SHM Publisher Journals
Not a member yet
315 research outputs found
Sort by
Crude oil price prediction using Artificial Neural Network-Backpropagation (ANN-BP) and Particle Swarm Optimization (PSO) methods
Get PDFCrude oil price fluctuations significantly affect commodity market price fluctuations, so a sudden drop in oil prices will cause a slowdown in the economy and other commodities. This is very important for Indonesia, one of the world's oil-producing countries, to gain multiple benefits from oil exports when world oil prices increase and increase economic growth. Therefore, a system is needed to predict world crude oil prices. In this case, the Particle Swarm Optimization (PSO) algorithm is applied as the optimization of the weight parameters in the Artificial Neural Network-Backpropagation (ANN-BP) method. We compared the ANN-BP–PSO and ANN-BP methods to obtain the method with the best causation value based on the MAPE and MSE results. PSO aims to find the best weight value by iterating the process of finding and increasing position, speed, Pbest, and Gbest until the iteration is complete. The results showed that the ANN-BP-PSO process was classified as very good and had a lower predictive error rate than the ANN-BP method based on the MAPE and MSE values, which is 5.02007% and 7.15827% compared to 6.28323% and 13.86345
Increased accuracy in predicting student academic performance using random forest classifier
No full textThis research aims to classify the academic performance of students who are successful and who have dropped out of school with high accuracy so that these matters can be addressed quickly. Things like this need fast handling to find out what factors influence it. In addition, this research was conducted to test how good the random forest algorithm is in classifying a problem. Random forest, which includes an algorithm that is commonly used for classifying a problem. By using the random forest algorithm, the accuracy results will be better than a single decision tree. This algorithm is quite good at handling and managing large datasets. From this study it can be concluded that this method can provide good prediction accuracy with a fairly high level of accuracy, namely 89%. Utilization of this random forest can be an alternative in classifying student academic achievement. This algorithm can work well in handling large datasets. This study discusses how the use of Random Forest can work to classify students' academic performance
W/O/W type lotion formulation of “arum manis” mango (Mangifera indica L.) pell as antioxidant
No full textArum manis mango peel contains compounds, namely flavonoids. Flavonoid compounds act as natural antioxidants. The weakness of flavonoid compounds is that they are not stable to the influence of high temperature and light intensity, so that the arum manis mango peel extract is made in the form of lotion type W/O/W. This study aims to determine the physical characteristics and stability of the W/O/W type emulsion form optimum formula in double emulsion preparations and lotion preparations, determine the stability of W/O/W type lotion preparations during storage using the cycling test method and determine the IC50 value in the optimum formula. lotion preparation type W/O/W. The optimum formula for double emulsion type W/O/W is found in formula 5 with a ratio of primary emulsion: secondary emulsion (80%:20%) with span 80 (10%) and tween 20 (5%) concentrations while the optimum formula for lotion preparations found in formula 3 with a ratio of double emulsion type W/O/W: lotion base (80%:20%) with a concentration of stearic acid (5%), cetyl alcohol (2.5%) and glycerin (10%). In the antioxidant activity of lotion preparations, the IC50 value was 136.543 ppm and the stability test on the cycling test method had an unstable form
Energy and Solar Irradiance Analysis for Hydroponic System
Get PDFA Simulated impact of partial shadow on PV modules and the different partial shading on the PV panel effect on the PV performance is being analysed. The setting for the report is a hydroponic plant system equipped with a solar energy source and IoT at Pangsapuri Jasa, Mutiara Rini. The system control can reduce the carbon footprint and cause no pollution to the environment, while the information gathering process is faster without requiring a lot of time and energy. By collecting the data at Pangsapuri Jasa, the suitable irradiation data is used. The power consumption cannot be monitored by users. A shadow is casted over a panel which make the amount of sunlight reaching the surface is reduced. In addition, the partial shading effects continue to be one of the most demanding issues that directly influence the effectiveness of PV networks in terms of power outputs, the development of several peaks on the power-voltage (P-V) characteristic curve, and the incidence of hot-phenomena. Furthermore, the effective strategies are not being implemented that could save the energy consumption where analysis of the system performance is not practiced consistently when there are available strategies that can improve the system. The purpose of this project is to focus on analyzing the effect of the partial shading to the PV output performance. Also, to monitor the real time monitoring of electricity usage for hydroponic system. This project also covers the analysis of the effect of different configuration of shaded area of partial shadings on PV output performance. The study focuses on a specific kind of shading where photovoltaic panels as a shading device. The study focusses on the analysis of PV output performance on different partial shading conditions. Different number of shadings are being presented to display the experimental set up by using MATLAB Simulink
 
The role of the ASEAN tourism forum (ATF) in supporting Indonesian tourism
Get PDFThis study aims to analyze the role of ASEAN Tourism Forum (ATF) in supporting tourism in Indonesia. Research methods are carried out qualitatively by collecting data through literature studies. The analysis uses Miles Huberman's analysis which includes data collection, data reduction, data presentation, and drawing conclusions. The results showed that the ATF has played a role in the development of tourism in Indonesia. Some of the roles that have been carried out by ATF are (1) ATF acts as a tourism promoter (Tourism Marketing Strategic (ATMS) to market the Wonderful Indonesia brand), (2) ATF acts as an investment cooperation forum (promotion of Indonesian tourism investment), (3) ATF acts as a tourism standardization forum (standards for green hotels, Food and Beverage, Public Restroom, Homestay, Ecotourism and Tourism Heritage), (4) ATF plays a role in increasing tourist visits in Indonesia by giving awards for the best destinations to boost the prestige of Indonesian tourism, and (5) ATF organizing TRAVEX (Travel Exchange) to boost economically profitable transactions
