International Journal of Integrated Engineering
Not a member yet
2309 research outputs found
Sort by
Artificial Neural Network in Predicting Risk Exposure in Malaysian Shipyard Industry
Full text linkRisk exposure prediction is an important task in risk management and control. The efficiency of occupational safety and health (OSH) risk prevention depends on the accuracy of predicting risk exposure. In this study, a multilayer perceptron training using the backpropagation algorithm neural network was developed and presented for risk exposure prediction in the Malaysian shipyard industry. The data was collected from industrial shipyards in Malaysia via related government agencies to train the model and evaluate its performance. The data was pre-processed to ensure homogeneity. The artificial neural network (ANN) model used 10 influencing factors as inputs for risk exposure prediction: gender, age, occupation, workplace factors, activities involved, nationality, working hours, educational level, years of employment, and working zone. Several network architectures were developed, and the best model was selected for the risk exposure prediction of workers in the shipyard industry. Three evaluation metrics used for the selection of the best modal were mean square error (MSE), mean average percentage error (MAPE), and correlated of coefficient (R). The results showed that the ANN model, which has an accurate performance of 90.2250% with a coefficient of correlation of 91.375%, can accurately estimate the risk exposure of workers in the shipyard industry. Sensitivity analysis also revealed that input factors, such as working hours and workplace factors, have significant effects on OSH risk prediction. Therefore, they should be taken seriously when dealing with the risk exposure in the Malaysian shipyard industry
Experimental Study on Flexural Performance of Reinforced Concrete Beams with Lap Splices and Threaded Coupler-type Mechanical Splice
Full text linkThis study aimed to assess the feasibility of mechanical splicing as an alternative to traditional lap splicing in reinforced concrete (RC) beams. Six RC beams, including a control beam, a lap-spliced beam, and a mechanically spliced beam using threaded couplers, were subjected to two-point load tests. While the lap-spliced beam exhibited the highest load-carrying capacity, the control beam demonstrated superior ductility, as indicated by higher deflection. The mechanically spliced beams, on the other hand, displayed inferior flexural performance compared to both the control and lap-spliced beams. This reduced performance was attributed to the decreased cross-sectional area of the rebars due to threading and the limited strain distribution caused by the short coupler sleeve. Consequently, this study concludes that lap splicing remains a more effective method for achieving desired levels of flexural strength and ductility in RC beams, and threaded coupler splicing, in its current form, is not a suitable replacement
Reinforcement Learning Algorithms for Probability Models Based on Mobile Robot Agent Path Planning in Unpredictable Environment
Full text linkIn recent years, the development of reinforcement learning algorithms (RLAs) significantly impacted various fields, including robotics. Mobile robots, which must navigate through unpredictable environments, present a complex challenge that traditional probability model-checking methods often struggle to address under dynamic and uncertain conditions. This research work focuses on modifying the Q-learning algorithm, a type of RLA, which is sequentially applied to establish a probability matrix under uncertain conditions. Subsequently, a probability model is developed with the assistance of the robot agent, selecting positions based on the maximum Q-table value of a matrix size 6x6 as per the assumed environment. The learned behaviour of the mobile robot agent, derived from the Q-learning method, is represented as a Markov Decision Process (MDP) model. To specify the dependability criteria of the mobile agent control system, Probabilistic Computation Tree Logic (PCTL) is employed. Furthermore, the MDP model, along with its designated attributes, is input into the Probabilistic Model Checker (PRISM) to facilitate automated verification. This approach proves effective in determining the goal position and selecting the optimal control model for evaluating performance, feasibility, reliability, and attaining the target point most efficiently. From the PRISM model for the episode 2500, the average reward and average steps obtained was 182.8 and 187.6 respectively. The mobile agent learned from the Q-learning algorithm for PRISM performance achieved a maximum reward of 84.99 and a minimum reward of 61.41 during the simulation
Development of Optical Sensor Using ZnO Microflowers as Sensing Material for Organophosphate Pesticide Detection
Full text linkThe widespread usage of organophosphates, such as insecticides, herbicides, and fungicides, presents considerable health hazards to humans owing to their ability to inhibit the acetylcholinesterase enzyme (AChE) in non-target organisms. Prolonged exposure to organophosphates has been associated with neurological disorders, developmental complications in children, and an increased risk of certain cancers. Profenofos and diazinon, a widely utilized organophosphate pesticide for crop pest control, have been categorized as moderately toxic by the World Health Organization (WHO). The identification of profenofos and diazinon residues on crops holds importance for ensuring food safety. This study focuses on the innovative profenofos and diazinon detection method utilizing optical sensors, offering a label-free and real-time measurement scheme. The sensor utilizes zinc oxide (ZnO) with a microflowers structure (ZnO MFs) as the sensing material, chosen for its enlarged surface area, which enhances sensitivity to alterations in the surrounding medium. Synthesized via the solution route method, the ZnO MFs exhibit dimensions of 5.47 ± 0.84 µm in length, 1.30 ± 0.26 µm in width, and an aspect ratio of 4.35 ± 1.02. Profenofos and diazinon concentrations ranging from 1 to 10,000 ppm are used as targeted analytes for sensor testing. The findings demonstrate distinct responses of the optical sensor, with a detection limit (LoD) of 1 ppm. The sensing parameter, Absolute Optical Change (AOC), exhibits its highest value at 1 ppm for profenofos and 100 ppm for diazinon, indicating an optimal sensitivity
