“Face Mask Detection Using the Convolutional Neural Network” is a PC based program that aims to detect and classify human beings whether a person is using a mask or not with access through a webcam camera. This program is created using the Python language with several libraries. The classification of face masks uses the Convolutional Neural Network method with the MobileNetV2 architecture. Meanwhile, human face detection uses the Haarcascade Classifier. How the program works is by accessing the connected camera and if the person detected is wearing a mask, the person will be labeled "using a mask" and given a green box to mark the detection along with the analysis value, whereas if not, it will be labeled "not using a mask" and a red box with also the predicted value. From the test results, it can be proven that the accuracy program is good enough to detect the use of face masks with an average object detection accuracy of 88.53% and the classifier for the use of mask an average of 84.45%.
The development of information technology is growing from year to year. To support the smooth flow of information, there are many internet service providers circulating in Indonesia to support their needs. Some of the largest internet service providers in Indonesia such as Indihome, First media, and Biznet Home definitely have their own advantages and disadvantages.At this time, internet provider providers only accept customer complaints or suggestions through the customer service (CS) call center. Meanwhile, many young Indonesians currently use one of the popular Social Media services, namely Twitter as a user-friendly microblogging service so that users can easily use it, especially in delivering messages in the form of tweets. Therefore, a sentiment analysis program was designed for several internet providers in Indonesia. Opinions or Opinions will be analyzed to determine public sentiment. These sentiments will be classified into 3 sentiments, namely negative, positive, and neutral sentiments. The sentiment classification process can be done manually, but if there is too much data, it requires a system equipped with a classification method, so that the determination of classification can be done quickly. The design of this program applies the Naive Bayes Classifier method. Because this method is supervised learning, it requires training datasets with labels. Labeling will be done automatically using the K-means method. K-Means will sort tweets into groups which are divided into 3 labels. The results of the K-means clustering accuracy are 73.4%. The results of this application are divided into 2 parts, namely a pie chart which is divided into slices that describe the results of the percentage of tweet classifications and a table of classification results containing the number, content of the tweet, and the results of the classification. The best level of accuracy in testing uses 220 training data, and 54 training data. The results of the accuracy of 83.3%.
Prediction credit card submission is a system that is able to provide an assessment of alternatives in order to help credit card applicants in making decisions. Many methods can be used in building a prediction system for credit card submissions. This research will compare two methods in predicting credit card submission, namely the naïve bayes method and c4.5 algorithm, case study of Credit Card Submission Prediction, the results of the research are, knowing the level of accuracy of the two methods. Criteria that form the basis of decision making include age, sex, recent education, marital status, number of dependents, type of company, monthly income, and salary slip. The final result found that the naïve bayes method and the c4.5 algorithm are relatively the same.
Stock is an instrumentation that has the fundamentalsof a company. Owning a share means owning theshares of the company. Shares can be traded on theIndonesian Stock Exchange by the entire public. TheLQ45 stock grouping and recommendation applicationis a desktop-based application that aims to assist inmaking investment decisions in the Indonesian CapitalMarket. The application is designed using the Pythonprogramming language. The application applies the KMedoidsClustering method to group stocks andExponential Moving Average along with WeightedProducts to make recommendations or sort shares.Users can enter the desired share criteria and theapplication will recommend according to the inputcriteria from the user. Testing on this application iscarried out by the BlackBox testing method,questionnaire, K-Medoids Algorithm Testing and theoutput results of the program. From the results of theblack box testing, the application results can runaccording to plan. In testing the K-Medoids Algorithm,the results obtained that the number of clustersdetermined are in accordance with the number of 2clusters using the elbow method. And in testing theoutput results of the program, the results obtained arethe recommendation accuracy of 80.8%.
In Google Play Store there are lots of application ready to be explored and downloaded. Google Play Store is a place where many developers can sell applications that they have made. Apart from being a place for searching and downloading applications, Google Play Store can also be used to conduct a research. E-Wallet is one of a technological development that can be used to do many transactions. Doing transaction with e-wallet can be done anywhere you want. E-wallet in Indonesia is growing very rapidly especially in the present time where covid-19 is growing rapidly. This is one of the reasons why many people now using e-wallet for doing transcations. Many interesting promotions that were given is also one of the reason why people start using e-wallet. This research had the objective to visualize people’s emotion on e-wallet based on user opinion in Google Play Store. The research stage starts from scrapping data from Google Play Store, preprocessing data, classification with Support Vector Machine, evaluation with confusion matrix. Data were scrapped from google play store using google_play_scrapper API. This research uses OVO review of 500 data, DANA review of 500 data, LinkAja review of 500 data. The classification results will then be evaluated using a confusion matrix. The highest accuracy results will be used as a model for the classification stage. The classification results will be displayed in the form of tables and pie charts that describe the percentage results of sentiment classification.
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.