Paradigma
The Paradigma Journal is intended as a medium for scientific studies of research, thought and analysis-critical issues on Computer Science, Information Systems, and Information Technology, both nationally and internationally. The scientific article refers to theoretical reviews and empirical studies of related sciences, which can be accounted for and disseminated nationally and internationally. Paradigma Journal accepts scientific articles research at Expert Systems, Information Systems, Web Programming, Mobile Programming, Games Programming, Data Mining, and Decision Support Systems.
Articles
90 Documents
<![CDATA[Grouping Data in Predicting Infant Mortality Using K-Means and Decision Tree ]]>
<![CDATA[Ridwansyah Ridwansyah]]>;
<![CDATA[Verry Riyanto]]>;
<![CDATA[Abdul Hamid]]>;
<![CDATA[Sri Rahayu]]>;
<![CDATA[Jajang Jaya Purnama]]>
<![CDATA[ Paradigma Vol. 24 No. 2 (2022): September 2022 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (391.355 KB)
|
DOI: 10.31294/paradigma.v24i2.1399
<![CDATA[Death is something that we cannot avoid where, when and how death comes. The high infant mortality rate is the main thing and the Indonesian government must prioritize, one of the government's efforts to reduce infant mortality is by conducting a surveillance program, namely PWS KIA where the program is uniting the health of mothers and babies in the local area, basically there are several infant deaths that have causes from the time of pregnancy, accidents, disasters, diseases or because it is destiny from God, for that research is carried out in classifying infant mortality data. For grouping infant mortality data, a K-Means method is needed to analyze data by carrying out a data modeling process without supervision or also known as unsupervised learning. In showing the centroid in the early stages of the k-means algorithm, it is very influential on the results of the cluster carried out on the infant mortality dataset. taken from data.go.id with different centroid results. The results of the clustering model pattern that can be trusted by the government or the Health department to prevent infant mortality. From the clustering results, four labels are tested again using the decision tree algorithm.]]>
<![CDATA[Aspect-Based Sentiment Analysis on Indonesian Presidential Election Using Deep Learning ]]>
<![CDATA[Fadillah Said]]>;
<![CDATA[Lindung Parningotan Manik]]>
<![CDATA[ Paradigma Vol. 24 No. 2 (2022): September 2022 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (206.706 KB)
|
DOI: 10.31294/paradigma.v24i2.1415
<![CDATA[The 2019 presidential election is a presidential election that has been a hot topic of discussion for some time, and people have even talked about this topic since 2018 on the internet. In predicting the winner of the presidential election, previous research has conducted research on the aspect-based sentiment analysis (ABSA) dataset of the 2019 presidential election using machine learning algorithms such as the Support Vector Machine (SVM), Naive Bayes (NB), and K-Nearest Neighbors (KNN) and produces good accuracy. This study proposes a deep learning method using the BERT (Bidirectional Encoder Representation Form Transformers) and RoBERTa (A Robustly Optimized BERT Pretraining Approach) models. The results of this study indicate that the indobenchmark BERT and RoBERTa base-Indonesian single label classification models on target features with preprocessing produce the best accuracy of 98.02%. The indolem BERT model and the indobenchmark single label classification on the target feature without preprocessing produce the best accuracy of 98.02%. The BERT indobenchmark single label classification model on aspect features with preprocessing produces the best accuracy of 74.26%. The BERT indolem single label classification model on aspect features without preprocessing produces the best accuracy of 74.26%. The BERT indolem single label classification model on the sentiment feature with preprocessing produces the best accuracy of 93.07%. The BERT indolem single label classification model on the sentiment feature without preprocessing produces the best accuracy of 94.06%. The BERT indobenchmark multi label classification model with preprocessing produces the best accuracy of 98.66%. The BERT indobenchmark multi label classification model without preprocessing produces the best accuracy of 98.66%.]]>
<![CDATA[Visitor Counter and Information Viewer at Photo Exhibitions using Embedded Systems and Web Services ]]>
<![CDATA[I Made Bhaskara Gautama]]>;
<![CDATA[I Gusti Ngurah Wikranta Arsa]]>;
<![CDATA[Ni Putu Virgi Savita]]>
<![CDATA[ Paradigma Vol. 24 No. 2 (2022): September 2022 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (523.193 KB)
|
DOI: 10.31294/paradigma.v24i2.1430
<![CDATA[Photography is the art and production of images and light on a film or sensitized surface. It becomes a popular art as a hobby or for a living. Thus, many photography events are held such as photo exhibitions. The exhibition aims to show the work of art to the public or to promote the work so it can be profitable for the artist. One of the problems that arise from this photo exhibition is the need for the owner of the work or the event organizer to find out how many people have visited/seen a photo earnestly. This can be an indicator of public interest in the artwork. Counting manually is less effective to do considering the number of photos on display. Therefore, we need a tool that can be mass-produced at a relatively low cost to detect visitors to the photo site. The tool is based on a microcontroller (embedded system) which also uses the IoT concept. The tool is made using a NodeMCU microcontroller and PIR sensor. Based on the test results, the tool can count visitors with an accuracy rate of 82% and successfully displays information when visitors are detected and hides information when visitors leave the detection area.]]>
