Claim Missing Document
Check
Articles

Automatic Aircraft Navigation Using Star Metric Dimension Theory in Fire Protected Forest Areas Saifudin, Ilham; Umilasari, Reni
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 5, No 2 (2021): October
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v5i2.4331

Abstract

The purpose of this research is to determine the navigation of an unmanned aircraft automatically using theory of the metric dimension of stars in a forest fire area. The research will also be expanded by determining the star metric dimensions on other unique graphs and graphs resulting from amalgamation operations. The methods used in this research are pattern recognition and axiomatic deductive methods. The pattern detection method is to look for patterns to construct differentiated sets on the metric dimension (dim) so that the coordinate values are minimum and different. Meanwhile, axiomatic deductive is a research method that uses deductive proof principles that apply in mathematical logic by using existing axioms or theorems to solve a problem. Then the method is used to determine the stars' metric dimensions.
THE EFFECT OF IMPERFECTIVE DATA SAMPLING METHOD ON SUPPORT VECTOR MACHINE ACCURACY Erna Cholida, Ferdy Maulana; Arifianto, Deni; Umilasari, Reni
Computing and Information System Journal Vol. 1 No. 3 (2025): Data Science, UI/UX, and E-Government for Decision Making
Publisher : IndoCompt Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sentiment analysis is used to understand the direction of public opinion, but problems arise due to the unbalanced distribution of sentiment data, where one class dominates. This imbalance causes classification models such as Support Vector Machine (SVM) to be biased towards the majority class, which results in decreased accuracy and generalizability of the model. This study aims to assess the effectiveness of two data balancing techniques, namely, SVM-SMOTE, and ADASYN, in improving SVM performance. The research data was taken from social media platform X (Twitter), and testing was conducted using the K-Fold Cross Validation method (K=2, 5, and 10) using evaluation metrics such as accuracy, precision, recall, and F1-score. The results show that without data balancing, the SVM model can only achieve an average accuracy of 76.34% and F1-score of 62.38%, which reflects the weakness in recognizing minority classes. The application of the two balancing methods successfully improved the model performance. ADASYN increased the F1-score to 67.94%, while SVM-SMOTE showed the most optimal results with 82.4% accuracy and 74.02% F1-score. These findings indicate that SVM-SMOTE is the most effective technique in handling data imbalance and improving sentiment classification accuracy equally.
STRATEGI PENGEMBANGAN BUDIDAYA IKAN LELE MELALUI USAHA ANEKA OLEH-OLEH KHAS OLAHAN IKAN LELE SIAP SAJI SEBAGAI BRAND KEUNIKAN Winahyu, Pawestri; Mufarida, Nely Ana; Umilasari, Reni
JMM (Jurnal Masyarakat Mandiri) Vol 9, No 4 (2025): Agustus
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jmm.v9i4.32218

Abstract

Abstrak: Desa Cakru memiliki potensi besar dalam perikanan air tawar, namun belum dimanfaatkan secara maksimal. Belum adanya produk olahan khas yang bernilai jual tinggi menjadi kendala utama, ditambah keterbatasan keterampilan teknis masyarakat dalam budidaya ikan lele dan pengolahan produk. Selain itu, pemanfaatan teknologi sederhana belum optimal. Program pengabdian ini bertujuan meningkatkan kapasitas masyarakat dalam budidaya ikan lele dan inovasi produk frozen food, sebagai upaya pemberdayaan ekonomi melalui branding oleh-oleh khas daerah. Kegiatan ini menitikberatkan pada peningkatan hardskill dalam teknik budidaya ikan lele dan pengolahan frozen food, serta softskill dalam kewirausahaan, manajemen usaha kecil, dan strategi branding agar produk lokal mampu bersaing di pasar. Metode pelaksanaan mencakup sosialisasi, pelatihan teknis, penerapan teknologi tepat guna, pendampingan intensif, serta evaluasi menggunakan observasi, angket, dan pretest serta posttest berbasis 15 soal pilihan ganda. Kegiatan melibatkan terdiri dari 15 pembudidaya pemula dan 10 pelaku usaha mikro yang berpotensi mengembangkan produk olahan berbasis ikan lele. Hasil menunjukkan peningkatan hardskill sebesar 61% dan softskill 58%, serta peningkatan pendapatan keluarga sebesar 20–30% dari pemasaran produk frozen food.Abstract: Cakru Village has great potential in freshwater fisheries, but has not been utilized optimally. The absence of typical processed products with high selling value is the main obstacle, coupled with the limited technical skills of the community in catfish cultivation and product processing. In addition, the use of simple technology has not been optimal. This community service program aims to increase community capacity in catfish cultivation and frozen food product innovation, as an effort to empower the economy through branding regional souvenirs. This activity focuses on improving hard skills in catfish cultivation techniques and frozen food processing, as well as soft skills in entrepreneurship, small business management, and branding strategies so that local products can compete in the market. The implementation method includes socialization, technical training, application of appropriate technology, intensive assistance, and evaluation using observation, questionnaires, and pre-tests and post-tests based on 15 multiple-choice questions. The activity involved 15 novice cultivators and 10 micro-entrepreneurs who have the potential to develop processed products based on catfish. The results showed an increase in hard skills of 61% and soft skills of 58%, as well as an increase in family income of 20-30% from marketing frozen food products.
Sosialisasi Strategi Branding Produk Untuk IMK Binaan PDNA Kabupaten Sorong Ginanjar Abdurrahman; Amalina Maryam Zakiyyah; Reni Umilasari; Sahiruddin Sahiruddin
Journal of Community Development Vol. 3 No. 2 (2022): December
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v3i2.79

