Search

This research initiative aims to reduce pneumonia-related mortality rates, particularly among children in remote areas. The proposed solution involves creating an AI-based automatic screening system that analyzes X-ray images of patients and stores image data across hospitals in a distributed manner. The main goal is achieved through a collaborative approach, utilizing Federated Learning to establish a platform for hospital cooperation. Each participating hospital contributes to diagnostic improvement by developing local models from their datasets. These local models are then sent to a central server, where they are combined and refined to form a comprehensive global model. This process ensures unbiased detection by considering data from various sources. Patient data security is prioritized, as the central server only stores local models and not sensitive patient information. Additionally, the project introduces an innovative system for managing medical image data. This system not only archives, anonymizes, and secures image data but also curates a dataset necessary for training Computer Assisted Diagnosis systems. This work aims to push the boundaries of machine learning, particularly in healthcare, with a strong focus on patient privacy and anonymity. [ABSTRACT FROM AUTHOR]

The Covid-19 pandemic and Russian invasion of Ukraine made food and energy prices in the world soar. This price spike has triggered inflation in various countries, such as Indonesia. Currently, the most developed forecasting method is the time series. The development of a multivariate time series, apart from looking at the time element, also involves an element of location. One model that involves time and location is the Generalized Space Time Autoregressive (GSTAR) model. The GSTAR model is a development of the Space Time Autoregressive (STAR) model which assumes that the location element is heterogeneous. The purpose of this study was to obtain the GSTAR model using Seemingly Unrelated Regression (SUR) on inflation data in five cities on the island of Sumatra. The methods used in this study are, 1) perform descriptive analysis, 2) perform stationarity test, 3) identify the GSTAR model, 4) calculate the location weight matrix, and 5) calculate parameter estimates for the GSTAR model using the SUR method. In this study, it is found that the inflation model for five cities on the island of Sumatra at time t is correlated with inflation data at the previous time and is influenced by inflation data from other cities. [ABSTRACT FROM AUTHOR]

The main purpose of this article is to explore the evidence that the Bayesian Vector Autoregressive Model (BVAR) is a good forecasting model in predicting the value of the JCI index, the USD-IDR exchange rate, and the EUR-IDR exchange rate during the COVID-19 pandemic which can be seen from the forecasting accuracy value. We can see the accuracy of forecasting from the value of Mean Error (ME) to see the unfamiliarity of forecasting, Root Mean Square Error (RMSE) to see the diversity of forecasting. The BVAR model uses the Bayesian method in estimating the parameters of the vector autoregressive (VAR) model. This article uses Minnesota priors in assessing the BVAR model. The variables used are Y1 for the JCI, Y2 for the USD-IDR exchange rate, and Y3 for the EUR-IDR exchange rate. The methodology carried out, 1) Presenting descriptive statistical data in the form of boxplots, 2) seeing the stationarity of the data, looking at the ACF, PACF and ADF diagrams, if there are variables that are not stationary then differencing will be carried out, 3) Identifying the BVAR model, 4) Seeing the accuracy of forecasting BVAR against the JCI index, USD-IDR exchange rate and EUR-IDR exchange rate with ME, and RMSE indicators. The BVAR model is proven to be a good forecasting model (unbiased and small variance) in predicting the value of the JCI index, USD-IDR exchange rate, and EUR-IDR exchange rate with an ME value of 7.79007 and RMSE of 52.70694. [ABSTRACT FROM AUTHOR]

Gold tailings processing using traditional methods with amalgamation can have a negative environmental impact, with potential heavy metal leaching during the rainy season. Solidification is a method that can reduce permeability and increase tailings' physical strength through the addition of adhesives such as sand and cement. This study aims to examine the effectiveness of sand and tailings' composition variation on compressive strength in paving blocks. The study used compressive strength testing to evaluate the physical characteristics of the blocks. Results showed that the addition of sand and tailings increased compressive strength, with the optimal mix ratio being 1:1.5 sand to tailings. These findings suggest that using solidification through adding sand and cement can mitigate environmental harm caused by untreated tailings and provide a useful application for waste material in the construction industry. [ABSTRACT FROM AUTHOR]

The initial process of developing a Javanese script transliteration system to other scripts using a character recognition approach requires training data in the form of script images of all possible forms. The source of the dataset are script images from a book written in Javanese and then processed using image processing approach. The captured images were then grouped into their respective classes. The study starts with pre-processing the document images that includes the sub-processes of binarization, inverse, filtering, and followed by script segmentation using the projection profile method. Each script image is then processed in the feature extraction steps using the Intensity of Character or IoC algorithm. The feature data of each script image is then grouped using the K-Means clustering algorithm. The data was taken from the scan results of Hamong Tani's book on pages 2 and 59. After pre-processed and segmented images, 597 images of Javanese script were obtained. Using the IoC 3x3 feature, and the number of groups determined by 65 classes, the silhouette index value of the grouping results was found to be 0.5060. After calculating the ground truth value, it was found that the accuracy of the results was 86%. It can be concluded that the steps taken in this research can be used as a model in the process of providing a Javanese script images dataset. [ABSTRACT FROM AUTHOR]

