Implementasi Deep Learning Menggunakan Metode CNN dan LSTM untuk Menentukan Berita Palsu dalam Bahasa Indonesia

This research aims to implement deep learning techniques to determine fact and fake news in Indonesian language. The methods used are Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The stages of the research consisted of collecting data, labeling data, preprocessing data, word embedding, splitting data, forming CNN and LSTM models, evaluating, testing new input data and comparing evaluations of the established CNN and LSTM models. The Data are collected from a fact and fake news provider site that is valid, namely TurnbackHoax.id. There are 1786 news used in this study, with 802 fact and 984 fake news. The results indicate that the CNN and LSTM methods were successfully applied to determine fact and fake news in Indonesian language properly. CNN has an accuracy test, precision and recall value of 0.88, while the LSTM model has an accuracy test and precision value of 0.84 and a recall of 0.83. In testing the new data input, all of the predictions obtained by CNN are correct, while the prediction results obtained by LSTM have 1 wrong prediction. Based on the evaluation results and the results of testing the new data input, the model produced by the CNN method is better than the model produced by the LSTM method.

ACCURACY TEST OF SUPERMARKET'S MUSHOLA QIBLA DIRECTION IN CIREBON CITY

This study aims to answer the questions that become the formulation of the problem “How is the method of measuring the Qibla direction of the supermarket prayer room in Cirebon City” and “How to analyze the accuracy of the supermarket prayer room Qibla direction in Cirebon City.” This study uses qualitative research; the data collected uses observation, interviews, documentation, and literature study. They were then analyzed by the descriptive analysis method in narration. The results of this study: that the Qibla direction of the supermarket in Cirebon City has all measured the Qibla direction. The method of measuring the Qibla direction was carried out by the musala supermarket, where the author’s research uses the Qibla compass and the Qibla direction application on the smartphone. Of course, using the Qibla direction application on a smartphone is an inaccurate method. This method’s method is partly an error in determining the Qibla direction. Due to his ignorance of astronomy in measuring the Qibla direction and ignorance of the magnitude of the Qibla direction angle in the Cirebon City area, resulting in the Qibla direction of the supermarket in the Cirebon City area experiencing a wrong Qibla direction.

Changes of seagrass area in Beralas Pasir and Beralas Bakau Island observed from Sentinel-2 Satellite and verified by Unmanned Surface Vehicle (USV)

Today, the area of seagrass ecosystems in Indonesia is estimated to have shrunk significantly. Bintan Island has quite a large seagrass ecosystems area. Along with the development of satellite technology, monitoring of conditions and changes to a coastal ecosystem can be carried out effectively through remote sensing technology. One satellite image that is relatively new and has good spatial quality is Sentinel-2 with a spatial resolution value of 10×10 m2 / pixel. Field data retrieval is facilitated by the use of Unmanned Surface Vehicle (USV). This research went through several stages such as image pre-processing, water column correction, masking, unsupervised classification, and detection of changes of seagrass area. The data obtained from the USV becomes the data for the accuracy-test in the supervised classification. Seagrass area was obtained in Beralas Pasir and Beralas Bakau Island is 84.27 ha (2016), 81.3 ha (2019) and 77.4 ha (2021). Detection of seagrass to non-seagrass area changes resulting 31.35 ha (2016-2019) and 30.91 ha (2019-2021). On the other hand non-seagrass to seagrass area is 24.84 ha (2016-2019) and 27.98 ha (2019-2021). The accuracy test of 2019 image classification and Unmanned Surface Vehicle data resulting overall accuracy at 62.20%.

Understanding the Link Between Discrete Negative Emotions and Empathic Accuracy

Extant theories have suggested that negative emotions generally harm cognitive processes. However, adopting a discrete emotion perspective, in this study, we predicted that only anger and fear but not sadness should be negatively associated with empathic accuracy, a process that has been shown to be cognitively highly demanding. Over 100 participants (Mage = 66.66 years, SDage = 1.00) reported their emotional reactions in response to a negative film in the laboratory, documented their everyday momentary emotions six times a day over seven consecutive days, and completed a film-based empathic accuracy test. Initial findings suggest that only fear but not anger or sadness was related to empathic accuracy. More specifically, high levels of fear both in the laboratory and in everyday life predicted low empathic accuracy. This pattern of findings will be discussed in the context of discrete emotions theories.

