Articles
Penerapan Metode MABAC dengan Pembobotan ROC Dalam Sistem Pendukung Keputusan Pemilihan Pengajar dengan Kinerja Terbaik
Kraugusteeliana, Kraugusteeliana;
Zen, Agustian;
Suryani, Suryani;
Alam, Sitti Nur;
Winarno, Edy
Building of Informatics, Technology and Science (BITS) Vol 4 No 4 (2023): March 2023
Publisher : Forum Kerjasama Pendidikan Tinggi
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47065/bits.v4i4.3000
Selection of the best teacher is one of the problems in a decision making according to semi-structured criteria. In this research, the decision support system explains how the process of selecting alternative teachers who have the best performance in elementary schools applies the MABAC method and weights it using the Rank Order Centroid (ROC) method. The use of this method can solve the problem of determining the best teacher that occurs in elementary schools. The final result of completing the method will produce the highest ranking value which will be determined to be the highest alternative. The data used in this study were 10 alternative teacher data using 5 criteria, resulting in 1 highest ranking of the 10 alternatives obtained by alternative 1 named Servin Manullang with a value of 0.6086 as a recommendation for the teacher with the best performance
SOCIAL NETWORK ANALYSIS UNTUK MENGIDENTIFIKASI AKUN KUNCI DALAM PERCAKAPAN CAPRES DI TWITTER
Amin, Fatkhul;
Al Amin, Imam Husni;
Winarno, Edy;
Wibisono, Setyawan;
Cahyono, Taufiq Dwi
Jurnal Teknoinfo Vol 18, No 2 (2024): Juli 2024
Publisher : Universitas Teknokrat Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33365/jti.v18i2.3620
Studi ini bertujuan untuk mengeksplorasi percakapan tentang calon presiden dari data Twitter (X) menggunakan analisis jaringan sosial. Metode analisis meliputi degree centrality, betweenness centrality, dan closeness centrality untuk mengidentifikasi akun-akun sentral dalam diskusi tentang calon presiden tertentu. Dataset Twitter (X) diproses dan dianalisis menggunakan alat analisis jaringan sosial. Visualisasi jaringan dilakukan dengan Gephi 0.10.1 untuk memahami struktur interaksi antar akun. Dalam contoh studi yang memfokuskan pada pasangan "Anies Muhaimin," analisis menunjukkan bahwa akun-akun seperti @kba_news dan @PeraWat81282560 memiliki degree centrality yang tinggi, menandakan keterlibatan yang signifikan dalam menyebarkan informasi dan mempertahankan koneksi langsung dengan akun-akun lain dalam jaringan. Sementara itu, untuk kata kunci "Ganjar Mahfud" dan "Prabowo Gibran," ditemukan bahwa terdapat akun-akun dominan dengan peran penting dalam mengoordinasikan dan memengaruhi percakapan. Implikasi dari temuan ini menyoroti bagaimana struktur jaringan sosial memengaruhi penyebaran informasi politik di media sosial. Studi ini memberikan wawasan tentang dinamika interaksi antar akun dalam konteks kampanye pemilihan presiden, serta pentingnya pemahaman tentang pengaruh akun-akun sentral dalam mempengaruhi opini publik. Secara kesimpulan, analisis jaringan sosial Twitter (X) memberikan pemahaman mendalam tentang bagaimana informasi politik tersebar dan dipengaruhi dalam konteks percakapan tentang calon presiden. Temuan ini relevan untuk strategi kampanye politik dan manajemen reputasi di era digital.
