cover
Contact Name
Dhanan Abimanto
Contact Email
dhananabimanto@gmail.com
Phone
+6289667747299
Journal Mail Official
dhananabimanto@gmail.com
Editorial Address
Jl. Soekarno-Hatta No. 180 Pedurungan, Semarang 50246
Location
Kota semarang,
Jawa tengah
INDONESIA
Populer: Jurnal Penelitian Mahasiswa
ISSN : 2962116X     EISSN : 29635306     DOI : -
Populer: Jurnal Penelitian Mahasiswa ini terbit 1 tahun 4 kali (Maret, Juni September dan Desember). Karya yang diterbitkan merupakan suatu hasil penelitian orisinil atau tinjauan Pustaka yang ditulis oleh mahasiswa. Ruang lingkup karya yang diterbitkan mencakup Multidisiplin diantaranya yaitu: Ilmu Sosial Humaniora, Politik, Pendidikan, Ilmu Teknik, Teknik Elektro dan Informatika, Desain Komunikasi Visual, Manajemen, Ekonomi dan Akuntansi, Kewirausahaan dan Bisnis.
Arjuna Subject : Umum - Umum
Articles 366 Documents
Prediksi Curah Hujan menggunakan Extreme Gradient Boosting (XGBoost) dan Interpretasi Large Language Model sebagai Pendukung Mitigasi Banjir di Kota Semarang Luluk Indah Rahmawati; Ghufron Asadly; Heru Hidayatulloh
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5474

Abstract

Rainfall is one of the factors associated with flooding in Semarang City, so information about future rainfall conditions is needed to support preparedness and mitigation. This study implements Extreme Gradient Boosting (XGBoost) to predict daily rainfall using historical rainfall observations obtained from the Meteorology, Climatology, and Geophysics Agency (BMKG) and integrates a Large Language Model (LLM) through Gemini AI to interpret prediction results. The research stages consist of data preparation, cleaning, feature engineering, model development, hyperparameter optimization, evaluation, iterative forecasting, and LLM-based interpretation. The model uses eight input features, namely RR_t-1, RR_t-2, RR_t-3, RR_t-7, rolling_3, rolling_7, sin_bulan, and cos_bulan, with the target transformed using log1p(). RandomizedSearchCV with TimeSeriesSplit was applied to evaluate 30 hyperparameter combinations using five folds. The final evaluation produced an MAE of 5.1502 mm, RMSE of 11.8584 mm, and R² of 0.7458. The model was subsequently used to forecast rainfall for 60 days ahead. The predicted daily values were summarized by month and interpreted by Gemini AI to provide descriptive information, an indicative flood-risk level, and mitigation recommendations. The resulting system provides not only numerical rainfall predictions but also contextual information that is easier for users to understand as supporting information for flood mitigation in Semarang City.  
Identifikasi Pelanggaran Lalu Lintas Kendaraan Mobil terhadap Larangan Putar Balik menggunakan Algoritma You Only Look Once (YOLOv11) Tiza Farhani Maulia; Dedy Kurniadi; Ghufron Ghufron
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5487

Abstract

The purpose of this study is to identify and analyze traffic violations involving cars that violate U-Turn prohibitions using the You Only Look Once (YOLOv11) algorithm. Illegal U-Turns in restricted areas are a primary cause of traffic congestion and accidents. This study develops an automated, real-time U-Turn violation monitoring system by integrating the YOLOv11n model, ByteTrack tracking algorithm, and Streamlit interface using 2-zone polygon logic. The dataset covers 7 vehicle classes evaluated on 1,072 validation images. Experimental results show that the YOLOv11n model achieves a mean Average Precision (mAP@50) of 66.5%, Precision of 68.4%, and Recall of 64.2%. With an inference speed of 3.2 ms per frame (169 FPS), the 2-zone logic integrated into Streamlit accurately detects illegal maneuvers, updates real-time metrics, and minimizes false alarms without frame lag. The proposed system demonstrates the potential of combining object detection, vehicle tracking, and zone-based logic for automated monitoring of U-Turn violations in restricted areas.
Rekomendasi Pembelian Rumah Huni Menggunakan Metode Analytical Hierarchy Process dan Profile Matching Ahmad Baihaqi Muslim; Dedy Kurniadi
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5501

