cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Rochmat Aldy Purnomo
Contact Email
purnomo@umpo.ac.id
Phone
-
Journal Mail Official
multitek@umpo.ac.id
Editorial Address
-
Location
Kab. ponorogo,
Jawa timur
INDONESIA
Multitek Indonesia : Jurnal Ilmiah
Published by Universitas Muhammadiyah Ponorogo
ISSN : 19076223     EISSN : 25793497     DOI : -
Core Subject : Science, Engineering,
Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering
Multitek Indonesia : Jurnal Ilmiah is a journal published by the Technic Faculty, Universitas Muhammadiyah Ponorogo (Unmuh Ponorogo) in collaboration with Universitas Muhammadiyah Ponorogo Research and Community Service. Published twice a year (June and Desember), contains six to ten articles and receive articles in the field of technic review studies with research methodologies that meet the standards set for publication. Manuscript articles can come from researchers, academics, practitioners, and other technic observers who are interested in research in the field of tehnic.
Arjuna Subject : -
Articles 7 Documents
 1 
Search results for , issue "Vol 18 No 2 (2024): Desember" : 7 Documents clear
PENERAPAN ALGORITMA K-MEANS, DBSCAN, DAN AHC UNTUK CLUSTERING KUALITAS GARAM PADA PT. GARAM (PERSERO) Putro, Sigit Susanto; Syarief, Mohammad; Rochman, Eka Mala Sari
MULTITEK INDONESIA Vol 18 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/mtkind.v18i2.8501

Abstract

Garam merupakan barang hasil produksi rakyat yang berperan penting dalam memenuhi kebutuhan konsumen dan berbagai kegiatan industri. Kualitas garam dapat mempengaruhi berbagai aspek, termasuk kesehatan, cita rasa makanan, dan penggunaan dalam kegiatan industri. Kualitas garam yang buruk dapat mempengaruhi kualitas produk akhir yang dihasilkan. Oleh sebab itu, perlu dilakukan pengelompokan kualitas garam untuk memastikan bahwa garam yang digunakan sesuai dengan kebutuhan dan standar kualitas untuk kebutuhan tertentu. Berkaitan dengan tujuan tersebut penelitian ini menerapkan 3 metode berbeda yaitu K-means, DBSCAN, dan AHC. K-means adalah algoritma clustering yang membagi data ke dalam K kelompok dengan cara meminimalkan jarak antara titik data dan pusat cluster. Agglomerative Hierarchical Clustering adalah metode dalam analisis data yang mengelompokkan objek-objek berdasarkan kesamaan karakteristik dengan cara menggabungkan kelompok-kelompok secara hirarki. DBSCAN adalah algoritma clustering yang menggunakan kerapatan spasial untuk mengelompokkan data. Dari jumlah data sebanyak 350 dengan 9 fitur yang berasal dari PT. Garam Sumenep yang di kelompokkan menggunakan tiga metode dilakukan pengujian kualitas clustering menggunakan silhuette coefficient yang menghasilkan nilai 0.345 untuk metode K-means, 0.32 untuk metode AHC dan 0.5 untuk metode DBSCAN.
SISTEM MONITORING SMART UPS BERBASIS TELEGRAM BOT DAN PREDIKSI PEMADAMAN LISTRIK DENGAN ARMA DI RUMAH SAKIT MITRA KELUARGA SURABAYA Novianti, Triuli; Akbar, Ridho
MULTITEK INDONESIA Vol 18 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/mtkind.v18i2.9177

Abstract

Uninterruptible power supply (UPS) digunakan sebagai sumber listrik cadangan jika listrik PLN padam. Perangkat UPS dapat melindungi segala jenis alat elektronik sensitif dari ketidakstabilan arus dan tegangan listrik. Rumah Sakit Mitra Keluarga Surabaya memiliki UPS 6 KVA dan 10 KVA yang digunakan untuk berbagai perangkat elektronik, termasuk komputer, peralatan medis, dan lainnya. Rumah Sakit Mitra Keluarga Surabaya juga menggunakan UPS sebagai perangkat backup atau pencadangan tegangan. Penelitian ini membuat sistem monitoring untuk menyelesaikan masalah yang sering terjadi pada unit UPS, seperti gagal memback-up atau mencadangkan daya saat pemadaman listrik. Sistem ini memantau UPS secara menyeluruh untuk memastikan bahwa mereka aman dan tidak rusak dengan cepat. Alat ini terdiri dari komponen mikrokontroller ESP-32, display LCD 20x4 I2C, sensor suhu MLX-90614, sensor tegangan dan arus PZEM-004T, dan bot Telegram. Sistem monitoring ini akan memantau suhu, tegangan, dan arus unit UPS. Adapun hasil prediksi ARMA menunjukkan bahwa ada 16 pemadaman listrik pada tahun 2019, 15 pemadaman listrik pada tahun 2020, 13 pemadaman listrik pada tahun 2022, dan 12 pemadaman listrik pada tahun 2023. Dengan demikian, prediksi pemadaman listrik selama 12 bulan pada tahun 2024 adalah 11 kali, dengan tingkat RMSE atau error data 0,8574011. Nilai RMSE ini dianggap sebagai nilai yang sangat baik.
GOLDFISH AQUARIUM WATER QUALITY CONTROL AND MONITORING SYSTEM USING FLC Santoso, Budi; Panuntun, Wisnuning Diah
MULTITEK INDONESIA Vol 18 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/mtkind.v18i2.9618

