Garuda - Garba Rujukan Digital

PENERAPAN METODE SURF DAN FLANN UNTUK MENDETEKSI TERBITAN SPAM PADA INSTAGRAM Dwi Sandi Yulianto; Adri Priadana; Andika Bayu Saputra; Fajar Syahruddin
Jurnal Teknomatika Vol 14 No 2 (2021): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v14i2.1125

Social media is a new media that utilizes the internet to share information, interact, participate and others, and to be used with each other. Currently there are many social media circulating, one of which is Instagram. At first Instagram was only used to share photos, then along with the development of technology and media, Instagram also developed into being able to share videos and shop on Instagram. Instagram is also one of the social media specifically used to upload images and videos. The growing use of Instagram in supporting promotion makes Instagram faced with various problems, one of which is the emergence of spam issues. For example, the publication of spam on Instagram is published by several sellers of products or the like continuously. It's good to promote a product. But on the other hand, it will interfere with other users if the spam often appears. This is exacerbated by the mass use of popular hashtags, done with the aim of getting more views. Popular hashtags are hashtags that are followed by many Instagram users. Based on these problems, it takes a computer program to detect spam issues based on certain hashtags on Instagram. In this final task, the Speeded-Up Robust Features (SURF) and Fast Library for Approximate Nearest Neighbor (FLANN) methods will be applied to detect spam publications on Instagram. The results of experiments that have been conducted on 12 images that produce 66 comparisons, the application of SURF and FLANN methods can be said to be very good in detecting the similarity of images between Instagram publications that indicate that the same image is a spam issue, which is with a maximum accuracy value of 100%.

PERBANDINGAN METODE DECISION TREE DAN NAIVE BAYES CLASSIFIER PADA ANALISIS SENTIMEN PENGGUNA LAYANAN PT PERUSAHAAN LISTRIK NEGARA (PLN) ABIYOGA BAGUS MUSTRIYANTO; Muhammad Habibi; Dayat Subekti; Fajar Syahruddin
Jurnal Teknomatika Vol 15 No 2 (2022): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v15i2.1131

Background : PLN is a state-owned company that is tasked with supplying electricity to all regions of Indonesia which certainly cannot be separated from the various obstacles experienced, to find out public sentiment on the services that have been provided, an analysis is carried out to determine public sentiment. The results of these sentiments are created in the dashboard using the Flask framework by comparing the Naive Bayes and Decision tree methods. To create a sentiment analysis dashboard for PT. PLN and make a research analysis model using a comparison of the Naive Bayes Classification and Decision tree methods. The method used in this research is Naive Bayes and Decision tree. The data obtained with a total of 40,745 Tweet data taken in the period 1 May 2022 - 4 June 2022 with the keyword "PLN". Making a dashboard that displays the results of the analysis where there is a menu to display the data and each analysis process. The use of 900 training data and 300 testing data resulted in the Naive Bayes method getting an accuracy of 83% on the training data and 80% for the Testing data, while the Decision tree method got an accuracy of 77% on the Training data and 56% on the Testing data. The analysis obtained for the method in this study also shows that the Naive Bayes method is better for classifying large amounts of data than the Decision tree. The sentiment generated by the highest number is negative, with most of the Tweets being complaints about the response to complaints and handling of damage reported by the public.

APLIKASI MONITORING DATA KETERSEDIAAN SOAL BERBASIS WEB PADA SITUS TANYA JAWAB BRAINLY Moch. Adji Prasetyo; Andika Bayu Saputra; Adri Priadana; Fajar Syahruddin
Jurnal Teknomatika Vol 14 No 1 (2021): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v14i1.1134

Brainly is a website that allows users to ask each other and answer questions related to school lessons openly to other users. On the site, you must first create an account as a questioner or answerer. Brainly harness the power Freelance to answer questions on the Brainly website. In working on the questions carried out by the Brainly Freelancer, there are often delays in updating questions at the Uniform Resource address Locator (URL) assigned to Freelancers. This results in Freelancers often being hampered in their work meet the target of working on the questions because the questions that have been answered are still not replaced with a new question. Therefore, the researcher designed and built an Application for Monitoring Data Availability of Web-Based Questions on the Tanya Site Answer on the Brainly site which aims to make it easier for Brainly Freelancers to meet their target for working on questions. This application is built using the Python programming language by utilizing the Flask framework. The results of this study state that the process contained in the application has been running smoothly as evidenced by the results of black box testing. User testing is done with Brainly Freelancers opening the application and viewing the availability of unanswered questions on the Brainly URL with a table view.

RANCANG BANGUN SISTEM PENYIRAMAN OTOMATIS MENGGUNAKAN SENSOR KELEMBABAN TANAH PADA TANAMAN SELEDRI BERBASIS NodeMCU ESP8266 Muhammad Chanafi; Landung Sudarmana; Fajar Syahruddin
Jurnal Teknomatika Vol 13 No 2 (2020): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v13i2.1136

Celery is the one of the vegeTabels that has several benefits, it can be used as a complement for cooking and it has medical function. Several factors that influence the growth of celery are soil and air conditions. These conditions must be always monitored so that the growth of celery becomes fertile. The design of automatic watering monitor system use soil’s moisture sensor, it can help the farmers and celery cultivators to increase the productivity and quality of celery cultivation. By using the NodelMCU ESP8266, which is equipped by a soil’s moisture sensor and DHT11 sensor. Thus, it can monitor the condition of soil’s moisture, air temperature, humidity, and record the data that can be stored in database and displayed on a web page by using Tabel form. This research produces a prototype system that can be able to monitor soil’s moisture conditions, air temperature and humidity in celery cultivation, it can be used to monitor soil conditions in order to maintain the humidity.

