions encompassing hybridisation techniques and surface modifications are provided
Mechanical properties and microstructural analysis of reinforcement steel bars in Osun State construction industry
Get PDFSteel bars are crucial components in structural engineering. The frequent incidents of building collapse in Nigeria highlight the importance of carefully analysing the characteristics of reinforcement steel bars available in the local market. A study was conducted in Osun State to evaluate the compliance of locally available steel bars with essential standards, addressing concerns related to building integrity. The study examined the mechanical properties of reinforcement steel rods with diameters of 7, 9, 12, and 14 mm, procured from four prominent dealers in the Osun State market. Standard procedures were employed to determine hardness values, yield strength, and ultimate tensile strength, utilizing an Instron Satec Series 600DX universal testing machine. Additionally, Scanning Electron Microscopy (SEM) was employed to investigate microstructural properties at the metallurgy laboratory of SARD and the Department of Materials Science and Engineering, Obafemi Awolowo University, Ile-Ife, Osun State. The findings showed that certain steel bars exceeded the hardness values, yield strengths, and ultimate tensile strengths set by BS4449, ISO, NIS, and ASTM A706. However, the studied steel bar samples showed commendable ductility. A strong correlation was established between microstructure and mechanical properties. It is noteworthy that the samples contained obvious levels of impurities. In conclusion, while the samples demonstrated satisfactory ductility, it is important to take into consideration the presence of impurities
Comparative design of flow reactors for the production of 100,000 tons per year of cumene from the catalytic alkylation of propylene and benzene
No full textThis research is driven by the need to ensure effective, economic and sustainable processes for cumene production from the catalytic alkylation of propylene and benzene in flow reactors. The flow reactors are the continuous stirred tank reactor (CSTR) and the plug flow reactor (PFR) where the alkylation reaction occurs. The reactors were designed by exploring the conservation principle of mass and energy over the reactors. The performance model of the reactors was simulated using MATLAB at the same initial feed and operating temperature of 481.1k and 483k with fractional conversion changes within the range of XA at an interval of 0.05. The comparative analysis of the flow reactor design was based on the target product yield (cumene yield) and the energy efficiency of the process. The cumene yield is dependent on the reactor volume while the energy efficiency of the process depends on the quantity of heat generated per unit volume of the reactor. At maximum fractional conversion of 0.95, the volume of the CSTR and the PFR design were 52.296m3 and 19.771m3 with a percentage difference of 22.6% while the quantity of heat generated per unit volume of the CSTR and PFR were 0.013j/sm3 and 0.035j/sm3 with a percentage difference of 22.9%. The above comparative design analysis showed that in terms of cumene yield, the CSTR displayed a better performance characteristic as indicated by the reactor volume while in terms of energy efficiency, the PFR showed a better performance characteristic as indicated by the quantity of heat generated per unit volume of the reactor. This article has shown that both the CSTR and the PFR are suitable for cumene production and the choice of reactor depends on the designer’s primary need.
