Engineering and Applied Technology

Digitization and Improvement of Lung X-ray Scan Display with WWW Filter and Histogram Equalization Method

2022-10-08T14:09:33+00:00

Detection of lung disease is generally done manually by trained professionals. The condition of pulmonary disorders has worsened since the outbreak of the 2019 coronavirus disease (COVID-19), which is a significant threat to people’s lives and health due to its high infectivity and rapid spread. Lung X-ray images are one way to detect various lung diseases and COVID-19 disorders. However, the image’s appearance is usually affected by pixels with uneven grayscale and isolated noise, making it weak in detecting the symptoms encountered. To solve this problem, a WWW filter method for preprocessing is proposed, as well as incorporating histogram equalization. In particular, histogram equalization is applied to increase the image’s contrast. The WWW filter combines wavelet, Wiener, and weighing methods to get a clear view of the lungs. The histogram process will provide a significant contrast value, making it easier for experts to further lung diagnosis. From the trial conducted, the PSNR value of 14.0931 to 19.9037 and an increase in EME from 23.1308 to 75.2877. The experimental results prove that the proposed algorithm can effectively detect pulmonary disease symptoms and is expected to be useful for diagnosing COVID-19.

Load Forecasting on 150 kV Grid Substation Based on Spatiotemporal Deep Neural Network

2022-10-10T06:48:35+00:00

A smart grid concept with a prediction system provides accurate information as an early warning in the process of generation and distribution of electrical energy. The complexity of the power distribution system that involves complex parameter settings is a major challenge that is difficult to predict. Although the data recording in the smart grid system is done centrally, however, the prediction system faces a lack of accuracy due to incomplete records and low data quantity. In this paper, a spatiotemporal deep neural network is developed based on convolutional long short-term memory (Conv-LSTM) to extract long-term short-term patterns in an electrical load dataset. This data set is obtained from daily measurements for six months at Cawang Baru Substation, Indonesia. The proposed model adopts the basic concept of multi-layer perceptron to record temporal patterns in several stages, thereby producing more accurate results. This model uses supervised learning techniques to propagate sequential data into the target which is the next event of the data series. Furthermore, the proposed architecture supports multivariate feature extraction so as to capture important correlations between multi-dimensional features. This study also uses the basic Multivariate LSTM (MV-LSTM) model and naive Machine Learning models including Logistic Regression (LR), Random Forest (RF), and Support Vector Regression (SVR) as benchmarking methods for the proposed model. In the testing process, Conv-LSTM achieves higher accuracy than MV-LSTM, SVR, LR, and RF with scores of 0.3688, 0.3645, 0.1332, 0.1438, and 0.1234, respectively, evaluated using R-squared. Finally, experimental results support the view that combining multivariate data and a spatiotemporal prediction model is superior for time series prediction tasks rather than univariate data.

The Use of Crowdsourcing Technology and TOPSIS Method in The Development of Tourism Decision Support System Based On Wisdom of The Crowd

2022-10-16T17:33:03+00:00

Decision support systems have often been used in making tourism destination selection decisions. The multi-criteria decision-making methods used in the decision support system still use the weighting criteria of each alternative using the assessment of one or several experts. This makes the recommendations generated by the DSS are not updated automatically over time. The authors want to change the paradigm from DSS based on experts assesment to DSS based on crowd assesment. This reserach aims to developmt a DSS application for selecting tourist spot based on the wisdom of the crowd and personal tastes of each user. By using crowdsourcing technology and the TOPSIS method, a DSS application can be built for the selection of tourist attractions based on the wisdom of the crowd and users' personal preferences.

A Tabu Search Algorithm for Optimization of Blood Distribution Routes

2022-10-15T16:15:21+00:00

PMI Blood Transfusion Unit is an agency that provides or a health service agency that organizes blood donation and blood supply. The observations and interviews showed that some existing cases were not carried out immediately and accurately, and there was no distance to align the duration with blood cells. The formation of blood distribution routes only stems from the highest number of requests and the delay in the distribution in several hospitals. Therefore, it is necessary to determine vehicle routes to meet demand due to the limited number of vehicles. The distribution time limit is another obstacle in the distribution process due to delays in delivering blood products from UTD to hospitals or hospital blood banks. In this study, the CCVRPTW solution was determined using a metaheuristic algorithm, namely the Tabu Search algorithm, to minimize blood distribution routes and distances at UTD PMI Pekanbaru. The solution for blood distribution is solved using a programming language through MATLAB software based on the Tabu Search algorithm. Based on the study results, the route 0-1-14-8-18-6-2-17-11-10-4-3-15-9-5-7-16-19-12-13-0 with a distance of 55, 9 KM in 67.1 Minutes. The initial distribution route is 0-1-2-6-5-4-3-7-17-8-13-11-12-14-16-15-18-9-10-19-0 with a distance of 130.7 KM in 156.8 minutes. UTD PMI uses one coolbox with 100 bags of blood capacity, but there is a delay because it only uses one vehicle. The optimized route is divided into two routes: car 1 has a route of 0-1-14-8-18-6-0 with a total distance of 9.2 KM, and car 2 has a route of 0-2-17-11-10-4 -3-15-9-5-7-16-19-12-13-0 with a total distance of 50.6 KM.

