Claim Missing Document
Check
Articles

Found 23 Documents
Search

SISTEM INFORMASI INVENTARIS BERBASIS WEB BIDANG PRODUKSI CV. TRI UTAMI JAYA : indonesia Muhammad Tahir; I Wayan Mustika Nayottama Adi Wijaya; Muhammad Wisnu Alfiansyah; Kurniadin Abd. Latif; I Nyoman Switrayana
Jurnal Manajemen Informatika dan Sistem Informasi Vol. 8 No. 2 (2025): MISI Juni 2025
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36595/misi.v8i2.1625

Abstract

Sistem informasi inventaris berbasis web ini dibuat untuk mempermudah dan mempercepat proses manajemen inventaris produksi pada CV. Tri Utami Jaya, sebuah perusahaan pengolah produk berbahan dasar kelor. Sistem manual sebelumnya menimbulkan berbagai kendala, seperti human error dan keterlambatan pencatatan. Solusi ini mengintegrasikan teknologi QR Code dan basis data MySQL untuk pencatatan barang masuk dan keluar secara real-time. Fitur utama meliputi pemindaian QR Code, manajemen data barang dan supplier, serta pelaporan inventaris. Hasil Implementasi sistem menunjukkan efisiensi operasional yang lebih tinggi, kesalahan yang lebih rendah, dan pelacakan stok yang lebih akurat, menjadikannya solusi efektif untuk pengelolaan inventaris yang modern dan terstruktur.
Optimizing Scalability in Spice Identification through Transfer Learning with Convolutional Neural Networks Switrayana, I Nyoman; Azwar, Muhamad
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.35453

Abstract

Indonesia is renowned for its rich diversity of spices, which hold significant cultural and economic value. However, public knowledge of these spices remains limited, making their identification challenging. Addressing this issue, this study aims to develop a scalable spice identification system using Convolutional Neural Networks (CNN) with a Transfer Learning approach. The system is designed to recognize 30 types of spices while maintaining high accuracy, utilizing the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework for systematic development. The dataset was collected through open sources and web scraping from Google Images. Four CNN models (ResNet50, EfficientNetB0, Xception, and MobileNet) were evaluated under three data splits: 90:10, 80:20, and 70:30. Performance metrics including accuracy, precision, recall, and F1-score were used for evaluation. Among these models, Xception achieved the best performance in the 90:10 split, with an accuracy of 84.51%, followed by EfficientNetB0 at 83.57%. The results demonstrate that transfer learning effectively enhances model accuracy and scalability, enabling reliable spice identification across diverse categories. This system has practical implications for promoting public awareness, supporting culinary industries, and preserving Indonesia’s rich spice heritage. The proposed approach highlights the potential of CNN-based systems for addressing classification challenges in resource-constrained settings, offering a foundation for future research and real-world applications.
Implementasi Aplikasi Microsoft Power BI Untuk Pengolahan dan Visualisasi Data Strategis Pemilu 2024 Bukran, Bukran; Switrayana, I Nyoman; Kayohana, Ketut Widya; Alfiansyah, Muhamad Wisnu
Jurnal Pengabdian Pada Masyarakat IPTEKS Vol. 1 No. 1: Jurnal Pengabdian Pada Masyarakat IPTEKS, Desember 2023
Publisher : CV. Global Cendekia Inti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71094/jppmi.v1i1.29

Abstract

This research focuses on the use of Microsoft Power BI by the DPD PKS Lombok Tengah Data Team in processing and visualizing strategic data for the 2024 election to formulate an effective winning strategy. This research begins with a brief background that highlights the increasing importance of data-based decision making in political campaigns. The primary objective was to assess the impact of implementing Microsoft Power BI in improving the team's analytical capabilities and informing strategic decisions for electoral success. The research utilized a comprehensive methodology involving training sessions and practical application of Microsoft Power BI. The results showed significant improvements in the team's proficiency in data analysis and visualization. Achievements include the successful integration of Microsoft Power BI into the election strategy formulation process, empowering the team to make informed decisions based on in-depth data visualization. This research contributes to the ever-evolving world of political campaigns by demonstrating the practical benefits of implementing advanced data processing tools for election success.
PERAN ARTIFICIAL INTELLIGENCE DALAM MENINGKATKAN KREATIVITAS WIRAUSAHAWAN PEMULA Mulawarman, Logi; Alfiansyah, Muhamad Wisnu; Switrayana, I Nyoman
JAIM: Jurnal Aliansi Ilmu Multidisiplin Vol. 1 No. 1 (2025): Januari 2025
Publisher : CV Sentra Nusa Connection

