Claim Missing Document
Check
Articles

Found 37 Documents
Search

Implementasi Pakan Ikan Dengan Sistem Pelontar Berbasis Sistem Tertanam aji saputra; Selamet Samsugi; styawati styawati
Jurnal Komputasi Vol. 12 No. 1 (2024): Jurnal Komputasi
Publisher : Jurusan Ilmu Komputer Fakultas MIPA Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v12i1.240

Abstract

Freshwater fish farming has high appeal among the public, however the process of feeding fish is still mostly done manually using traditional methods that are less effective. This article discusses the implementation of fish feed with a throwing system based on an integrated system using an ultrasonic sensor, DC motor, and 5V relay with an Arduino Uno microcontroller. Feeding fish is an important aspect of fish farming. Currently, fish feeding methods are still mostly done manually by throwing bait by hand. These manual techniques tend to be ineffective and can result in irregular feeding. For example, using a bucket to throw food directly into a fish pond can cause the fish to eat too much without proper control. This can result in excessive feeding, additional costs, and poor air quality. Therefore, it is necessary to develop an automatic and programmed fish food throwing system to increase the efficiency and effectiveness of feeding. It is hoped that the use of ultrasonic sensors, DC motors and 5V relays with the Arduino Uno microcontroller can provide a solution to overcome this problem. The main objective of this research is to design and implement an embedded system-based fish feed launcher that can provide feed automatically with good control. This system is expected to improve fish quality, reduce additional costs, and provide convenience for fish farmers. The problem that this tool wants to solve is how to increase the efficiency and effectiveness of fish feeding in freshwater fish farming. Currently, feeding is still done manually, and uncontrolled feeding frequency can result in problems such as excessive feeding and poor air quality. The implementation of a throwing system based on an embedded system with an ultrasonic sensor is expected to be able to overcome this problem by providing feed automatically and programmed. Thus, this research aims to create innovative solutions in fish feeding that can increase production efficiency and the welfare of fish farmers.
Implementasi Smart Roaster Berbasis IoT dan Sistem Pencatatan Keuangan Digital pada UMKM Kopi Supri Styawati; Wulan Amalya; Muhammad Syaukani; Medy Kurniawan; Rizky Khoiri; Ferman Ferdaus
Journal of Community Development Vol. 6 No. 1 (2025): August
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v6i1.1722

Abstract

Tujuan dari Program Pengabdian kepada Masyarakat (PkM) ini adalah menghadirkan solusi inovatif bagi UMKM Kopi Jempol Supri melalui penerapan Smart Roaster berbasis Internet of Things (IoT) dengan web monitoring serta Web Pencatatan Stok dan Laporan Keuangan. Permasalahan utama yang dihadapi mitra adalah risiko kegosongan biji kopi akibat pengendalian suhu manual serta pencatatan stok dan keuangan yang masih dilakukan secara konvensional sehingga sering menimbulkan kesalahan. Metode pelaksanaan mencakup sosialisasi, pelatihan, dan pendampingan kepada mitra, serta pengujian sistem dengan pendekatan partisipatif. Uji coba dilakukan pada sensor termokopel, sensor MQ-135, website Smart Roaster, dan Web Pencatatan Stok dan Laporan Keuangan. Hasil menunjukkan adanya peningkatan signifikan pemahaman mitra melalui perbandingan pretest dan posttest. Sensor termokopel membuktikan bahwa kopi mencapai kematangan optimal pada suhu 223–232 °C dengan durasi 80–110 menit, sedangkan sensor MQ-135 menghasilkan data asap yang progresif sesuai tahap roasting. Website Smart Roaster berjalan baik sesuai skenario blackbox testing, mampu menampilkan suhu dan asap secara real-time serta mengendalikan mesin dari jarak jauh. Web Pencatatan Stok dan Laporan Keuangan juga berfungsi optimal, terbukti melalui uji blackbox dan memperoleh skor 90,52% (sangat baik) berdasarkan ISO/IEC 25010 pada aspek functional suitability, performance efficiency, dan usability. Kesimpulannya, penerapan Smart Roaster IoT dan Web Pencatatan Stok dan Laporan Keuangan berhasil meningkatkan konsistensi mutu kopi, mengurangi kerugian produksi, serta mempercepat dan mengefisienkan pengelolaan administrasi pada UMKM Kopi Jempol Supri.
Analisis Perbandingan Kinerja Model Transfer Learning VGG16 Dan CNN Baseline Dalam Deteksi Penyakit Tanaman Tomat Berdasarkan Citra Daun Budi Riansyah; Styawati Styawati
Dinamik Vol 31 No 2 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i2.10533

Abstract

Tomatoes (Solanum lycopersicum) are a vital horticultural commodity that is highly susceptible to pathogen attacks, making visual symptoms on leaves the main indicator for early detection. However, these automatic detection efforts face significant challenges related to the limited variety and number of image datasets, which often hinder the performance of Deep Learning models. This study aims to compare the performance of Baseline CNN (training from scratch) with VGG16 (fixed feature extraction) on 10 classes of tomato leaf diseases. The evaluation results show that Baseline CNN achieved an accuracy of 87.30% and VGG16 achieved 85.30%. The advantage of the Baseline model lies in its flexibility in learning visual features from scratch, making it more adept at capturing specific details such as ring patterns in Early Blight. In contrast, VGG16 provides computational efficiency with 40% less parameter training load and proves superior in recognizing texture patterns, such as in Bacterial Spot (Recall 97%). In conclusion, although Transfer Learning is efficient and robust, this model has limitations in understanding the unique characteristics of plants (semantic gap).
A Hybrid AI–SEMPLS Model for Digital Visualization Acceptance in Blue Tourism: Evidence from Lampung Province Debby Alita; Khoirin Nisa; Styawati; Dina Amelia
Advance Sustainable Science Engineering and Technology Vol. 8 No. 2 (2026): February-April
Publisher : Science and Technology Research Centre Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v8i2.2909

