2023 | Journal article | Conceptualization, Data curation, Formal analysis, Methodology, Software, Supervision, Visualization, Writing - original draft
Contributors: Otanasap, Nuth; Bangkomkun, Pornpimol; Tanantpapat, Tanainan; Nuth Otanasap
https://ph01.tci-thaijo.org/index.php/saujournalst/article/view/251805
Otanasap, Nuth (Author)
Bangkomkun, Pornpimol (Author)
Tanantpapat, Tanainan (Author)
Nuth Otanasap (Conceptualization, Data curation, Formal analysis, Methodology, Software, Supervision, Visualization, Writing - original draft, 0000-0002-8713-3951)
The problem of falling among the elderly has significantly increased continuously. Researchers are trying to find a suitable way to monitor and alert before a fall to protect the body using an airbag, for example, to prevent the consequences of falls. In this paper, pre-fall surveillance and detection using three Kinnects installed at different angles enable detection without body tracking devices, which causes trouble. In addition, Kinnect detection uses only the head position, the center of gravity, and the position of the feet to calculate the base support area, so there are no privacy violations. The model used to predict the fall event was a logistic regression analysis that used predictive variables of head displacement versus dynamic threshold and body center of gravity versus base support area. From the pre-impact fall predictor experimental results, the accuracy was 98.17%, the sensitivity was 87.97%, and the specificity was 98.98%. Therefore, it can be concluded that the developed system can detect pre-impact fall events using the logistic regression model and can function at the specified time according to the objective.
The 1st International Conference on Social Sciences, Management and Technology (ICSSMT2023)
2023-12-21 | Conference paper | Supervision
Contributors: Nuth Otanasap
Show less detail
Nuth Otanasap (Supervision, 0000-0002-8713-3951)
This study investigated the use of data mining techniques to predict theacademic performance of students who have integrated the precepts of the SevenfoldPath into their lives, including studying, working, and daily living. The study used asample of 313 undergraduate and postgraduate students from Southeast Asia University .Data was collected using an online questionnaire and analyzed using Weka software.The results showed that the decision tree algorithm achieved the highest predictionaccuracy, followed by the random forest and Naïve Bayes algorithms. The studysuggests that the precepts of the Sevenfold Path (Pubbanimitta of Magga 7) can be usedto develop predictive models for student academic performance.
The 46th Electrical Engineering Conference (EECON-46)
2023-11 | Conference paper | Supervision
Contributors: Nuth Otanasap
Nuth Otanasap (Supervision, 0000-0002-8713-3951)
Flooding and drought are some of the natural disasters in Thailand. It is a challenge to manage water resources to control the water level. However, many dams have been built to sufficiently hold Thailand's water resource reservation in the dry season. Oversupply water retention lead to flooding in the rainy season. Accurate forecasting of water level is, therefore, one of the important factors to make a decision-making process in controlling water level. This research aims to study machine learning techniques for water level prediction in the Pasak River basin. Extreme Gradient Boosting, a useful machine learning technique, has been implemented. Water level and precipitation of stations PAS001, PAS002, PAS003, and PAS004 are variables, and water level in PAS004 is the target prediction. The study found that ANN and XGBoost algorithm are accurate in predicting water levels. The evaluation means absolute error (MAE) by ANN is 2.42 cm. and XGBoost is 3.14 cm. The ANN algorithm uses computer's memory much more and takes time for learning process longer than XGBoost.
The 46 th Electrical Engineering Conference (EECON-46)
2023-11 | Conference paper | Conceptualization, Data curation, Formal analysis, Methodology, Software, Writing - original draft
Contributors: Nuth Otanasap
Nuth Otanasap (Conceptualization, Data curation, Formal analysis, Methodology, Software, Writing - original draft, 0000-0002-8713-3951)
Due to the COVID-19 epidemic resulting in manypatients, to assist patients and medical personnel whohave large workloads, the researchers developed a deviceto measure the patient’s heart rate and blood oxygen withan automatic IoT device. The device permits patients andhealthcare professionals to monitor their heart rate andblood oxygen levels in real time through the device’sscreen and mobile application. In addition, the device canalert when oxygen and heart rate reach a critical point. Thedeveloped device comprises a Max30102 sensor, aWemos D1 Mini microcontroller board, and a 0.96-inchOLED display. The program is developed with ArduinoIDE using C language. ThingSpeak was used as anintermediary that receives values from the microcontrollerboard and sends the deals to display to mobile apps. Thedeveloper experimented with five male and five femalevolunteers, a total of 10 with 100 trials.The experimental results in measuring heart rateusing the developed device compared to standardmeasuring devices found that the average accuracy was91.43 percent. The percentage of oxygen in the bloodmeasured by the developed device compared to thestandard measuring instruments. It was found that theaverage accuracy was 98.96 percent. For the compressedair system to increase blood oxygen rate so that the systemcould work correctly, the average total accuracy was 92.50percent. It meets the objectives of this development.