Abstract

Purchasing a house is an important decision, yet selecting a property that matches individual preferences can be challenging because buyers must consider multiple criteria, including price, location, accessibility, facilities, building area, and financial capacity. Differences among consumer segments, such as laborers, civil servants, and entrepreneurs, also lead to varying housing priorities. This study develops a housing purchase recommendation system integrating the Analytical Hierarchy Process (AHP) and Profile Matching methods. AHP is used to objectively determine criterion weights, while Profile Matching ranks housing alternatives based on their similarity to user preferences. The system uses 1,220 housing listings collected through web scraping from the OLX marketplace, with 1,186 usable data points after data cleaning, covering three provinces on Java Island. Three consumer segments were analyzed, each producing different AHP weights with a Consistency Ratio (CR) of 0, indicating consistent assessments. Black-box testing across four scenarios achieved 100% conformity with expected results. The highest recommendation scores were 4.56 for laborers and 4.72 for entrepreneurs, reflecting differences in segment priorities. Manual calculation and system output also showed 100% agreement at every calculation stage. The proposed system can support more objective and efficient housing decisions.
Penerapan Extratrees Classifier dan Light Gradient Boosting Machine untuk Rekomendasi Perdagangan Kripto Berdasarkan Filter Volatilitas Pasar Aditya Bachtiar; Ghufron Ghufron
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5503

Abstract

The cryptocurrency market is characterized by fluctuating, non-stationary prices and rapidly changing volatility, which makes market-condition analysis complex. This study applies a hybrid machine learning approach combining ExtraTrees Classifier and LightGBM Regressor to support Ethereum trading analysis. Daily ETH/USDT data were collected from the Binance Public API for 1 January 2021 to 31 December 2025, totaling 1,826 raw observations. After preprocessing, feature engineering, and target formation, 1,622 observations were used and split chronologically into 70% training and 30% testing data. ExtraTrees classifies the next-period market condition into Low Volatility and High Volatility, while LightGBM estimates the next-period price change as a price delta. ExtraTrees achieved 89.12% test accuracy, exceeding the 65.91% majority baseline. On the training data, LightGBM obtained MAE of US$47.41, RMSE of US$75.68, R² of 0.9930, and Directional Accuracy of 93.04%. The outputs of both models were integrated using fusion logic with 75% volatility score and 25% magnitude score, producing Prepare to Trade, No Trade Zone (Sideways), and High Vol (No Trade) recommendations. The three-state accuracy reached 73.31%, while binary volatility accuracy reached 90.55%. SHAP was used to explain feature contributions, and the final model was implemented in a Streamlit-based Decision Support System.
Pengaruh Pupuk Organik Cair (POC) Berbahan Dasar Cangkang Telur terhadap Pertumbuhan dan Produksi Tanaman Mentimun (Cucumis Sativus L.) Pikirkan Waruwu; Helmin Parida Zebua; Yoel Melsaro Larosa; Desti Kurniawan Gulo
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5512

Abstract

This study aims to analyze the effect of applying liquid organic fertilizer (LOF) made from eggshells on the growth and yield components of cucumber plants (Cucumis sativus L.), to determine the most effective dose, and to determine the nitrogen (N), phosphorus (P), potassium (K), and organic carbon content of the eggshell-based LOF. The research was conducted on a research plot in Ombolata Ulu Village, Gunungsitoli District, Gunungsitoli City, North Sumatra, from May to July 2026, using a non-factorial randomized block design (RBD) with six dose levels of eggshell-based LOF, namely P0 (control), P1 (40 mL/L), P2 (60 mL/L), P3 (80 mL/L), P4 (100 mL/L), and P5 (120 mL/L), each replicated three times, resulting in 18 experimental units. The parameters observed were plant height, stem diameter, number of leaves, fruit length, number of fruits, and fruit weight per sample plant. Data were analyzed using Analysis of Variance (ANOVA) followed by the Honestly Significant Difference (HSD) test at the 5% level. The results showed that the application of eggshell-based LOF had a significant effect on the growth of cucumber, namely plant height, stem diameter, and number of leaves, as well as on the yield components, namely fruit length, number of fruits, and fruit weight per sample plant. The most effective treatment for enhancing the growth and yield of cucumber was P5, with a dose of 120 mL/L of water. Laboratory analysis showed that the eggshell-based LOF contained 0.07% nitrogen (N), 0.01% phosphorus (P), 0.07% potassium (K), and 2.81% organic carbon.
Deteksi Real-Time dan Pemetaan Lokasi Jalan Berlubang menggunakan Algoritma YOLOv11 Trianando Mohammad Dahlan Wirayudha; Dedy Kurniadi; Ghufron Ghufron; Muhamad Miftahul Huda
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5513

