Weather forecasting has gained attention many researchers from various research communities due to its effect the global human life. The emerging deep learning techniques in last decade coupled and wide availability of massive weather observation data have motivated researches explore hidden hierarchical pattern large volume dataset for forecasting. purposes this are build a robust adaptive statistical model univariate variable Indonesian airport area intermediate related accuracy prediction...

Weather forecasting has gained attention many researchers from various research communities due to its effect the global human life. The emerging deep learning techniques in last decade coupled with wide availability of massive weather observation data and advent information computer technology have motivated researches explore hidden hierarchical pattern large volume dataset for forecasting. This study investigates In particular, this will compare prediction performance Recurrence Neural...

This paper aims to explore deep learning model learn short-term and long-term patterns from imbalanced input dataset. Data for this study are card transactions an Indonesia bank in period 2016–2017 with binary labels (nonfraud or fraud). From 50 features of the dataset, 30 principal components data contribute 87 % cumulative Eigenvalues. explores effect nonfraud fraud sample ratio 1 4 three models: Convolutional Neural Network (CNN), Stacked Long Short-term Memory (SLSTM), Hybrid CNN-LSTM....

This paper presents finger-spelling recognition method for American Sign Language (ASL) Alphabet using k-Nearest Neighbours (k-NN) Classifier. research also examines the effect of PCA dimensional reduction to k-NN performance. The empiric results show that classifier achieves highest accuracy (99.8 percent) k=3 when pattern is represented by full feature. However, only 28.6 percent (for k=5) PCAreduced low due several factors, among others, presence high numbers redundant or highly...

Covid-19 pandemic is an international disaster that experienced by almost all countries in the world. This has impact on lines of life each country. Among them education sector. Aside from efforts to solve this co-19 problem, state must continue maintain stability and sustainability learning process right citizens. Indonesia same thing. face "shock" immediately take fastest action utilizing existing technology, but not are ready. Using survey methods adopting theories Delon McLean, study...

Weather forecasting is an interesting research problem in flight navigation area. One of the important weather data aviation visibility. Visibility factor all phases flight, especially when aircraft maneuvering on or close to ground, i.e., during taxi-out, take-off and initial climb, approach landing taxi-in. The aim these study analyze intermediate variables do comparison visibility by using Autoregressive Integrated Moving Average (ARIMA) Long Short Term Memory (LSTM) Model. This paper...

This study aims to implement and compare the Long Short Term Memory (LSTM) Simple Recurrent Neural Networks (RNN) algorithm in case of chatbot using Bahasa Indonesia data. The model used is a cahatbot across business/service fields. training data this research are on customer service talks with its customers several business fields or services. To models generated from LSTM RNN algorithm, two tests were carried out, first test testing chat output manually which was done directly by humans...

We are presenting our research about the importance of User Interface (UI) and Experience (UX) Gameplay experience (GX) on a video game. In order to find effect user in forms UI, UX GX games, quick survey was done using Google Form for 60 participants only 52 respondents which answer yes question number 1, where 36 16 male female respectively. The spread into 4 range ages 16, 24, 8 between 13–20, 21–30, 31–40 age more than 41 interesting thing is from 69.2%(36 respondents) 46.2% (24 34.6%...

The technological revolution in warehouse management is accelerating, especially with the use of drones and deep learning algorithms to overcome operational challenges. This research aims develop a learning-based automation system that integrates for accurate efficient identification inventory calculation retail warehouses. method uses Design Science Research Methodology (DSRM) approach, which includes problem identification, solution development, demonstration, evaluation, communication....

The Ministry of Marine Affairs and Fisheries (MMAF) carry out the responsibilities features associated with policy marine fisheries. MMAF fisheries policy. One their duties functions are organized fishery statistics, in accordance to Law Republic Indonesia Number sixteen 1997 regarding Statistics. main problem is number enumerators at each Basis Landing Of Fish. This paper proposed a fish classification on images using transfer learning Matlab as first stage tackling problem. FishNet...

Doing Data Warehouse (DW) to your business or system is not only think about the trend only, but how understand DW knowledge itself and implement it. as a real technology of Artificial Intelligent (AI) which show up like human, inevitably help human particularly in making quick decision reports. systems should apply mother AI we recognized Software Engineering (SE) where best software application more importantly satisfy user. In order make good model design user expectation then 3 steps...

The increasing number of inhabitants a city, there will be more challenges in the management city. Many events that can not controlled by either causing slow response relevant institutions. Sensing smart city through social media is offered for such solution. Text mining done to analyze posts based on occurred and emotion follows text, hashtag geo-tagging. Methodology used text approach kernel methods, particularly support vector machine (SVM). Results are expected with this concept listen...

This paper presents some empiric results on teaching basic Mandarin as second language to college students using gamification approach. study shows evidences that outperform non-gamification method in related learning concentration, skills, feedback, and immersion. However, has drawbacks compliance of quiz difficulty with the level/learning progress, clarity overall goal, goal at each level. These strength design are expected give valuable information for teachers delivering language.

Abstract Nowadays mixing one language with another either in spoken or written communication has become a common practice for bilingual speakers daily conversation as well social media. Lexicon based approach is of the approaches extracting sentiment analysis. This study aimed to compare two lexicon models which are SentiNetWord and VADER polarity code-mixed sentences Indonesian Javanese language. 3,963 tweets were gathered from accounts that provide tweets. Pre-processing such removing...

Education field is rich of data, and machine learning used in this are increasing lately. Based on their first semester result, using techniques, the student's final year result (GPA) can be predicted. The data experiment from computer science subjects, 6 1 laboratories results GPA graduation year. techniques Generalized Linear Model, Deep Learning Decision Tree. From what important factors that impact extracted to help students prepared themselves earlier.

Semantic image segmentation is an interesting problem in Computer Vision with many potential applications. The DeepLab model combined two other networks: Resnet and Conditional Random Field networks, making the a fairly deep network structure to increase semantic performance. Many previous studies argued that there are some limits on learning model's depth as may lead vanishing/exploding gradient, which This paper presents experimental study compare effect of several ImageNet pre-trained...

Over decades, weather forecasting has attracted researchers from worldwide communities due to itssignificant effect global human life ranging agriculture, air trafic control public security. Although formal study on been started since 19th century, research attention tasks increased significantly after big data are widely available. This paper proposed merged-Long Short-term Memory for ground visibility at the airpot using timeseries of predictor variable combined with another as moderating...

Due to hypercompetitive internet service provider market, customers can easily move from one companies or operator another if they did not obtain a good service. This customers' movement is major issue for as the reason most often found why customer churn. Churn management an important program maintain valuable thus predicting churn crucial. In literature, analysis has been widely studied with various techniques. These techniques mostly utilize complaint data, tenure, usage, payment...

Detecting building location distribution in an urban area has been a concern of city government many developing countries as basis for planning and development. In recent years, deep learning gained research attention the most attractive approach to address classification remote sensing field. One application is semantic image segmentation method whose aim classify each pixel into predetermined set labels. this experiment, objective detection areas using model which categorized either or...