 
Assessment of water quality variation: tool for effective water treatment system operations
No full textWater quality and treatment systems are dynamic because they constantly undergo seasonal variations in water chemistry, varying plant operating conditions, and new environmental laws, among others. Because of this, proper monitoring is essential to ensure that the water supplied by the treatment system safeguards public health from waterborne diseases. Selected surface water quality parameters as inflow were obtained before treatment against the treated water for different hydrological periods (2009 – 2019) from a water treatment system to determine the trend in water quality variation, water quality index, and effectiveness of the treatment process. Each hydrologic year had varying concentrations of selected parameters for raw and treated water quality. The concentration values of pH, electrical conductivity, total hardness, calcium and magnesium hardness, chloride, and total dissolved solids of the natural source water were within the recommended limit. Turbidity concentrations were above the recommended value for each hydrologic year, values ranging from 14.65 – 57.98 NTU, and iron concentration was above the permissible for 2010 and 2012. Selected parameters were all within the threshold limit after treatment with a water quality index (WQI) ranging between 1.09 – 39.39, rated as good/excellent water quality. The treatment system operations were effective throughout the observation period. However, turbidity, iron and hardness should be tested more frequently during the operational and verification monitoring process
Remediation of colour from distillery wastewater using orange peels as adsorbent
Get PDFThe dark-brown color of Distillery Wastewater (DWW), often termed melanoidin, causes discoloration and turbidity rise in water bodies, restraining water usage and detrimental to aquatic life. This study investigates Orange Peels (OP) efficiency as a low-cost adsorbent for color removal from DWW. The color of Fresh DWW’s was confirmed on platinum-cobalt color scale, its color concentration was measured at 620-nm using UV-visible spectrophotometer. OP was carbonized and characterized for chemical composition, specific surface area, surface functional group and surface morphology. Batch adsorption experiment was performed on Orange Peel Carbon (OPc) and compared with coal-based commercial activated carbon (ACC) to determine the effects of agitation speed, retention time, carbon dosage, DWW pH on the Maximum Removal Efficiency (MRE) of color. The adsorption capacity was evaluated using Langmuir, Freundlich, Elovich, Pseudo-first-order and Pseudo-second-order models. OPc showed good-quality adsorbent. DWW was dark-brown in color (2.030 Abs). A 60.20 % MRE was achieved at 100 RPM agitation speed, 60 mins retention time, 2.5 g/100ml OPc dosage and pH of 4.0. ACC showed better performance of 79.46 % color removal. The adsorption followed Elovich isotherm, implying multilayer adsorption with correlation factor of 0.9414. In general, OPc proved effective in reducing color from DWW, and thus, recommended as a suitable adsorbent to replace the costly commercial adsorbents for DWW treatment
LSTM-BASED MODEL FOR CYBERBULLY DETECTION
Get PDFCyberbully has become rampant due to digitalization and conventional cyberbully detection is time consuming, this led to the development of cyberbully detection systems. Previous cyberbully detection systems yielded low accuracy, hence, this research developed a LSTM-based model for cyberbully detection. The dataset for training the model was obtained from Kaggle and pre-processed by removing punctuation marks and stop words, stemming, tokenization and one hot representation. Feature extraction was done on the datasets to remove outliers and Python 3.9 was used for implementation. The developed system was evaluated using: accuracy, precision, Recall and F1 measure and the results obtained were compared to other machine learning models as well as a hybrid of CNN-LSTM. Result shows The developed model yielded an accuracy of 77.0% with a validation time of 3.024 sec in the detection of cyberbully while the hybridization of LSTM-CNN gave an accuracy of 74.80% for fake news and cyberbully detection. The developed model was also bench marked with other machine learning models: SVM, KNN and RF and the system developed outperformed them. The outcome of this research show that deep learning approach used outperformed the machine learning models considered in this research for cyberbully detection. However, future research should employ locally collected dataset for cyberbully detection
Software development for design of solar energy photovoltaic system for rural and urban communities in nigeria
Get PDFSolar Photovoltaic systems for a given load work dependably and remain the finest alternative regarding numerous utilizations only when preceded with accurate pre-installation design. The output power generated and ability of such Photovoltaic system to meet load demand by a solar photovoltaic (PV) system greatly depends on accurate sizing of the PV system’s parts. The Solar planner software developed in this study provides an effective solution to problems associated with most pre-installation design of Photovoltaic systems in Nigeria. The software accurately carries out the sizing of the various system components, thereby providing the technical personnel with sufficient information about the PV project design prior to installation stage. It also uses the average daily sunshine method and design equations modeled for PV systems to achieve the correct sizing of the components. It follows a procedural sequence in executing the sizing equations developed in JAVA programming language on a JAVA developmental Kit (JDK 1.6). The software produced useful parameters for the technical personnel. The parameters include the total power, design energy, capacity of the solar panel required, number of solar panel required, capacity and number of batteries required, size of charge controller and inverter rating, optimum tilt angle and cable size. The use of this solar planner software for design of PV system gives an effective, faster, cost effective and a reliable accurate sizing and PV system’s improved performance in the Nigerian solar business market