International Journal on Advanced Science, Engineering and Information Technology
Not a member yet
2006 research outputs found
Sort by
Evaluation of Land Suitability for Cacao in Takapala Watershed Using Geographic Information System
Get PDFDue to the great variety of land resources in Indonesia, there is a wide range of levels of land appropriateness for various commodities. In order to provide the most physically feasible cultivation pattern and the greatest possible economic results, a land plan is required. This study aims to determine the suitability level of cocoa plantations in the Takapala Watershed (Jeneberang Sub-watershed) using a geographic information system (GIS) method with overlays of slope maps, geomorphological maps, soil type maps, and land use maps. According to the analysis's findings, the Takapala watershed's area is suitable for growing cocoa (Jeneberang Sub-watershed). Obtaining five land suitability sub-classes, including S2 extremely appropriate (with a 93.94 ha area), S3-W1 (marginally suitable class with a factor of 0.8), and S4-W1 (not at all suitable class) as a limiting factor for rainfall 1022.33 Ha with marginally suitable class. There is very good potential for cocoa plant growth in the Takapala Watershed, where the land adaptability level can reach 69.6%. This demonstrates that cocoa trees can develop into crops that can be grown in the Takapala watershed. On the one hand, the Takapala Watershed's topography will present a barrier to cacao development, needing specific approaches to cacao production. Future research should, it is anticipated, look into how cocoa plants should be managed in environments with steep-to-steep slopes
Transformer-based Deep Learning for COVID-19 Prediction Based on Climate Variables in Indonesia
Get PDFRecent research on the effect of climate variables on coronavirus (COVID-19) transmission has emerged. Climate change has the potential to cause new viral outbreaks, illness, and death. This study contributes to COVID-19 disease prevention efforts. This study makes two contributions: (1) we investigated the impact of climate variables on the number of COVID-19 cases in 34 Indonesian provinces; and (2) we developed a transformer-based deep learning model for time series forecasting for the number of positive COVID-19 cases the following day based on climate variables in 34 Indonesian provinces. We obtained data from March 15, 2020 to July 22, 2021 on the number of positive COVID-19 cases and climate change variables (wind, temperature, humidity) in Indonesia. To examine the effect of climate change on the number of positive COVID-19 cases, we employed 15 scenarios for training. The experiment results of the proposed model show that the combination of wind speed and humidity has a weakly positive correlation with positive COVID-19 incidence. However, temperature has a considerably negative association with positive COVID-19 incidences. Compared to the other testing scenarios, the transformer-based deep learning model produced the lowest MAE of 175.96 and the lowest RMSE of 375.81. This study demonstrates that the transformer model works well in several provinces, such as Sumatra, Java, Papua, Bali, West Nusa Tenggara, East Nusa Tenggara, East Kalimantan, and Sulawesi, but not in Central Kalimantan, West Sulawesi, South Sulawesi, and North Sulawesi
Study on the Behavior of a Simple House Partially Retrofitted Using Ferrocement Layers due to Earthquake Loads
Get PDFEarthquakes are a serious threat in Indonesia. Large-scale earthquakes that have occurred, such as the Aceh earthquake (2004), the West Sumatra earthquake (2009), the Lombok earthquake (2018), the Mamuju earthquake (2021), and most recently, the West Pasaman earthquake (2022), which caused many fatalities and damaged infrastructure and building houses, especially houses of the economically weak community. These houses were generally built using adobe bricks using the ½ brick masonry method without structural elements such as columns and beams that do not meet earthquake-safe house standards. In an effort to mitigate earthquake disasters, a strengthening method was developed in this study, namely by using ferrocement layers. In this research, a simple house model with adobe walls with a scale of 1:4 will be made, which will be partially strengthened using ferrocement layers tested on a vibrating table and given an earthquake load. Furthermore, numerical analysis was carried out to validate the results of experimental testing. The results of the tests show that the partial reinforcement has contributed significantly to increasing the shear capacity of the adobe brick walls. This is evidenced by the fact that there were no cracks in the reinforced walls up to the acceleration of the earthquake of 1.5 g, while the other walls of the house that were not reinforced experienced cracks and even collapsed
ANOVA Decomposition and Importance Variable Process in Multivariate Adaptive Regression Spline Model
