Articles
<![CDATA[HYBRIDIZATION OF THE NAIVE BAYES CLASSIFICATION METHOD IN THE FRESHWATER FISH SEED SELLER CLASSIFICATION MODEL ]]>
<![CDATA[M Hafidz Ariansyah]]>;
<![CDATA[Esmi Nur Fitri]]>;
<![CDATA[Sri Winarno]]>;
<![CDATA[Asih Rohmani]]>;
<![CDATA[Fikri Budiman]]>;
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Edi Sugiarto]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 4 No. 2 (2023): JUTIF Volume 4, Number 2, April 2023 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2023.4.2.715
<![CDATA[Freshwater fish seed sellers play several roles in the supply chain process in the freshwater fish farming business. The role of the seller of freshwater fish seeds in this process is to distribute fish seeds which are one of the upstream sources in the supply chain process. Freshwater fish cultivators must select competent freshwater fish seed sellers so the supply chain process can run well. A large number of freshwater fish seed sellers in the market remind freshwater fish cultivators to choose the quality of the freshwater fish seed seller in terms of seed quality, low prices, shipping that can reach many areas, ergonomic packaging, and others. This study proposes Hybrid Naïve Bayes Classifiers (HNBCs) as a machine learning method for classification. This study aimed to compare the seed seller classification method in which the appropriate pattern of seed seller was identified by hybridization of Naïve Bayes Classifiers (NBCs), and then the researchers conducted performance appraisal and evaluation. The results are beneficial for freshwater fish cultivators and researchers which will enable them to formulate their plans according to the predicted results. The proposed method has produced significant results by achieving a training data accuracy of 82.61% and the testing data accuracy of 73.91%.]]>
<![CDATA[DECISION TREE SIMPLIFICATION THROUGH FEATURE SELECTION APPROACH IN SELECTING FISH FEED SELLERS ]]>
<![CDATA[Esmi Nur Fitri]]>;
<![CDATA[Sri Winarno]]>;
<![CDATA[Fikri Budiman]]>;
<![CDATA[Asih Rohmani]]>;
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Edi Sugiarto]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 4 No. 2 (2023): JUTIF Volume 4, Number 2, April 2023 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2023.4.2.747
<![CDATA[Feed is a crucial variable because it can determine the success of fish farming. Breeders can use two types of artificial feed, namely alternative feed and pellets. Many cultivators need pellets as the main consumption for the fish they are cultivating because the pellets contain a composition that has been adjusted to their needs based on the type and age of the fish. However, currently, cultivators are facing a problem, namely the high price of fish pellets on the market. Therefore, an analysis of the classification of the selection of fish feed sellers is needed that is adjusted to several criteria like the number of types of feed, price, order, delivery, and availability of discounts. This study conducted a classification analysis of simplification of characteristics in selecting fish feed sellers in Kendal Regency that would then be compared with a model without feature selection by utilizing the Decision Tree C4.5 method. The results of this study are the decision tree with the best performance where C4.5 with the application of the selected feature has an accuracy value of 92%, while C4.5 without the selection feature has an accuracy of 86.8%. The results of this study indicate that the C4.5 method with the application of selection features is better than C4.5 without selection features so that it can be applied to the selection of freshwater fish feed sellers in Kendal Regency.]]>
<![CDATA[Seleksi Fitur dan Perbandingan Algoritma Klasifikasi untuk Prediksi Kelulusan Mahasiswa ]]>
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Abu Salam]]>;
<![CDATA[Farda Alan Ma'ruf]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 18, No 2 (2022) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (650.804 KB)
|
DOI: 10.17529/jre.v18i2.24047
<![CDATA[Students are a major part of the life cycle of a university. The number of students graduating from a university often has a small ratio when compared to the number of students obtained in the same academic year. This small student graduation rate can be caused by several aspects, such as the many student activities accompanied by economic aspects, as well as other aspects. This makes it mandatory for a university to have a model that can take into account whether the student can graduate on time or not. One of the main factors that determine the reputation of a university is student graduation on time. The higher the level of new students at a university, with the same ratio, there must also be students who graduate on time. An