International Journal on Advanced Science, Engineering and Information Technology
Not a member yet
2006 research outputs found
Sort by
Analysis of Dam Break Wave Using Analytical, Computational Fluid Dynamics, and Experimental Approaches
Get PDFThis research aims to examine the capability of the Computational Fluid Dynamics (CFD) method in simulating the behavior of dam break waves. It begins by building a 2D numerical simulation using OpenFOAM. To overcome the influence of turbulence, we employed the Large Eddy Simulation (LES) turbulent model, specifically the k-Equation and Smagorinsky model. The simulation was developed by applying the Navier-Stokes equations using the finite volume method in OpenFOAM. The analysis focuses on the free surface of a dam break. The results are in good accordance with both analytical and experimental results. The simulation has followed the trend of experimental and analytical free surface profiles at the dam break’s early and late conditions. The low mesh number on the computational domain caused significant differences in the wavefront of the dam break. It reduced the accuracy of the calculation between the water and air interface. This study highlights the importance of understanding dam break wave behavior as part of risk mitigation for dam leakage. The behavior of dam break waves can be observed by determining observation positions at different locations, with the water gate of a dam serving as the reference point. These highly accurate numerical results indicate that the CFD approach employing OpenFOAM can be relatively cost-effective yet accurate in analyzing multiphase problems, such as dam breaks. This CFD approach is expected to contribute to developing mitigation and disaster prevention in the future
Road Maintenance Management Based on Geographic Information System (GIS)
Get PDFThis research implements GIS in transportation, specifically road maintenance. The system is built by utilizing 2D/3D models from aerial photographs using UAV as a base map. Attribute data such as the type and dimensions of road damage can be obtained by interpreting high-resolution 2D/3D models, which display each road damage, making it easier to measure the dimensions of road damage. The assessment of road conditions is done using the PCI method, which indicates that 51% of the roads fall under the category of people with low incomes to severely damaged category. These roads are prioritized on a map based on their area and cost of maintenance. The projection calculation of the amount of damage is analyzed with one do-nothing scenario, where the roads have not been maintained for ten years. The progression of the damage is observed each year, and the reactive maintenance cost is calculated from 2023 to 2032. The cost and duration are analyzed using three do-something scenarios: optimistic, moderate, and pessimistic. The research results show that the moderate scenario has the lowest cost among the other scenarios and is the most effective scenario, as it produces road conditions with an International Roughness Index (IRI) value of less than 6. This research can assist the government in making informed decisions regarding road maintenance
Regression-based Analytical Approach for Speech Emotion Prediction based on Multivariate Additive Regression Spline (MARS)
Get PDFUsing regression analysis techniques for speech-emotion recognition (SER) is an excellent method of resource efficiency. The labeled speech emotion data has high emotional complexity and ambiguity, making this research difficult. The maximum average difference is used to consider the marginal agreement between the source and target domains without focusing on the distribution of the previous classes in the two domains. To address this issue, we propose emotion recognition in speech using a regression analysis technique based on local domain adaptation. The results of this study show that the model's generalization ability with the function of the local additive method is very good for improving speech emotion recognition performance. Even though it provides excellent benefits in resource efficiency, regression analytical techniques are rarely used in the SER field; however, we believe this method is the best solution for SER problems. Using the Multivariate Additive Regression Spline, this study developed a predictive model for the existence of angry and non-angry emotions (MARS). Using probability analysis of error values, this approach can overcome regression on data that is not typically distributed. This method yields an ideal basis function that significantly impacts changes in emotional form. This study generates a prediction model with a Mean Square Error (MSE) of 0.0130, a Generalized Cross Validation (GCV) value of 0.0062, and a R Square (RSQ) value of 0.9721, yielding test results with a 97% accuracy rate
A Novel Design of Error Backpropagation Algorithm for Ingredient Mixing Process Tamarind Turmeric Herb