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63545/jaim.v1.i1.99

Abstract

Perkembangan teknologi Artificial Intelligence (AI) telah membuka peluang baru dalam berbagai bidang, termasuk wirausaha. Penelitian ini bertujuan untuk menganalisis peran AI dalam meningkatkan kreativitas wirausahawan pemula. Dengan pendekatan kualitatif dan metode studi kasus, penelitian ini mengeksplorasi bagaimana AI dapat digunakan sebagai alat untuk menggali ide inovatif, mempermudah proses pengambilan keputusan, dan mengoptimalkan strategi bisnis. Data dikumpulkan melalui wawancara mendalam dengan 10 wirausahawan pemula yang telah menggunakan alat berbasis AI, serta analisis dokumen pada artikel penelitian relevan. Analisis data pada penelitian ini memanfaatkan software NVivo. Hasil penelitian menunjukkan bahwa AI mampu mempercepat proses brainstorming, memberikan wawasan berdasarkan data yang kompleks, dan membantu dalam menciptakan solusi kreatif untuk tantangan bisnis. Namun, penelitian ini juga mengidentifikasi beberapa kendala, seperti keterbatasan akses terhadap teknologi canggih dan kurangnya literasi digital di kalangan wirausahawan pemula. Implikasi dari penelitian ini menyoroti pentingnya pelatihan dan edukasi AI untuk mendorong kreativitas yang lebih produktif di sektor wirausaha.
Integrasi Bagging dan Stacking Untuk Memperbaiki Kinerja Algoritma Klasifikasi C4.5 dan K-Nearest Neighbor(KNN) Syahrir, Moch.; Switrayana, I Nyoman; Darmawan, I Made Angga Wahyu
JST (Jurnal Sains dan Teknologi) Vol. 14 No. 2 (2025): July
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jst-undiksha.v14i2.100794

Abstract

Permasalahan utama dalam klasifikasi data berdimensi tinggi adalah lambatnya proses pemindaian dan inkonsistensi akurasi model, yang berdampak negatif terhadap kualitas informasi dan pengambilan keputusan berbasis data. Dalam konteks prediksi risiko keuangan, seperti kredit macet, keterbatasan ini dapat menghambat efektivitas sistem pendukung keputusan. Penelitian ini bertujuan untuk mengevaluasi dan mengembangkan kinerja algoritma klasifikasi dasar, yaitu C4.5 dan K-Nearest Neighbor (KNN), melalui integrasi teknik ensemble learning bagging dan stacking. Penelitian ini merupakan penelitian kuantitatif dengan desain eksperimen komparatif. Subjek penelitian adalah empat dataset publik yang merepresentasikan data keuangan, yaitu Bank Marketing (41188 record), Credit Card (1319 record), Credit Risk Assessment (32581 record), dan Credit Card Defaulter (10000 record). Data dikumpulkan dari repositori Kaggle, kemudian diolah menggunakan algoritma C4.5 dan KNN yang diintegrasikan dengan teknik ensemble. Instrumen penelitian berupa implementasi model klasifikasi menggunakan perangkat lunak Rapid Miner dan Python, dengan pengujian validitas melalui k-fold cross validation dan pengukuran reliabilitas menggunakan metrik akurasi. Teknik analisis data meliputi pengujian performa model berdasarkan nilai akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa bagging dengan algoritma C4.5 memberikan hasil terbaik pada tiga dari empat dataset, masing-masing dengan akurasi 91,21%, 97,73%, dan 92,11%. Sedangkan pada dataset keempat, kombinasi bagging dan KNN menghasilkan akurasi tertinggi sebesar 97,06%. Simpulan dari penelitian ini adalah bahwa teknik bagging secara signifikan mampu meningkatkan akurasi dan konsistensi model klasifikasi dasar. Implikasi dari hasil ini menunjukkan bahwa integrasi metode ensemble dapat menjadi solusi praktis dan teoretis untuk meningkatkan kualitas klasifikasi dalam domain keuangan, khususnya dalam memprediksi risiko kredit.
Data Augmentation-Driven Predictive Performance Refinement in Multi-Model Convolutional Neural Network for Cocoa Ripeness Prediction Apriani, Apriani; Switrayana, I Nyoman; Hammad, Rifqi; Irfan, Pahrul; Pratama, Gede Yogi
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5298