<![CDATA[Determining the Best Answers for Balinese Language Problems using Latent Semantic Analysis ]]>
<![CDATA[Made Agus Putra Subali]]>;
<![CDATA[I Ketut Putu Suniantara]]>
<![CDATA[ Paradigma Vol. 24 No. 2 (2022): September 2022 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (277.645 KB)
|
DOI: 10.31294/paradigma.v24i2.1437
<![CDATA[In Balinese, descriptions or essays are formed in an interrogative format using question words such as “akuda”, “apa”, “dija”, “kenken”, “kuda”, dan “nyen”. The assessment process on description questions tends to be more difficult and complex than multiple choice questions, this is because the description questions are described in sentence form. The solution to facilitate the assessment process on description questions can be done using automated essay scoring. Based on the results of previous studies, the Latent Semantic Analysis (LSA) method provides a better level of accuracy, because the LSA method uses the Singular Value Decomposition (SVD) method to obtain a new pattern of relationships between terms and reference terms. The data used in this study are five questions and their answer keys and there are five candidate answers for each question in Balinese. Based on the tests that have been carried out, the method used obtained an overall average accuracy of 70.26%, this shows that the LSA method can be used well in the assessment process or automatic essay assessment.]]>
<![CDATA[Penerapan Naïve Bayes untuk Klasifikasi Kriteria Air Layak Minum dengan Metode CRISP-DM ]]>
<![CDATA[Ibnu Alfitra Salam]]>;
<![CDATA[Katon Wahyudi Putra]]>;
<![CDATA[Sisca Yuliatina]]>;
<![CDATA[Betha Nurina Sari]]>
<![CDATA[ Paradigma Vol. 25 No. 1 (2023): March 2023 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31294/p.v25i1.1754
<![CDATA[With water, living things can do various things easily. The adequacy of water is also important in maintaining human health. Water can be said to be feasible if its content is in accordance with the feasible criteria. From the dataset obtained regarding the feasibility of water for this study, it will calculate the accuracy value obtained using the Naive Bayes algorithm. To simplify the process of processing research data this time using the CRISP-DM methodology which is a stage for data mining. The study uses two tools, namely Rapidminer and Google Collab to compare their accuracy values. By using the two tools in implementing the Naive Bayes algorithm on a potable water quality dataset, an accuracy of 62.8% is obtained. This value is accurate enough to predict the quality of drinking water.]]>
<![CDATA[Application of C4.5 Classification in Improving Recitation Fluency in Students ]]>
<![CDATA[Sisca Yuliantina]]>;
<![CDATA[Betha Nurina Sari]]>
<![CDATA[ Paradigma Vol. 25 No. 1 (2023): March 2023 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31294/p.v25i1.1775
<![CDATA[Fluency in reciting the Koran is learning the recitation of the Qur'an in a tartil way. Based on the observations of researchers, the learning of tajwid in recitation and at school has not been effective so far. Because of this, both teachers and students at recitation or at school need improvement by finding out what can increase fluency in reciting the Koran and what has the most influence on improving fluency. So this study aims to improve the fluency of the Koran in students. The research method used is the Decision Tree data mining classification method with the C4.5 algorithm. The results of data processing with the C4.5 algorithm using the Rapidminer tools are attribute C1(fluency) being the most influential attribute for increasing students' reading fluency and performance data obtained with an accuracy of 83,33%.]]>
<![CDATA[Comparison of SAW and Topsis Methods in The Selection of The Best Online Bike Shops ]]>
<![CDATA[Pri Camelia Marissa Jannah]]>;
<![CDATA[Rani Irma Handayani]]>;
<![CDATA[F. Lia Dwi Cahyani]]>
<![CDATA[ Paradigma Vol. 25 No. 1 (2023): March 2023 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31294/p.v25i1.1314
<![CDATA[The need for information technology in this pandemic era is greatly increasing. Many people meet their needs by doing buying and selling transactions as if they were online. Through a decision support system using the SAW (Simple Additive Weighting) and TOPSIS (Technique for Others Reference by Similarity to Ideal Solution), methods can provide the best decision in choosing the best online bicycle store site. On the result of the calculation, it is obtained that the results of the two are appropriate. The SAW and TOPSIS methods produced the same ranking, namely the Rodalink site got the highest ranking with a value of 1.019 on the SAW method of 0.833 on the TOPSIS method followed by serbasepeda, united, and cycles. The results of comparing calculations using these 2 methods are considered the SAW method is the most relevant method.]]>
