Claim Missing Document
Check
Articles

IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBOUR UNTUK PREDIKSI KETEPATAN KELULUSAN Manarul Hidayat; Ahmad Faqih; Tati Suprapti
JURSIMA (Jurnal Sistem Informasi dan Manajemen) Vol 10 No 2 (2022): Jursima Vol. 10 No. 2, Agustus Tahun 2022
Publisher : INSTITUT TEKNOLOGI DAN BISNIS INDOBARU NASIONAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47024/js.v10i2.420

Abstract

In an education system, students are an important asset of a college and therefore, it is important to pay attention to the percentage of students who graduate on time. However, there is an imbalance between the inputs and outputs of the completed students. Students who enroll in large numbers, but students who graduate on time compared to those who are late according to regulations are fewer. In this study, the author aims to apply the K-NN method using cross validation to predict student graduation rates at STMIK IKMI. The results of this study are in the form of models and evaluations of student graduation predictions, whether they graduate on time or not on time. Based on the results of the design, implementation, testing using the RapidMiner program for predicting student graduation using the k-NN method with Cross Validation resulting in an accuracy of 70.28%, an error of 29.78%, and AUC of 0.739 Keywords: Graduation, Student, K-NN, Cross Validation
KOMPARASI METODE KLASIFIKASI DATA MINING UNTUK PREDIKSI PENYAKIT STROKE Fitri Adha Hariyati Airi; Tati Suprapti; Agus Bahtiar
E-Link: Jurnal Teknik Elektro dan Informatika Vol 18 No 1 (2023): Mei 2023
Publisher : Universitas Muhammadiyah Gresik

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30587/e-link.v18i1.5271

Abstract

Stroke merupakan penyakit dengan kondisi bahaya dan menjadi penyebab kematian nomor tiga setelah penyakit jantung koroner dan kanker. Kurangnya pengetahuan menjadikan masyarakat tidak menyadari tanda-tanda yang mungkin sudah terlihat. Apabila masyarakat mendapatkan pengenalan tentang penyakit stroke diharapkan dapat mengurangi dampak paling parah yaitu kematian. Oleh karena itu perlu dilakukan sebuah prediksi menggunakan metode klasifikasi. Hasil prediksi yang akurat dapat memudahkan para praktisi kesehatan dalam mengambil keputusan yang tepat. Data yang diambil merupakan data bersifat public dari situs kaggle. Pada penelitian ini Orange digunakan sebagai perangkat lunak. Penelitian ini melakukan sebuah perbandingan algoritma Naive Bayes, K-Nearest Neighbor dan Random Forest. Hasil yang diperoleh pada penelitian ini untuk algoritma Naive Bayes sebesar 71.9% accuracy, 71.7% precision, 71.9% recall. Sedangkan untuk algoritma K-NN mendapatkan nilai accuracy sebesar 73.6%, precision sebesar 73%, recall 73.6% dan untuk algoritma Random Forest mendapatkan nilai accuracy sebesar 92.5%, precision 92.5%, recall 92.5%.
KLASIFIKASI ALGORITMA NAIVE BAYES DAN K-NEAREST NEIGHBOR PADA PENDERITA DIABETES Feri Irawan Irawan; Tati Suprapti; Agus Bahtiar
E-Link: Jurnal Teknik Elektro dan Informatika Vol 18 No 1 (2023): Mei 2023
Publisher : Universitas Muhammadiyah Gresik

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30587/e-link.v18i1.5303

Abstract

Diabetes Melitus merupakan penyakit kronis yang disebabkan oleh gangguan metabolisme dimana glukosa tidak dapat digunakan dengan baik dan ditandai dengan hiperglikemia. Diabetes adalah penyakit yang terjadi ketika gula darah terlalu tinggi dan tubuh tidak lagi merespon hormon insulin dampak yang ditimbulkan jika penyakit diabetes tidak ditangani dengan cepat dapat menimbulkan komplikasi hingga kematian. Tujuan penelitian ini adalah untuk memprediksi dengan menggunakan klasifikasi untuk menentukan algoritma apa yang cocok dalam mendiagnosa penyakit diabetes. Data yang diambil merupakan data dari source kaggle yang bersifat publik. Pada penelitian ini menggunakan aplikasi Orange dalam pengklasifikasiannya. Penelitian ini menggunakan dua algoritma Naive Bayes dan K-Nearest Neighbor. Hasil yang diperoleh dari klasifikasi Naive Bayes accuracy sebesar 76.6 precision sebesar 76.8, recall sebesar 76.7 sedangkan K-Nearest Neighbor mendapatkan accurasy sebesar 92.6, Precision sebesar 92.6, recall sebesar 92.6.
ANALISIS SENTIMEN PENGGUNA TWITTER TERHADAP PELAKSANAAN KURIKULUM MBKM Nur Amalia; Tati Suprapti; Gifthera Dwilestari
E-Link: Jurnal Teknik Elektro dan Informatika Vol 18 No 1 (2023): Mei 2023
Publisher : Universitas Muhammadiyah Gresik