Get PDFThe goal of this study is to determine the best picture pattern for the tamarind turmeric herb. So far, the taste and color of tamarind turmeric herb have not been consistent, as they are impacted by maturity, and the amount of Turmeric used. The error backpropagation technique, which is commonly used in Content-based image retrieval systems, will be used to recognize image patterns. The main goal is to capture various portions of the tamarind turmeric herb during the extraction procedure. The camera is used to classify the tamarind turmeric herb product, process it into 5x5 pixels, and average the RGB value to obtain stable RGB values in each category, which are then fed into the Error Backpropagation algorithm. The most appropriate and fastest Error Backpropagation algorithm procedure will be found and implemented in a real-time computer. The first way will be to train the algorithm with ten data by changing neurons, layer, momentum, and learning rate, and the second technique will be to test the algorithm with ten data. The results of the training and testing procedure show that the two hidden layers can recognize 100% of inputs, with three input layers for R, G, and B values, ten neurons in the first and second hidden layers, and one output layer with Learning rate 0.5 and Momentum 0.6 as a parameter. Dark yellow is the best image pattern standard for tamarind turmeric herb, with RGB values in the range from 255, 103, 32 to 255, 128, 48
Deep Learning Model for Identification of Diseases on Strawberry (Fragaria sp.) Plants
Get PDFPlant diseases can significantly affect crop productivity if not effectively managed. Accurate disease identification is critical for disease control and yield enhancement. Addressing these concerns, the potential application of deep learning techniques for plant disease identification is promising in Indonesia. This research aims to formulate a deep learning model tailored to detect strawberry (Fragaria sp.) plant diseases. The study encompasses several key phases, including: (1) collecting datasets, (2) preprocessing datasets, (3) annotating datasets, (4) configuring and training deep learning models, and (5) validating and evaluating the model. The developed model employs YOLOv7 and YOLOv7-X algorithms, utilizing a dataset of 7337 instances across three disease categories: tip burn, leaf scorch, and anthracnose. These datasets were obtained from publicly accessible repositories. The evaluation of the deep learning model's performance in detecting plant diseases involved using 717 in-field plant images. The outcomes of the evaluation, employing YOLOv7 and YOLOv7-X algorithms, demonstrated accuracy rates of 92.5% and 92.3%, precision levels of 94.5% and 95.1%, and recall values of 90.5% and 89.6%, respectively. These results emphasize the effectiveness of the deep learning model in accurately and precisely identifying diseases in strawberry plants
Environmental Quality Deterioration in the Mamminasata Metropolitan New City Area, South Sulawesi, Indonesia
Get PDFExcessive urbanization in the development dynamics of Makassar City in its position as the main city in the Mamminasata Metropolitan urban system has an impact on the expansion of the area towards suburban areas for the needs of new city development. The development of new cities through the development of socio-economic activities contributes positively to the quality of the environment. Increased housing development and socio-economic activities mark this condition, and urban infrastructure is allocated for new urban areas. The development of the new city area of Moncongloe-Pattalasang impacts changes in spatial attributes, spatial dynamics, and urban transportation systems based on patterns of origin and travel destinations towards the complexity of space utilization and environmental degradation from the suburbs. This study analyzes the direct and indirect effects of land cover change, land elevation, and agricultural land conversion on environmental degradation. This study uses a quantitative survey approach, and data was obtained through observation, survey, and documentation. The study results show that the development of new urban areas has positively contributed to the spatial dynamics and socio-economic system of the Mamminasata urban community. Furthermore, the difference in land elevation has positively affected changes in spatial activity patterns, environmental quality degradation, and the potential risk of urban flooding in the new city area of Moncongloe-Pattalassang. This study recommends restoring the environmental quality of new urban areas in formulating policies to support the sustainability of the Mamminasata Metropolitan urban development
An Efficient and Robust Ischemic Stroke Detection Using a Combination of Convolutional Neural Network (CNN) and Kernel K-Means Clustering
Get PDFThis study introduces a combined approach utilizing the widely-used Convolutional Neural Network (CNN) and Kernel K-Means clustering method for the detection of ischemic stroke from Magnetic Resonance Imaging (MRI) images. We propose an efficient and robust alternating classification scheme to overcome the challenges of extensive computation time and noisy ischemic stroke images obtained from Cipto Mangunkusumo Hospital in Indonesia. The method incorporates multiple convolutional layers from the CNN architecture and subsequently vectorizes the matrix output to serve as input for Kernel K-Means clustering. Through a series of experiments, our proposed method has demonstrated highly promising results. Employing 11-fold cross-validation and the RBF kernel function (sigma= 0.05), we achieved exceptional performance metrics, including 99% accuracy, 100% sensitivity, 98% precision, 98.04% specificity, and 98.99% F1-Score. These outcomes underscore the remarkable capabilities of the combined CNN and Kernel K-Means clustering approach in accurately identifying ischemic stroke cases. Furthermore, our method exhibits competitive performance when compared to several other state-of-the-art methods in the field of deep learning. By harnessing the power of CNN's convolutional layers and the clustering capability of Kernel K-Means, we have achieved significant advancements in the domain of ischemic stroke detection from MRI images. The implications of this research are substantial. By enhancing the accuracy and efficiency of ischemic stroke detection, our method has the potential to assist medical professionals in making timely and informed decisions for stroke patients. Early detection and intervention can greatly improve patient outcomes and contribute to more effective treatment strategies
