Garuda - Garba Rujukan Digital

Optimization of the Travelling Salesman Problem Based on Genetic Algorithm with Adaptive Crossover and Mutation Probabilitie Chichi Rizka Gunawan
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 3 No. 3 (2024): September 2024
Publisher : LKP Unity Academy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70340/jirsi.v3i3.166

The Travelling Salesman Problem (TSP) is a combinatorial optimization problem that aims to find the shortest route to visit each city exactly once and return to the starting city. As an NP-hard problem, solving TSP requires heuristic approaches. This study employs the Genetic Algorithm to solve TSP by integrating adaptive crossover and mutation probabilities. The adaptive approach allows the crossover and mutation parameters to be dynamically adjusted based on the population conditions at each generation, thereby improving the efficiency of the optimal solution search. The research begins with chromosome representation as a sequence of cities, followed by the initialization of the initial population randomly. Fitness evaluation is conducted based on the total travel distance to determine the solution’s quality. Selection of the best individuals, adaptive crossover, and adaptive mutation are applied to generate a better new population. Elitism is used to ensure that the best solutions are preserved. The algorithm iterates until it reaches the maximum number of generations or a specific fitness threshold. The results show that the adaptive approach produces an optimal travel route with the minimum total distance. The optimal route is visualized by connecting city points, and the fitness progression demonstrates significant improvement in the early generations and stabilization in the later generations. With a crossover probability of 0.8 and mutation probability of 0.005, the algorithm effectively maintains a balance between exploration and exploitation of the solution space, preventing premature convergence, and producing efficient solutions. This study demonstrates that the Genetic Algorithm with an adaptive approach if effective in solving TSP with a moderate number of cities. Additionally, this approach can be adapted for larger datasets or compared with other optimization methods, such as Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO), to further evaluate its performance.

Optimized Land Surface Low Point Detection Using the D8 Algorithm in a Geographic Information System (GIS) Framework Khairul Muttaqin; Novianda Novianda; Ahmad Ihsan; Dea Ayuni Putri; Cut Alna Fadhilla; Chichi Rizka Gunawan; Chicha Rizka Gunawan; Jefril Rahmadoni
Jurnal Testing dan Implementasi Sistem Informasi Vol. 4 No. 1 (2026): Jurnal Testing dan Implementasi Sistem Informasi
Publisher : Lembaga Riset dan Inovasi Almatani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55583/jtisi.v4i1.2205

Hydrological analysis in urban areas often suffers from inaccuracies in Digital Elevation Model (DEM) interpretation, especially in detecting micro-depressions and small-scale surface flow patterns. Previous studies typically relied solely on the automatic D8 algorithm in GIS without manual verification, resulting in flow directions that do not fully represent actual surface conditions. This study aims to compare manual D8-based flow direction calculations with automatic ArcGIS processing using DEMNAS data for Langsa City. The DEM (8.1 m resolution) underwent sink filling, hydrological conditioning, slope and aspect processing, followed by field validation using GPS measurements. The results show that the manual method identified 23 flow paths, whereas ArcGIS detected only 11. The differences stem mainly from micro-topographic variations that the automatic algorithm failed to capture in flat areas or anthropogenically modified surfaces. Field validation confirmed that 8 of the 11 ArcGIS-derived paths matched the actual drainage patterns, while the additional manual paths better represented subtle elevation gradients.This research contributes by offering a systematic comparison between manual and automatic D8 approaches, highlighting the importance of manual verification in low-slope urban terrains. The findings are valuable for micro-scale flood mitigation planning and urban surface hydrology analysis.