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30587/e-link.v18i1.5335

Abstract

Kurikulum Merdeka Belajar Kampus Merdeka (MBKM) merupakan suatu kebijakan yang dicetuskan oleh Menteri Pendidikan dan Kebudayaan Indonesia. Isi mengenai kebijakan tersebut diantaranya mempermudah perguruan tinggi membuka prodi baru, kemudahan perguruan tinggi negeri memiliki badan hukum, serta hak mahasiswa mendapatkan kebebasan dengan mengambil pembelajaran satu semester diluar program studi dan dua semester diluar kampus. Adapun program yang menunjang mahasiswa belajar diluar kampus ialah magang, studi independen, wirausaha, KKN tematik/membangun desa, program kemanusiaan, pertukaran pelajar, riset, dan asistensi mengajar. Namun, dalam pelaksanaan kurikulum MBKM ini tidak luput dari berbagai hambatan baik dalam segi pemahaman, kesiapan perguruan tinggi, maupun mahasiswa itu sendiri. Hal ini menimbulkan berbagai opini masyarakat baik yang bersifat positive maupun negative terhadap pelaksanaan kurikulum MBKM yang di tuangkan melalui media sosial twitter sehingga perlu adanya analisa untuk mendapatkan informasi melalui tanggapan tersebut. Tujuan penelitian ini untuk menganalisis sentimen pengguna twitter terhadap pelaksanaan kurikulum MBKM untuk mengelompokkan tanggapan yang bersifat positive dan negative dari tulisan menggunakan analisa teks. Metode pada penelitian menerapkan Naïve Bayes dan Decision Tree untuk melihat akurasi dari kedua algoritma tersebut. Dataset berupa tanggapan pengguna twitter terhadap pelaksanaan kurikulum MBKM, kemudian dilakukan pengelompokkan sentimen pada data tersebut untuk diklasifikasi. Dataset yang digunakan sebanyak 1275 tweet. Hasil dari penelitian ini menunjukan algoritma Naive Bayes cukup baik dengan nilai akurasi sebesar 81,15%, recall 75,98%, dan precision 91,10%. Sedangkan Decision Tree memiliki nilai akurasi 68,19%, recall 96,33% dan precision sebesar 37,83%.
Mengimplementasi Algoritma Self-Organizing Map untuk pemetaan data kasus COVID-19 di Jawa Barat Achmad Suharno; Ahmad Faqih; Tati Suprapti
JURSIMA (Jurnal Sistem Informasi dan Manajemen) Vol 10 No 3: Jursima Vol.10 No.3
Publisher : INSTITUT TEKNOLOGI DAN BISNIS INDOBARU NASIONAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47024/js.v10i3.417

Abstract

ABSTRACT COVID-19 is a contagious disease characterized by respiratory symptoms. This virus has a higher rate of spread or transmission than the previous variant of the virus. The mapping of the area of COVID-19 spread carried out by the government has not been optimally adhered to by the community. High community activity (mobility) is one of the causes of the spread of COVID-19. People are still traveling (mobility) in areas of high COVID-19 spread. The public needs a lot of additional information about mapping the spread of COVID-19. The grouping method uses the Self-Organizing Map algorithm. The dataset used is the latest data that includes the number of closecontact_total (direct interaction), suspect_total (total covid symptoms), probable_total (suspected exposure), confirmation_total (confirmed covid-19) in West Java. Furthermore, the results of the grouping are evaluated. Evaluation in the form of internal evaluation using davies-bouldin indeks. The expected result is mapping of kab / city in West Java based on the latest Covid data with a DBI value of 1.04768 at k = 6 Keywords: Self-Organizing Map, Davies Bouldin Indeks, Covid-19 West Java
IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBOUR UNTUK PREDIKSI KETEPATAN KELULUSAN Manarul Hidayat; Ahmad Faqih; Tati Suprapti
JURSIMA (Jurnal Sistem Informasi dan Manajemen) Vol 10 No 2 (2022): Jursima Vol. 10 No. 2, Agustus Tahun 2022
Publisher : INSTITUT TEKNOLOGI DAN BISNIS INDOBARU NASIONAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47024/js.v10i2.420

