A New Simple Procedure for Extracting Coastline from SAR Image Based on Low Pass Filter and Edge Detection Algorithm

This study proposes a new simple procedure for extracting coastline from Synthetic Aperture Radar (SAR) images by utilizing a low-pass filter and edge detection algorithm. The low-pass filter is used to improve the histogram of the pixel value of the SAR image. It provides better distribution of pixel value and makes it easy to separate between sea and land surfaces. This study provides the processing steps using open-source software, i.e., SNAP SAR processor and QGIS application. This procedure has been tested using dual polarization Sentinel-1 (10x10 meters resolution) and single polarization ALOS-2 (3x3 meters resolution) dataset. The results show that using Sentinel-1 with dual polarization (VH) provides a better result than single polarization (VV). In the ALOS-2 case, only single polarization (HH) is available. However, even using only HH polarization, ALOS-2 provides a good result. In terms of resolution, ALOS-2 provides a better coastline than Sentinel-1 data due to ALOS-2 has better resolution. This procedure is expected to be helpful to detect coastline changes and for coastal area management.

Propeller Speed Control System on Autonomous Quadcopter with Variations in Load Fulcrum Point

The need for unmanned vehicles is increasingly needed in certain conditions, such as distribution of disaster supply, distribution of medicines, distribution of vaccines in the affected areas in pandemic situations. The various types of goods to be distributed require a different fulcrum. This research implemented PID control for the quadcopter balance control system to achieve stability during hovering. PID control is used to achieve a certain setpoint to produce the required PWM output for the propeller to reach a speed that can fly the quadcopter tilted until it reaches a steady state. Tests were carried out on the roll and pitch motion of the quadcopter by providing a load. The results show that PID control can be implemented for the quadcopter balance control system during hovering by determining the PID constants for each roll and pitch motion with the constanta of Kp = 0.15, Kd = 0.108, and Ki = 0.05. The quadcopter takes 3 – 6 seconds to return to the 0 degree setpoint when it is loaded.

Detecting Excessive Daytime Sleepiness With CNN And Commercial Grade EEG

Epworth sleepiness scale is a self-assessment method in sleep medicine that has been proven to be a good predictor of obstructive sleep apnea. However, the over-reliance of the method making the process not socially distancing friendly enough in response to a global covid-19 pandemic. A study states that the Epworth sleepiness scale is correlated with the brainwave signal that commercial-grade EEG can capture. This study tried to train a classifier powered by CNN and deep learning that could perform as well as the Epworth with the objectiveness of brainwave signal. We test the classifier using the 20 university student using the Epworth sleepiness test beforehand. Then, we put the participant in 10 minutes EEG session, downsampling the data for normalization purposes and trying to predict the outcome of the ESS in respect of their brainwave state. The AI predict the reaching 65% of accuracy and 81% of sensitivity with just under 100.000 dataset which is excellent considering small dataset although this still have plenty room for improvement.

Modified KNN-LVQ for Stairs Down Detection Based on Digital Image

Persons with visual impairments need a tool that can detect obstacles around them. The obstacles that exist can endanger their activities. The obstacle that is quite dangerous for the visually impaired is the stairs down. The stairs down can cause accidents for blind people if they are not aware of their existence. Therefore we need a system that can identify the presence of stairs down. This study uses digital image processing technology in recognizing the stairs down. Digital images are used as input objects which will be extracted using the Gray Level Co-occurrence Matrix method and then classified using the KNN-LVQ hybrid method. The proposed algorithm is tested to determine the accuracy and computational speed obtained. Hybrid KNN-LVQ gets an accuracy of 95%. While the average computing speed obtained is 0.07248 (s).

Water and Air Quality Monitoring System based on the Internet of Things

Environmental pollution is a global issue that occurs at this time. It is caused by various human activities that produce pollutants that endanger their lives. By utilizing current technology, it is possible to design a Water and Air Quality Monitoring System based on the Internet of Things to monitor air and water quality quickly and in real-time in the surrounding environment. The users can access this system via the web and Android / IOS mobile applications that display the data obtained by the sensor in the form of real-time graphics of water and air conditions. In addition, this system consists of several sensor nodes in charge of providing field data regarding the parameters used as the basis for assessing water and air quality according to the applicable standards in Indonesia. Sensors for water using a Turbidity Sensor, DS18B20 Sensor, PH Sensor, DHT 11, and TDS (Total Dissolved Solids) Sensor. Sensors for air consist of the DHT11 sensor, the MQ-7sensor, the MQ-135 sensor, and the dust sensor GP2Y1010AU0F.