Abstract

Goldfish is a unique type of carp. Its interesting shape makes it popularly kept by people as a hobby or business. In goldfish farming, it is necessary to manage water quality properly to meet the required water quality criteria to support their life. In this study, a water quality monitoring and control system was developed so that breeders can observe water quality conditions online, and the water quality control process can be carried out automatically. The system utilizes two sensors, namely turbidity sensor and pH sensor, to detect turbidity and pH levels in the aquarium water. The method employed in this study utilizes fuzzy logic to control the filter and pump in the aquarium. The results of the trial showed that turbidity decreased by 21.84%, from an initial value of 16.66 NTU to 13.02 NTU, and pH decreased by 15.26%, from an initial value of 7.86 to 6.66.
OPTIMIZING SENTIMENT ANALYSIS FOR USABILITY TESTING: ENHANCING SVM ACCURACY THROUGH KERNEL SELECTION AND TUNING METHODS Basri, Hasan
MULTITEK INDONESIA Vol 18 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/mtkind.v18i2.10615

Abstract

With over 2.4 million apps on the Google Play Store by 2023, app developers face increasing demands to ensure high usability quality to remain competitive. Traditional usability testing methods, including heuristic evaluations and user questionnaires, are often limited by high costs, time constraints, and lack of real-world context. Sentiment analysis presents an alternative approach, leveraging user reviews as a resource for usability insights. This research applies Support Vector Machine (SVM) for sentiment analysis and usability testing on Google Play Store reviews, focusing on five usability criteria. Data collection yielded 2,000 reviews from a banking app, with two annotators conducting multi-label labeling for both sentiment and usability criteria. Through a series of experiments, the Linear Kernel in SVM demonstrated the highest performance, achieving 70.50% accuracy, an F1 Score of 0.8618, and a Hamming Loss of 0.0783. Grid Search was employed to optimize the C parameter for the linear kernel, revealing an optimal C value of 0.01, which resulted in an improved accuracy of 75.20%, F1 Score of 0.8775, and Hamming Loss of 0.0686. Experiments with values above or below 0.01 showed decreased accuracy, underscoring the importance of a balanced C value to enhance model generalization and avoid overfitting. These findings suggest that sentiment analysis via SVM can effectively capture usability feedback from user reviews, providing a scalable, data-driven solution for app usability assessment. This study is part of the Machine Learning for Software Engineering (ML4SE) domain, where machine learning techniques are applied to enhance software engineering practices, specifically in optimizing usability assessment through automated analysis of user feedback.
PENGGUNAAN ALGORITMA K-NEAREST NEIGHBOR (K-NN) UNTUK PREDIKSI CUACA DENGAN DATA RECORD Verian Dwi Saputra, Rezano; Tsaqila, Siti Lathifah; Widaningrum, Ida; Karaman, Jamilah
MULTITEK INDONESIA Vol 18 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/mtkind.v18i2.11092

Abstract

Desa Plancungan, Kecamatan Slahung, Kabupaten Ponorogo, merupakan penghasil tembakau,  salah satu produk pertanian yang berperan penting dalam mendukung mata pencaharian,  pertumbuhan ekonomi, dan penyerapan tenaga kerja. Di desa ini, petani membudidayakan  tembakau rajangan, termasuk tembakau Virginia. Namun, proses penjemuran tembakau yang  dilakukan di ruang terbuka selama dua hingga tiga hari sangat bergantung pada kondisi cuaca  yang tidak menentu, yang sering kali memengaruhi kualitas hasil panen. Untuk mengatasi  tantangan tersebut, penelitian ini menerapkan algoritma K-Nearest Neighbor (K-NN) guna  memprediksi cuaca di Desa Plancungan. Data cuaca dikumpulkan menggunakan alat  mikrokontroler yang dipasang di lokasi, yang merekam tiga parameter utama: suhu,  kelembapan, dan tekanan udara. Dari total 10.000 data yang diperoleh, sebanyak 2.500 data  digunakan untuk pelatihan dan pengujian algoritma. Hasil penelitian berupa prediksi cuaca—hujan, cerah, atau berawan—ditampilkan dalam bentuk halaman web. Informasi ini memungkinkan petani mendapatkan gambaran kondisi cuaca lebih awal, sehingga mereka dapat merencanakan langkah antisipasi untuk menjaga kualitas hasil panen dan mengoptimalkan  proses penjemuran tembakau di tengah tantangan cuaca yang berubah- ubah.
ANALISIS SENTIMEN BERDASARKAN KOMENTAR PUBLIK TERHADAP SITUS BELANJA ONLINE PADA FACEBOOK (STUDI KASUS: AKUN FACEBOOK OFFICIAL SHOPEE, LAZADA DAN TOKOPEDIA) Prasetya, Angga Hadi; Buntoro, Ghulam Asrofi; Astuti, Indah Puji
MULTITEK INDONESIA Vol 18 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/mtkind.v18i2.11814