increase in the number of student data and academic data occurs if many students do not graduate on time from all registered students. So that it will affect the image and reputation of the university which can later threaten the accreditation value of the university. To overcome this, we need a model that can predict student graduation so that it can be used as policy making later. The purpose of this study is to propose the best classification model by comparing the highest level of accuracy of several classification algorithms including Naïve Bayes, Random Forest, Decision Tree, K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) to predict student graduation. In addition, the feature selection process is also used before the classification process to optimize the model. The use of feature selection in this model with the best features using 12 regular attribute features and 1 attribute as a label. It was found that the classification model using the Random Forest algorithm was chosen, with the highest accuracy value reaching 77.35% better than other algorithms.]]>
<![CDATA[PERFORMANCE OF K-MEANS CLUSTERING AND KNN CLASSIFIER IN FISH FEED SELLER DETERMINATION MODELS ]]>
<![CDATA[Esmi Nur Fitri]]>;
<![CDATA[M. Hafidz Ariansyah]]>;
<![CDATA[Sri Winarno]]>;
<![CDATA[Fikri Budiman]]>;
<![CDATA[Asih Rohmani]]>;
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Edi Sugiarto]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 4 No. 3 (2023): JUTIF Volume 4, Number 3, June 2023 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2023.4.3.725
<![CDATA[Feed is a crucial variable because it can determine the success of fish farming. Farmers can use two types of artificial feed, namely alternative feed and pellets. Many cultivators need pellets as the main food for the fish they are cultivating because the pellets contain a composition that has been adjusted to their needs based on the type and age of the fish. However, currently, cultivators are facing problem, namely the high price of fish pellets on the market. Therefore, an analysis of the classification of the selection of fish feed sellers is needed according to several criteria like the number of types of feed, price, order, delivery, payment, availability of discounts, and the number of assessments. This study conducted a predictive analysis to determine the criteria for selecting fish feed sellers in Kendal Regency by utilizing the K-Means Clustering and KNN Classifier methods in the classification method. This research aims to compare the fish feed seller classification method where the pattern of fish feed seller is identified by K-Means Clustering and KNN Classifier, and then the researcher conducts performance appraisal and evaluation. The results of this study are decision-making patterns to help formulate strategies for cultivators and other interested parties. For verifying the method used, measurements were made to obtain an accuracy value where K-Means was 98.6% and KNN was 86.7%.The results of this study indicate that the K-Means Clustering and KNN Classifier methods can classify the selection of freshwater fish feed sellers in Kendal Regency.]]>
<![CDATA[IMPLEMENTATION OF THE RANDOM FOREST ALGORITHM IN CLASSIFYING THE ACCURACY OF GRADUATION TIME FOR COMPUTER ENGINEERING STUDENTS AT DIAN NUSWANTORO UNIVERSITY ]]>
<![CDATA[Devi Ayu Rachmawati]]>;
<![CDATA[Nitho Alif Ibadurrahman]]>;
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Novi Hendriyanto]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 4 No. 3 (2023): JUTIF Volume 4, Number 3, June 2023 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2023.4.3.920
<![CDATA[To ensure the existence of a university remains intact, one way that can be done is by optimizing the performance of the students so that they can graduate on time. A high percentage of on-time graduation will result in a good assessment of the accreditation of the department in the university. However, there are many factors that affect the graduation rate, such as the student's academic performance, extracurricular activities, and other factors. The data of graduation of students in the Computer Science program at the Faculty of Computer Science, Dian Nuswantoro University, for the academic years 2008-2017 is the object of this study. The objective of this research is to create the best classification model using the Random Forest algorithm to predict the accuracy of the graduation time of students, which will be useful for policy making in the future. The results of the classification using this algorithm received an accuracy of 93% for the training data and 91% for the test data.]]>
<![CDATA[Seleksi Fitur dan Perbandingan Algoritma Klasifikasi untuk Prediksi Kelulusan Mahasiswa ]]>
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Abu Salam]]>;