Data on the poverty rate in Indonesia is very important because it can be used as a parameter of the prosperity of the Indonesian people and can also be an evaluation for the government. BPS is in charge of presenting real data through survey and census results and the data presented by the Central Statistics Agency is often delayed. To overcome the delay, predictions are made using the simple moving average method to extract and identify potential and useful knowledge information stored in large databases. [ABSTRACT FROM AUTHOR]

Current learning process for digital system course in Computer Systems Engineering, Prasetiya Mulya University utilized basic digital IC as tools to enable student experimenting with digital circuit. However, in recent years, the decreasing price of FPGA makes it as a good candidate tools for teaching digital system. FPGA has advantages over digital ICs due to its capability to be programmed and simulate more complex systems. In this work, the possibility of using FPGA to enhance the understanding of digital system material was analyzed. From the experiment, results obtained show positive contribution on raising the students' interests and understanding of digital and embedded systems in general. [ABSTRACT FROM AUTHOR]

Synthesis and characterization of Fe-N-TiO2 photocatalyst material by sol gel method using polyacrylamide and Polyethylene Glycol templates have been carried out. The purpose of this study was to determine the effect of single dopant Fe, single dopant N and double dopant Fe-N on the characteristics of TiO2 material with titanium butoxide as a precursor. All materials, namely TiO2, Fe-TiO2, N-TiO2 and Fe-N-TiO2 were synthesized by the sol-gel method using titanium butoxide as TiO2 precursor. Precursor Fe(NO3)3.9H2O was used as Fe dopant and solid CO(NH2)2 as N dopant. The calcination process was carried out at 450oC. The results of X-Ray Diffraction (XRD) characterization show that TiO2, Fe-TiO2, N-TiO2 and Fe-N-TiO2 materials have an anatase phase and an optimum particle size at 9.4187 nm. The results of the Diffuse Reflectance UV-Visible (DR-UV) characterization showed a decrease in the band gap (Eg) from 3.1 eV to 2.29 eV. The results of the Fourier Transform Infrared (FTIR) characterization show that the Ti-O, C-O functional group appears at the wave number 620.51 cm-1; 1111.9 cm−1 and 1628.8 cm−1 while the C-H functional group appears at 2371.3 cm−1. [ABSTRACT FROM AUTHOR]

Somopuro Village has approximately ten household scale tofu industries. However, the wastewater produced from its process has been affecting water quality due to untreated disposal, which flows into surface water, known as Panggang River, despite its functions for irrigation. As a result, the surface water quality has dropped significantly, such as change in the natural color of the river and foul smell emerging from it, as well as concerns about the groundwater quality in the surrounding areas. This research set out to determine the groundwater vulnerability in Somopuro Village using a DRASTIC method and validated the results the between vulnerable area and groundwater quality using pollution index (PI). The result shows, the distribution of groundwater vulnerability is divided into two classes namely, high vulnerability covering 1,48 km2 (approximately 69,8113% of the study area) and very high vulnerability covering 0,64 km2 (30,1887%). In addition, the laboratory test carried out and calculated using PI shows 4 out of 6 samples classified as not polluted (PI range from 0,74 – 0,87) and other 2 out of 6 samples classified as low polluted (PI range from 1,00 – 1,57). Hence, the validation between groundwater vulnerability and its quality concluded that the incompatibility rate is 66,67%, and the compatibility rate is 33,33%. This shows that the higher groundwater vulnerability does not always indicate the actual quality of groundwater conditions. [ABSTRACT FROM AUTHOR]

The composition of waste in landfills needs to be studied because it's related to waste management. The Tanggan Landfill, which is located in Sragen Regency, has been operating for 29 years, so the amount of waste is very high. The daily amount of waste that goes to Tanggan Landfill is up to 85 tons/day. The source of waste is dominated by residential areas. The purpose of this research is to find out the physical characteristic and composition of the waste in Tanggan Landfill. The method is used for waste sampling is cluster sampling. There's three sampling locations in The Tanggan Landfill based on the difference between the newly disposed of waste and the waste far from the dumping location. The characteristic of the waste tested is waste moisture by laboratory test using three samples. The result of the research is the waste composition in Tanggan Landfill is dominated by non-organic waste (62%). The average waste density sample is 32,97 kg/m3. The result of the waste moisture test is 60,22%, it has met the optimum criteria for the recommended water content. [ABSTRACT FROM AUTHOR]