Abstract

Road damage, particularly potholes, in Genuk District, Semarang City, is dynamic due to tidal flooding and heavy logistics vehicle loads. Conventional monitoring based on manual surveys and citizen reports is relatively slow and may delay repair responses. This study develops a real-time pothole detection and mapping system by integrating the YOLOv11 algorithm with a Web-GIS interface. The system uses a distributed architecture in which a Python-based local inference layer processes video streams and synchronizes detected potholes with GPS coordinates. Image evidence is uploaded to Cloudinary, while spatial coordinates are stored in a PostGIS-configured PostgreSQL database. The resulting spatial data are visualized through an interactive map developed using TypeScript and Leaflet.js on Vercel serverless infrastructure. The YOLOv11 model was trained for 300 epochs using an NVIDIA Tesla T4 GPU. Evaluation achieved 97.4% precision, 90.4% recall, and 95.1% mAP@50, with an inference latency of 9.3 milliseconds per frame, equivalent to approximately 107 FPS. Functional testing confirmed reliable data transmission and automatic deduplication using the ST_DWithin spatial query. The system provides accurate, responsive, and reliable support for mapping potholes and accelerating road infrastructure repair processes.
Implementasi Vision Transformer (VIT) dan K-Means Clustering dalam Klasifikasi Gaya Visual Poster untuk Otomatisasi Ekstraksi Skema Warna Digital Muhammadun Hanif; Bagus Satrio Waluyo Poetro; Ghufron Ghufron
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5516

Abstract

The purpose of this study is to implement the Vision Transformer (ViT) architecture and K-Means Clustering algorithm to automate fine-grained visual style classification of posters and the extraction of digital color schemes. MSMEs and beginner digital creators often face challenges in determining harmonious color schemes for promotional poster designs, leading to a time-consuming trial-and-error design process. The research utilized a custom dataset of 1,011 poster images scraped from the Behance platform, evenly distributed into three visual style classes: Bauhaus, Swiss Style, and Minimalist. The data preprocessing employed a dual-pipeline approach, where color extraction was optimized through SLIC Superpixel segmentation within the CIELab* perceptual color space to significantly reduce computational complexity without degrading the boundaries of original visual elements. The evaluation results demonstrated that the ViT model performed exceptionally well, achieving an accuracy of 79% and a Macro F1-Score of 0.80. In the color extraction module, the K-Means algorithm successfully formed five highly separated dominant palette clusters with an average Silhouette Score of 0.7698. The perceptual color accuracy validation recorded an average  of 4.7648, proving that the extracted hexadecimal (HEX) palette codes operate well within the acceptable limits of human visual deviation.
Deteksi Cyberbullying pada Twitter menggunakan Distilbert dan (Explainable Ai) Shap Hadana Maulana; Mustafa Mustafa; Ghufron Ghufron
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5517