Pengembangan Chatbot Berbasis Dialogflow Dengan Metode Natural Language Processing Untuk Menyediakan Informasi Mengenai Stunting Melalui Platform Telegram
Rahardika, Anindyta Fernanda;
Winarno, Edy
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 1 (2024): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30645/jurasik.v9i1.732
Stunting is a serious problem in children's health in Indonesia, so more in-depth knowledge is needed. Based on the results of the 2019 Ministry of Communication and Information survey, it shows that the Indonesian people have a poor understanding of stunting. A system is needed that can make it easy for the public to get stunting information accurately and quickly, so this research proposes the development of a dialogue-based chatbot that is integrated with the Telegram platform, which can be used as a step to increase public accessibility regarding stunting information. Chatbots are able to effectively assist humans in providing automatic answers to questions from various topics. This research aims to provide stunting information to the public and provide access to stunting information easily and quickly. The stunting information chatbot was developed using the Dialogflow platform by applying natural language processing (NLP) which is integrated with the Telegram application. The chatbot testing results using the black box test obtained an accuracy of 90%, which shows that the output provided by the chatbot is appropriate. The test results using the user experience questionnaire (UEQ) showed that the attractiveness score was 1.80, clarity was 1.17, efficiency was 1.81, decision was 1.74, stimulation was 1.59 and novelty was 1.14.
Enhanced multi-lingual Twitter sentiment analysis using hyperparameter tuning k-nearest neighbors
Nugroho, Kristiawan;
Winarno, Edy;
Setiadi, De Rosal Ignatius Moses;
Farooq, Omar
Bulletin of Electrical Engineering and Informatics Vol 13, No 6: December 2024
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/eei.v13i6.7265
Social media is a medium that is often used by someone to express themselves. These various problems on social media have encouraged research in sentiment analysis to become one of the most popular research fields. Various methods are used in sentiment analysis research, ranging from classic machine learning (ML) to deep learning. Researchers nowadays often use deep learning methods in sentiment analysis research because they have advantages in processing large amounts of data and providing high accuracy. However, deep learning also has limitations on the longer computational side due to the complexity of its network architecture. K-nearest neighbor (KNN) is a robust ML method but does not yet provide high-accuracy results in multi-lingual sentiment analysis research, so a hyperparameter tuning KNN approach is proposed. The results showed that using the proposed method, the accuracy level improved to 98.37%, and the classification error (CE) improved to 1.63%. The model performed better than other ML and even deep learning methods. The results of this study indicate that KNN using hyperparameter tuning is a method that contributes to the sentiment analysis classification model using the Twitter dataset.
Pengenalan Wajah Dengan Face-Api.js Berbasis CNN dan Geolokasi Menggunakan Equirectangular Approximation
Fadli, Bimo Akbar;
Winarno, Edy
Progresif: Jurnal Ilmiah Komputer Vol 19, No 2: Agustus 2023
Publisher : STMIK Banjarbaru
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35889/progresif.v19i2.1398
Computer vision usag on an attendance system role is to make sure that the attendance cannot be done by another person. Besides that, the attendance system could also use geolocation to determine the attendee location and the supposed attendance location. These process takes a considerable amount of server resource. To reduce the load of a server, a client side process could be used. Face recognition is done by using face-api.js which is a javascript module build on top of tensoflow.js core that implements some CNN (Convolutional Neural Networks) to detect, recognize, and extract feature of a face, that is optimized for website and mobile device. For the calculation of geolocation coordinate an equirectangular approximation formula is used. The accuracy of face recognition ranges between 93% to 97% and the geolocation