Get PDFThis article reviews one of the non-parametric functions, namely the MARS (Multivariate Adaptive Regression Spline) method, a complex combination of recursive partitioning and spline regression. The many advantages of the MARS function over other non-parametric regression functions are of interest to researchers. One of them is it can accommodate the additive and interaction model to improve the prediction and interpretation of the data. There are some important things in the MARS method, namely, ANOVA decomposition and Importance Variable. Decomposition ANOVA is a technique in MARS that is useful for grouping basis function based on variables engagement, whether they enter by one variable or interactions with other variables, making it easier to interpret in graphical form. In comparison, the important variables are a technique that can be used to determine which predictor variables most influence the MARS modeling. This study assesses ANOVA decomposition, and the important variables process in MARS modeling based on GCV and MSE criteria. We use the poverty rate modeling data on Java Island to implement the study results. The results show that the MARS model's interpretation of the poverty rate can be better done through ANOVA decomposition. Besides that, based on GCV and MSE criteria, the result also shows that the biggest variable importance in poverty rate modeling on Java Island is the percentage of per capita expenditure for food, while the smallest is the economic growth variable
Physiochemical Properties and Cupping Quality of Gayo Espresso Coffee Based on Blending Ratio and Roasting Techniques
Get PDFEspresso is considered the finest brewing technique to provide coffee's optimum sensory and physiochemical quality. The quality of the Espresso is influenced by many factors, such as bean varieties and origin, roasting process, and blending formation. This research investigated the effect of the blending ratio of two varieties (70:30; 80:20; 90:10 of Arabica and Robusta) of the coffee blend from Gayo Highland Aceh Indonesia, and roasting techniques (conventional and torrefacto) on physiochemical and cupping quality of Gayo espresso. Coffee cupping quality assesses ten coffee sensory attributes based on SCAA cupping test procedures. Physiochemical characteristics refer to pH, total dissolved solids, phenolic contents, and antioxidant activity of Espresso. The research applied a completely factorial randomized design. The research stages were roasting, blending, grinding, and brewing the Espresso. The results showed that both factors blending ratio and roasting techniques, had a significant effect (P≤0.01) on cupping quality (fragrance/aroma, flavor, aftertaste body, overall and balance attributes) and the physiochemical characteristics (pH, total dissolved solids, phenolic contents, and antioxidant activity) of Gayo espresso. The Torrefacto roasting technique, which refers to adding 11% sugar at the end of the roasting process, tends to provide Espresso with better cupping quality, higher pH, total solid particles, and antioxidant activity than the conventional roasting technique. On the other hand, Espresso, which had a blending ratio of 80:20 showed better cupping quality, whereas a blending ratio of 70:30 produced the Espresso with higher total phenol content and antioxidant activity than other ratios
Tree-Based Ensemble Methods and Their Applications for Predicting Students’ Academic Performance
Get PDFStudents’ academic performance is a key aspect of online learning success. Online learning applications known as Learning Management Systems (LMS) store various online learning activities. In this research, students’ academic performances in online course X are predicted such that teachers could identify students who are at risk much sooner. The prediction uses tree-based ensemble methods such as Random Forest, XGBoost (Extreme Gradient Boosting), and LightGBM (Light Gradient Boosting Machine). Random Forest is a bagging method, whereas XGBoost and LightGBM are boosting methods. The data recorded in LMS UI, or EMAS (e-Learning Management Systems) is collected. The data consists of activity data for 232 students (219 passed, 13 failed) in course X. This data is divided into three proportions (80:20, 70:30, and 60:40) and three periods (the first, first two, and first three months of the study period). Data is pre-processed using the SMOTE method to handle imbalanced data and implemented in all categories, with and without feature selection. The prediction results are compared to determine the best time for predicting students’ academic performance and how well each model can predict the number of unsuccessful students. The implementation results show that students’ academic performance can be predicted at the end of the second month, with best prediction rates of 86.8%, 80%, and 75% for the LightGBM, Random Forest, and XGBoost models, respectively, with feature selection. Therefore, with this prediction, students who could fail still have time to improve their academic performance
Improving Accuracy of Cloud Images using DenseNet-VGG19
Get PDFWeather classification has become a significant challenge due to the unpredictable nature of climate conditions. For farmers, predicting the start of the rainy season is very important. This is because it is related to the cost factor that must be incurred, and also, the waiting time for the harvest will have an effect if the weather is not supportive. Farmers also have to prepare seeds for the start of their farming. Therefore, farmers who start nurseries early in the rainy season will miss significant planting time. Based on these problems, this study uses a convolutional neural network (CNN) for weather classification using cloud imagery. CNN is shown to classify different spectro-temporal features of sound and is thus suitable for cloud image classification. We collect cloud image data using secondary data. Our model will use a layer based on the convolution CNN architecture with a pooling layer and a solid layer as the output layer. The cloud dataset used is 1230 data divided into five classes, namely cloudy, foggy, rain, shine, and sunrise, which we use to train our model in research for the feature extraction process using DenseNet and VGG19. We use two types of classification, namely fully connected and Global Average Pooling (GAP). Our model can achieve a classification accuracy of 90.8% DenseNet-Fully Connected from our training process. From our testing process, our model can reach 95.7% using DenseNet-Fully Connected classification accuracy. Thus, the CNN model proved very accurate in classifying cloud images
