CNN originates from image processing and is not commonly known as a forecasting technique in time-series analysis which depends on the quality of input data. One methods to improve by smoothing This study introduces novel hybrid exponential using called Smoothed-CNN (S-CNN). The method combining tactics outperforms majority individual solutions forecasting. S-CNN was compared with original other such Multilayer Perceptron (MLP) Long Short-Term Memory (LSTM). dataset year daily website...

The need for accurate time-series results is badly demanding. LSTM has been applied forecasting time series, which generated when variables are observed at discrete and equal intervals. Nevertheless, the problem of determining hyperparameters with a relatively high random rate will reduce accuracy prediction results. This paper aims to promote tuned-PSO Bifold-Attention mechanism. PSO optimizes hyperparameters, Bifold-attention mechanism selects optimal input LSTM. An accurate, adaptive,...

Due to the evident importance of e-learning in education, number e-courses and systems delivering various services has exploded. Thus, evaluating is critical ensuring their successful delivery, practical use, beneficial effects on learners. Therefore, this study aims evaluate success learning management using modified DeLone McLean model. A survey involving 239 in-service vocational teachers evaluated research Statistical analysis was used examine hypotheses, specifically linear regression...

Text annotation is an essential element of the natural language processing approaches. The manual process performed by humans has various drawbacks, such as subjectivity, slowness, fatigue, and possibly carelessness. In addition, annotators may annotate ambiguous data. Therefore, we have developed concept automated to get best annotations using several machine-learning proposed approach based on ensemble algorithm meta-learners meta-vectorizer techniques. employs a semi-supervised learning...

The present study explores the domain of Keris classification by employing advanced Convolutional Neural Networks (CNNs) as a potent technique for identifying subtle patterns and cultural characteristics inherent in these renowned Indonesian daggers. has presented encouraging findings about identification Pamor, Dhapur, Tangguh categories. However, it is crucial to recognise confront constraints associated with this research. key pertain diversity data, accuracy labelling, generalizability...

Using virtual environments as teaching aids has been increasingly common in recent decades. Virtual Reality (VR) recently gained popularity construction engineering education and training (CEET). Immersive interfaces have proven benefits Engineering Education. In fact, VR offer new ways to improve user knowledge transfer communication. Therefore, this study aims describe an immersive interface built for aspiring Civil students. The development of the consists three main stages: needs...

This study aims to classify the maturity level of oil palm using K-Nearest Neighbors (KNN) method based on extraction RGB and L*a*b color features. classification determines optimal production palm. However, this process is often carried out by humans, so sorting not because it done manually, takes a long time. Thus, we propose automatic detection machine learning approach. In study, image processing methods are used maturity. The starts with taking 150 photos smartphone. Each them then...

Reviews are a form of user experience information on product or service that can be used as reference for potential consumers’ preferences to buy, use, consume product. They also by business entities find out public opinion about their the performance products. It will very difficult process review data manually and it take long time. Therefore, sentiment analysis automation get polarity from existing reviews. In this study, IndoBERT with Recurrent Convolutional Neural Network (RCNN) was...

Long Short-Term Memory (LSTM) neural networks must consider parameter settings for more accurate prediction results. This study aims to improve the LSTM performance using Particle Swarm Optimization (PSO) hyperparameters selection. PSO may optimize weight of network, which results in minimal error due its feature selection and data normalization abilities. applies architecture, consisting 3 layers (input, hidden, output) with several 7, 3, 1. Root mean squared (RMSE) processing time evaluate...

Deep learning is a machine approach that produces excellent performance in various applications, including natural language processing, image identification, and forecasting. network depends on the hyperparameter settings. This research attempts to optimize deep architecture of Long short term memory (LSTM), Convolutional neural (CNN), Multilayer perceptron (MLP) for forecasting tasks using Particle swarm optimization (PSO), intelligence-based metaheuristic methodology: Proposed M-1...

Support Vector Regression (SVR) is a supervised learning algorithm to predict continuous variable values. The basic goal of the SVR find most suitable decision line. has been successfully applied several issues in time series prediction. In this research, used price staple commodity, which are constantly changing at any due factors making it difficult for public get groceries that easy reach. National commodity data consisting 17 commodities, including shallots, honan garlic, kating medium...