Alternative solution for human error in hospitality industry
Get PDFA hotel is a service that offers accommodation to visitors. Things don't always go smoothly in the hospitality industry, so mistakes are bound to happen. Because guests feel uncomfortable or even make mistakes in cooperation between employees. Interpersonal problems are called human error. Human error or in another sense a standard deviation that can cause problems in the hotel. The cause of the problem itself stems from several factors that occur inside and outside the hotel. An example of a problem that arises in the hotel is the lack of knowledge and skills in dealing with guests. This requires solutions to improve employee performance through orientation and training provided by the hotel to educate employees even better. Usually the culprit of the problems that arise is the hotel staff, including managers, supervisors, insiders and others. Many different actions arise from the problem and all actions inevitably have a cause and effect, especially when it comes to the hospitality business. The purpose of the author writing this article is to know how to solve the problem with a good solution. The method used is qualitative, the author knows how to collect information from various sources. We, the author, tried to offer solutions and actions for human error in hotels
Technology for SMS-based assistive device for the visually impaired
Get PDFThe term "tunanetra" is used to refer to someone who experiences total blindness or visual impairment. Such visual limitations result in visually impaired individuals facing difficulties in accessing information quickly and performing daily activities like walking, driving, and more. Walking is one of the crucial activities for visually impaired individuals because it is one way to explore the world and engage in daily activities. Based on this issue, an assistive device for the visually impaired was designed using embedded system technology. In 2022, Serly Juliana Taneo, Jonshon Tarigan, Frederika Rambu Ngana, and Andreas Ch. Louk developed a mobility aid device for individuals with visual impairments using ultrasonic sensors for distance detection and Arduino as the microcontroller. However, the device primarily focused on mobility, and there is a need to add new features, such as emergency information using SMS technology that can send messages with the press of a button. The research results indicate that the ultrasonic sensor successfully triggers vibrations within a range of 1-100 cm, and the button can send emergency notifications via SMS when pressed. Therefore, it can be concluded that all connected components can function as intended. By combining SMS technology and ultrasonic sensors, this assistive device is expected to enhance the safety and independence of individuals with visual impairments as they navigate their surroundings
Portfolio Selection Strategies in Bursa Malaysia Based on Quadratic Programming
Get PDFThe study aims to select the efficient portfolio on stock listed in Bursa Malaysia by using the quadratic programming method. It can help the investors to gain expected returns from the diversification portfolio. However, there are some problems that should be considered such as the measurement of inputs for Mean-Variance Models (MVM), use of portfolio models through time and consistency with management objectives in the portfolio. These problems will affect the performance of selected portfolio and cause the loss problem. Therefore, this study implements a quadratic programming approach to select an efficient portfolio on stocks listed in Bursa Malaysia. The study will choose 15 potential companies which have the best performance in the Bursa Malaysia. Quadratic programming (QP) model can solve any type of mathematical optimisation problem in the study. Therefore, investors can optimise the investment portfolio returns by using QP methods. However, we can observe the efficient frontier which is a graph that representing a list of portfolios that optimising expected return for a different level of portfolio risk so can help the investors make a good decision. The findings of this study will give important inputs, especially to the investors to maximise their portfolio return at different level of risks
Bankruptcy Prediction Using Genetic Algorithm-Support Vector Machine (GA-SVM) Feature Selection and Stacking
Get PDFBankruptcy is an impact caused by a company's financial failure. Financial failure in the company must be avoided so as not to cause losses to the company. In the research that was carried out utilizing a data set from the Taiwan Economic Journal as many as 6,819 to be trained using machine learning algorithms using classification techniques. The goal obtained from the research conducted is to obtain a classification technique with the best accuracy results. The method used in this research is preprocessing using the synthetic minority over-sampling technique to handling unbalanced data sets. Then, the results of the balanced data set will be processed using a genetic algorithm-support vector machine feature selection algorithm to reduce the attributes of the data set. Data sets that have experienced reduced attributes will be trained using the stacking method with a single classifier base learner in the form of k-nearest neighbors, naïve bayes, decision trees with classification and regression tree models, gradient boosting decision trees, and light gradient boosting. The meta-learner used in the stacking method is extreme gradient boosting. The results of the accuracy obtained from the research conducted were 99.22%
Smart Doors For Monitoring Body Temperature And Space Capacity Based On IoT
Get PDFPresently, multiple countries are engaged in combatting virus outbreaks transmitted through contact with infected individuals. To address this issue, several measures have been taken to shift the pandemic status to an endemic state. This study introduces an Internet of Things (IoT) device designed to monitor body temperature and room occupancy in real-time. Notifications are sent when a room surpasses its capacity or when body temperature exceeds the allowable threshold. The system enables real-time alerts and stores data for remote accessibility and analysis. The experiments conducted involve Infra Red Proximity, temperature sensor (MLX90614), object distance sensor (HCSR04), Wemos, and Solenoid Door Lock. Telegram is used as the medium for data transmission. The developed system proves effective in continuously monitoring body temperature and room occupancy.