Abstract

Online shopping is the process of buying goods and services from merchants that are sold or presented on theinternet. Consumers can visit online shopping sites from home or the office comfortably while sitting in front ofa computer or smartphone. As many as 43% agree that social media is a tool to meet the need for knowledge inthe form of product reviews and forum reviews to help make purchasing decisions. Product reviews and forumreviews are conveyed through comments on social media containing complaints, praise, or views on products orservices from an online shopping site. In Indonesia, there are several e-commerce sites used by consumers. Inthis case, the author only emphasizes the three e-commerce sites, namely Shopee, Tokopedia, and Lazada. Theauthor decided to choose these three sites as research objects because there are many reviews on the three sites,especially on Facebook social media, and to find out the general picture of the perception of Indonesian peoplewho use Facebook towards online shopping sites Lazada, Shopee, and Tokopedia. This analysis provides resultsthat the sentiment of these three online stores tends to get positive sentiment based on comments on Facebooksocial media.
PENGARUH CONVOLUTIONAL NEURAL NETWORK UNTUK PROSES DETEKSI PENYAKIT PADA DAUN TOMAT Renaldy, Aldi; Litanianda, Yovi; Zulkarnain, Ismail Abdurrazzaq
MULTITEK INDONESIA Vol 18 No 2 (2024): Desember
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/mtkind.v18i2.11816

Abstract

Tomato plants are one of the plants that are often planted by farmers and are the main food requirement insociety. Tomato cultivation is often faced with disease problems that can attack the leaves, stems and fruit.However, many farmers often face difficulties in overcoming this problem. To solve this problem, researcherswill use a web-based system that is able to classify images of tomato leaves. The system will process the imagefirst before training the CNN model. The resulting model will be used to classify images entered through thewebsite. Apart from that, this design also has several useful benefits. The results of the analysis of the modelshow that there are challenges in distinguishing the characteristics of diseases in tomato plants, so that thedevelopment of the CNN model experiences difficulties. Despite these difficulties, the CNN algorithm providesan accuracy score of 0.9091. This number reflects the model's level of accuracy in classifying images into thecorrect categories. From these results, it can be concluded that disease detection in tomato plants using theCNN algorithm requires special effort and attention, especially in collecting representative datasets andmodeling optimal CNN architecture. A deeper understanding of the characteristics of diseases in tomato plantsalso needs to be considered to increase the accuracy of model predictions. Although there is still room forimprovement, these results provide a basis for continuing to develop and improve disease detection models intomato plants using CNN approaches.

Page 1 of 1 | Total Record : 7

 1 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol 19 No 2 (2025): Desember Vol 19, No 1 (2025): Juli Vol 19 No 1 (2025): Juli Vol 18 No 2 (2024): Desember Vol 18, No 2 (2024): Desember Vol 18, No 1 (2024): Juli Vol 18 No 1 (2024): Juli Vol 17, No 2 (2023): Desember Vol 17 No 2 (2023): Desember Vol 17 No 1 (2023): Juli Vol 17, No 1 (2023): Juli Vol 16, No 2 (2022): Desember Vol 16, No 1 (2022): Juli Vol 15, No 2 (2021): Desember Vol 15, No 1 (2021): Juli Vol 14, No 2 (2020): Desember Vol 14, No 1 (2020): Juli Vol 13, No 2 (2019): Desember Vol 13, No 1 (2019): Juli Vol 12, No 2 (2018): Desember Vol 12, No 1 (2018): Juli Vol 11, No 2 (2017): Desember Vol 11, No 1 (2017): Juni Vol 10, No 2 (2016): Desember Vol 8, No 1 (2014): JUNI Vol 10, No 1 (2016): Juni Vol 9, No 1 (2015): Juni Vol 7, No 1 (2013): JUNI Vol 6, No 2 (2012): DESEMBER Vol 6, No 1 (2012): Juni More Issue