https://ejournal.ikado.ac.id/index.php/teknika/issue/feed Teknika 2024-11-01T10:26:28+07:00 Ir. Raymond Sutjiadi, S.T., M.Kom. p3m@ikado.ac.id Open Journal Systems <p><strong>Teknika (ISSN 2549-8037, EISSN 2549-8045)</strong> is a peer-reviewed scientific journal published three times a year in <strong>March, July,</strong>&nbsp;and&nbsp;<strong>November</strong>&nbsp;by the Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya. It presents articles on <strong>Information and Communication Technology (ICT)</strong> that come from empirical research or conceptual works.</p> <p><strong>Teknika&nbsp;</strong>has been accredited&nbsp;<a href="http://sinta.kemdikbud.go.id/journals/detail?id=293" target="_blank" rel="noopener"><strong>SINTA-3 (S3)</strong></a> by the decree of the Ministry of Education, Culture, Research, and Technology, Republic of Indonesia No. 105/E/KPT/2022, 7 April 2022.</p> <p><strong>DOI:</strong> <a href="https://doi.org/10.34148/teknika">https://doi.org/10.34148/teknika</a></p> <p><strong>Teknika</strong> has been indexed in:<br><a href="https://search.crossref.org/?q=2549-8037&amp;from_ui=yes" target="_blank" rel="noopener">Crossref</a><br><a href="https://doaj.org/toc/2549-8045" target="_blank" rel="noopener">Directory of Open Access Journals (DOAJ)<br></a><a href="https://journals.indexcopernicus.com/search/details?id=48529" target="_blank" rel="noopener">Index Copernicus International (ICI Journals Master List) - ICV 2023: 76.30</a><br><a href="https://www.scilit.net/journal/4223227" target="_blank" rel="noopener">Scientific Literature (Scilit)<br></a><a href="http://www.worldcat.org/search?q=on:DGCNT+http://ejournal.ikado.ac.id/index.php/teknika/oai+teknika:ART+IDISU&amp;qt=results_page" target="_blank" rel="noopener">OCLC WorldCat</a><br><a href="https://scholar.google.co.id/citations?hl=en&amp;user=upIi57wAAAAJ" target="_blank" rel="noopener">Google Scholar<br></a><a href="https://app.dimensions.ai/discover/publication?and_facet_source_title=jour.1313918" target="_blank" rel="noopener">Dimensions</a><br><a href="https://www.base-search.net/Search/Results?q=dccoll%3Aftikadoojs+url%3Ateknika&amp;refid=dclink" target="_blank" rel="noopener">Bielefeld Academic Search Engine (BASE)<br></a><a href="https://www.mendeley.com/community/teknika/documents/" target="_blank" rel="noopener">Mendeley</a><br><a href="http://www.openarchives.org/Register/BrowseSites?viewRecord=http://ejournal.ikado.ac.id/index.php/teknika/oai" target="_blank" rel="noopener">Open Archives Initiative</a><br><a href="http://sinta.kemdikbud.go.id/journals/detail?id=293" target="_blank" rel="noopener">Science and Technology Index (SINTA) - SINTA Score: S3</a><br><a href="http://garuda.kemdikbud.go.id/journal/view/20103" target="_blank" rel="noopener">Garba Rujukan Digital (GARUDA)</a><a href="http://onesearch.id/Search/Results?filter[]=repoId:IOS6424" target="_blank" rel="noopener"><br>Indonesia One Search</a><br><a title="Directory of Research Journals Indexing (DRJI)" href="http://olddrji.lbp.world/JournalProfile.aspx?jid=2549-8037" target="_blank" rel="noopener">Directory of Research Journals Indexing (DRJI)</a><br><a title="Neliti" href="https://www.neliti.com/journals/teknika-ikado" target="_blank" rel="noopener">Neliti</a></p> <p>&nbsp;</p> https://ejournal.ikado.ac.id/index.php/teknika/article/view/973 The Analysis and Improvement of User Interface Design on Climate Information Service Mobile Application Using the Lean UX Method 2024-11-01T10:26:28+07:00 Muhammad Fauzi chiekiepoygaming@gmail.com Ni Kadek Ayu Wirdiani ayuwirdiani@unud.ac.id Ni Kadek Dwi Rusjayanthi dwi.rusjayanthi@unud.ac.id <p>Info BMKG is an iOS and Android app providing weather, temperature, air quality, and earthquake data across Indonesia. Issues related to the usability of the BMKG Info application were identified through observations and feedback found on the Google Play Store, which has a rating of 4.4. The responses identified included an unattractive appearance, limited features, increasing complexity, and a need for more innovation, necessitating usability evaluation and UI design improvements to enhance user experience. The analysis and redesign follow the Lean UX approach and Heuristic Evaluation method. Usability testing, specifically the Post-Study System Usability Questionnaire, is used to assess user satisfaction. The study finds that implementing Lean UX significantly improves the system's quality and user experience. UI design enhancements, based on usability testing, improve navigation, information clarity, and ease of use. Recommendations result in better outcomes, with Heuristic Evaluation yielding scores of H1 = 1 (System status visibility), H2 = 1 (Match between the system and the real world), H4 = 1 (Consistency and standards), H5 = 1 (Error prevention), H7 = 1 (Flexibility and efficiency of use), H8 = 1 (Aesthetic and minimalist design), and H9 = 1 (Help users recognize, diagnose, and recover from errors). The Post-Study System Usability Questionnaire method shows an improvement from high to a better category.