Influence of Control Points Configuration on the Mobile Laser Scanning Accuracy

Mobile mapping systems (MMS) are becoming widely used in standard geodetic tasks more commonly in the last years. The paper is focused on the influence of control points (CPs) number and configuration on mobile laser scanning accuracy. The mobile laser scanning (MLS) data was acquired by MMS RIEGL VMX-450. The resulting point cloud was compared with two different reference data sets. The first reference data set consisted of a high-accuracy test point field (TPF) measured by a Trimble R8s GNSS system and a Trimble S8 HP total station. The second reference data set was a point cloud from terrestrial laser scanning (TLS) using two Faro Focus3D X 130 laser scanners. The coordinates of both reference data sets were determined with significantly higher accuracy than the coordinates of the tested MLS point cloud. The accuracy testing is based on coordinate differences between the reference data set and the tested MLS point cloud. There is a minimum number of 6–7 CPs in our scanned area (based on MLS trajectory length) to achieve the declared relative accuracy of trajectory positioning according to the RIEGL datasheet. We tested two types of ground control point (GCP) configurations for 7 GCPs, using TPF reference data. The first type is a trajectory-based CPs configuration, and the second is a geometry-based CPs configuration. The accuracy differences of the MLS point clouds with trajectory-based CPs configuration and geometry-based CPs configuration are not statistically significant. From a practical perspective, a geometry-based CPs configuration is more advantageous in the nonlinear type of urban area such as our one. The following analyzes are performed on geometry-based CPs configuration variants. We tested the influence of changing the location of two CPs from ground to roof. The effect of the vertical configuration of the CPs on the accuracy of the tested MLS point cloud has not been demonstrated. The effect of the number of control points on the accuracy of the MLS point cloud was also tested. In the overall statistics using TPF, the accuracy increases significantly with increasing the number of GCPs up to 6. This number corresponds to a requirement of the manufacturer. Although further increasing the number of CPs does not significantly increase the global accuracy, local accuracy improves with increasing the number of CPs up to 10 (average spacing 50 m) according to the comparison with the TLS reference point cloud. The accuracy test of the MLS point cloud was divided into the horizontal accuracy test on the façade data subset and the vertical accuracy test on the road data subset using the TLS reference point cloud. The results of this paper can help improve the efficiency and accuracy of the mobile mapping process in geodetic praxis.

Simple Method of 9,10-Anthraquinone Assay in Eleutherine americana (Aubl.) Merr. ex K. Heyne using High-Performance Liquid Chromatography

Eleutherine americana (E. americana) is a medicinal plant commonly found on the island of Borneo, Indonesia. This plant is known to have several biological activities. However, anthraquinone residues are generally present as contaminants. This study was aimed to develop a method of determining the levels of 9,10-anthraquinone in plant extracts and fractions using High Performance Liquid Chromatography (HPLC). The research aims to optimize the mobile phase, the system suitability test, and the system validation. The optimal mobile phase was acetonitrile:distilled water 1:1 v/v with a flow rate of 1.25 mL/min. The validation result shows that the linearity was obtained with a correlation coefficient (r) of 0.9995 and an r2 coefficient of 0.9991. The estimated limits for detection and quantification values were 0.178 and 0.594 µg/mL, respectively. In the intraday and inter-day accuracy test, the coefficient of variance for reference was 0.627 and 0.774, while the results for the sample were 2.966 and 2.658. The percentage recovery rate for reference was between 98.976–101.452%, and for the sample, the result was 89.191–94.667%. The average 9,10-anthraquinone content in the acetate fraction of E. americana plant was 9.799 µg/g ± 5.243.