Social media currently becoming a that cover all ages-users in aspects of life. The power social to change lifestyle is potentially used transform information, science, and technology. A popular such as YouTube, Instagram, WhatsApp, Facebook has reached more than million users each year. use basic need for most the students right now. Therefore, purpose this study discover utilization learning tools environments. comparative done describe comparison overview environment. result shows many...

This study aims to find out the effect of Google SketchUp application and need for achievement on students’ learning achievements building interior design. Quasi-experimental research was conducted at Vocational High School (VHS) with a 2 x factorial The used in experimental group, while PowerPoint Slides were control group. sample consisted 56 VHS students, program modeling design information. instruments are tests reliability coefficients 0.916 0.671. To test hypothesis using multiple...

Mental health problems are increasingly crucial in the workplace. These issues affect employee productivity and accordingly it affects company's prolificacy. To minimize mental among employees, companies must identify factors related to employee's health. Therefore, a classification method find out whether an requires treatment or not is highly much-needed. This paper seeks develop application of features selection using chi-square performance K-Nearest Neighbor (KNN) algorithm conducting...

Educational games enable students to learn and play. The use of educational as learning media can also encourage users discover build their own knowledge learning. purpose this study is show the impact using on student outcomes. be used an alternative choice a media. research instruments were post test pre test. Data analysis was done by comparing results This conducted see whether there changes in shows that students’ outcome are increase implementing games.

Abstract In the disruptive era, online learning models began to be widely developed. Malang State University as one of state universities in Indonesia is developing and implementing a new curriculum with theme Life-Based Learning (LBL) form adaptation facing Industrial 4.0 era. Through LBL, college graduates are expected not only master competencies, but able develop their abilities face needs developments industrial revolution era 4.0. This study aims an LMS-based transdisciplinary portal...

Stemming is the process of finding a basic word with several stages affix removal. The main reason for stemming to check spelling and machine translation support effectiveness retrieval process. This study uses Nazief Adriani algorithm Javanese-influenced words. first step taken data collection making dictionary. Then do Before stemming, modifications are made rules. rules algorithm, which based on morphology Indonesian language, modified suit morphological Javanese language. Of 366 words...

The Indonesian police department has a role in maintaining security and law enforcement under the Republic of Indonesia Law Number 2 2002. In this study, data on crime rate Bontang City area been analyzed. It becomes basis for Police anticipating various crimes. K-Means algorithm is used analysis. Based test results, there are three levels crime: high, medium, low. According to analysis, high special case theft vehicle theft. Furthermore, it program maintain personal safety.

This research aims to develop MOOC content with a STEM approach using the Schoology Learning Management System (LMS) and apply developed product assess its impact on students' geographical literacy abilities. The falls under category of Research Development (R&D) mixed-method analysis. development model used in this study is ASSURE. design implemented one-group pretest-posttest N-gain score test when significant difference was found between average pretest posttest scores through paired...

Steganografi merupakan teknik penyembunyian data dalam media. Dalam penyembunyiannya, pesan rahasia disisipkan pada media pembawa(carrier file) antara lain, teks, gambar, audio dan video. Salah satu carrier file steganografi adalah gambar/citra digital, yang paling sering digunakan pertukaran melalui internet. review literatur ini, akan dijelaskan tentang metode citra seperti LSB, MSB, DCT, DWT, Spread Spectrum BPCS. Termasuk penjelasan perbandingan berupa kelebihan kelemahan dari...

Social informatics is an interdisciplinary area that examines how information and communication technologies (ICT) the complex web of social cultural contexts interact change over time. This study not only helps with design use ICT but also shows these significantly affect society culture. It encourages new ideas, collaborations between different fields, policymaking insights, which drives technological innovation a better knowledge affects society. The Conceive, Design, Implement, operate...

Computational methods have been used extensively to solve problems in the education sector. This paper aims explore computational method's recent implementation solving global Vocational and training (VET) problems. The study a systematic literature review answer specific research questions by identifying, assessing, interpreting all available shreds of evidence. result shows that researchers use method predict various cases VET. most popular are ANN Naïve Bayes. It has significant potential...

The paper deals with developing backgrounds to design the control systems for electrical motors and actuators. We offer controllers by using known approach based on symmetry principle. This principle similar feedback linearization allows us fully compensate inner dynamic of a plant but contrary it forms system's desired motion defining transfer function open-loop system. Since used operates functions apparatus we generalize these taking into account plant's non-zero initial state while...