</p> 2024-09-02T16:03:02+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/982 Descending Stairs Detection Using Digital Image Processing to Guide Visually Impaired 2024-11-01T10:26:28+07:00 Ahmad Wali Satria Bahari Johan ahmadsatria@telkomuniversity.ac.id Rizky Fenaldo Maulana rizkyfenaldo@telkomuniversity.ac.id <p>Blindness refers to a condition in which an individual experiences limitations in their visual ability. Individuals with visual impairments require specific assistance to facilitate their movement from one location to another. The need for this assistance arises due to various obstacles scattered throughout their environment. One of the most significant challenges is navigating descending stairs. To address this issue, a descending stairs detection system based on digital image processing has been developed. Through this approach, the mobility of individuals with visual impairments can be enhanced. The descending stairs detection system is designed using the Gray Level Co-occurrence Matrix (GLCM) method to extract distinctive features of descending stairs and the surrounding floor surfaces. Seven GLCM features are incorporated into the development of this system, allowing it to differentiate between descending stairs and floors using the Extra Tree Classifier classification method. Through a series of tests, the system's accuracy is measured at 84%, demonstrating its adequate ability to identify descending stairs. Additionally, the average computation time for detecting descending stairs and floors is recorded at 0.121 (s), indicating the efficient performance of this system in supporting the mobility of individuals in need.</p> 2024-09-09T14:52:10+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1010 Precision in Obstetric Care: A Machine Learning Approach with CatBoost and Grid Search Optimization 2024-11-01T10:26:28+07:00 Marselina Endah Hiswati marsel.endah@respati.ac.id Mohammad Diqi diqi@respati.ac.id Izattul Azijah iza@urindo.ac.id Yeyen Subandi yeyensubandi@respati.ac.id Azzah Fathinah 322220025@respati.ac.id Rahayu Cahya Ariani 3225050016@urindo.ac.id <p>This study focuses on improving how we classify fetal health using machine learning by fine-tuning the CatBoostClassifier with Grid Search. Our main achievement in this research is significantly boosting the accuracy of fetal health classification based on Cardiotocogram (CTG) data. Finding the best hyperparameters has created a more precise and reliable diagnostic tool for making informed prenatal care decisions. The model reached an impressive overall accuracy of 96%, especially excelling in identifying Normal and Pathological cases. However, it faced some challenges in classifying Suspect cases, suggesting room for further improvement. These results highlight the potential of machine learning to enhance the reliability of fetal health assessments, which could lead to better outcomes in clinical settings. The success of Grid Search in this study is evident, as the optimized parameters led to the highest accuracy and lowest loss values, proving its effectiveness in fine-tuning the model.</p> 2024-09-09T14:54:01+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/928 Optimalisasi Proses Data Warehouse Melalui Business Process Optimization (BPO) Untuk Meningkatkan Efisiensi Pengambilan Keputusan 2024-11-01T10:26:27+07:00 Fajar Ciputra Daeng Bani daengbani.18@gmail.com Agus Wahyudin aguswahyudin2508@gmail.com Bayu Prabowo Sutjiatmo bayu.prabowo@poltekapp.ac.id Intan Maria Lewiayu Vierke intan@kemenperin.go.id Avia Enggar Tyasti aviaenggar@kemenperin.go.id <p>Proses pengambilan keputusan yang cepat dan tepat merupakan kebutuhan utama dalam lingkungan bisnis yang dinamis. Namun, banyak perusahaan freight forwarder menghadapi permasalahan dalam efisiensi pengambilan keputusan karena ketidaksempurnaan proses pengolahan data di dalam data warehouse. Untuk mengatasi permasalahan tersebut. Penelitian ini bertujuan untuk mengoptimalkan proses Data Warehouse (DWH) guna meningkatkan produktivitas dalam pengambilan keputusan di perusahaan freight forwarder di Indonesia. Dalam konteks lingkungan bisnis yang semakin kompleks dan dinamis, kebutuhan akan informasi yang tepat waktu dan akurat sangat penting untuk mendukung pengambilan keputusan yang efektif. DWH telah menjadi solusi populer untuk mengintegrasikan dan menganalisis data dari berbagai sumber guna mendukung proses pengambilan keputusan. Business Process Optimization (BPO) diterapkan untuk menganalisis dan merancang ulang proses bisnis yang terkait dengan pengolahan data, sehingga meningkatkan efisiensi dan akurasi pengolahan data dalam DWH. Dalam penelitian ini, digunakan model optimasi yang dirancang untuk memaksimalkan efisiensi proses ETL dan meningkatkan kinerja sistem Online Analytical Processing (OLAP) serta Online Transaction Processing (OLTP). Metode-metode ini diharapkan dapat meningkatkan kualitas dan kecepatan pengambilan keputusan, serta efisiensi operasional perusahaan freight forwarder. Hasil dari penelitian ini diharapkan dapat memberikan produktivitas dan daya saing bagi perusahaan di industri logistik.