<![CDATA[Farda Alan Ma'ruf]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 18, No 2 (2022) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.17529/jre.v18i2.24047
<![CDATA[Students are a major part of the life cycle of a university. The number of students graduating from a university often has a small ratio when compared to the number of students obtained in the same academic year. This small student graduation rate can be caused by several aspects, such as the many student activities accompanied by economic aspects, as well as other aspects. This makes it mandatory for a university to have a model that can take into account whether the student can graduate on time or not. One of the main factors that determine the reputation of a university is student graduation on time. The higher the level of new students at a university, with the same ratio, there must also be students who graduate on time. An increase in the number of student data and academic data occurs if many students do not graduate on time from all registered students. So that it will affect the image and reputation of the university which can later threaten the accreditation value of the university. To overcome this, we need a model that can predict student graduation so that it can be used as policy making later. The purpose of this study is to propose the best classification model by comparing the highest level of accuracy of several classification algorithms including Naïve Bayes, Random Forest, Decision Tree, K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) to predict student graduation. In addition, the feature selection process is also used before the classification process to optimize the model. The use of feature selection in this model with the best features using 12 regular attribute features and 1 attribute as a label. It was found that the classification model using the Random Forest algorithm was chosen, with the highest accuracy value reaching 77.35% better than other algorithms.]]>
<![CDATA[Pengembangan Chatbot Kesehatan Mental Menggunakan Algoritma Long Short-Term Memory ]]>
<![CDATA[Fajarudin Zakariya]]>;
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Sri Winarno]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v8i1.7177
<![CDATA[Mental health has now become a crucial aspect of contemporary society, especially in Indonesia. This reflects the emotional, psychological, and social well-being of individuals, encompassing the ability to cope with stress in daily life. A comprehensive understanding of mental health has become highly important for the community to prevent the occurrence of mental health problems or disorders. The objective of this research is to design a chatbot as an information and solution hub for maintaining mental health, with the hope that the development of this chatbot can help reduce the risk of mental health-related issues. In the development process of this chatbot, the author applies the AI Project Cycle and utilizes a deep learning approach for the chatbot model. The development involves the Flask platform, and to achieve high accuracy, the model employs the Long Short-Term Memory (LSTM) architecturea type of recurrent neural network (RNN) specifically designed to handle long-term dependency issues common in complex mental health contexts. LSTM enables the model to store and access long-term contextual information, which can be highly beneficial in providing accurate solutions and understanding emotional condition changes. The trained LSTM model demonstrates an accuracy of 93%, validation accuracy of 82%, a loss of 0.3%, and validation loss of 1.6% after 200 epochs. Therefore, it can be concluded that using the LSTM algorithm for the chatbot model in this development is quite effective.]]>
<![CDATA[Ensemble Klasifikasi Penyakit Tuberculosis Pada Hasil Pengobatan Menggunakan Metode Hybrid K-Nearest Neighbor (K-NN), Decision Tree dan Support Vector Machine (SVM) ]]>
<![CDATA[Alya Nurfaiza Azzahra]]>;
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Ardytha Luthfiarta]]>;
<![CDATA[Mufida Rahayu]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v8i1.7021