Abstract

Blue tourism destinations often lack advanced digital tools capable of providing real-time, AI-driven visualization and user-centered information services. This study addresses this gap by developing JELAMBU, an AI-enabled digital visualization platform, and by evaluating user acceptance through a hybrid SEMPLS models. The research aims to: (i) design and implement an AI-based system that combines chatbot interaction, realtime sentiment analytics, and digital visualization; and (ii) examine the determinants of tourists’ intention to adopt AI-enabled e-tourism technologies. A structured questionnaire was administered to 467 visitors of destinations, and 16 hypotheses were tested. The results show that platform design, facilitating conditions, AI technology, perceived ease of use, perceived usefulness, social influence, service quality, trust, and risk perception significantly shape intention to use, whereas information quality, perceived benefits, and performance expectancy do not show significant effects. The model demonstrates substantial predictive power (R² = 0.703), strong effect sizes (f² > 0.225), and acceptable fit (SRMR = 0.084). These findings highlight the pivotal role of design and system conditions in AI-driven tourism platforms and provide practical guidance for developers and policymakers in strengthening digital visualization, personalization features, and sustainable blue tourism management. Future studies may extend this framework to multi-regional settings or longitudinal adoption scenarios.
PENERAPAN NAÏVE BAYES CLASSIFIER UNTUK PENDUKUNG KEPUTUSAN PENERIMA BEASISWA Debby Alita; Indah Sari; Auliya Rahman Isnain; Styawati Styawati
Jurnal Data Mining dan Sistem Informasi Vol 2, No 1 (2021): Februari 2021
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jdmsi.v2i1.1028

Abstract

Scholarships are the provision of assistance in the form of financial assistance provided to individuals with the aim of being used for the sustainability of the education achieved. The problem that occurs in this research is that the process of determining which is still carried out conventionally the student section must check one by one the scholarship application files submitted by students because each data will be compared one by one according to predetermined criteria, which results in the student section becoming difficult in the decision so that It takes a long time, therefore we need a decision support system that can help schools make decisions about scholarship recipients.The Naive Bayes Classifier method is a method that can be used in decision making to get better results on a classification problem. The purpose of this study is to build a scholarship recipient decision support system using the Naïve Bayes Classifier method. In this study, a problem analysis was carried out using PIECES analysis and for the system development method using.The result of this research is that applying the naïve Bayes method to the scholarship recipient's decision support system can assist the school in determining the scholarship recipient more quickly and accurately. The scholarship recipient's decision support system was built using the Java programming language and MySQL database. Keyword: Decision Support Systems, Naïve Bayes Classifier, Waterfall, Blackbox Testing, PIECES
ANALISIS SURVEI KEPUASAN MASYARAKAT MENGGUNKAN PENDEKATAN E-CRM (Studi Kasus : BP3TKI Lampung) Ida Bagus Gede Sarasvananda; Choirul Anwar; Donaya Pasha; Styawati Styawati
Jurnal Data Mining dan Sistem Informasi Vol 2, No 1 (2021): Februari 2021
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jdmsi.v2i1.1026

Abstract

BP3TKI Lampung has a problem in the section regarding the Community Satisfaction Survey (SKM) activity, namely the data processing of the survey results must be calculated manually so it takes a long time. It is expected from this research how to build a web-based community satisfaction survey system, where this system can directly calculate and display the final results of the survey in the form of graphs. In this study, data collection methods were used in the form of interviews, observation, literature review, and documentation at the BP3TKI Lampung office. . The system design is carried out using a modeling language using UML. While the programming used is PHP using the MySQL database. And for the system development method in the form of Extreme Programming. There are four stages in extreme programming, namely planning (planning), design (design), coding (coding), and testing (testing). The final result of this design produces a web-based community satisfaction survey system for BP3TKI Lampung which is expected to make it easier for agencies to conduct surveys and calculate survey results more easily and quickly.Keyword: System, Survey, Satisfaction, Society.
Implementasi Lowk-Rank Adaptation of Large Langauage Model (LoRA) Untuk Effisiensi Large Language Model Anton Mahendra; Styawati Styawati
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.5519

Abstract

Model transformator seperti LlaMA 2 sangat kuat untuk memproses berbagai tugas bahasa alami, namun memiliki kekuatan pemrosesan yang signifikan dan keterbatasan memori yang membuatnya sulit untuk diimplementasikan. Tantangan terbesarnya terletak pada konsumsi sumber daya penyimpanan yang besar dan kebutuhan daya komputasi dalam jumlah besar. Untuk mengatasi permasalahan tersebut, dikembangkan solusi berupa implementasi LoRA (Low Rank Adapter). LoRA, khususnya di LlaMA 2, menggunakan pendekatan adaptif dalam mengompresi model Transformer menggunakan adaptor berdaya rendah. Penerapan LoRA pada model ini mengurangi jumlah operasi floating-point, sehingga mempercepat proses pelatihan dan inferensi.  Secara signifikan mengurangi  konsumsi daya dan penggunaan memori. Tujuan utama penerapan LoRA di LlaMA 2 adalah untuk mengoptimalkan efisiensi model, dengan fokus pada pengurangan operasi floating-point dan meningkatkan penggunaan memori GPU.