</p> 2024-09-23T09:41:22+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/987 Klasterisasi Data Obat Farmasi Berdasarkan Jumlah Persediaan Dengan Menggunakan Metode K-Means 2024-11-01T10:26:27+07:00 Heri Supriyanto heri.supriyanto@hayamwuruk.ac.id Mohammad Al Hafidz mohammad.hafidz@hayamwuruk.ac.id Ari Cahaya Puspitaningrum ari.cahaya@hayamwuruk.ac.id Rayhan Abdillah Putra Firmansyah 202102021003@mhs.hayamwuruk.ac.id Rafi Zuhdi 2102021009@mhs.hayamwuruk.ac.id <p>Instalasi Farmasi memiliki peran penting terhadap pelayanan kesehatan di sebuah fasilitas kesehatan. Farmasi bertanggung jawab atas pengelolaan, pengadaan, penyimpanan, distribusi, dan penggunaan persediaan obat. Persediaan obat merupakan bagian penting dalam memastikan ketersediaan, aksesibilitas, dan penggunaan obat yang efektif serta aman bagi pasien. Tujuan penelitian ini untuk melakukan klasterisasi data obat yang berguna untuk meningkatkan efisiensi proses manajemen persediaan obat, sehingga dapat menghindari kelebihan atau kekurangan yang dapat mengganggu kelancaran layanan pemberian obat dan mencegah terjadinya kerugian penjualan obat. Pengelompokan data dilakukan dengan memanfaatkan data Persedian Obat dari data masa lalu yaitu data transaksi pembelian dan penjualan dengan memanfaatkan teori Data Mining dengan menggunakan metode Clustering yaitu <strong><em>K-Means</em></strong>. Dataset pada penelitian ini sebanyak 1<strong><em>.</em></strong>389 dengan 6 variabel. Sebelum dilakukan klasterisasi dilakukan proses optimasi jumlah klaster dengan dua metode yaitu Metode Elbow dan Metode Gap Statistik. Hasil kedua metode tersebut menunjukkan nilai optimasi k klaster k = 3. Hasil klasteriasi yaitu Klaster 1 sebanyak 41 data obat yang menunjukkan golongan obat Generik. Klaster 2 sebanyak 116 data obat yang menunjukkan obat Paten. Kedua klaster tersebut menunjukkan tingkat penjualan yang kurang cepat (slow moving). Sedangkan pada Klaster 3 sebanyak 1<strong><em>.</em></strong>232 data obat yang menunjukkan gabungan dari golongan obat generik dan paten yang memiliki tingkat penjualan yang cukup cepat (fast moving).</p> 2024-09-19T13:50:16+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/992 Pengembangan Model Klasifikasi Kendaraan Keluar Masuk Area Parkir Dengan Algoritma YOLOv8 2024-11-01T10:26:25+07:00 Argi Nur Faturrohman 2011102441016@umkt.ac.id Sayekti Harits Suryawan shs500@umkt.ac.id Abdul Rahim ar622@umkt.ac.id <p>Peningkatan laju pertumbuhan mahasiswa baru menimbulkan tantangan serius terhadap infrastruktur parkir di Universitas Muhammadiyah Kalimantan Timur (UMKT). Data terkini menunjukkan adanya peningkatan signifikan sekitar 10% dari tahun sebelumnya, mencapai 2.598 mahasiswa baru pada tahun 2022. Ruang lingkup penelitian ini adalah melakukan proses klasifikasi kendaraan tetapi tidak melakukan tracking kendaraan, data yang digunakan adalah data dari perekaman video yang dilakukan pada simpang tanjakan menuju area parkir kampus bagian atas di siang hari, serta objek yang dideteksi adalah motor, mobil dan manusia, sedangkan yang dihitung keluar masuknya adalah mobil dan motor. Tujuan penelitian ini adalah mengimplementasikan algoritma YOLOv8 agar dapat mendeteksi serta mengklasifikasikan kendaraan keluar masuk area parkir serta untuk mengetahui bagaimana proses deteksi dapat diterapkan agar dapat akurat untuk mendeteksi kendaraan yang keluar masuk area parkir. Metode penelitian melibatkan pengumpulan data dan penerapan algoritma YOLOv8 (You Only Look Once) untuk training dan validasi model pada platform Google Colab yang mendukung GPU untuk mempercepat komputasi dan memungkinkan pengolahan data dalam skala besar. Hasil dari penelitian ini adalah model klasifikasi yang dapat mendeteksi kendaraan keluar masuk area parkir UMKT dengan memiliki nilai mAP50 sebesar 89,8% dan nilai presisi sebesar 86,5%. Penelitian selanjutnya diharapkan dapat mengembangkan model dengan tingkat akurasi yang lebih tinggi dengan mengintegrasikan CCTV sebagai sumber video secara real-time.