Article Per Year (5 Year)
p-Index From 2020 - 2025
2.345
P-Index
This Author published in this journals
All Journal Jurnal Buana Informatika Jurnal Sisfokom (Sistem Informasi dan Komputer) Jurnal Teknologi Sistem Informasi dan Aplikasi Informatika : Jurnal Informatika, Manajemen dan Komputer Jurnal Tekno Kompak Jurnal Mantik Community Engagement and Emergence Journal (CEEJ) Jurnal Abdimas Musi Charitas Eduvest - Journal of Universal Studies SmartComp Seminar Nasional Teknologi dan Multidisiplin Ilmu
Sulastri
Universitas Stikubank
Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Medicine & Pharmacology Neuroscience Nursing Public Health Social Sciences

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Data Induk Mahasiswa sebagai Prediktor Ketepatan Waktu Lulus Menggunakan Algoritma CART Klasifikasi Data Mining Arief Jananto; Sulastri Sulastri; Eko Nur Wahyudi; Sunardi Sunardi
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 10, No 1 (2021): MARCH
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v10i1.991

Abstract

Fakultas Teknologi Informasi Universitas Stikubank (UNISBANK) as one of the faculties in higher education in implementing learning activities has produced a lot of stored data and has graduated many students. The level of timeliness of graduation is important for study programs as an assessment of success. This research tries to dig up the pile of student parent data and graduation data in order to get the pass rate and graduation prediction of active students. By implementing the classification data mining technique and the CART algorithm, it is hoped that a decision tree can be used to predict the class timeliness of graduating from active students. By using the graduation data and student parent data totaling 1018 records, a decision tree model was obtained with an accuracy rate of 63% from the data testing test. Determination of split nodes using the Gini Index which breaks the dataset based on its impurity value. Tests conducted in this study show that the order of the variables in the decision tree is gender, origin school status, parental education, age at entry, city of birth, parent's occupation. The prediction with the resulting model is that 71% of active S1 Information Systems students can graduate on time and 51% for S1 Informatics Engineering students.
PERBANDINGAN ALGORITMA C4.5 DAN ALGORITMA NAIVE BAYES UNTUK KLASIFIKASI PEKERJA MIGRAN INDONESIA Saufika Sukmawati; Sulastri Sulastri; Herny Februariyanti; Arief Jananto
I N F O R M A T I K A Vol 14, No 1 (2022): MEI 2022
Publisher : STMIK DUMAI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36723/juri.v14i1.280

Abstract

Penempatan tenaga kerja Indonesia ke luar negeri merupakan salah satu upaya pemerintah dalam mewujudkan hak masyarakat untuk mendapatkan kesempatan bekerja serta meningkatkan perekonomian negara. Sebagai salah satu upaya pelindungan pekerja migran Indonesia maka dikembangkan sebuah sistem komputerisasi tenaga kerja luar negeri (SISKOTKLN) oleh Badan Nasional Penempatan dan Perlindungan TKI (BNP2TKI). Permasalahan yang menjadi kendala adalah adanya pekerja migran Indonesia (PMI) yang dipulangkan atau mendapat permasalahan ketenagakerjaan selama di luar negeri. Sehingga dibutuhkan sebuah interpretasi pada pola data penempatan PMI yang dapat digunakan sebagai prediksi negara tujuan penempatan para calon PMI yang ingin bekerja ke luar negeri.Penelitian ini akan membandingkan dua algoritma klasifikasi dalam data mining yaitu algoritma C 4.5 dan algoritma Naïve Bayes untuk mengetahui pola penempatan PMI dengan menggunakan data penempatan PMI pada wilayah BP3TKI Semarang. Percobaan dilakukan dengan data training sebanyak 1802 data dan data testing sebanyak 772 menghasilkan nilai akurasi paling tinggi bagi kedua algoritma. Algoritma C 4.5 mampu memprediksi lebih baik dengan tingkat akurasi sebesar 84.84% sedangkan pada Algoritma Naïve Bayes menghasilkan nilai akurasi sebesar 58.29%.
CLUSTERING POP SONGS BASED ON SPOTIFY DATA USING K-MEANS AND K-MEDOIDS ALGORITHM Novia Ayu Privandhani; Sulastri
Jurnal Mantik Vol. 6 No. 2 (2022): August: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v6i2.2517