Abstract

Corona Virus Disease (Covid-19) began to enter Indonesia in March 2020. The spread of this virus was massive in July with the highest case on July 15, 2021. So far, cases have started to decline because the discipline of health protocols has begun to be applied, and most Indonesians have received the Covid-19 vaccine. The growth of Covid-19 had a major impact and became an obstacle to Indonesia's economic growth, especially the Micro and Small Industry (MSI). According to the Asian Development Bank (ADB) there are 50% of Small and Medium Industries went bankrupt due to Covid-19 because turnover has decreased by 40% - 70%. In the Covid-19 pandemic situation, Product Branding can be offered to MSI as one of the solutions to problems to achieve economic resilience. The Community Partnership Program is expected to be able to contribute to solving the problems faced by IMK in Sorong, namely "competitor constraints" and "marketing constraints". In relation to competitor constraints and marketing constraints, MSI is expected to be able to market products easily and be able to compete. For this reason, product branding insight is needed. In this case, MSI actors need to be equipped with product branding insights, so that they can sell their products easily, precisely in booking, easy to recognize their products, and customer loyalty. For this reason, product branding skills need to be socialized to improve the quality of MSI Actors' Human Resources. Based on evaluation results, in general the initial knowledge related to product branding is good, with the lowest score for the pretest 54 and the highest score being 70. Meanwhile, in the posttest score there was a significant increase in the value, with the lowest score being 73 and the highest score reaching 95.
Sosialisasi Pemanfaatan Limbah Tumbuhan untuk Mendukung Kemandirian Ekonomi Komunitas Kelompok Wanita Tani Pra Karang Tengah Hadi Jatmiko; Muhammad Zainur Ridlo; Reni Umilasari
MIMBAR INTEGRITAS : Jurnal Pengabdian Vol 5 No 2 (2026): Februari - Agustus
Publisher : Biro Administrasi dan Akademik

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36841/mimbarintegritas.v5i2.7964