<![CDATA[Prediction of Black Soldier Fly Larva Sales and Production Using Linear Regression Method ]]>
<![CDATA[I Made Arya Budhi Saputra]]>;
<![CDATA[Kadek Ardi Juniawan]]>;
<![CDATA[Ni Nyoman Utami Januhari]]>;
<![CDATA[I Made Bhaskara Gautama]]>;
<![CDATA[Ni Made Wirastika Sari]]>;
<![CDATA[I Gusti Ngurah Wikranta Arsa]]>;
<![CDATA[IGKG. Puritan Wijaya]]>
<![CDATA[ Paradigma Vol. 25 No. 1 (2023): March 2023 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31294/p.v25i1.1512
<![CDATA[The waste problem is a problem that plagues the world. Various programs and methods have been carried out in processing waste. Until now, Bali has become the area with the most waste production in Indonesia, where every day the waste produced reaches 4,281 tons or in other words 1.5 million tons per year. In early 2021, a campaign on the separation of organic and non-organic waste has been initiated in several districts/cities in the province of Bali. The next problem is that people do not know how to process organic waste other than being compost for plants. Black Soldier Fly (BSF) or black soldier fly is an order of diptera whose physical characteristics are similar to wasps. BSF itself has an average life cycle from egg to adult of 45 days. Where the main consumption of BSF itself is organic waste. In Pelaga village, Petang sub-district, Badung district, there is an effort to breed BSF. Where in this effort, it can produce no less than 100 kg of BSF larvae within 15-20 days. The problems encountered by these entrepreneurs are often difficult to predict the amount of BSF larvae production, because around the area there are quite a lot of catfish and chicken farmers who need BSF larvae as feed. The use of linear regression method can overcome these problems. The results obtained between the application of this method include the accuracy value which reaches 62.5% for prediction of sales and 32.5% for prediction of production.]]>
<![CDATA[Implementation of Simple Additive Weighting Method To Analyze The Selection of The Laptop ]]>
<![CDATA[Luhut Frenando]]>;
<![CDATA[Nury Handayani]]>;
<![CDATA[Evi Niastuti]]>;
<![CDATA[Susy Rosyida]]>
<![CDATA[ Paradigma Vol. 25 No. 1 (2023): March 2023 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31294/p.v25i1.1577
<![CDATA[The existence of the laptop currently has been a basic need to help in completing work or daily activities. the many options of laptop types with different specifications are currently, creating some problems such as difficulty or confused when determining the laptop options to purchase. These problems are also found at the office of Satker PJN 1 Banten which is still done by considering only on laptop trends or only from specific advantages but not according to the existing needs and budget. The purpose of this research is to provide solutions to the problems by making a decision-making information system in analyzing the selection of the laptop at the office of Satker PJN 1 Banten. The proposed method is implementing the Simple Additive Weighting (SAW) method implemented by using a web-based application for the decision-making system in the selection of the laptop. The Simple Additive Weighting (SAW) method is a method used to produce the best alternative ranking value from some alternatives based on the weight of each criterion obtained from the result of the questionnaire data processing questionnaire. the results obtained from the selection of the laptop using the Simple Additive Weighting (SAW) method based on this web-based that can analyze the selection of the laptop objectively according to the ranking results of the calculations of the saw method, so the selection of the laptop is objective.]]>
<![CDATA[Quality Analysis of the BNI Mobile Banking Application for Customers Using Webqual 4.0 ]]>
<![CDATA[Yuni Eka Achyani]]>;
<![CDATA[Yehezkiel Hardy Saputra]]>
<![CDATA[ Paradigma Vol. 25 No. 1 (2023): March 2023 Period ]]>
Publisher : <![CDATA[LPPM Universitas Bina Sarana Informatika ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31294/p.v25i1.1723
<![CDATA[PT. Bank Negara Indonesia (Persero) Tbk. is a bank institution owned by the government of the Republic of Indonesia or better known as a state-owned company. In today's digital era, online services are the choice of most customers. This is because all types of banking transactions can be done easily. With the inclusion of smartphones as the devices most needed by the public at this time, BNI offers a mobile banking service called BNI Mobile Banking. This study will measure the quality of the BNI Mobile Banking application through the Webqual dimensions (usability, information quality, interaction quality) and the variable user satisfaction, namely BNI KCU Bogor customers. The data collection method uses primary data in the form of questionnaires distributed to 100 respondents. Data processing is done using SPSS. Based on data processing, it can be seen that the user's perception of ease of use, quality of information, quality of interaction is included in the very good category. Based on the results of the study, it was found that there was only an effect of usability and information quality and no effect of interaction quality on user satisfaction for BNI KCU Bogor customers. From the research results, it can be seen that the information quality variable contributes the largest contribution, namely 94.75% of the other variables]]>