Optimized Land Surface Low Point Detection Using the D8 Algorithm in a Geographic Information System (GIS) Framework Khairul Muttaqin; Novianda Novianda; Ahmad Ihsan; Dea Ayuni Putri; Cut Alna Fadhilla; Chichi Rizka Gunawan; Chicha Rizka Gunawan; Jefril Rahmadoni
Jurnal Testing dan Implementasi Sistem Informasi Vol. 4 No. 1 (2026): Jurnal Testing dan Implementasi Sistem Informasi
Publisher : Lembaga Riset dan Inovasi Almatani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55583/jtisi.v4i1.2205

Hydrological analysis in urban areas often suffers from inaccuracies in Digital Elevation Model (DEM) interpretation, especially in detecting micro-depressions and small-scale surface flow patterns. Previous studies typically relied solely on the automatic D8 algorithm in GIS without manual verification, resulting in flow directions that do not fully represent actual surface conditions. This study aims to compare manual D8-based flow direction calculations with automatic ArcGIS processing using DEMNAS data for Langsa City. The DEM (8.1 m resolution) underwent sink filling, hydrological conditioning, slope and aspect processing, followed by field validation using GPS measurements. The results show that the manual method identified 23 flow paths, whereas ArcGIS detected only 11. The differences stem mainly from micro-topographic variations that the automatic algorithm failed to capture in flat areas or anthropogenically modified surfaces. Field validation confirmed that 8 of the 11 ArcGIS-derived paths matched the actual drainage patterns, while the additional manual paths better represented subtle elevation gradients.This research contributes by offering a systematic comparison between manual and automatic D8 approaches, highlighting the importance of manual verification in low-slope urban terrains. The findings are valuable for micro-scale flood mitigation planning and urban surface hydrology analysis.

Deteksi Penyakit Mata Menggunakan Algoritma Region Growing Chicha Rizka Gunawan; Mahara Bengi; Chichi Rizka Gunawan; Cut Alna Fadhilla
Algoritma: Jurnal Ilmu Komputer dan Informatika Vol 9, No 2 (2025): November 2025
Publisher : Universitas Islam Negeri Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/algoritma.v9i2.27908

Medical image processing is a data manipulation process aimed at producing new images with improved quality. The primary objective of medical image processing is to obtain information, perform screening procedures, and support disease diagnosis, one of which is eye diseases. Nodules, as one of the indications of eye diseases, are generally analyzed visually by physicians. This study develops an algorithm to detect nodules in eye CT scan images based on the morphological characteristics of nodules, which are generally circular in shape. The experimental results show that the nodule area can be calculated based on the number of pixels forming the nodule region. In several image slices, the nodule area cannot be detected due to the condition where the nodule is attached to other parts of the eye. The developed algorithm is capable of detecting nodules in multiple eye CT scan slices and calculating the nodule area in each image slice. Therefore, the proposed nodule detection algorithm is expected to assist physicians in diagnosing eye diseases more accurately and objectively. Keywords: Detection, Region Growing, Eye Disease, Medical Image Processing, Nodule

PEMBERDAYAAN PANTI ASUHAN MELALUI PENERAPAN SISTEM INFORMASI DIGITAL DALAM MENINGKATKAN TRANSPARANSI DAN PENGELOLAAN DONATUR SERTA ANAK ASUH Chicha Rizka; Chichi Rizka Gunawan; Rahmad Bahri; Rahman Pradipta; Ayu Syahputri; Mahara Bengi; Muhammad Daffa Z
Jurnal Masyarakat Berdikari dan Berkarya (Mardika) Vol 3 No 3 (2025): Jurnal Masyarakat Berdikari dan Berkarya (MARDIKA)
Publisher : Fakultas Teknik, Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/mardika.v3i3.13518