Abstract

Timely and accurate prediction of cocoa fruit ripeness is critical for optimizing harvest schedules, improving yield quality, and supporting post-harvest processing. Conventional visual inspection methods are prone to subjectivity and inconsistencies, especially when distinguishing among multiple ripeness levels based on fruit age. This study proposes a deep learning approach that leverages multi-model convolutional neural network transfer learning combined with image data augmentation to classify cocoa fruit into four maturity stages derived from fruit age. An augmented dataset of cocoa fruit images was used to fine-tune five well-established pre-trained models: MobileNetV2, Xception, ResNet50, DenseNet121, and DenseNet169. Data augmentation techniques were employed to increase variability and improve model generalization. Model evaluation was conducted using a standard 80:20 training-to-testing split to ensure sufficient data for learning while preserving a representative test set across all ripeness classes. The results demonstrate that DenseNet169 consistently outperformed other models, achieving the highest average accuracy of 85,05%, followed by DenseNet121 84,06%. Across all models, the use of data augmentation led to notable performance gains, highlighting its importance in enhancing predictive capability and reducing overfitting. The proposed framework shows promising potential for automating ripeness classification in agricultural contexts, offering a robust, scalable, and accurate solution for intelligent cocoa harvest management. This work contributes to the growing application of deep learning in precision agriculture, particularly in addressing fine-grained classification problems using limited but enriched visual data.
A Robust Gender Recognition System using Convolutional Neural Network on Indonesian Speaker Switrayana, I Nyoman; Hadi, Sirojul; Sulistianingsih, Neny
Sistemasi: Jurnal Sistem Informasi Vol 13, No 3 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i3.3698

Abstract

Voice is one of the biometrics that humans have. Humans can be recognized by the sounds produced by their vocal cords and vocal tracts. One of the uses of voice is to recognize gender. Despite extensive research, gender recognition using machine learning remains unsatisfactory due to the complexity of voice features and the limitations of conventional algorithms. In this research, voice-based gender recognition is performed by applying deep learning. The deep learning model used is the Convolutional Neural Network (CNN). The input of CNN is the result of feature extraction from the Mel-Frequency Cepstral Coefficients (MFCC) method. MFCC produces Mel-Spectograms which are important features of sound. The dataset used is Indonesian speech. In the research, there are imbalanced and balanced dataset scenarios to see the performance of the model. To produce a balanced dataset, random undersampling is performed on the majority class. In addition, the effect of dividing training and testing data with a composition of 70:30, 80:20, and 90:10 was observed. The results show that the model has 100% accuracy for all imbalanced dataset scenarios. Then the highest accuracy is 99.65% for the balanced dataset scenario with 70:30 splitting. In summary, it can be concluded that CNN performs very well in identifying gender from voice features overall, although its performance decreases when random undersampling is applied to the dataset.
Sosialisasi Sadar Wisata dalam Mendorong Partisipasi Masyarakat untuk Pengembangan Pariwisata Berkelanjutan Roodhi, Mohammad Najib; Dakwah, Muhammad Mujahid; Abdurrahman, Abdurrahman; Muhtarom, Zamroni Alpian; Girsang, Zefanya Andryan; Bratayasa, I Wayan; Switrayana, I Nyoman; Nasri, Muhammad Haris
Bakti Sekawan : Jurnal Pengabdian Masyarakat Vol. 5 No. 1 (2025): Juni
Publisher : Puslitbang Sekawan Institute Nusa Tenggara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/bakwan.v5i1.785