Internet of Things for Underwater Shrimp Image Detection Using Blob Detector
Get PDFMeasuring biomass content is an important stage in harvesting shrimp as it will determine the harvest time. Manual detection has caused shrimp stress and eventually caused shrimp death; therefore, a new shrimp biomass determination is required. This research aims to design an IoT technique-based biomass measurement, using underwater shrimp video with fog and cloud computing processes to easily detect shrimp underwater, irrespective of the complex noise. The method consists of several steps: image processing using grayscale, thresholding, contour edge detection, labeling, and blob detection. The results revealed that the highest SSIM value in the thresholding process was 0.18, while the lowest MSE was 91.35. In addition, in the contour edge detection process, the highest PSNR value was 3.6, and the lowest MSE was 2.06. The blob detection process produces a maximum key performance of 566, 411, and 387 in the Laplacian of Gaussian (LoG), Difference of Gaussian (DoG), and Determinants of Hessian (DoH) methods, respectively. The Quality of Service (QoS) obtained throughput, loss, and delay values of 832.25, 0%, and 7.25 ms, respectively, in the data acquisition and computation processes, with the three parameters at a very good level. In conclusion, the IoT model is very suitable for underwater shrimp detection because it is a non-invasive method, contains high key performance blob detection, and has a very good QoS level and high-speed computation process
Bioremediation Performance of Marine Sponge Symbiont Bacteria against Nickel and Mercury Heavy Metal Pollutants
Get PDFHeavy metals, mercury, and nickel are toxic contaminants, forming positive ions when concentrated and dissolved, and can accumulate in a specific object, including water. The activity and performance of bacterial bioremediation against toxic heavy metals vary due to bacterial characteristics and internal contaminant factors. This research aims to analyze the activity, performance, and efficiency of bioremediation of nickel and mercury pollutants using marine sponge symbiont bacteria. The bioremediation analysis procedure, suspension of bacteria Alcaligenes faecalis strain Cu4-1 (AF), and Acinetobacter calcoaceticus strain PHCDB14 (AC) interacted with heavy metal pollutants as contaminants for 15 days. Bioremediation performance and efficiency were measured using AAS. The analysis parameters consisted of the performance, efficiency, and mechanism of bacterial bioremediation against nickel and mercury pollutants. The research results show that the bioremediation performance of AF and AC bacteria can carry out the bioremediation function against Ni+2 and Hg+2 contaminants. The bioremediation performance of AF bacteria against Ni+2 pollutant is, on average 167.64±0.9 mg/L, equivalent to 66.85% bioremediation efficiency, and against Hg+2 an average 171.55±0.7 equivalent to the efficiency of 65.47%. The performance of bioremediation of AC bacteria on Ni+2 pollutant was 168.92±0.7 or efficiency reached 66.97%, and 145.87±0.8 for Hg+2, equivalent to 58.35% efficiency. The bioremediation performance of AF ˂ AC bacteria against Ni+2 pollutants, but against Hg+2 pollutants, the bioremediation performance of AF ˃ AC bacteria. The symbiotic bacteria of marine sponges are thought to have bioremediation performance against toxic metal pollutants are bacteria isolated from sponges whose body surface is covered with mucus substances
Rice Food Security on Small Farmer Households Under Current Mechanization Level in Kampar Region, Indonesia
Get PDFRice is Indonesia's most important staple food and has become a key indicator of the country's food security. In Kampar Region, most small farmers face challenges in meeting their households’ rice food security under a relatively limited application of mechanization and small farm scale. This study examines the rice food security status of small farmer households under current levels of mechanization in Kampar Region, Indonesia. Field surveys were conducted in two districts, Bangkinang and Kuok in Kampar region in April-June 2020. A total of 72 small farmers were purposively selected for the sample, of which 36 were farmers from each district. Data were collected through interviews using semi-structured questionnaires and analyzed using descriptive-quantitative techniques. As a result, the current mechanization application was classified as intermediate level. At this level, 1.33 tons of rice were produced, and the cultivated area was 0.37 ha on average. Rice productivity averaged 3.56 tons. ha-1 and varied with various farm sizes. The per capita rice consumption was still high, approximately 114.6 kg per year, and it requires a farm size of 0.054 ha to meet annual rice consumption, or 0.27 ha for households with 5 family members. About 46% of small farmers could not meet their rice needs within one year. They could supply rice for less than 12 months and up to 21 percent of them could supply rice for up to 6 months. Therefore, the level of mechanization must be increased to improve rice productivity