</p> 2024-09-30T14:51:18+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1037 Optimizing Tourism Promotion for Situ Bagendit Through Innovation in a Web-Based Virtual Tour Application 2024-11-01T10:26:26+07:00 Sri Rahayu srirahayu@itg.c.id Syahrul Yanuar 2006088@itg.ac.id Yosep Bustomi yosep@uniga.ac.id <p>Situ Bagendit is a well-known natural lake tourist destination in Garut, West Java. However, information about Situ Bagendit is still difficult for the public to access. Information is often spread by word of mouth and social networks, which highlights the need for more effective promotional media. This research aims to create a virtual tour to promote Situ Bagendit and address the issue of information accessibility for tourists. The application was developed using the Multimedia Development Life Cycle (MDLC) method, utilizing VR technology and 3DVISTA software, and incorporating images and videos captured with a mobile or 360° camera. The application is hosted on Instagram, featuring interactive elements such as chat and location information via Google Maps. The research findings indicate that the virtual tour application was successfully built with features like a gallery, videos, information, WhatsApp, and Google Maps. It received a score of 80.25 on the System Usability Scale (SUS), earning an "Excellent" rating and falling within the "Acceptable" category. This application is expected to increase tourist interest in visiting Situ Bagendit.</p> 2024-09-30T14:00:30+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/993 Analisis Sentimen Ulasan Game Stumble Guys Pada Playstore Menggunakan Algoritma Naïve Bayes 2024-11-01T10:26:25+07:00 Awang Herjunie Nurdy 2011102441020@umkt.ac.id Abdul Rahim ar622@umkt.ac.id Arbansyah arb381@umkt.ac.id <p>Perkembangan teknologi yang pesat mempermudah akses ke berbagai hiburan digital, termasuk game online seperti Stumble Guys, yang telah diunduh lebih dari 163 juta kali dan mendapatkan ulasan beragam di Google Play Store. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna Stumble Guys menggunakan algoritma Naïve Bayes. Metode penelitian melibatkan tahapan Knowledge Discovery in Databases (KDD), meliputi pemilihan data, preprocessing, transformasi dengan CountVectorizer dan TF-IDF, serta pengklasifikasian dengan Naïve Bayes. Dengan menggunakan 1.500 ulasan dari Google Play Store, model Naïve Bayes mencapai akurasi 86%, dengan precision, recall, dan f1 score masing-masing sebesar 86%. Hasil penelitian menunjukkan bahwa Naïve Bayes efektif dalam mengklasifikasikan sentimen ulasan game Stumble Guys.</p> 2024-09-30T14:53:13+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/943 Penerapan Metode ROC dan MAIRCA Dalam Pemilihan Web Hosting VPS Cloud 2024-11-01T10:26:26+07:00 Brian Ardianto bryanardy017@gmail.com Mey Tri Widya Pangesti meytriwidya34@gmail.com Prind Triajeng Pungkasanti prind@usm.ac.id <p>Perkembangan teknologi informasi yang pesat membuat website menjadi kebutuhan yang penting, bagi individu maupun pelaku usaha mikro yang digunakan sebagai portal digital yang membantu membangun identitas, sarana promosi produk dan jasa, serta menjangkau khalayak yang lebih luas. Untuk membuat website, diperlukan web hosting server yang memadai, salah satunya adalah VPS yang berbasis cloud (VPS Cloud). VPS Cloud merupakan teknologi server virtual yang dikombinasikan dengan cloud computing, di mana pengguna memiliki akses penuh terhadap server. Namun, ada banyak penyedia layanan VPS cloud yang menawarkan berbagai spesifikasi dan harga yang dapat disesuaikan dengan kebutuhan website, sehingga dibutuhkan rekomendasi yang tepat dengan ketentuan harga terjangkau dan spesifikasi yang sesuai terutama bagi individu atau pelaku usaha mikro kecil dengan kebutuhan untuk situs web ringan, seperti blog pribadi atau platform untuk memperkenalkan produk. Dalam penelitian ini, didapatkan data sepuluh penyedia jasa layanan VPS Cloud dengan harga terjangkau, dengan kriteria harga, kapasitas RAM, jumlah CPU, kapasitas penyimpanan, jenis penyimpanan, bandwidth, dan sistem operasi yang akan dihitung menggunakan metode ROC (Rank Order Centroid) dan pemodelan MAIRCA (Multi Attribrute Ideal Real Comparative Analysis). Metode ROC akan merangking kriteria tersebut berdasarkan urutan prioritas dan kepentigan dengan prioritas utama adalah kriteria harga (cost). Metode MAIRCA digunakan untuk membandingkan nilai ideal dan nilai sebenarnya. Hasil yang didapatkan melalui penelitian ini, terkait dengan penyedia layanan VPS Cloud yang berada pada peringkat ke-1 adalah Dewaweb dengan nilai akhir 0,0883.</p> 2024-09-26T08:50:43+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1060 Analysis of LoRaWAN Network Signal Coverage and Quality Parameters in Real-Time: Case Study of Cikumpa River Water Quality Monitoring, Depok City 2024-11-01T10:26:24+07:00 Hasri Ariansa hasri@student.jgu.ac.id Legenda Prameswono Pratama legend92pp@gmail.com Safira Faizah safirafaizah@jgu.ac.id Arisa Olivia Putri arisa@jgu.ac.id Ariep Jaenul ariep@jgu.ac.id Brainvendra Widi Dionova brainvendra@jgu.ac.id Safaa Najah Sahud Al-Humairi safaa_najah@msu.edu.my M. N. Mohammed dr.mohammed.alshekhly@gulfuniversity.edu.bh <p>In the context of an increasingly advanced era, Internet of Things (IoT) technology has emerged as a significant innovation across a range of fields. One of the most rapidly developing Internet of Things (IoT) technologies is the Long Range Wide Area Network (LoRaWAN). LoRaWAN is capable of long-distance communication while simultaneously consuming minimal power. In this study, we analyze the coverage of the LoRaWAN network in transmitting data with Cikumpa river water objects, with a 100–600 meters distance between the transmitter (TX) and receiver (RX). This study assesses the RSSI network quality, LoRaWAN SNR, and LoRaWAN network QoS quality concerning throughput, delay, jitter, and packet loss parameters. The testing results demonstrated that the LoRaWAN network coverage reaches a maximum distance of 600 meters. Researchers conducted the testing in the Cikumpa River area. They then analyzed the RSSI and SNR test results in the morning, afternoon, and evening. The results of the RSSI test and calculations demonstrate that as the distance between the transmitter and receiver increases, the RSSI value decreases. The RSSI testing conducted in the morning exhibited a range of -99 dBm to -121 dBm, with the SNR values spanning from -3.25 dB to 8.75 dB. The results of the daytime RSSI tests ranged from -104 dBm to -124 dBm, with the corresponding SNR values ranging from -8.50 dB to 9.00 dB. The RSSI test results for the afternoon period exhibited a range of -96 dBm to -120 dBm, while the SNR demonstrated a range of -7.25 dB to 9.00 dB. In addition, the quality of service (QoS) can be considered stable based on the results of the RSSI and SNR for each test. During the testing process, conducted at distances between 100 and 600 meters, there was no packet loss when data transmission occurred. This research demonstrates the potential for utilizing LoRaWAN technology to monitor a desired object remotely.</p> 2024-10-07T10:27:55+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1063 Comparison of Deep Neural Networks and Random Forest Algorithms for Multiclass Stunting Prediction in Toddlers 2024-11-01T10:26:24+07:00 Wulan Sri Lestari wulan.lestari@mikroskil.ac.id Yuni Marlina Saragih yuni.saragih@mikroskil.ac.id Caroline caroline.chong@mikroskil.ac.id <p>Stunting in toddlers is a serious global health issue, with long-term impacts on physical growth and cognitive development. To address this problem more effectively, it is crucial not only to identify whether a child is stunted but also to predict the severity of the condition. Multiclass stunting prediction offers deeper insights into a child’s condition, enabling more precise and targeted interventions. This study aims to compare the performance of multiclass stunting prediction models using two machine learning algorithms: Deep Neural Networks and Random Forest. The research process involved data collection, preprocessing, as well as model development and testing. The results show that the Random Forest model achieved 100% accuracy in training and 99.92% accuracy in testing, while the Deep Neural Networks model achieved 93.49% accuracy in training and 93.21% in testing. Both models demonstrated strong performance in multiclass stunting prediction, with Random Forest proving superior in terms of accuracy compared to Deep Neural Networks.</p> 2024-10-07T00:00:00+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1024 Penerapan Metode Simple Additive Weighting (SAW) Dalam Pemilihan Supplier Terbaik Pada Industri Manufaktur 2024-11-01T10:26:25+07:00 Zaenul Muttaqin acc.muttaqinzaenul@gmail.com Dini Handayani 2211601727@student.budiluhur.ac.id Gandung Triyono gandung.triyono@budiluhur.ac.id <p>Memilih supplier didalam rantai pasok industri manufaktur merupakan hal yang sangat penting untuk keberhasilan operasional dan daya saing perusahaan, karena mempengaruhi biaya, efisiensi, kualitas produk, kepuasan pelanggan, dan reputasi perusahaan. Dalam konteks globalisasi dan kompleksitas rantai pasok yang meningkat, berbagai kriteria seperti kualitas produk, ketepatan waktu pengiriman, dan kepatuhan terhadap standar internasional seperti International Organization for Standardization (ISO) 22000:2018 dan ISO 9001:2015 harus dipertimbangkan untuk memastikan pemenuhan kebutuhan jangka pendek serta keberlanjutan operasional jangka panjang. Penelitian ini bertujuan mengatasi masalah pemilihan supplier terbaik dengan menerapkan metode Simple Additive Weighting (SAW), yang efisien dalam mengevaluasi kriteria relevan. Langkah awal melibatkan identifikasi kriteria penilaian yang relevan seperti kualitas, waktu pengiriman, dan kepatuhan standar ISO, kemudian memberikan bobot pada setiap kriteria berdasarkan tingkat kepentingannya. Data kinerja supplier dikumpulkan secara sistematis dan diproses melalui metode Simple Additive Weighting (SAW) untuk menghasilkan peringkat relatif dari setiap supplier. Hasil penelitian menunjukkan supplier V7 memperoleh peringkat tertinggi dengan nilai 50,8, memberikan kontribusi berharga dalam pemahaman dan pemilihan supplier terbaik dalam konteks keandalan, kualitas, dan kepatuhan standar industri, serta menunjukkan bahwa penggunaan metode Simple Additive Weighting (SAW) meningkatkan efisiensi perhitungan dan pengelolaan data.