calculation takes around 0.008300000003ms to complete.Key words: Face Detection; Geolocation; Tensorflow; Attendance  AbstrakPenggunaan computer vision pada sistem absensi berperan sebagai pengaman untuk memastikan bahwa absensi tidak dapat diwakilkan oleh orang lain. Selain itu pada sistem absensi juga dapat ditambahkan sistem geolokasi untuk menentukan jarak pelaku dari jarak lokasi yang sudah ditentukan. Proses-proses tersebut memakan sumber daya besar pada server. Dengan mendelegasikan proses tersebut kepada klien, beban serer akan berkurang secara signifikan. Pengenalan wajah dilakukan dengan menerapkan face-api.js yang merupakan sebuah modul javascript yang dibangun diatas tensorflow.js core, yang mengimplementasikan beberapa CNN (Convolutional Neural Networks) untuk melakukan deteksi, pengenalan, dan deteksi fitur-fitur wajah, yang dioptimalkan untuk web dan perangkat mobile. Untuk geolokasi pengukuran jarak koordinat, digunakan formula equirectangular approximation. Dari penerapan pengenalan wajah dan geolokasi tersebut didapatkan akurasi pengenalan wajah berkisar antara 93% hingga 97% dan geolokasi menggunakan equirectangular approximation berjalan dalam waktu rata-rata 0.008300000003ms.Kata kunci: Pengenalan wajah; Geolokasi; Tensorflow; Presensi
Perbandingan Algoritma Klasifikasi Data Mining Dalam Diagnosa Penyakit Arteri Koroner
Sudarsono, Bernadus Gunawan;
Winarno, Edy
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47065/bits.v6i3.5981
Coronary artery disease is one of the diseases that often attacks humans. The cause of this disease is due to narrowing or blockage of the coronary blood vessels that supply blood to the heart. The diagnosis of coronary artery disease by medical personnel has so far been constrained by the limited number of doctors, in terms of the number of doctors and time, because the number of specialist doctors is limited. The limited number of doctors causes several difficulties for medical personnel who diagnose the patient's disease and over time can become a serious problem. Information technology that can help medical personnel is by applying data mining techniques which are techniques to help diagnose coronary artery disease. Data mining can identify patterns or relationships between disease symptoms and diagnostic results, so that patients with a high risk of developing the disease can be identified. The Naïve Bayes algorithm is one of the algorithms of the Data Mining classification technique, which is based on Bayes' theorem. The C4.5 algorithm is one of the algorithms of the Data Mining classification technique, which uses decision trees in classifying data. Algorithm comparisons are carried out in order to obtain the appropriate or best algorithm for use in diagnosing a disease. The comparison process of the Naïve Bayes algorithm and the C.45 algorithm in diagnosing coronary artery disease, obtained the best algorithm results based on the largest percentage value, namely the C4.5 algorithm, with a value of 46.9%.
OPTIMASI PENJUALAN UNTUK MENINGKATKAN PROFITABILITAS DI PT MUTIARA COLLECTION SLEMAN, YOGYAKARTA
MARATUN NAFIAH;
DIAS AYU LISTYORINI;
DHINI AMINATI NURHASANAH;
SITI AISYAH;
EDY WINARNO;
KHUSNUL WIBI PRASETYO;
UNNA RIA SAFITRI
JURNAL EKONOMI, SOSIAL & HUMANIORA Vol 7 No 01 (2025): INTELEKTIVA : JURNAL EKONOMI, SOSIAL DAN HUMANIORA - EDISI JANUARI-APRIL 2025
Publisher : KULTURA DIGITAL MEDIA ( Research and Academic Publication Consulting )
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Mutiara Collection, sebuah konveksi di Sleman, Yogyakarta, membuat perlengkapan sekolah seperti jilbab, dasi, topi, dan lainnya dengan baik. Tujuan penelitian ini adalah untuk menemukan cara untuk meningkatkan daya saing perusahaan melalui pemasaran produk dan pengembangan kualitas. Menurut pengamatan langsung dan wawancara dengan pemilik bisnis, PT. Mutiara Collection berfokus pada kualitas bahan baku, ketepatan waktu produksi, dan sistem pembayaran pasca-pengiriman sebagai cara utama untuk membangun kepercayaan pelanggan. Promosi dilakukan melalui media sosial seperti WhatsApp, yang memudahkan interaksi yang mudah dengan konsumen. Strategi pemasaran yang fleksibel dan inovatif untuk produk sangat penting untuk mempertahankan loyalitas pelanggan dan meningkatkan penjualan. Perusahaan menargetkan siswa di Sleman, tetapi juga menerima pesanan dari seluruh Indonesia.