<![CDATA[Tuberculosis (TB) is an infectious disease with the highest cause of death in the world. This disease can be transmitted through the air and attacks the pulmonary respiratory system. The increase in TB cases from year to year is due to little information about the treatment of this disease. This requires the process of diagnosing and treating TB requiring accurate data analysis. From these problems, classification of tuberculosis disease is needed to improve better treatment results. In this study, experiments were used with the Hybrid model classification algorithm with a method that combines three approaches, namely K-Nearest Neighbor (K-NN), Decision Tree, Support Vector Machine (SVM) to classify treatment results using the Ensemble classification method and aims to combine each method in order to create a stronger Ensemble model and increase accuracy in treatment results, using data from the Semarang City Health Service or what is called Tuberculosis Information System (SITB) data in 2020-2023 with 80% training data and test data 20%. Based on the results of testing and analysis using the confusion matrix, the highest accuracy value was obtained at 78.55% using K-Fold Cross validation, namely k equals 7 and the Ensemble model obtained high results for treatment outcomes.]]>
<![CDATA[The Development of Javanese Glossary Website as a Form of Language Maintenance and Revitalization ]]>
<![CDATA[Muljono Muljono]]>;
<![CDATA[Junta Zeniarja]]>;
<![CDATA[Nur Rokhman]]>;
<![CDATA[Raden Arief Nugroho]]>;
<![CDATA[Valentina Widya Suryaningtyas]]>;
<![CDATA[Bayu Aryanto]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 20, No 2 (2024) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.17529/jre.v20i2.34638
<![CDATA[As a vital component of cultural identity, language is under pressure as a result of globalization. This article discusses the creation of a website that provides a dictionary of Javanese phrases to help preserve and revitalize the language. In this study, we collect, categorize, and display Javanese words on electronic resources. In addition, the system usability scale (SUS) was used to conduct usability tests on the investigated websites to determine how user-friendly they actually were. Gathering terms from multiple sources, categorizing them, and developing a user-friendly interface with a search bar are all steps in the process of making a website. Users from all walks of life fill out the SUS questionnaire as part of the usability testing process. The test results reveal how well the website satisfies its users' requirements. Creating a database of Javanese words online and putting it through the SUS test is a great example of how technology can be used to help preserve a language and its heritage. It is believed that by taking this step, more people will become familiar with the Javanese language and become invested in its continued existence in the modern world. The usability testing results demonstrate that the development strategy and interface design effectively fostered a positive user experience. High scores on the SUS questionnaire, with an average rating of 80.25, indicate that users find the website satisfactory and user-friendly.]]>
<![CDATA[IMPLEMENTASI ALGORITMA APRIORI UNTUK ANALISIS POLA PEMBELIAN KONSUMEN PADA TOSERBA YUSUF SEMARANG ]]>
<![CDATA[Dianti, Reza Nur]]>;
<![CDATA[Zeniarja, Junta]]>
<![CDATA[ JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 2 (2024) ]]>
Publisher : <![CDATA[STKIP PGRI Tulungagung ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.29100/jipi.v9i2.5421
<![CDATA[Pada aktivitas jual beli barang atau jasa, data transaksi selalu tercatat sebagai bukti pembelian, namun data yang ada tidak dimanfaatkan secara optimal oleh Toserba Yusuf. Data tersebut memiliki potensi untuk diolah guna memberikan informasi bermanfaat yang dapat meningkatkan nilai penjualan bagi para pelaku bisnis. Salah satu tantangan yang sering dihadapi oleh Toserba Yusuf adalah kehabisan stok produk tertentu yang dibutuhkan oleh konsumen. Untuk mengatasi hal ini, biasanya diperlukan waktu yang cukup lama karena toko harus mendata barang yang habis terlebih dahulu setelah itu baru melakukan restok barang untuk menyediakan kembali persediaan. Untuk mengatasi permasalahan yang ada, penelitian ini mengembangkan aplikasi Data Mining membantu dalam mengidentifikasi kebiasaan pembelian konsumen. Tujuan utama penelitian adalah mencari informasi mengenai produk yang paling sering terjual bersamaan. Hal ini bertujuan untuk memungkinkan pemilik toko untuk mengantisipasi kebutuhan stok produk di masa mendatang. Penelitian ini menggunakan algoritma apriori untuk memudahkan dalam mengolah data, selain itu penelitian ini memanfaatkan association rule untuk menemukan kombinasi antar item dalam dataset yang memenuhi nilai support dan confidence yang telah ditetapkan sebelumnya. Hasil penelitian ini menunjukkan bahwa kombinasi pembelian dan penjualan 2 itemset barang berbeda secara bersamaan. Hasil pengujian yang memperhitungkan keakuratan dengan menggunakan lift ratio sebagai persentase menghasilkan beberapa aturan. Salah satunya adalah jika pelanggan membeli kentang goreng dengan lift ratio yang tinggi, maka ada kemungkinan bahwa pelanggan juga akan membeli telur dengan tingkat confidence sebesar 0,19, support 0,039, dan lift ratio 1,308. Hal ini membuktikan bahwa algoritma apriori dapat membantu dalam menganalisa pola pembelian konsumen.]]>