</p> 2024-10-07T00:00:00+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1071 Coloring Pekalongan Batik Using a Madura Dataset: A Comparative Study of GAN and Caffe-Based CNN Models 2024-11-01T10:26:22+07:00 Muhamad Machrus Ali Wahyudi machrusaw99@gmail.com Arik Kurniawati arik.kurniawati@trunojoyo.ac.id Fitri Damayanti fitrid@trunojoyo.ac.id I Ketut Adi Purnawan adipurnawan@unud.ac.id <p>Madura Batik, as one of Indonesia's valuable cultural heritages, is known for its unique characteristics involving the use of bright colors such as red, yellow, and green, as well as traditional motifs that often feature elements of nature like flowers, leaves, and animals. Each motif in Madura Batik reflects the rich philosophy, values, and stories of Madura culture. This batik is also famous for its production process, which is largely carried out manually using traditional dyeing techniques. However, with the advancement of technology, there is a growing need to integrate technological innovations into the batik dyeing process without losing its traditional essence. This research combines Generative Adversarial Networks (GAN) models and compares them with Caffe-based pretrained Convolutional Neural Networks (CNN) to create new color variations in Pekalongan batik images. The input for the models is grayscale batik images, which are then processed to generate colorful outputs. The dataset used consists of 519 Madura batik images, with a distribution of 80% for training, 20% for validation, and 10 images for testing. The preprocessing process includes resizing, normalization, and batching to accelerate model convergence. Performance evaluation is conducted using FID, MSE, PSNR, and SSIM metrics. The results show that the GAN model with 100 epochs produces better image quality compared to the Caffe-based pretrained CNN model, particularly in terms of visual and structural similarity. In conclusion, the GAN method offers great potential for innovation in batik coloring without compromising its traditional motifs.</p> 2024-10-18T13:55:12+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1068 The Role of Information and Communication Technology in Advancing Sustainable Energy Transition in Developing Countries: Progress, Opportunities and Challenges 2024-11-01T10:26:23+07:00 Yusak Tanoto tanyusak@petra.ac.id <p>Sustainable energy transitions in developing countries are critical for balancing economic growth and environmental sustainability. Transitioning to renewable energy sources alleviates energy poverty and reduces reliance on fossil fuels. Information and communication technology (ICT) plays an important role in advancing the energy transition and achieving low-carbon energy utilization by facilitating the transition of power sectors to renewable energy sources. This paper provides an overview of the role of ICT in achieving sustainable energy transition in developing countries and jurisdictions. It emphasises the significance of SDG 7 and other sustainable energy transition indices for energy access and transition, as well as presenting their status and progress in various regions, including developing countries. This paper also discusses several types of available ICT tools and methods that enable digitalization in the power sector, such as smart grids, smart metres, energy management systems, Internet of Things (IoT) for energy, and renewable energy monitoring systems, as well as the opportunities and challenges of incorporating ICT into the context of developing countries' sustainable power sector.</p> 2024-10-14T13:10:35+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1061 Design and Construction of a Web-Based Fixed Asset Management System with a Combination of Straight Line Method, MAUT, and Telegram Bot Integration: Case Study of North Lombok District Hospital 2024-11-01T10:26:22+07:00 I Made Teguh Arthana teguharthana@gmail.com Ni Kadek Ayu Wirdiani ayuwirdiani@unud.ac.id Desy Purnami Singgih Putri desysinggihputri@unud.ac.id <p>North Lombok District Hospital is a health service institution in North Lombok District, West Nusa Tenggara Province, that provides health facilities and services to the community. Health service facilities provided to the community come from fixed assets owned by the North Lombok District Hospital. Management of fixed assets used for health service facilities at the North Lombok District Hospital is still done manually in planning, receiving, repairing, maintaining, and releasing assets. So, hospital employees have difficulty managing the assets they own. This study was conducted to help design and build a fixed asset management information system at the North Lombok Hospital using the SDLC Method with the Waterfall Model approach and system development using PHP, HTML, CSS, and JS languages with the