Abstract

The development of music service technology is currently making it easier to listen to songs. One of them is the Spotify application. Services on music attributes are random, such as Danceability, Energy, Acousticness, Instrumentalness, Liveness, Loudness, Speechiness, Valence, and Tempo. The purpose of this study is to compare the results of clustering on the K-Means and K-Medoids algorithms using the Rstudio tools. The results of this comparison obtain the optimal number of clusters and obtain high, medium, and low cluster results. The results of the K-Means calculation are based on the average in cluster 1 the highest is Tempo with a value of 118 in cluster 2 the highest is Tempo with a value of 125, and in cluster 3 the highest is Tempo with a value of 123. The calculation of K-Medoids is based on the average in cluster 1 the highest is Tempo with a value of 129, in cluster 2 the highest is Tempo with a value of 122, and in cluster 3 the highest is Tempo with a value of 110.
Bimbingan Teknis Problematika dan Tata Kelola Usaha Koperasi Wilayah Binaan Dinas Koperasi dan UMKM Kabupaten Demak Pancawati Hardiningsih; Novita Mariana; Ceacilia Srimindarti; Sulastri Sulastri
Jurnal Abdimas Musi Charitas Vol. 5 No. 2 (2021): Jurnal Abdimas Musi Charitas Vol. 5 No. 2, Desember 2021
Publisher : Universitas katolik Musi Charitas

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (409.867 KB)

Abstract

The failure of a business carried out by novice entrepreneurs occurs because they set up a business without thinking. This happens because the preparation is not yet mature, so that it develops its business on the fly and many adjustments must be made during the course of the business because from the start the business model is not right. This happened to MSME players and cooperatives under the guidance of the Department of Cooperatives and UMKM in Demak Regency. The canvas business model is an alternative design using a business model, it will be easier to get business certainty, it is easy to see the current state of the business and how to advance it. This business model can also be used as a basis for creating a business plan. Guidance is carried out as a form of understanding the introduction of a strategy to read business conditions and potential, governance and growth up zone of internal and external potential for good and structured management of MSMEs and cooperatives for business actors. The result of this training activity is that cooperative managers and SME entrepreneurs have the knowledge, insight and are able to make a business model that fits the business plan.
Temu Kembali Berbasis Citra untuk Menemukan Kemiripan Merek Menggunakan Algoritma SIFT dan SURF Eri Zuliarso; Sulastri; Yunus Anis
Jurnal Buana Informatika Vol. 13 No. 02 (2022): Jurnal Buana Informatika, Volume 13, Nomor 2, Oktober 2022
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v13i02.6328

Abstract

Abstract. Image-Based Retrieval to Find Trademark Similarities Using SIFT and SURF Algorithms. In the world of trade in products and services, brands are essential. Every company wants to register a unique trademark for its products and services. Registration and evaluation to find the uniqueness of a trademark is challenging. Trademark image registration is one of the critical application areas of Content-BasedRetrieval (CBIR), which compares new brands with existing ones to ensure no dispute in the community. This study used SIFT and SURF algorithms to build a content-based brand image retrieval system. The research data used trademark data dispute cases that were decided in court. The features extracted from the SIFT and SURF algorithms are used to find similarities between the query image and the image in the database. Furthermore, the k-Nearest Neighbors algorithm with Euclidean distance measurements was used to sort the database images that were most similar to the query image. Experiments were conducted to find the algorithm and sequencing with the highest precision and recall values.Keywords: Trademark, SIFT, SURF, K-Nearest Neighbors, Euclidean. Abstrak. Dalam dunia perdagangan produk dan jasa, merek menjadi sangat penting. Setiap perusahaan ingin mendaftarkan merek dagang yang unik untuk produk dan jasanya. Pendaftaran dan evaluasi untuk menemukan kekhasan suatu merek dagang menjadi suatu pekerjaan yang sangat sulit. Pendaftaran citra merek dagang adalah salah satu area aplikasi penting Content Based Information Retrieval (CBIR) yang membandingkan merek baru dengan merek yang ada untuk memastikan tidak ada sengketa di masyarakat. Penelitian ini menggunakan algoritma SIFT dan SURF untuk membangun sistem temu kembali citra merek berbasis konten . Data penelitian menggunakan kasus sengketa data merek yang diputuskan di pengadilan. Fitur hasil ekstraksi algoritma SIFT dan SURF digunakan untuk mencari kemiripan citra query dan citra dalam basis data. Selanjutnya algoritma k-Nearest Neighbors dengan pengukuran jarak Euclidean digunakan untuk mengurutkan citra basis data yang paling mirip dengan citra query. Eksperimen dilakukan untuk mengetahui algoritma dan pengurutan dengan nilai presisi dan recall tertinggi. Kata Kunci: Merek, SIFT, SURF, K-Nearest Neighbors, Euclidean.
Analisis Perbandingan Klasifikasi Algoritma CART dengan Algoritma C 4.5 Pada Kasus Penderita Kanker Payudara Fitria Melani; Sulastri Sulastri
Jurnal Tekno Kompak Vol 17, No 1 (2023): Februari
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jtk.v17i1.2379