Abstract

In an education system, students are an important asset of a college and therefore, it is important to pay attention to the percentage of students who graduate on time. However, there is an imbalance between the inputs and outputs of the completed students. Students who enroll in large numbers, but students who graduate on time compared to those who are late according to regulations are fewer. In this study, the author aims to apply the K-NN method using cross validation to predict student graduation rates at STMIK IKMI. The results of this study are in the form of models and evaluations of student graduation predictions, whether they graduate on time or not on time. Based on the results of the design, implementation, testing using the RapidMiner program for predicting student graduation using the k-NN method with Cross Validation resulting in an accuracy of 70.28%, an error of 29.78%, and AUC of 0.739 Keywords: Graduation, Student, K-NN, Cross Validation
Aplikasi Pemesanan Online Barbershop Berbasis Android untuk Meningkatkan Layanan Cep Lukman Rohmat; Irfan Ali; Mulyawan Mulyawan; Tati Suprapti; Utami Aryanti
Jurnal Accounting Information System (AIMS) Vol. 4 No. 2 (2021)
Publisher : Ma'soem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/aims.v4i2.237

Abstract

The development of information and technology is a development that can be felt in everyday life, almost all activities already use digital. The problem in the barbershop business is the length of the queue which causes customers to feel bored or there are also busy customers. Therefore, technology is needed in the barbershop business. Based on these problems, it can be concluded that there is a need to build an android-based ordering application. The purpose of this research is to increase productivity, creativity, revenue and customer satisfaction. This study uses the stages of the Waterfall method. The Waterfall method is used as a reference in the process of making the online ordering application. The results of this study are an android-based online ordering application, this application is enough to help customers so they don't have to bother waiting in line at the barbershop because customers can set schedules on the application, especially during a pandemic like today. This application displays information about available time slots and those that have been booked by other customers so that customers can adjust their free time. The barbershop also does not need to register customers who place orders manually. This online booking application has passed trials with white box testing and black box testing methods. The result is that all the components contained in this online booking application system work as expected.
Implementasi Algoritma K-Nearest Neighbor dalam Menentukan Buku Berdasarkan Peminatan Faujatun Hasanah; Tati Suprapti; Nining Rahaningsih; Irfan Ali
Jurnal Accounting Information System (AIMS) Vol. 5 No. 1 (2022)
Publisher : Ma'soem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/aims.v5i1.467

Abstract

The use of computer technology helps a lot in human performance in various data and information management. Therefore, researchers use computers to make analyzes that can predict favorite books based on data from book borrowing records in the library. Researchers use is data mining. Data mining is a term used to describe the discovery of knowledge in databases, using statistical techniques, mathematics, artificial intelligence, and machine learning to extract and identify information that is useful for science. The use of data mining requires a method that can manage book borrowing data so that it gets the predictions of favorite books. The method used is K-Nearest Neighbor (KNN). The results of the accuracy in this study are 98.75%, Prediction of Disinterest with true Not Interest is 28 data, Prediction of Disinterest with true Interest is 1 data, Prediction of Interest with true No Interest is 0 data, Interest Prediction with true Interest is 54 data.
Implementasi Model Algoritma Generative Adversarial Network (Gan) Pada Sistem Presensi Berbasis Deteksi Wajah (SIDEWA) Suprapti, Tati; Dian Ade Kurnia; Doni Anggara; Rananda Deva Rian; Aldi Setiawan
TEMATIK Vol 9 No 2 (2022): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Desember 2022
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v9i2.1048

Abstract

Penelitian ini bertujuan untuk mengukur tingkat keberhasilan model algoritma Generative Adversarial Network (GAN) terhadap objek gambar wajah yang diimplemntasikan pada sistem presensi berbasis deteksi wajah di Kantor BPS Kota Cirebon. GAN terdiri dari dua jaringan terpisah, di antaranya ditargetkan satu sama lain. Kumpulan jaringan pertama adalah pengklasifikasi yang perlu dilatih untuk mengetahui apakah itu nyata atau salah, dan kumpulan jaringan kedua adalah generator yang menghasilkan sampel acak yang mirip dengan sampel nyata dan menggunakannya sebagai sampel palsu. GAN merupakan teknik deep learning yang digunakan untuk memproses data yang tidak terstruktur salah satunya gambar wajah. Beberapa tahapan dalam melakukan penelitian ini diantaranya adalah penyiapan dataset, pemrosesan data set, membuat model generator, membuat model diskriminator, menggabungkan model generator dan diskriminator , membuat proses training GAN dan menganalisis kemampuan generator dan diskriminator. Berdasarkan hasil eksperimen yang telah dilakukan pada sampel gambar wajah melalui 1000 epoch dengan 10 iterations setiap 1 epoch diperlukan waktu training selama 5 menit, dengan menghasilkan rata rata akurasi 66,06 %. Dari hasil dari proses training yang dilakukan, gambar yang diperoleh dapat dikatakan berhasil karena terlihat walaupun belum nampak dengan sangat jelas. Kata Kunci : Generative Adversarial Networks, Deep Learning, Epoch, Wajah
ANALISIS ALGORITMA KLASIFIKASI NEURAL NETWORK PADA PENDERITA PENYAKIT KANKER PAYUDARA Auliya; Tati Suprapti; Gifthera Dwilestari
JURNAL ILMIAH BETRIK Vol. 14 No. 01 APRIL (2023): JURNAL ILMIAH BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : P3M Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/betrik.v14i01 APRIL.24