Laravel Framework and MYSQL Database. This study uses the Straight Line Method to calculate asset depreciation, the MAUT Method to assist in decision-making for the elimination of damaged assets, and the Telegram Bot to send notifications from the website to each unit group in the hospital. The final result of this study is a web-based fixed asset management information system with developed features, namely asset planning features, asset planning change features, asset handover minutes features, asset inventory features, asset maintenance features, asset repair features, asset write-off features, asset whitening features, asset reporting features, master data features, and user access rights management features. The testing method used in this study is the Blackbox testing method, which tests the functionality of the system using 150 test scenarios on eight employees of the North Lombok Regional Hospital, with the test results showing that the system is running well and in accordance with the SOP that has been given, PSSUQ testing was carried out to evaluate user satisfaction with the system. The test results showed a SysUse subscale value of 1.93, IntQual 1.6, InfoQual 1.92, and Overall 1.93. Based on the results of the PSSUQ test, it can be concluded that the fixed asset management system has run very well and meets user expectations.</p> 2024-10-22T00:00:00+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1075 Classification of Student Learning Styles Using Artificial Neural Networks on Imbalanced Data 2024-11-01T10:26:23+07:00 Fikri Baharuddin fikribaharuddin@staff.ubaya.ac.id Ahmad Miftah Fajrin ahmadmiftah@staff.ubaya.ac.id Felix Handani felix.handani@staff.ubaya.ac.id <p>The transformation of learning activities towards digital form since the COVID-19 pandemic can affect students' learning process. One of the factors that can affect this learning process is the learning style owned by each student. Learning patterns that are not in line with students' learning styles can influence their learning process. This study aims to identify students' learning styles based on data extracted from the Moodle Learning Management System (LMS). The research methods applied in this study include data collection by extracting data from Moodle LMS logs and classifying student learning styles using the Artificial Neural Network (ANN) algorithm. This study uses 310 log extraction data on the Moodle platform. The Isolation Forest algorithm was applied to this study to detect anomalies or outliers in the dataset. The data used in this study also has an unbalanced distribution of data per class. To prevent the performance degradation of the classifier model caused by the imbalance of data distribution, this study uses the SMOTE algorithm which can generate new synthetic data on minority class. This study combines three algorithms consisting of the Isolation Forest Algorithm for dataset management, the SMOTE Algorithm to solve the problem of data imbalance, and the ANN Algorithm to build a classification model. The model evaluation is carried out by considering the values of accuracy, precision, recall, and F1-Score to identify the reliability level of the produced model. Based on the research, this study produced a classifying model with an accuracy of 96%. The model produced in this study can be used to identify students' learning styles and as a reference for improving the quality of the teaching and learning process.</p> 2024-10-15T14:02:21+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1082 The Role of UTAUT2 in Understanding Technology Adoption: A Study of the Merdeka Mengajar Platform Among Indonesian Teachers 2024-11-01T10:26:23+07:00 Siti Aminah sitiaminah@stiki.ac.id Addin Aditya addin@stiki.ac.id Yekti Asmoro Kanthi yektiasmoro@stiki.ac.id <p>This research investigates the adoption of the Merdeka Mengajar application using the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) framework. The study aims to identify the factors influencing teachers' behavioral intentions and usage behavior regarding this educational technology platform. A total of 383 teachers from various levels in Malang were sampled from a broader population of 8,936. Statistical analysis uses SEM (Structural Equation Modelling) analysis techniques. The findings suggest that performance expectancy, effort expectancy, social influence, hedonic motivation, and price value significantly influence behavioral intention. However, facilitating conditions and habit do not show a direct significant impact on use behavior. These results indicate that while technological support such as infrastructure and internet access is necessary, it alone may not be enough to motivate consistent usage without internal factors like perceived usefulness or enjoyment of the app. Moreover, the habitual use of new technology may require additional support and time before it can significantly affect behavior. This study contributes valuable insights into the adoption of educational technologies, especially in the Indonesian context, where digital learning platforms are increasingly being integrated into teaching practices. Future research may explore how ongoing support and user experience improvements can further enhance the app's adoption.