Abstract

Kanker menjadi salah satu jenis penyakit berbahaya penyebab terjadinya kematian. Dari jumlah keseluruhan kasus kanker di dunia, jenis kanker yang banyak diderita manusia dengan presentase kasus mencapai 11,7% tercatat sebagai kanker payudara. Hal ini dapat terjadi dikarenakan kanker payudara tidak didiagnosa lebih awal. Maka dari itu, jika penyakit kanker payudara dapat diidentifikasi lebih cepat, maka resiko yang mungkin terjadi dapat diminimalisir. Seiring dengan kemajuan teknologi saat ini, data – data pasien kanker payudara dapat diolah dan dimanfaatkan untuk menemukan informasi yang berguna bagi kehidupan masyarakat. Dalam melakukan pengolahan data ada beragam cara yang dapat digunakan, contohnya dengan menggunakan teknik pengolahan data mining. Data mining memiliki bermacam – macam metode yang dapat diterapkan bergantung dengan tujuan dalam penggunaannya, Klasifikasi menjadi salah satu metode yang paling sering dipergunakan dalam teknik data mining. Dalam data mining teknik klasifikasi memiliki beragam model algoritma dengan tingkat kinerja yang bervariasi. Permasalahan dalam penelitian ini berfokus tentang bagaimana cara dalam melakukan analisis perbandingan model algoritma klasifikasi pada dataset kanker payudara yang diambil dari platform Kaggle.com. Penelitian ini bertujuan membandingkan algoritma CART dan C 4.5 untuk mendapatkan hasil performa yang optimal. Implementasi pada penelitian ini menggunakan bahasa pemrograman R dengan software Rstudio. Dalam 6 kali percobaan dengan probabilitas dataset yang berbeda menghasilkan model pohon keputusan dengan nilai Accuracy, Recall, Precision dan Error rate yang berbeda. Dari percobaan yang dilakukan, didapatkan rata-rata tingkat performa algoritma CART sebesar 72 %, sedangkan algoritma C 4.5 sebesar 73%, sementara itu variabel yang paling berpengaruh dalam kematian pasien kanker payudara adalah Survival Months. Berdasarkan hasil analisis perbandingan yang telah dilakukan dapat diketahui bahwa tingkat performa dari algoritma C 4.5 lebih baik dan stabil jika dibandingkan dengan tingkat performa dari algoritma CART.
Prediction of the Development of Covid-19 Case in Indonesia Based on Google Trend Analysis Sulastri Sulastri; Eri Zuliarso; Arief Jananto
Eduvest - Journal of Universal Studies Vol. 2 No. 7 (2022): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (6167.478 KB) | DOI: 10.59188/eduvest.v2i7.530

Abstract

The global outbreak of the coronavirus disease (COVID-19) has recently hit many countries around the world. Indonesia is one of the 10 most affected countries. Search engines such as Google provide data on search activity in a population, and this data may be useful for analyzing epidemics. Leveraging data mining methods on electronic resource data can provide better insights into the COVID-19 outbreak to manage health crises in every country and around the world. This study aims to predict the incidence of COVID-19 by utilizing data from the Covid 19 Task Force and the Google Trends website. Linear regression and long-term memory (LSTM) models were used to estimate the number of positive COVID-19 cases.
Klasifikasi Hasil Cardiotocography (CTG) Ibu Hamil untuk Memprediksi Kesehatan Janin Aprindita Dwi Monica; Sulastri Sulastri
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 6 No. 3 (2023): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