Kegiatan pengabdian ini bertujuan untuk meningkatkan efektivitas, akurasi, dan transparansi pengelolaan administrasi di panti asuhan melalui penerapan sistem informasi digital berbasis web. Selama ini, pendataan anak asuh dan donatur dilakukan secara manual sehingga sering menimbulkan masalah seperti duplikasi data, keterlambatan pelaporan, kesalahan pencatatan, serta kurangnya transparansi dalam pemanfaatan donasi. Melalui kegiatan ini, tim pengabdian melakukan analisis kebutuhan, perancangan, implementasi sistem, serta pelatihan penggunaan kepada pengurus panti. Sistem informasi yang dibangun mencakup fitur pengelolaan data anak asuh, pencatatan donatur, histori donasi, laporan keuangan sederhana, dan dashboard visual. Hasil kegiatan menunjukkan bahwa sistem informasi digital mampu meningkatkan efisiensi kerja pengurus, meningkatkan transparansi informasi kepada donatur, serta mendukung pengelolaan panti secara lebih terstruktur dan profesional. Dengan demikian, implementasi sistem informasi terbukti efektif sebagai bentuk pemberdayaan panti asuhan menuju tata kelola yang lebih modern, akuntabel, dan berkelanjutan.

Enhancing the Performance of Machine Learning Algorithm for Intent Sentiment Analysis on Village Fund Topic M. Khairul Anam; Pandu Pratama Putra; Rio Andika Malik; Karfindo Karfindo; Teri Ade Putra; Yesri Elva; Raja Ayu Mahessya; Muhammad Bambang Firdaus; Ikhsan Ikhsan; Chichi Rizka Gunawan
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.637

This study explores the implementation of Intent Sentiment Analysis on Twitter data related to the Village Fund program, leveraging Multinomial Naïve Bayes (MNB) and enhancing it with Synthetic Minority Over-sampling Technique (SMOTE) and XGBoost (XGB). The analysis categorizes tweets into six labels: Optimistic, Pessimistic, Advice, Satire, Appreciation, and No Intent. Initially, the MNB model achieved an accuracy of 67% on a 90:10 data split. By applying SMOTE, accuracy improved by 12%, reaching 89%. However, adding Chi-Square feature selection did not increase accuracy further. Incorporating XGB into the MNB+SMOTE model led to a 6% improvement, achieving a final accuracy of 95%. Comprehensive model evaluation revealed that the MNB+SMOTE+XGB model achieved 96% accuracy, 96% precision, 96% recall, and a 96% F1-score, with an AUC of 99%, categorizing it as excellent. These findings demonstrate that the combination of SMOTE for addressing class imbalance and XGBoost for boosting performance significantly enhances the MNB model's classification capabilities. The novelty lies in the integration of these techniques to improve intent sentiment classification for public opinion analysis on the Village Fund program. The results indicate that the majority of tweets labeled as "No Intent" reflect a lack of specific sentiment or actionable intent, providing valuable insights into public perception of the program.

Sistem Kontrol Dan Monitoring Budidaya Jamur Tiram Berbasis Iot Menggunakan Metode Fuzzy Logic Tsukamoto Chicha Rizka Gunawan; Chichi Rizka Gunawan; Cut Alna Fadhilla; Sari Raspika
Jurnal Informatika dan Teknologi Komputer (J-ICOM) Vol 7 No 2 (2026): Jurnal Informatika dan Teknologi Komputer ( J-ICOM)
Publisher : E-Jurnal Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/j-icom.v7i2.15336

Oyster mushroom cultivation requires stable temperature and air humidity to support growth. In the study location, environmental control was still performed manually, making consistent control difficult. This study developed an Internet of Things (IoT)-based control and monitoring system using the Tsukamoto fuzzy logic method. The system uses a DHT22 sensor to measure temperature and humidity, a Wemos D1 Mini as the controller, and a fan and humidifier as actuators. Sensor data are processed using fuzzy membership, rule inference, and defuzzification to determine actuator control, while monitoring data are delivered to a web interface. Testing was conducted using a prototype in Limau Mungkur Village, Pematang Jaya District, Langkat Regency, North Sumatra, with observations over 20 days. The system produced an average temperature of 25.1 °C and average humidity of 85.6%. Ten representative control tests were classified as appropriate, resulting in 100% agreement between the system decisions and the defined ideal cultivation conditions. The implementation demonstrates that the IoT and Tsukamoto fuzzy logic approach can automate environmental monitoring and control for oyster mushroom cultivation.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search