</p> 2024-10-14T14:47:17+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1006 Analisis Faktor Yang Mempengaruhi Kepuasan Pengguna Media Sosial X Menggunakan Metode End User Computing Satisfaction (EUCS) 2024-11-01T10:25:53+07:00 Flourensia Sapty Rahayu saptyrahayu@gmail.com Generosa Lukhayu Pritalia generosa.pritalia@uajy.ac.id Felix Kurniawan fkmgame12@gmail.com <p>Aplikasi media sosial adalah salah satu teknologi berbasis internet yang menghubungkan masyarakat dalam mengekspresikan diri, melakukan kolaborasi, dan menyebarkan serta memperoleh data informasi secara digital. Beberapa tahun belakangan ini, aplikasi media sosial Twitter menuai kontroversi akibat diakuisisi dan melakukan rebranding menjadi X dimana merupakan aplikasi microblogging yang memungkinkan penggunanya dalam mengunggah status atau opini terkait suatu objek atau fenomena, menyiarkan berita, periklanan, hingga isu politik. Sampai saat ini, X belum diketahui telah terbukti mampu memberikan kepuasan terhadap penggunanya dimana akan bermanfaat apabila hal tersebut dievaluasi. Penelitian ini bertujuan untuk mengidentifikasi faktor-faktor yang berkontribusi terhadap tingkat kepuasan pengguna aplikasi media sosial X dengan End-User Computing Satisfaction (EUCS) sebagai teori dan model penelitian. Metodologi dari penelitian ini menggunakan pendekatan kuantitatif dengan melibatkan 384 responden. Data dari responden diolah dan dianalisa dengan bantuan software Statistical Product and Service Solutions (SPSS). Hasil penelitian menunjukkan responden pengguna aplikasi media sosial X merasakan kepuasan yang cukup baik dimana setiap faktor dari EUCS yaitu konten, akurasi, tampilan, kemudahan penggunaan, serta ketepatan waktu secara signifikan dan parsial mempengaruhi kepuasan pengguna aplikasi media sosial X.</p> 2024-10-29T15:00:10+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1067 Classification of Foods Based on Nutritional Content Using K-Means and DBSCAN Clustering Methods 2024-11-01T10:26:21+07:00 Fitria Nurulhikmah fitrianhikma@gmail.com Deden Nur Eka Abdi 6025232025@student.its.ac.id <p>This study classifies foods based on their nutritional content using K-Means and DBSCAN clustering methods. The clustering quality was evaluated using the Davies-Bouldin Index (DBI) and Silhouette Score. K-Means was tested with different k values, while DBSCAN was analyzed with varying min_samples parameters. Additionally, a function was developed to group foods into three categories: Weight Gain, Obesity Prevention, and Weight Loss, based on calories, protein, fat, and carbohydrate content. The results show that K-Means is more effective than DBSCAN in clustering foods by nutritional content, yielding lower DBI values and higher Silhouette Scores. For example, K-Means with k = 3 achieved a DBI of 0.694930 and a Silhouette Score of 0.538921, while DBSCAN with eps = 0.75 and min_samples = 4 produced a DBI of 0.34546577 and a Silhouette Score of 0.492830814. This study concludes that K-Means provides superior clustering performance, enabling more specific dietary recommendations tailored to individual nutritional needs.</p> 2024-10-29T09:12:01+07:00 Copyright (c) 2024 Teknika https://ejournal.ikado.ac.id/index.php/teknika/article/view/1093 Perancangan Aplikasi Mobile Menggunakan Machine Learning Untuk Menentukan Klasifikasi Kategori Berita 2024-11-01T10:26:21+07:00 Novi Tri Hariyanti novi@ikado.ac.id Titasari Rahmawati tita@ikado.ac.id Alexander Wirapraja awirapraja85@gmail.com <p>Berita yang umumnya terdapat pada media publikasi baik elektronik maupun media cetak yang beredar setiap harinya dalam volume yang besar, saat ini sebagian besar telah berpindah ke media digital yang memudahkan pengguna untuk mengakses artikel berita. Jumlah peredaran berita yang besar setiap harinya inilah yang seringkali membebani kerja dari editor dan penulis berita dalam menentukan kategori dari berita yang akan dirilis. Sistem ini dirancang untuk membantu dalam melakukan klasifikasi kategori berita, pada aplikasi ini aplikasi dirancang dalam bentuk aplikasi portal berita berbasis aplikasi mobil berbasis android. Pada penelitian ini menggunakan metode logistic regression sebagai metode klasifikasi biner dengan dataset yang digunakan pada penelitian ini merupakan judul berita yang dipublikasikan pada tahun 2020 dengan pembagian data sekitar 2000 dataset. Hasil dari penelitian ini adalah sistem aplikasi yang membantu dalam melakukan klasifikasi kategori berita dengan tingkat akurasi diatas 85%.</p> 2024-10-28T11:33:16+07:00 Copyright (c) 2024 Teknika