Enhancing Engineering Education in the Roblox Metaverse: Utilizing chatGPT for Game Development for Electrical Machine Course
Get PDFThis research paper explores the use of chatGPT to facilitate the development of educational experiences in the Roblox metaverse, specifically focusing on the electrical machine course. The primary objectives of this study are to demonstrate how chatGPT can streamline the creation of immersive and interactive learning environments within Roblox and to evaluate the efficacy of these experiences in engaging students and enhancing their understanding of electrical machines. Our approach leverages chatGPT's capabilities to optimize client-side scripts for server-side implementation efficiently, create well-structured dictionaries for describing game activities, stages, and points, and simplify the implementation of various effects and interactions. Upon completing our Roblox-based educational experience, the resulting code will be available under a Creative Commons license, allowing other educators and developers to build upon and customize our work for their needs. We tested this project with a group of 22 college-level students studying electrical machines, whose feedback has been instrumental in understanding the effectiveness of our methods and identifying areas for improvement. The results of this study suggest that integrating chatGPT into the development process of Roblox-based electrical machine-learning experiences can lead to increased student engagement and understanding. Further research is recommended to explore the broader implications of using chatGPT and other AI-powered tools in developing metaverse-based educational content across various subjects and learning environments. By doing so, we can continue to push the boundaries of what is possible in virtual education and provide more engaging and effective learning experiences for students worldwide
Magnetic Signature and Element Content of Upflow and Outflow Hotspring in Arjuno–Welirang Geothermal System
Get PDFResearch on magnetic properties and chemical element content of environmental deposits has been conducted for various purposes. This study focuses on characteristic magnetic susceptibility, magnetic mineral morphology, and the elemental composition of Cangar and Padusan hot springs in the Arjuno-Welirang geothermal system to differentiate upflow and outflow systems, respectively. The measurements were performed for better understand the relation between magnetic susceptibility, Fe-Silicate content, magnetic mineral morphology, surface temperature and compare these characteristics in two kinds of hot springs in the same mountain system. Magnetic susceptibility ranged (7.558 - 62.694 ) × 10-6 m3/kg with an average of 30.651 × 10-6 m3/kg for Cangar (upflow) and (11.821 - 28.101) × 10-6 m3/kg with an average of 18.148 × 10-6 m3/kg for Padusan (outflow). In situ magnetic minerals extracted of hot springs are averaged of magnetic susceptibility is 26.981 × 10-6 m3/kg for Cangar and 24.445 × 10-6 m3/kg for Padusan. The element content dominated by Al, Si, K, Ca, Ti and Fe, where Fe is more abundant in Cangar as an upflow. The higher magnetic susceptibility, the greater of Fe-silicate content in both of hot springs. The surface temperature ranged from 38 - 48°C, where the higher temperature, the magnetic susceptibility increased. In Cangar, extracted magnetic minerals tend show crystalline, especially hedralic shape with very fine surface, clean and free of impurities. Meanwhile, some magnetic minerals are also found in spherical shapes, especially in Padusan
SARS-Corona Virus Type-2 Detection of Cohabiting Feline with COVID-Positive Individuals in Bandung, Indonesia
Get PDFSince people and domesticated animals have lived together for a long time, it is possible that diseases could be spread by accident, as happened with SARS-CoV-2. There have been reports of cats in Italy, Spain, and France being exposed to SARS-CoV-2. Not much is known about how farmed animals were exposed to SARS-CoV-2 in Indonesia, which was named the epicenter of COVID-19 in July 2021. The study's goal was to determine if SARS-CoV-2 was present in felines living with people who had COVID-19 in the Bandung, Indonesia, area. Nineteen felines were used in the study. These felines came from seven people who had tested positive for COVID-19. For RT-qPCR testing, samples were taken from the nose, oropharynx, and rectal areas. Blood sera were taken for quick IgM/IgG antibody tests for SARS CoV-2. Using RT-qPCR on nasopharyngeal samples from the felines being studied, it has been seen that four of them have tested positive. But it is interesting to note that only one of these people could be found using a rectal test. There was no clear sign of antibody formation when IgM/IgG rapid test results from blood samples were looked at. The felines that showed positive results were very close to their caretakers and had symptoms that were similar to those of influenza. The results of our study show that there is a chance that SARS-CoV-2 could be passed on to felines who live with people who have COVID-19. Because of this finding, more study needs to be done in this area