Abstract

Breast cancer is classified as a type of malignant disease and ranks first in terms of the highest number of cancers in Indonesia and is one of the first contributors to deaths from cancer. About 43% of deaths from cancer can be prevented if breast cancer sufferers routinely carry out early detection or early diagnosis and avoid risk factors that cause cancer. In this study, a classification data mining technique will be used to predict living and deceased status using the Neural Network algorithm with rapidminer 10.0 tools. Neural network algorithm is a neural network of the human brain that is designed to follow the way the human brain processes and stores information in carrying out pattern recognition tasks, especially classification. The results of the accuracy show that the ratio of correct predictions with all data is 89.22%. With a true positive class recall of 97.08%, a true negative class recall of 49.12%, a precision Pred class. positive by 90.69% and Class precision Pred. negative by 76.71%. Analysis of positive breast cancer patients died as many as 565 records. With this classification benchmark, it is hoped that it can reduce mortality from breast cancer.
Co-Authors Abdul Hakim Abdul Mukhyidin Abrar Bayan, Athaullah Achmad Suharno Adam Firmansyah Ade Irma Purnamasari Ade Irma Purnamasari Aditia agus bahtiar Ahmad Faqih Ahmad Faqih Aldi Setiawan Ali Ali Alpian Novansyah, Indi Amaliah, Novi Andi Ardiansyah Andri Yanto Apriliani, Yuni Aribah, Firyal Arif Rinaldi Dikananda ASEP SAEFUDDIN Auliya Azhar, Alwan Cep Lukman Rohmat Christian Anderson Wint's II, Hans Darussalam, Luthvi Nurfauzi Dayanti, Resda Dian Ade Kurnia Dodi Solihin Doni Anggara Dwi Prasetyo Faujatun Hasanah Fazrian, Vivi Feri Irawan Irawan Fikri, Achmad Fitri Adha Hariyati Airi Fitriani Agustina Fitriani Fitriani Gifthera Dwilestari Gifthera Dwilestari Gilang Perwati, Intan Gilang Ramadhan Gustiani Regina Pratama Putri Gustino, Gustino Hadianti, Isan Hafshoh Habiballoh Hajaroh, Hajaroh Hartati Hartati Hayati, Umi Hendriyansyah, Hendriyansyah Hidayat, Manarul Hidayat, Muhamad Taufiq Hidayat, Peri Husni Mubarok Ilham Kurniawan Imam Arifin imam maulana, imam Indrawan, Heru Irfan Ali Irma Purnamasari, Ade Kaslani Khoirunisa, Irma Lestari, Hasanah Lukman Rohmat, Cep Mahda, Muhammad Manarul Hidayat Martanto . Maryam, Beby Muhaimin, Ahmad Muhamad Basysyar, Fadhil Mulyawan Nana Siti Nurjanah Narasati, Riri Narasati Naufan, Muhammad Hilmy Nining Rahaningsih Nur Amalia Nurmala, Sri Pratiwi, Intan Purnamasari, Ade Irma Raditya Danar Dana Rananda Deva Rian Raudotul Janah, Fina Rini Astuti Rini Astuti Riri Narasati Rizki Ani, Fitri Rosdiana Rosdiana Rudi Kurniawan Rudi Kurniawan Rudi Kurniawan Ruli Herdiana Ryan Hmonangan Saeful Anwar Saeful Anwar, Saeful Sajidan, Dzikri Santi Nurjulaiha Shalihah, Ghina Shinta Virgiana Silalahi, Ryan H Siti Aisah, Iis siti azhar Sri Nurmala, Ai Suarna, Nana Suharno, Achmad Sukma Maula, Intan Syajida, Hanna Syaripah, Imas Tegar Lazuardi, Muhammad Tengku Riza Zarzani N Tohidi, Edi Tri Aditama Tri Gustiane, Indri Umi Hayati Umi Hayati Utami Aryanti Vinna Agustina Wahyudin, Edi Widiawati, Fitri Widisa Adi Kumara Wijaya, Yudhitira Arie Willy Prihartono Yudhistira Arie Wijaya Yusuf Sidiq, Yusuf Sidiq Zaki Nur Rahmat Hidayat Zulfa Hana Aqliyah