Motif tenun melayu sangat beragam. Keberagaman ini membuat sulit membedakan motif-motif kain tenun tersebut. Klasifikasi data diperlukan untuk mengidentifikasi karakteristik objek yang terkandung dalam basis data agar kemudian dikategorikan ke dalam kelompok yang berbeda. Tujuan penelitian yang dicapai dalam penelitian ini yaitu untuk mengetahui performa pengenalan dan klasifikasi motif tenun melayu menggunakan Faster R-CNN dengan model arsitektur VGG, dengan cara mengukur persentase dari tingkat akurasi, presisi, dan recall yang akan divalidasi menggunakan K-Fold Cross Validation. Penelitian ini menggunakan algoritma deteksi objek Faster R-CNN sebagai metode pengenalan dan klasifikasi pola kain berbasis citra digital. Faster R-CNN merupakan salah satu metode yang digunakan untuk mengenali objek pada citra digital. Kemampuan pengenalan objek ini digenean untuk mengenali dan mengklasifikasi motif-motif kain tenun melayu. Jumlah dataset yang digunakan berjumlah 100 citra yang diacak untuk masing-masing dari 5 (lima) fold pada K-fold cross validation. Data tersebut dibagi menjadi 80 data train dan 20 data test. Setelah dilakukan persiapan data, pre-processing, serta implementasi, dilakukan pengujian dengan hasil bahwa dari data latih yang berupa citra kain tenun melayu, didapatkan skor rata-rata training loss dari step pertama hingga step terakhir sebesar 1,915. Klasifikasi karakteristik pengenalan motif tenun melayu menggunakan Metode deteksi objek Faster R-CNN melalui validasi K-Fold Cross Validation dengan nilai k=5, didapatkan akurasi 82.14%, presisi 91.38% dan recall 91.36%.
The beauty of tourist attractions in Indonesia has a certain attraction for foreign tourists to serve as a place for vacation. However, the number of visitors needs to be predicted to anticipate an increase or decrease in the number of visitors, so that the state can determine policies regarding changes in the number of visitors in the future. Forecasting is used to predict previous data patterns so that further data patterns can be known. Multilayer Perceptron (MLP) is a neural network development that can be used for modeling time series data. Several researchers have conducted research using the Multilayer Perceptron method in making predictions. Forecasting systems or forecasting are very helpful in the current era, forecasting aims to predict future conditions. Prediction results, obtained 82% accuracy for tourist predictions in Period 7, namely September 2020, 97% for Prediction Period 8, namely December 2020 so that the Number of Tourists for Period 9 is 7,106 people.
Autism is a developmental and behavioral disorder of children where social relationships are disrupted, namely children with autism cannot interact with other people, including their parents. Autistic children experience disorders such as communication disorders, social relationship disorders, and behavioral disorders, resulting in a child. Parents often do not realize the differences and abnormalities that appear in their children until they are three years old. They just realized that their child is different from other children. There are several basics of treating autism and there are some teachers who can help cure autism in children. The teacher treats autistic children with an approach that is adapted to the problem. Types of autism basically this child is divided into four categories, including social interaction disorders, behavioral generalized disorders, communication disorders, and self-stimulation disorders. This research designs and builds an expert system (expert system) for diagnosing Autism disorders in early childhood based on the web Method of Forward Chaining. This Forward Chaining is very good to use if the work starts with recording the initial information and wants to reach the completion or final goal. This expert system is considered capable of providing information and solutions for parents, about the types of autism disorders in early childhood, based on the symptoms entered and can provide solutions
Republic of Indonesia Law No. 14 of 2005 describes teachers as professional educators with the main task of educating, teaching, guiding, directing, training, evaluating, and evaluating students in the formal education listed. The teacher has an important role in planning and implementing the learning process, so as to obtain opportunities to improve competence. One of the activities that must be carried out by teachers in developing their competence as teachers is scientific publications, which are listed in Article 11 of the Minister of PAN & RB Regulation No.16 of 2009 concerning teacher functional positions. In designing scientific publications there are stages and methods that are different from other papers. The research work comes from the research activities carried out so that it can be a reference in the follow-up of educational activities. The existence of information technology devices makes it easy for teachers to carry out research activities to publish them. The more research carried out at this time is not necessarily comparable with the quality of research. The demand to fulfill good and correct reference criteria is a challenge for teachers in the stages of reviewing and following up on publications. This service activity provides other insights into better article writing and reference techniques using computer-assisted devices. Problems with the obstacles faced so far by the teacher in writing are expected to be solved so that joint efforts in creating an environment of professionalism in education can be realized.
In many studies, Google Trends Data is efficient to analyze and estimate as explanatory variables, including tourism predictions. However, data retrieval and tourism are always plagued by noise. Without noise processing, the predictive ability of search engine data may be weak, even invalid. As a noise processing method, Hilbert-Huang Transform (HHT) can reduce or clean noise. Forecasting is the art and science of predicting future events. LSTM is able to overcome long-term dependence. This study tries to provide predictions of tourist visits by processing noise in search engines using the Hilbert-Huang Transform method. The forecasting architecture that is built is composed of 3 hidden LSTM layers with 100 units of neurons or nerves that function to process information, which in the LSTM layer also becomes the input layer. Prediction test results on a dataset of 156 rows, resulting in RMSE values in 2019 getting RMSE LSTM 129249 results, and RMSE HHT + LSTM 653058. so that the resulting RMSE is closer to remembering 0.
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.