Abstract

This community service activity was carried out with the main objective of increasing public awareness of the importance of tourism awareness as a foundation for achieving sustainable tourism development, particularly in the coastal area of Batu Layar, Senggigi. The activity was implemented using educational and participatory approaches involving more than 20 community partners, consisting of village officials, youth groups, MSME actors, community leaders, and local representatives. The implementation process included several key stages: delivering awareness material, conducting focused group discussions, simulating tourism service practices, and evaluating participants' understanding through pre-test and post-test assessments. The results of the activity showed a significant improvement in participants' understanding of tourism awareness concepts. This was evidenced by evaluation data, where the average pre-test score of 63.2 increased to 84.5 in the post-test. In addition to the cognitive improvements, this activity also resulted in tangible community impact in the form of collective commitments to support sustainable tourism development. Real actions taken by the community included the formation of a tourism awareness group (Pokdarwis), initiation of beach clean-up programs, and digital tourism promotion through social media platforms. This activity demonstrates that a well-designed, interactive, and stakeholder-inclusive socialization strategy can be an effective means of building collective awareness and encouraging active community participation in developing inclusive, competitive, and sustainable tourism destinations.
Sentiment Analysis and Topic Modeling of Kitabisa Applications using Support Vector Machine (SVM) and Smote-Tomek Links Methods Switrayana, I Nyoman; Ashadi, Diki; Hairani, Hairani; Aminuddin, Afrig
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 2 No. 2 (2023): September 2023
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v2i2.3406

Abstract

Kitabisa is an Indonesian application that functions to raise funds online. Users can easily support various types of campaigns and donate funds to various social causes through the app. User reviews of the application are very diverse, and it is not sure whether user reviews of the application tend to be positive, neutral, or negative. This research aimed to analyze the sentiment of the Kitabisa application by modeling topics using Latent Dirichlet Allocation (LDA) and classifying user reviews using a Support Vector Machine (SVM). The scrapped dataset showed imbalanced dataset problems, so the SMOTE-Tomek Links oversampling technique was proposed. The results of this study show that using LDA produces five topics often discussed in 750 reviews. Then, the performance of SVM without using SMOTE-Tomek Links was 72% accuracy, 76% precision, 72% recall, and 64% f1 score. Meanwhile, using SMOTE-Tomek Links could significantly improve the performance, namely 98% accuracy, 98% precision, 98% recall, and 98% f1 score. Based on this research, the application of SVM achieved high performance for user sentiment classification, especially when the dataset was in a balanced state. Therefore, the SMOTE-Tomek Links oversampling technique is recommended for dealing with unbalanced sentiment datasets.
Coaching Clinic Online: Pembuatan Artikel Ilmiah Auliana, Rini Adriani; Fitri, Yelli; Fatimah, Siti; Switrayana, I Nyoman; Talidobel, Susilo; Ramdani, Rizal; Solina, Eva
Jurnal Pengabdian Magister Pendidikan IPA Vol 8 No 4 (2025): Oktober-Desember 2025
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jpmpi.v8i4.13705

Abstract

This coaching clinic activity aims to improve and provide students with an understanding of the techniques and methods of writing scientific articles, determining research theories and appropriate research methodologies. This coaching clinic is carried out through a participatory approach and learning by doing, as well as with a learning scheme. This coaching clinic activity was conducted online through the MS Teams application platform, with 15 participants from the Accounting Department of Universitas Terbuka who came from regions throughout Indonesia. This activity was carried out four times with each meeting lasting a maximum of 120 minutes. The results of the activity were very significant, seen from the students' ability to write good scientific articles, even some scientific articles written by the training participants are planned to be published in reputable national journals. The impact of this activity was felt not only by the students who participated in the training but also by the supervising lecturers and the university.