Exploring Ozone Precursor Patterns in The Urban Area: A Case Study in Peninsular Malaysia
Full text linkOzone precursors are chemical compounds that interact with oxygen in the environment, leading to the formation of ozone. Volatile organic compounds (VOCs) are common ozone precursors. Ozone precursors can affect air quality and human health. The objective of this study is to investigate and evaluate ozone precursors in Cheras and Seremban in the central zone of Peninsular Malaysia using monthly data from 2018 to 2021. The Kolmogorov-Smirnov test found a p-value of less than 0.05, significantly rejecting the hypothesis of normal distribution. Exploratory data analysis was used to evaluate the data at both stations based on descriptive statistics, scatter plots, boxplots, and correlations between parameters. The maximum value of toluene from 2018 to 2021, is 5,738 ppb, which is more higher than Seremban\u27s 2,228 ppb and than other ozone precursors in both stations. Meanwhile, the minimum of benzene, ethylbenzene and xylene in Cheras are 0.3201 ppb, 0.1470 ppb and 0.2910 ppb and in Seremban are 0.3794 ppb, 0.1770 ppb and 0.1400 ppb while the maximum value in Cheras are 1.3892 ppb, 0.7826 ppb and 1.3498 ppb and Seremban are 1.6955 ppb, 1.3117 ppb and 1.7801. Spearman\u27s correlation shows that there is a strong positive monotonic relationship between toluene and benzene at both Cheras and Seremban stations (0.71 and 0.91) while most pollutants have a weak correlation with each other. After comparing the two locations, it was found that Cheras had a higher concentration of pollutants than Seremban. Cheras’ growing economy and central location mean that there are more manufacturers, fuel-burning vehicles, and chemicals emitting into the air than in Seremban. The results of the study can help governments develop more effective strategies to reduce the release of ozone precursors into the atmosphere, which can harm humans if emission limits are exceeded
A New Approach to Determine the Flexural Stiffness Coefficient for Reinforced Concrete Shear Walls According to Non-Linear Behaviour
Full text linkThe precision in calculating the stiffness of reinforced concrete sections is critical for establishing accurate values for structural stiffness and the associated seismic loads. This study investigated effective stiffnesses recommended for use in designing and analysing structures. A total of 135 section models with transverse and longitudinal reinforcement ratios, compressive strength of concrete and axial load levels affecting the analytical analysis of the nonlinear behavior of reinforced concrete shear walls with high ductility levels were considered. The key parameters influencing effective stiffness an aspect that encompasses the impact of cracking and theoretical yielding within structural sections were identified through thorough moment-curvature analyses conducted on a range of shear wall sections. According to the numerical analysis results of the shear wall models, it was found that these design parameters were effective on the stiffness coefficient of the sections. Considering the effective stiffness of section models, a secure and simpler equation is proposed to include these parameters. The equation provides a high degree of accuracy in design and analysis by considering the nonlinear behavior of shear walls in buildings concerning important design parameters. Based on the results of the nonlinear analysis, the proposed predictions for the effective stiffness coefficient, relations proposed by many researchers, standards, and codes, are verified by comparisons with moment-curvature relations. The proposed equation for the effective stiffness of shear wall sections with high ductility levels offers fairly accurate and consistent estimates since it considers all design parameters that affect the non-linear behavior of the sections. This equation has been compared with nonlinear analyses of section models and existing relationships in the literature and has been proven to be reasonably accurate for practical engineering design applications. In the proposed equation, the stiffness coefficients of shear walls can be calculated according to these effective design parameters, and it can verify and design high ductility shear walls with sufficient accuracy in practical engineering design and analysis applications
Performance Evaluation of Different Classification Algorithms Applied for Identifying Maternal Nutritional Status by Anthropometric Measurements
Full text linkPregnancy significantly influences infant quality and development. Maternal monitoring, indicated by body mass index (BMI) and mid-upper arm circumference (MUAC) measurements, reflects a country\u27s socioeconomic development. Improper measurements heighten the risk of chronic energy deficiency (CED) in pregnant women and low birth weight (LBW) in infants. This study leverages artificial intelligence (AI) to enhance the detection process. Specifically, it evaluates the prediction performance of various classification methods: Decision Tree (DT), K-Nearest Neighbors (KNN), Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM). Using interviews in Jombang District, Indonesia, these methods were expected to identify maternal nutritional status. The model design was divided into two stages: MUAC estimation generated binary classes, and BMI estimation generated multiple classes. The evaluation of these methods included various performance metrics: Accuracy (Acc), G-means, Sensitivity (Sens), Specificity (Spec), Positive Predictive Value (PPV), and Negative Predictive Value (NPV). Based on the results, all methods are proposed for both classifications, except KNN on multiple classification. KNN achieved significant scores in all matrices with p<0.01. KNN\u27s performance is impacted by data imbalance. The study revealed a strong correlation (0.92 coefficient) between BMI and MUAC variables. The application of ML algorithms in detecting maternal nutritional status can significantly enhance the effectiveness and efficiency of health facilities, especially in areas with inadequate resources and medical personnel. However, exploring diverse ML algorithms is recommended to find optimal approaches for more varied data and to contribute solutions for sustainable development in the country.