A future mother must want the fetus in her womb to be in a healthy condition. A healthy fetus is one that has optimal growth and has sufficient nutrients at the time it is in the womb. The risk of miscarriage and maternal and fetal deaths can be reduced by monitoring fetal health and staying alert when necessary. CTG is carried out in cases where there is a risk of pregnancy and a relatively worrying birth. It will be easier to make further decisions to reduce health risks at birth if the CTG examination shows a good fetal condition. The study aims to study the comparison of different classification algorithms used in determining the exact values of the fetal health datasets used through Knowledge Discovery in Databases (KDD). The researchers used a data collection of 2126 data points from Kaggle’s website that had 22 variables divided into three categories Normal, Suspect, and Pathological. Prolonged decelerations, abnormal short-term variability, and the percentage of time with abnormally long-term variability are the most significant variables. The results of the study were obtained by dividing the data set into training and trial data, which were then divided into three trials. The results showed that the KNN algorithm had the best accuracy value of 91% in the second trial, the SVM algorithm had the most accurate value of 87% in the first and second trials, the Logistic Regression algorithm had the Best Accuracy Value of 84% in the Second Trial, the Naive Bayes algorithm had the Best Accuracy value of 84%, and the Decision Tree Algorithm had 89% in the First and Second Trials.
Analisis Sentimen Aplikasi Tiktok dengan Metode Support Vector Machine (SVM), Logistic Regression dan Naïve Bayes Isna Riaandita Ainunnisa; Sulastri Sulastri
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 6 No. 3 (2023): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The tiktok application is a platform application specifically for photos, music and videos that many people like, from children, teenagers, and even adults. Tiktok is in great demand because there is a lot of interesting and useful content. Currently, reviews on the TikTok application have reached 16 million reviews with a rating of 4.4 on the Google Play Store, which has reached 500 million downloads. Many users also have many positive and negative reviews on the TikTok application. Because of this, the researcher conducted a sentiment analysis which was used to analyze user opinions by grouping positive, neutral or negative reviews. The data taken in this study was 2100, using the Python programming language. Then the preprocessing stage is carried out, namely case folding, tokenizing, filtering and stemming. The methods used in this study are the Support Vector Machine (SVM) method, Logistic Regression, and Naïve Bayes. The results of applying the 3 sentiment analysis methods are the Sopport Vector Machine method producing an accuracy value of 82%, Precision 82%, Recall 81% and F1 score 81%. The Naïve Bayes method produces an accuracy value of 79%, Precision 81%, Recall 77% and F1 score 78%, Logisstic Regression Method an accuracy value of 84%, precision 83%, recall 82%, F1 score 83%.
Perbandingan Algoritma K-Means dan K-Median Clustering Terhadap Nilai Ujian Nasional SMP di Jawa Tengah Nur aini fadhila; Sulastri Sulastri
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 11, No 4 (2022): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v11i4.3915

Abstract

Ujian Nasional (UN) merupakan kegiatan yang diselenggarakan oleh Pemerintah untuk mengukur kemampuan siswa dalam bersaing secara nasional sekaligus untuk mengukur mutu dan kualitas pendidikan sekolah. Tujuan dari penelitian ini untuk mengelompokkan mutu dan kualitas pendidikan di wilayah Jawa Tengah untuk memudahkan mengetahui perbedaan. Penelitian ini menggunakan metode clustering dengan algoritma k-means dan algoritma k-median. Proses kalkulasi menggunakan software RStudio. Data yang digunakan dalam penelitian ini yaitu data Nilai Ujian Nasional di Jawa Tengah yang diperoleh dari situs resmi Pusat Penilaian Pendidikan dan Kebudayaan Kementerian Pendidikan dan Kebudayaan Republik Indonesia sebanyak 1769 sekolah. Hasil dari penelitian kedua algoritma menggunakan metode siluet diperoleh jumlah kluster sebanyak 5 cluster dengan kategori sangat baik, cukup baik, buruk, dan sangat buruk. Perbedaan hasil dari kedua algoritma terletak pada jumlah kluster, pusat kluster, dan nilai rata – rata pada masing – masing kluster
Co-Authors Aprindita Dwi Monica Arief Jananto Ceacilia Srimindarti Eko Nur Wahyudi Eri Zuliarso Felix Andreas Sutanto Fitria Melani Heribertus Yulianton Herny Februariyanti Isna Riaandita Ainunnisa Kristophorus Hadionod Novia Ayu Privandhani Novita Mariana Nur aini fadhila Pancawati Hardiningsih Rina Candra Noor Santi Saufika Sukmawati Sri Eniyati Sunardi Sunardi Yohanes Suhari Yunus Anis, Yunus