Abstract

The prevalence of cyberbullying on Twitter demands a fast and transparent automated moderation system. This study designs an efficient and explainable binary cyberbullying detection system using DistilBERT and the SHAP-based Explainable AI (XAI) method. The dataset, sourced from Kaggle, consists of 13,169 raw data filtered into 12,548 clean tweets. Preprocessing was conducted without stemming and stopword removal to preserve the language's semantic context, setting a max_length of 48 tokens. The pre-trained distilbert-base-multilingual-cased model was evaluated on an 80% training and 20% testing data split, while model transparency was validated using SHAP's PartitionExplainer algorithm. Evaluation results show DistilBERT performed robustly, achieving 84% accuracy, 84% precision, 86% F1-score, and 88% recall in detecting bullying, with an Area Under Curve (AUC) score reaching 0.9207. Locally, SHAP evaluation proved that the model concentrated heavy penalty weights on abusive words like "brengsek". Globally, SHAP revealed a unique phenomenon where the most important features were dominated by neutral vocabularies such as "times. roman" and "pendidikan", which the model cleverly utilized as strong discriminative indicators to validate normal texts. In conclusion, the integration of DistilBERT and SHAP yields a classification system that is not only accurate and efficient but also transparent and logically reasoned.
Implementasi Arsitektur Temporal Fusion Transformer (Tft) Berbasis Interpretable Multi-Horizon Forecasting Prediksi Volatilitas Harga Aset Kripto Solana Mahmudi Husain Hasbullah; Ghufron Ghufron
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5520

Abstract

The cryptocurrency market, specifically Solana (SOL), exhibits extreme volatility that is difficult for conventional algorithms to predict accurately. Additionally, advanced Deep Learning models often act as black-boxes. This study implements the Temporal Fusion Transformer (TFT) architecture for robust and interpretable multi-horizon volatility prediction of SOL/USDT. High-frequency historical data (1-hour intervals) was acquired via Binance API from January 2023 to December 2024. Data preprocessing included technical indicator feature engineering, Z-Score normalization, and chronological data splitting. Hyperparameters were optimized using Optuna. The TFT architecture performed exceptionally, achieving a Root Mean Squared Error (RMSE) of 2.5191 USDT and a Coefficient of Determination (R2) of 0.9987. Probabilistically, the model successfully mapped risk ranges with a Weighted Mean Quantile Loss of 0.4629. Explainable AI analysis revealed that predictions were heavily influenced by historical closing price, RSI, Volume, and MACD. Innovatively, TFT outputs were integrated into a Decision Support System utilizing Google Gemini 2.5-Flash to automatically generate market analysis narratives. In conclusion, this study produced a robust forecasting model, successfully resolving the black-box problem into a transparent virtual analyst assistant.
Analisis Sentimen Masyarakat Terhadap Program Makan Bergizi Gratis (MBG) di Jawa Tengah Menggunakan Model Bidirectional Encoder Representations From Transformers For Indonesian (Indobert) Ibra Andnan Faiz Sempana; Imam Much Ibnu Subroto; Ghufron Ghufron
Populer: Jurnal Penelitian Mahasiswa Vol. 5 No. 3 (2026): September : Populer: Jurnal Penelitian Mahasiswa
Publisher : Universitas Maritim AMNI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/populer.v5i3.5530

Abstract

This study analyzes public sentiment toward the Free Nutritious Meal (Makan Bergizi Gratis/MBG) program in Central Java using data from the social media platform X. Data were collected automatically with Python and Selenium WebDriver, yielding 2,000 tweets containing username, date, location, and comment text. The comments were labeled manually, producing a relatively balanced dataset of 1,017 negative and 983 positive comments. After preprocessing cleaning, case folding, slang normalization, and WordPiece tokenization the dataset was split 80:10:10 for training, validation, and testing. A pre-trained IndoBERT model (124,442,882 total parameters, of which 28,943,618 were trainable) was fine-tuned for binary sentiment classification over 8 epochs; training loss fell from 0.6925 to 0.4914 while validation accuracy rose from 71.00% to 76.50%. On the 200-sample held-out test set, the final model achieved 84.50% accuracy, 84.89% precision, 84.50% recall, and an 84.44% F1-score, with a confusion matrix of 92 true negatives, 77 true positives, 21 false negatives, and 10 false positives. As a practical output, the sentiment analysis results were integrated into an interactive Streamlit dashboard to support real-time monitoring of public opinion.