A Review of Machine Learning Used in the Diagnosis of Parkinson’s Disease
Full text linkParkinson’s Disease (PD) is projected to impact an increasing number of individuals due to the anticipated growth of the global elderly population. While there is currently no cure, early diagnosis remains crucial for extending the quality of life for individuals with PD. Machine Learning (ML) techniques have been found to be effective in facilitating remote monitoring and enabling early diagnosis of PD. ML algorithms have shown to be able to achieve higher accuracy diagnostics compared to experts, and there is still room for improvement. This paper aims to provide a comprehensive overview of recent developments in diagnosing PD using ML. The study investigates eight of the most widely used ML algorithms, namely Support Vector Machines (SVMs), Neural Networks (NNs), Ensemble Learning, K Nearest Neighbours, Logistic Regression, Decision Trees, Naive Bayes and Discriminant Analysis, to provide a thorough analysis of their applicability and effectiveness in PD diagnosis. This paper will focus on these algorithms as they are the basis of many other variants, and they are most popularly researched and used. The paper discusses the strengths and weaknesses of each algorithm, presents examples of their usage, and highlights their efficacy with different PD indicators. Moreover, this paper reviews some of the most influential works in recent years, identifying the most significant challenges in the field of PD diagnosis. It highlights how researchers have attempted to address them and outlines directions for future research. First, this paper reviews the ML techniques used in diagnosis of PD. Then, we discuss the ML models’ shortcomings and strength. Finally, we discuss the challenges and future directions in research of this field. Notably, the study shows that SVMs and NNs emerge as popular choices due to their efficacy with commonly used datasets in PD diagnosis
Comparison of Myocardial Mechanical Metrics in Electromechanical Model vs. Fluid-Electromechanical Model
Full text linkThe development of multiphysics heart model has grown tremendously over the past decade. In this paper, we compare two multiphysics approaches: electromechanics and fluid-electromechanics, in simulating left ventricular mechanics and the output of mechanical metrics. Cardiac electromechanical (EM) model refers to the approach of simulating heart mechanical deformation, triggered by cardiac action potential, while the generated ventricular pressure is determined by a penalty function and applied uniformly across the endocardium. Fluid-electromechanics (Fluid-EM) approach relies on similar action potential wave to trigger mechanical deformation but the ventricular pressure is determined by solving the Navier-Stokes equations within the ventricular cavity. Thus, Fluid-EM is more accurate as it models the blood-ventricular interaction, producing more realistic loading on the endocardium and enabling analysis of blood flow dynamics. Due to its complexity, the Fluid-EM approach is more computationally demanding than the EM approach. We assessed several mechanical metrics within the ventricle namely stresses and strains to assess regional differences in the heart by implementing both approach in a heart geometry extracted from a healthy patient. Differences in the mechanical metrics were noted indicating both models were loaded differently due to differences in modelling the blood. This suggests that in greater differences can be expected should there be more regional differences in the myocardium such as in infarct cases
Rubber Seed Shell Based Activated Carbon as Potential Biosorbent for the Removal of Heavy Metals from Aqueous Solution
Full text linkHeavy metals contamination in water body and aquatic ecosystems has significantly affects and posing serious threats to the environment, aquatic life, and public health. Due to its widespread occurence and harmful effects, adressing this issues remains a critical challege. This study explores the utilization of a widely available agricultural by-product in Malaysia such as rubber seed shells (RSS), as a raw material for producing low-cost activated carbon (AC) for heavy metal removal applications. To enhance the surface porosity and adsorbent characteristics, the RSS was chemically activated using sodium hydroxide (NaOH) and carbonized. Scanning Electron Microscopy (SEM), Fourier Transform Infrared Spectroscopy (FTIR), and X-ray Diffraction (XRD) analyses was carried out to characterized the rubber seed shell ras sample (raw-RSS) and rubber seed shell activated carbon (RSS-AC), respectively. The removal efficiency of lead (Pb) and copper (Cu) were evaluted via batch biosorption test under varying conditions of initial concentration (200 - 800 ppm), contact time (15 - 60 min), and biosorbent dosage (0.05 - 0.20 g). Results shows that under optimum conditions of 200 ppm initial concentration, 60 minutes contact time, and 0.20 gram biosorbent dosage yielded removal efficiencies of 77.45% for Cu and 99.20% for Pb. These results highlight that rubber seed shell based activated carbon as an effective, eco-friendly biosorbent for wastewater treatment