Fast image watermarking based on signum of cosine matrix
Ernawan, Ferda;
Adi, Prajanto Wahyu;
Liew, Siau-Chuin;
Sarwoko, Eko Adi;
Winarno, Edy
Indonesian Journal of Electrical Engineering and Computer Science Vol 25, No 3: March 2022
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v25.i3.pp1383-1391
In the field of image watermarking, the singular value decomposition has good imperceptibility and robustness, but it has high complexity. It divides a host image into matrices of U, S, and V. Singular matrix S has been widely used for embedding and extracting watermark, while orthogonal matrices of U and V are used in decomposition and reconstruction. The proposed signum of cosine matrix method is carried out to eliminate the generation of the three matrices at each block and replace it with a signum of cosine matrix. The proposed signum of cosine matrix is performed faster on the decomposition and reconstruction. The image is transformed into a coefficient matrix C using the signum matrix. The C matrix values are closer to the S value of singular value decomposition which can preserve high quality of the watermarked image. The experimental results show that our method is able to produce similar imperceptibility and robustness level of the watermarked image with less computational time.
PENDEKATAN DESIGN THINGKING BAGI PKK RW III KELURAHAN GAYAMSARI MELALUI KREATIFITAS KRIYA ECOPRINTING
Imam Husni Al Amin;
Edy Winarno;
Budi Hartono;
Dewi Handayani U.N;
Veronica Lusiana
Servis : Jurnal Pengabdian dan Layanan kepada Masyarakat Vol. 2 No. 2 (2024): Juni
Publisher : CV. Nature Creative Innovation
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Kewirausahaan adalah suatu proses kreatif dan inovatif dengan tingkat risiko tinggi yang bertujuan menciptakan nilai tambah bagi produk atau jasa yang bermanfaat bagi konsumen atau masyarakat. Kewirausahaan melibatkan sifat dan karakteristik individu yang didorong oleh keinginan dan kemampuan untuk menghasilkan gagasan inovatif secara produktif dan kreatif. Ini memberikan peluang kepada setiap orang untuk mengidentifikasi dan mengejar peluang bisnis dengan menggunakan sumber daya yang tersedia guna mencapai tujuan bisnis mereka. Pendekatan "design thinking" digunakan untuk memecahkan masalah yang kompleks dan tidak jelas dengan memahami masalah secara mendalam, menciptakan solusi inovatif, dan menguji ide secara berulang. Pendekatan ini memungkinkan para wirausaha untuk melihat peluang, memahami masalah dengan baik, menciptakan lapangan kerja, mendorong inovasi, dan memberdayakan komunitas serta mengkaji penerapan pendekatan "design thinking" dalam pengembangan kewirausahaan, khususnya pada ibu-ibu yang tergabung dalam PKK di lingkungan RW. III, Kelurahan Gayamsari, Kota Semarang. Mereka diberikan pelatihan dan bimbingan teknik dengan fokus pada kreativitas dan penggunaan sumber daya sekitar untuk menghasilkan produk kriya Ecoprint. Hasil dari pelatihan ini dapat mengasah keterampilan para peserta dan menghasilkan produk alternatif yang bernilai ekonomis dan relevan bagi kebutuhan pelanggan.
Inovasi Pembelajaran Interaktif Mengenal Jenis Sampah untuk Anak Sekolah Dasar Dengan Media Game
Aditya Putra Ramdani;
Nova Christina Sari;
Diaz Aditya;
Karima Elsami;
Naimatul Husna;
Achmad Solichan;
Edy Winarno;
Muhammad Zainudin Al Amin;
Basirudin Ansor
Jurnal Pengabdian Masyarakat Waradin Vol. 5 No. 2 (2025): Jurnal Pengabdian Masyarakat Waradin
Publisher : Sekolah Tinggi Ilmu Ekonomi Pariwisata Indonesia Semarang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.56910/wrd.v5i2.603
The issue of waste management remains one of the significant environmental challenges in Indonesia, mainly due to the lack of awareness and understanding from an early age. This article discusses the implementation of a community service program through innovative interactive learning using educational games "Reresik" and "Bersihkan Sampah di Laut" designed to enhance elementary school students' interest and understanding of waste management. The implementation method includes teacher training, the introduction of waste material, the application of educational games, and the evaluation of program effectiveness through satisfaction surveys. The results indicate that game-based learning methods significantly increase student enthusiasm, simplify understanding, and foster positive habits in maintaining environmental cleanliness. Moreover, the training provided to teachers improved their ability to integrate educational technology into the learning process. This program is expected to serve as a sustainable innovative learning model to raise environmental awareness among younger generations.