Forecasting of Sea Level Time Series using RNN and LSTM Case Study in Sunda Strait

Sea-level forecasting is essential for coastal development planning and minimizing their signi?cantconsequences in coastal operations, such as naval engineering and navigation. Conventional sealevel predictions, such as tidal harmonic analysis, do not consider the in?uence of non-tidal elementsand require long-term historical sea level data. In this paper, two deep learning approachesare applied to forecast sea level. The ?rst deep learning is Recurrent Neural Network (RNN), andthe second is Long Short Term Memory (LSTM). Sea level data was obtained from IDSL (InexpensiveDevice for Sea Level Measurement) at Sebesi, Sunda Strait, Indonesia. We trained themodel for forecasting 3, 5, 7, 10, and 14 days using three months of hourly data in 2020 from 1stMay to 1st August. We compared forecasting results with RNN and LSTM with the results of theconventional method, namely tidal harmonic analysis. The LSTM’s results showed better performancethan the RNN and the tidal harmonic analysis, with a correlation coef?cient of R2 0.97 andan RMSE value of 0.036 for the 14 days prediction. Moreover, RNN and LSTM can accommodatenon-tidal harmonic data such as sea level anomalies.

Dempster Shafer Algorithm For Expert System Early Detection of Anxiety Disorders

Anxiety is an excessive anxiety disorder that is often found in psychology. Some people generally do not realize that they may have symptoms of this anxiety disorder. If ignored and continued continuously, it can interfere with one's activities, reduce academic achievement, and disrupt psychological conditions that affect their lives. This expert system for early detection of anxiety disorders is carried out using forward chaining tracing techniques to explore the knowledge base, and the inference motor is the Dempster Shafer algorithm. Dempster Shafer calculation is done by combining symptom pieces to calculate the possibility of the anxiety disorder. This anxiety disorder detection system is built on the web. Then the test is carried out by comparing the value generated by the system with the value generated by two experts. The test results prove that the value generated by the system has a similarity of 85% to the value produced by the two experts. It can be concluded that implementing the Dempster Shafer algorithm for this expert system in the early detection of anxiety disorders is feasible.

Offline Signature Identification Using Deep Learning and Euclidean Distance

Hand signature is one of human characteristic that human have since birth, which can be used as identity recognition. A high accuracy signature recognition is needed to identify the right owner of signature. This study present signature identification using a combination method between Deep Learning and Euclidean Distance. 3 different signature datasets are used in this study which consist of SigComp2009, SigComp2011, and private dataset. Signature images preprocessed using binary image conversion, Region of Interest, and thinning. Several testing scenarios is applied to measure proposed method robustness, such as usage of various Pretrained Deep Learning, dataset augmentation, and dataset split ratio modifier. The best accuracy achieved is 99.44% with high precision rate.

Classification Of Rice Plant Diseases Using the Convolutional Neural Network Method

Indonesia is one of the countries with the population majority of farming. The agricultural sector in Indonesia is supported by fertile land and a tropical climate. Rice is one of the agricultural sectors in Indonesia. Rice production in Indonesia has decreased every year. Thus, rice production factors are very significant. Rice disease is one of the factors causing the decline in rice production in Indonesia. Technological developments have made it easier to recognize the types of rice plant diseases. Machine learning is one of the technologies used to identify types of rice diseases. The classification system of rice plant disease used the Convolutional Neural Network method. Convolutional Neural Network (CNN) is a machine learning method used in object recognition. This method applies to the VGG19 architecture, which has features to improve results. The image used as training and test data consists of 105 images, divided into training and test images. Parameter testing using epoch variations and data augmentation. The research results obtained a test accuracy of 95.24%.

KEBI 1.0: Indonesian Spelling Error Detection System for Scientific Papers using Dictionary Lookup and Peter Norvig Spelling Corrector

Many Indonesian spelling errors occur in research papers published to the public, closely related to academics in all institutions such as research institutions, government, schools, and universities. The spelling errors usually writing punctuation, writing letters, writing words, writing words originating from foreign or regional languages (uptake words), using affixed words, and writing ineffective sentences. The mistakes made by the academics then become a cycle in the academic environment. They usually provide guidance for writing an undergraduate thesis, thesis, dissertations to students, or the other forms of documents and scientific papers. Therefore, the research proposed the application to facilitate all authors of scientific papers in producing quality scientific works based on the General Guidelines for Indonesian Spelling published by the Agency for Development and Language Development. The application is named KEBI 1.0 Checker (Indonesian Spelling Error 1.0 Checker), a web-based application with a built-in algorithm to detect and correct Indonesian Spelling in scientific papers. The experiment result shows that the application has given the best accuracy performance to correct the non-standard words, and typographical errors reached 100% and 55,52%, respectively. The application also has been detected 209 meaningless words. The application processing time is relatively low, the average time needed to correct non-standard words is 0.016 seconds, and typo words are 14.58 seconds. KEBI 1.0 Checker is helpful for the end-user in academics but needs to improve the vocabulary of the large corpus in various fields of science for correcting typo words.