The Design Water Flow Measurement with Ultra Sonic Sensor

2022-10-16T10:07:13+00:00

Human life in the world cannot be separated from the need for water. This water utilization can be maximized by implementing water use management. To carry out water usage management, precise measuring instruments are needed and continuous and up-to-date observations are made. So the measurement of water discharge needs to be done carefully and automatically. In this system the flow meter readings use ultrasonic. The reading results are obtained on the microcontroller. The output of this microcontroller is displayed through a display that can be read directly. Besides that, the reading results are also sent via modbus to an android phone or other receiving system. To determine the precision of the measurement, it is necessary to compare it with a manual flow meter. The process of comparing the measurement results with ultrasonic with manual measurements is carried out by installing a series between ultrasonic and manual meters. After that, the remote delivery process is carried out using modbus. The measurement results of the comparison of ultrasonic and manual meters show an error value of 6.45%. This tool can be used as a means of controlling water consumption and the results can be transmitted over long distances.

The Use of Solar Power in Liquid Spraying Robots

2022-10-11T12:40:18+00:00

Solar power plants are renewable energy needed as a source of energy for electronic equipment, Robots are needed to replace human work. This study discusses robots in charge of spraying liquids and batteries charged by solar panels as a robot energy source. The analysis is carried out by measuring voltage, current, and the power generated by the solar panel, battery, and voltage regulator LM317. The results of this study used a 20 WP solar panel. 12 lithium-ion batteries are used in combination, 4 lithium-ion batteries are connected in series and 3 in parallel so that the desired capacity of 12V/8AH is obtained, and the battery is filled with a solar charge controller circuit regulated by the Arduino ATMega8. The LM317 battery voltage regulator produces direct current as the robot's main energy source. According to the test results, the robot requires 55.1 watts of power and 55.1 watt-hours of energy to function at one o'clock. The LM317 voltage regulator output voltage of 14.44 volts is sent to the battery.

Mobile Forensics on social media Using Digital Forensics Research Workshop Methods

2022-10-06T22:20:18+00:00

The rapidly growing digital technology is also followed by many loopholes in cybercrime if it is not balanced with the user's knowledge and knowledge of digital data. Instagram and WhatsApp are among the most popular apps in the social media category. Cybercrime often utilizes social media apps as a place of practice. Cyber allegations that often occur on social media are online prostitution, fraud, online gambling, hate speech, fake news, and the sale of illegal drugs. Law enforcement officials will secure smartphone used for cybercrime as physical evidence. Digital evidence on smartphones will be obtained through a process called digital forensics. Digital Forensics Research Workshop (DFRWS) is one of the methods applied to investigate smartphones. The Digital Forensics Research Workshop has six stages: identification, preservation, collection, examination, analysis and presentation. The final result of this study is the result of digital data analysis obtained on smartphone.

Production And Analysis Of Soap Using Variations Of Palm Oil, Virgin Coconut Oil, And Ylang Flower Extract

2023-07-03T15:19:14+00:00

Soap is a mixture of oil or fat with alkali or base through saponification, namely the hydrolysis of fat into fatty acids and glycerol under alkaline conditions. This solid bath soap from ylang flower extract is made in 8 formulas. The temperature used in the soap-making process for each formula is the same, namely 90 ℃. The stages of this research included the steps of providing raw materials (palm oil, virgin coconut oil, olive oil, castor oil, cocamide DEA, glycerin, ylang extract, and distilled water) with various oils, namely palm oil and virgin coconut oil, variations in the mass of NaOH 25 gr and 35 gr and the addition of ylang flower extract. The added ylang flower extract is an active ingredient, antibacterial, and deodorizer. This research contributes to analyzing the soap produced from palm oil and virgin coconut oil. In the water content test, the highest water content was 1.0737% with a variation of virgin coconut oil with a mass of 35 grams NaOH with the addition of extract. In the pH test, the highest pH that complied with SNI 3532-2016, namely 11, was produced in variations of palm oil with a mass of 25 grams NaOH without extract. In the free fatty acid test, free fatty acids were the highest and fulfilled according to SNI 3532-2016, which was 1.9199% produced in the virgin coconut oil variation with a NaOH mass of 25 grams with the added extract. In the stability test of solid soap foam, it was obtained that foam stability complied with SNI 3235-2016, a variation of virgin coconut oil with a mass of 25 gr NaOH with an extract of 61.4285%.