The 46th Electrical Engineering Conference (EECON-46)
2023-11 | Conference paper | Writing - review & editing, Conceptualization, Supervision
Contributors: Nuth Otanasap
Nuth Otanasap (Writing - review & editing, Conceptualization, Supervision, 0000-0002-8713-3951)
This research paper aims to develop an accurate power consumption forecasting model to help factories efficiently plan their electricity consumption costs for production planning and power distribution expansion. The prediction models were compared using Artificial Neural Network (ANN), Multiple Linear Regression (MLR), and Random Forest (RF) analysis to determine the model with the highest accuracy. The data from recording electricity consumption of a factory in Rayong. According to the simulation test results, the ANN and the RF analysis's coefficient of determination (R 2) was equal to 0.85, which was higher than that of the MLR analysis with an R 2 of 0.84. In addition, it was found that the ANN had the lowest mean absolute error (MAE) of 1,990.64. Therefore, it can be concluded that the model developed with the ANN has the highest accuracy in forecasting the total kWh of electricity consumption to plan the use and control the cost of electricity for production, including reducing financial risks and increasing the business strength of the factory according to the objectives.
The 46th Electrical Engineering Conference (EECON-46)
2023-11 | Conference paper
Contributors: Nuth Otanasap
Nuth Otanasap (0000-0002-8713-3951)
Thailand's rice cultivation plays an important role in the economy regarding consumption and is the number one agricultural export. In off-season rice cultivation, it was found that various problems affect rice production. This research aims to apply a data mining model and compare the accuracy of off-season rice yield forecasting. Data used consisted of monthly secondary data of off-season rice in 22 provinces, from 2014-2022, from the Office of Economics and Agriculture, Meteorological Information Service Group, Thai Meteorological Department, and Royal Irrigation Department. It consisted of factors such as province, crop area, harvested area, product, crop month, average rainfall, average temperature, average relative humidity, fertilizer amount, fertilizer price, and average water discharge amount, totaling 976 items. WEKA processed data with three predictive models: K nearest neighbors (KNN), neural network, and decision tree. The J48 algorithm was used to test the accuracy or performance of data prediction models by dividing the data into 10-fold cross-validation. The experiments found that the highest overall efficiency was the decision tree model with an accuracy of 87.50%, which could be applied to predict the yield of off-season rice according to the objectives.
The 46 th Electrical Engineering Conference (EECON-46)
2023-11 | Conference paper | Conceptualization, Data curation
Contributors: Nuth Otanasap
Nuth Otanasap (Conceptualization, Data curation, 0000-0002-8713-3951)
The objective of this research aims to design and develop a contactless passenger elevator command system to avoid the spread of not only COVID-19 but also other contact-transmitted pathogens. The developed system consists of a Raspberry Pi connected to the elevator control panel and a mobile application that can operate the elevator by scanning a QR code. It can work in both online mode and offline mode. In online mode, the mobile application communicates with the Raspberry Pi through cloud computing. It can also record usage history for traceability and notification to users who were in the elevator on the same day and time in the event of an outbreak of germs. Additionally, in cases where the Raspberry Pi cannot connect to the internet, it can still function with the mobile app generating a QR code to command the elevator via a camera mounted on the Raspberry Pi directly. The trial's results using the mobile app and QR code, both online and offline, compared with manual commands, showed that the developed system could work with 100 percent accuracy. It has an average wait time of 5.62 seconds online mode and 5.60 seconds offline mode but is still slower than its manual counterpart, with an average wait time of 2.99 seconds. The developed and presented system meets the objective of this research, which is to enable users to avoid touching the control buttons to operate passenger elevators, which are shared by many users and cause a spread of germs.
The 46th Electrical Engineering Conference (EECON-46)
2023-11 | Conference paper | Supervision
Contributors: Nuth Otanasap
Nuth Otanasap (Supervision, 0000-0002-8713-3951)
This study applies Machine Learning techniques and financial indicators, specifically Exponential Moving Average (EMA), to predict gold price movements in the Forex market. Technical analyses such as EMA are employed to analyze price trends and create data features for training and testing Machine Learning models. Experimental results demonstrate that these techniques effectively predict the movements of gold prices in the Forex market. It is concluded that the application of Machine Learning coupled with financial indicators serves as a competent tool in forecasting price trends in the gold market, enabling enhanced adjustment and decision-making in trading activities.