Development of Multi-Item Air Quality Monitoring System Based on Real-Time Data

Many air pollutants are inhaled by human breathing, increasing the prevalence of respiratory disease and even mortality. With the recent COVID-19 issue, the number of air pollutants affecting humans is demands further investigation. However, there are not many adequate air measuring devices that can cover a variety of air pollutants. In this study, the developed air measurement system is able to measure sixteen air pollutants (PM10, PM2.5, PM4.0, PM1.0, CO2, CH4, temperature, humidity, VOCs, O2, H2S, NH3, SO2, CO, O3, NO2) in real time. The developed ‘multi-item air quality monitoring system’ can measure sixteen air pollutants in real time and transmit them to the server and the smartphone application at the same time. It was developed to reduce air pollutant damage to humans by emergency alerts using the smartphone application. The development system is composed of hardware development (measurement device) and software development (smartphone application, server). To verify the reliability of the developed equipment, a comparative test, temperature–humidity accuracy test, and operating temperature test were conducted. In the comparative test, difference ratios of ±5% for PM10, ±6% for PM2.5, ±4% for O3, ±5% for NO2, ±7% for CO, and ±7% for SO2 were found compared to the professional measuring devices. The temperature and humidity accuracy test result showed high reliability at ±1% and humidity ± 2%. The result of the operating temperature test showed that there was no problem in normal operation, However, further tests including the long-term comparative test and the closed chamber test will be carried out for all sensors. Additional work including a long-term test for more clear reliability of the device and closed chamber accuracy test for all 16-item sensors, data acquisition rate, and data transmit rate are in progress for commercializing the device.

ESTIMATION OF ABOVEGROUND CARBON STOCK USING SAR SENTINEL-1 IMAGERY IN SAMARINDA CITY

Estimation of aboveground carbon stock on stands vegetation, especially in green open space, has become an urgent issue in the effort to calculate, monitor, manage, and evaluate carbon stocks, especially in a massive urban area such as Samarinda City, Kalimantan Timur Province, Indonesia. The use of Sentinel-1 imagery was maximised to accommodate the weaknesses in its optical imagery, and combined with its ability to produce cloud-free imagery and minimal atmospheric influence. The study aims to test the accuracy of the estimated model of above-ground carbon stocks, to ascertain the total carbon stock, and to map the spatial distribution of carbon stocks on stands vegetation in Samarinda City. The methods used included empirical modelling of carbon stocks and statistical analysis comparing backscatter values and actual carbon stocks in the field using VV and VH polarisation. Model accuracy tests were performed using the standard error of estimate in independent accuracy test samples. The results show that Samarinda Utara subdistrict had the highest carbon stock of 3,765,255.9 tons in the VH exponential model. Total carbon stocks in the exponential VH models were 6,489,478.1 tons, with the highest maximum accuracy of 87.6 %, and an estimated error of 0.57 tons/pixel.

Teaching the Technical Essentials of Direct Ophthalmoscopy Using a Portable Fundus Camera

Aim: A portable fundus camera could allow the third person to observe the technique essentials of direct ophthalmoscopy from a real time screen. This study was designed to compare the proficiency of teaching direct ophthalmoscopy using a portable camera with conventional way in medical students. Methods: Medical students of fourth year were invited to participate the study. At baseline, the participants were taught fundoscopy with a conventional direct ophthalmoscope shortly. Then they were randomized to be taught the skill of fundoscopy either with a portable fundus camera or with a conventional direct ophthalmoscope as control for two days. Accuracy tests to match a subject’s fundus with one of the four photographs after examining an undilated eye using a direct ophthalmoscope were performed at baseline and end point. Accuracy test scores and self-reported confidence were compared between the two groups. Results: A total of 160 students participated the study, with 79 assigned to the intervention group, and 81 to the control group. All the students finished the study. At baseline, there was no difference in accuracy test score between the two groups. After two-day training session, the accuracy score improved in 26/79 (32.9%) students of intervention group versus 15/81 (18.5%) of the control group (p=0.037). At end point, a total of 39/79 (49.4%) students in the intervention groups versus 25/81 (30.9%) in the control group identified the correct fundus photograph (p=0.017). The confidence levels were significantly higher in the intervention group than the control group. Conclusions: Teaching direct ophthalmoscope using a portable fundus camera is associated with improved accuracy score and elevated confidence level in medical students when compared with conventional method.