ANALISIS SENTIMEN ULASAN BANTUAN SOSIAL (BANSOS) DI TWITTER MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM) GILANG BRILIAN RACHMAT; Puji Winar Cahyo; Fajar Syahruddin
Jurnal Teknomatika Vol 15 No 1 (2022): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v15i1.1137

Background: Social assistance (bansos) is assistance provided to the community/social institutions in a non-continuous and selective manner in the form of money/goods to the community, aiming to improve the welfare of the community. The purpose of this study is to create an analytical model using the Support Vector Machine method which is used to perform Sentiment analysis regarding social assistance (bansos) on Twitter. Research Method: using the Support Vector Machine (svm) method. Based on the classification results, a lot of negative tweet data and many netizens regret that social assistance is still not evenly distributed and there is still a lot of social assistance corruption by the government itself which is marked by a lot of negative sentiments rather than positive sentiments. Conclusion: This study succeeded in testing the accuracy using the Support Vector Machine (SVM) method with a value of 84% on training data and 97% on testing data.

ANALISIS KOMPARATIF UX DESIGN PADA PLATFORM EDUKASI ONLINE Hendry Agus Setiawan; Muhammad Rifqi Ma’arif; Chanief Budi Setiawan; Fajar Syahruddin
Jurnal Teknomatika Vol 13 No 1 (2020): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v13i1.1138

User experience is the result of what the user feels and thinks when using a product or service, and makes the user experience subjective, therefore the user experience (user experience) can be tested in conjunction with other tests to get an objective assessment of the user when can be done directly with the product. This study will discuss the user experience using the User Experience Questionnaire and Focus Group Discussion methods. The process to be carried out is by using the Brainly and Quora applications obtained from the UEQ and FGD test questionnaires through interviews and data interviews from questionnaires. Based on the results of this study, the results of the analysis and comparisons with UEQ and FGD were obtained. The first test objectively used direct testing to respondents using the UEQ questionnaire which has 6 scales, namely: attractiveness, efficiency, perspective, dependability, stimulation and novelty, which are given to 11 respondents. Second, subjective testing using Focus Group Discussion for perceptions and more detailed user problems with interviews. From the second test conducted, it can be denied that the Brainly application is superior to Quora.

PEMODELAN TOPIK TERKAIT BANJIR PADA TWITTER DENGAN MENGGUNAKAN LATENT DIRICHLET ALLOCATION MUHAMMAD SUTAN IRWANSYAH; Muhammad Habibi; Fajar Syahruddin
Jurnal Teknomatika Vol 16 No 1 (2023): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v16i1.1139

In this background discusses the topic of tweet about Flooding on Twitter using the keyword "Flood". Tweet data was taken from June 1, 2021 to June 2, 2021 with the number of tweet data obtained, which was 2000 tweets. The number of tweets related to flooding has not been analyzed so that the topics contained in it are not yet known. Research . Modeling topics related to floods in Indonesia on Twitter social media with the LDA method. Research. This study uses experimental methods with several variables to test hypotheses. Then the data is processed with stages, namely web data extraction, preprocessing, feature extraction, topic modeling using latent dirichlet allocation algorithms, visualization, and analysis. Research. The results of the topic coherence stage were carried out a search for the most optimal topic from the 20 topics that had been determined at the beginning. The results of topic coherence for 20 topics concluded that for topic 10 it has a total topic value of 0.41 and has an ideal topic modeling result and is in accordance with the provisions. Conclusion : Based on the results of the discussion of topic coherence, it can be concluded that the most ideal number of topics is topic 10 because it has the highest value compared to other topics. The advice here is to be able to display or get flood information in Indonesia in real time and accurately.

Desain User Interface Dan User Experience Prototype Mobile Learning Menggunakan Metode Design Thinking Metode Design Thinking Muhamad Arabi Rizki Angkotasan; Aris Wahyu Murdiyanto; Arif Himawan; Fajar Syahruddin
Jurnal Teknomatika Vol 16 No 2 (2023): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v16i2.1254

Abstract - Do Up uses the website as online learning. users complain about the accessibility of the website with some minimal features and an unattractive UI when accessed via a smartphone will make the UX limited and will limit user interaction in using Do Up. Designing UI and UX prototypes of mobile learning at startup Do Up, using the design thinking method to solve problems and find the right solution according to the user's wishes. The author applies design thinking in this research. The author makes an illustration in the form of a Do Up mobile learning UI design that is in accordance with user needs and provides the design to Do Up stakeholders. In SEQ there are 4 scales given by users, namely 4.5, 6 and 7 scale. Most users give a 7 scale on the UI/UX design of the Do Up mobile learning prototype. On SUS which shows that the final score is 87 It means that the prototype has been well received by the users. The author has applied design thinking which consists of empathize, define, ideate, prototype and test stages in this study.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search