Abstract

Limbah tumbuhan di Karangtengah, Kecamatan Ambulu, Kabupaten Jember tersedia secara kontinu dari aktivitas rumah tangga, tumbuhan alam, dan kegiatan pertanian warga, namun pemanfaatannya masih terbatas karena rendahnya edukasi serta belum terbentuknya pemahaman dan kebiasaan pemilahan yang mendukung pengolahan lanjutan. Kegiatan pengabdian ini bertujuan meningkatkan pengetahuan dan pemahaman anggota Kelompok Wanita Tani (KWT) PRA Karangtengah mengenai limbah tumbuhan sebagai sumber daya dan peluang ekonomi komunitas, baik melalui penghematan biaya input maupun potensi pengembangan produk turunan. Metode yang digunakan berupa intervensi bertahap meliputi pre-test untuk mengukur pemahaman awal, sosialisasi materi “limbah tumbuhan sebagai sumber daya & peluang ekonomi”, diskusi kelompok, pemetaan partisipatif sumber limbah dan kebutuhan komunitas, praktik pemilahan, keamanan bahan, persiapan bahan baku, serta post-test sebagai evaluasi akhir. Hasil kegiatan menunjukkan terjadinya penguatan pemahaman peserta pada aspek klasifikasi limbah tumbuhan yang layak diolah, pentingnya pemilahan bahan hijau dan bahan cokelat untuk kelayakan proses, serta keterkaitan pengelolaan limbah dengan manfaat ekonomi. Selain itu, peserta mampu mengidentifikasi sumber limbah dominan di lingkungan setempat dan menyiapkan bahan siap olah (bersih, dicacah, terpisah), disertai perubahan perilaku awal dari kebiasaan “membuang cepat” menuju “mengumpulkan dan menyiapkan” limbah sebagai bahan berguna.
Analisis Sentimen Polemik Kebijakan Pemerintah Makan Siang Gratis pada Twitter Menggunakan Metode Neural Network Classification Dandy Tri Prasetyo; Deni Arifianto; Reni Umilasari
Modem : Jurnal Informatika dan Sains Teknologi. Vol. 4 No. 3 (2026): Juli : Modem : Jurnal Informatika dan Sains Teknologi
Publisher : Asosiasi Profesi Telekomunikasi Dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/modem.v4i3.924

Abstract

This study aims to investigate public sentiment toward the Indonesian government's free lunch program by analyzing discussions on the X social media platform. A total of 1,500 tweets were collected through a web scraping process using relevant keywords and hashtags. The research workflow consisted of text preprocessing, including data cleaning, case folding, tokenization, stop-word removal, and stemming. The processed text was then transformed into numerical features using the Term Frequency–Inverse Document Frequency (TF-IDF) weighting method, followed by sentiment classification using the Neural Network Classification algorithm. Model performance was evaluated through K-Fold Cross Validation and a Confusion Matrix based on accuracy, precision, recall, and F1-score metrics. To address the issue of class imbalance, Random Over Sampling (ROS) was applied before the classification stage. The experimental results indicate that incorporating ROS improved the classification performance compared with the model trained on the original imbalanced dataset. Furthermore, the Neural Network Classification model effectively categorized public opinions into positive, negative, and neutral sentiments. The findings of this study are expected to provide valuable insights for policymakers in understanding public perceptions of the free lunch program and supporting future policy evaluation.
PROTOTIPE SISTEM DIGITAL SIGNAGE BERBASIS WEB UNTUK MENYAJIKAN INFORMASI PUBLIK DI AREA PENUMPANG Reni Umilasari; Aulivia Gustiniar Fitrianavrisha; Amalia Kartika; Amalina Maryam Zakiyyah; Ginanjar Abdurrahman
Journal of Social Outreach Vol 5, No 1 (2026): Journal of Social Outreach
Publisher : Fakultas Sains dan Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15548/jso.v5i1.12958

Abstract

Digital signage merupakan solusi modern dalam penyampaian informasi publik secara otomatis, visual, dan terstruktur. Kegiatan Pengabdian Kepada Masyarakat ini terdiri dari perancangan prototipe dan implementasi sistem digital signage berbasis web yang ditujukan untuk area penumpang seperti pelabuhan atau terminal yang bekerjasama dengan PT Sinovasi Idea Karya. Sistem ini menampilkan informasi penting seperti jadwal keberangkatan, cuaca, rekomendasi hotel, dan tempat wisata dalam format slide yang bergantian setiap beberapa menit secara otomatis. Sistem dirancang menggunakan teknologi HTML, Tailwind CSS, dan JavaScript tanpa melibatkan basis data maupun backend server, sehingga seluruh konten disusun secara statis dan dijalankan langsung melalui browser dalam mode kiosk fullscreen. Informasi diatur dalam struktur slide dan dikendalikan oleh skrip JavaScript untuk rotasi konten otomatis. Pengujian dilakukan secara manual melalui browser pada layar komputer berukuran besar sebagai simulasi smart TV. Hasil pengujian menunjukkan bahwa sistem berjalan stabil, responsif, dan menampilkan informasi dengan jelas sesuai desain. Sistem ini diharapkan dapat menjadi solusi sederhana namun efektif dalam meningkatkan kualitas layanan informasi di area publik.