The training function used in the ANN method, especially backpropagation, can produce different forecasting accuracy, depending on the method parameters given and the data to be predicted. This paper aims to analyze the ability and performance of one of the training functions in the backpropagation algorithm, namely One-step secant, which can later be used or used as a reference in the case of data forecasting. This method is able to update the values of bias and weights according to the one-step secant method. The analysis process uses a dataset of Foreign Exchange Reserves (US $ Million) in Indonesia 2011-2020. Based on this dataset, the dataset will be divided into two parts. The training data uses the 2011-2014 and 2015 dataset as the training data target. Meanwhile, the test data used 2016-2019 and 2020 as the target test data. The analysis process uses 5 experimental architectures, namely 4-5-1, 4-7-1, 4-9-1, 4-11-1 and 4-13-1. The results of the research based on the analysis obtained the best network architecture 4-11-1 with an MSE Training value of 0.00000012, MSE testing/performance of 0.00115144 (the smallest compared to other architectures) and Epoch 343 Iterations.
Problems that often occur when online learning are, the material delivered by lecturers isn’t optimally taught due to lack of use good learning media. This study aims to find the effective use of online learning platforms in higher education. The research uses a qualitative approach, which aims to analyze, investigate and assess the effectiveness of online learning using e-learning in Indonesia during the Covid-19 pandemic. In addition, this study also compares which e-learning is easy to use, which has full-featured e-learning and which is economical. The subjects in this study were students enrolled in various universities in Indonesia with a total of 136 students. The method of data collection was done by distributing questionnaires via google forms to students. In this study, two analysis were used: descriptive analysis, and qualitative response analysis. The indicators used to see the effectiveness of e-learning are widely used, easy to use, full-featured, and economical. The most widely used e-learning in Indonesia are WhatsApp Group, Google Classroom, Ms. Teams, Schoology, Edmodo, and Moodle. From the results of the analysis it was found that the most effective e-learning used during a pandemic was Moodle. Because Moodle has complete and interesting features compared to other e-learning.
<span lang="EN-US">The selection of learning media in accordance with the subject will greatly affect the interest and response of students in attending learning. In addition, during the COVID-19 pandemic, learning is conducted online, many students are not serious and are not interested in attending learning. Therefore, it is necessary to have media or online lecture platforms that can attract students’ attention, so that students can follow and be interested in learning. The purpose of this study was to look into the impact of Moodle on the research methodology performances of college students in Indonesia. Its goal was to investigate college students’ reactions to Moodle as an innovative online platform. This study included 86 Indonesian college students who sat in a single intact group. Based on the quantitative data, the study used a quasi-experimental design and a one-group pretest-posttest design. A test and a questionnaire were used to collect data. According to the study’s findings, Moodle improved Indonesian students’ research methodology performance. Students were excited to use Moodle because of its simplicity, usefulness, and accessibility. Moodle’s effectiveness in other contexts should be investigated in future research. This study confirmed Moodle's dependability in broader contexts.</span>
Water hyacinth is aquatic weed plant that has medium fiber content with length about 1.75 – 2.12 mm and diameter about 11.15 – 11.65 μm in its stem. Water hyacinth contains 90% of water by weight reduction from 10 Kg when wet to 1 Kg when dry. In dry conditions, water hyacinth contains crude protein 13.03%, crude fiber 20.6%, fat 1.1%, ash 23.8% and the rest is vortex that contains polysaccharides and minerals. Research was done to obtain the design of heat absorbing product that modified with additional of water hyacinth. The method that was uesd begin with drying water hyacinth to obtain good fiber. water hyacinth fibers then mixed with cement and sand which are made as composites in order to reduce the heat of room. The result of the research is make a product that can overcome thermal comfort problems in deep room temperature condition. Water hyacinth was chosen because it is easy to obtain, cheap and can reduce environmental pollution (biodegradability) so that the composite can overcome environment ptoblem and its used doesn’t endanger health. Based on the test result by providing a heat source of 40 Watt bulb lamp to the media for 15 minutes, it was found that the final temperature of the media 1 without additional of water hyacinth fiber was 32.5oC, final temperature of media 2 with additional of 100 gr water hyacinth was 32.2oC, and the final temperature of media 3 with additional 150 gr water hyacinth was 31.7oC. it shows heat temperature that is released and cannot be absorbed by composite in media 3 is only 0.50C, in meida 2 is only 10C while in composite in media 1 without additional of water hyacinth fiber that release heat about 1.3oC. it shows that the product is suitable to use because composite with additional of water hyacinth can absorb heat and release less heat compared to composite without additional water hyacinth fiber so that the room become cooler.
This research study focuses on the differences ineffectiveness in the use of media e-learning in the course of research methodology. This type of research is a quasi-experimental research design with a post-test control group design. The populations of this study were all students majoring in electrical engineering education, Faculty of Technic, State University Of Medan, batch 2017 and 2018. Sampling was done by random sampling technique. The research sample of the e-learning Schoology class was 42 students and the e-learning web class was 40 students. From the research data, it was found that there was no difference in learning outcomes between the e-learning Schoology class and the e-learning web. For the effectiveness of using learning media, it was found that web e-learning was considered quite effective compared to e-learning Schoology.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.