Jurnal Universitas Siliwangi
Not a member yet
2884 research outputs found
Sort by
OPTIMALISASI PENGEMBANGAN PERTANIAN PADI DI KABUPATEN JEMBER: PENDEKATAN KOLABORATIF TRIPLE HELIX DENGAN METODE SWOT UNTUK KETAHANAN PANGAN BERKELANJUTAN
Full text linkKabupaten Jember dikenal sebagai salah satu lumbung padi di Jawa Timur, namun dalam beberapa tahun terakhir mengalami penurunan signifikan dalam produksi padi. Penelitian ini bertujuan untuk mengidentifikasi kekuatan, kelemahan, peluang, dan ancaman yang dihadapi dalam pengembangan pertanian padi dengan menggunakan analisis SWOT dan Triple Helix Model. Melalui kolaborasi antara pemerintah, akademisi, dan industri, penelitian ini menemukan bahwa meskipun terdapat tantangan seperti fluktuasi harga dan keterbatasan infrastruktur, terdapat peluang besar untuk mengoptimalkan potensi pertanian melalui dukungan kebijakan, inovasi teknologi, dan peningkatan kolaborasi lintas sektor. Hasil penelitian ini diharapkan dapat menjadi dasar bagi strategi pengembangan pertanian padi yang berkelanjutan di Kabupaten Jembe
Data Augmentation Strategies on Spectrogram Features for Infant Cry Classification Using Convolutional Neural Networks
Full text linkInfant cry classification is an important task to support parents and healthcare professionals in understanding infants’ needs, yet the challenge of limited and imbalanced datasets often reduces model accuracy and generalization. This study proposes the application of diverse audio data augmentation strategies including time stretching, time shifting, pitch scaling, and polarity inversion combined with spectrogram representation to enhance Convolutional Neural Network (CNN) performance in classifying infant cries. The dataset from the Donate-a-Cry Corpus was expanded from 457 to 6,855 samples through augmentation, improving class balance and variability. Experimental results show that CNN accuracy increased from 85% before augmentation to 99.85% after augmentation, with precision, recall, and F1-score reaching near-perfect values across all categories. The confusion matrix further confirms robust classification with minimal misclassifications. These findings demonstrate that data augmentation is crucial to overcoming dataset limitations, enriching acoustic feature diversity, and reducing model bias, while offering practical implications for the development of accurate, reliable, and real-world applicable infant cry detection systems
Automated Identification of Oil Palm’s 17th Leaf Using YOLOv12 and Spatial Positioning
No full textThis study proposes an artificial intelligence–based approach for automatic identification of the 17th leaf in oil-palm trees (Elaeis guineensis), which serves as a key physiological indicator for nutrient monitoring. The method integrates YOLOv12 object detection with a spatial-positioning algorithm that estimates leaf order through vertical sorting of detected fronds. A total of 1,250 annotated field images were collected from farmer-recorded videos to train and evaluate the system. The proposed model achieved a mean average precision ([email protected]) of 92.4% and an average positional error of 10.6 pixels in locating the 17th leaf. Compared with manual identification that requires 3–5 minutes per tree, the automated system performs the entire process in under 15 seconds, providing over 95% time efficiency improvement. This work demonstrates a novel fusion of real-time deep-learning detection and spatial reasoning for nutrient-focused precision agriculture and establishes a practical foundation for scalable, automated leaf indexing in plantation management
Operational Analysis of Rooftop Solar Power Plant at SMK Negeri 3 Kupang
Full text linkThe implementation of 25 kWp On-Grid Rooftop Solar Power Plant at SMK Negeri 3 Kupang is expected to provide a solution to the problem of dependence on conventional energy and reduce school operational costs. Therefore, it is important to conduct an analysis of the Rooftop Solar Power Plant system at SMK Negeri 3 Kupang, in order to optimize the use of renewable energy and reduce school electricity operational costs. This study aims to determine the performance of the Rooftop Solar Power Plant and the amount of savings that occur. The research method used is a descriptive method and direct measurement of the inverter, MDP, LVMDP to measure the current and voltage to obtain the output power of the Solar Power Plant, PLN and load. The results of the study showed that the operational performance of the Rooftop Solar Power Plant can be known through the efficiency of the Rooftop Solar Power Plant at SMK Negeri 3 Kupang which was obtained with a maximum value that occurred on Saturday of 86.96%. The measurement results showed that there were savings in power and bills at SMK Negeri 3 Kupang. With savings for 7 consecutive days of 84.87%; 91.60%; 35.98%; 58.73%; 57.74%;
25.15%; 84.04%
Classifying Object Size in an Arduino-Based RADAR System Using an IR Sensor and I2C-LCD
Full text linkThe radio detection and ranging (RADAR) system uses electromagnetic waves to measure the distance and direction of an object. The IR (infrared) sensor uses infrared light to detect an object. This study uses the IR sensor to classify the size of an object in an Arduino-based RADAR system. A binary logical method classifies the size of an object as either long or small. The result is displayed on a liquid crystal display (LCD). An I2C module is used to easily connect the LCD to the Arduino. The system has been simulated in Proteus software to verify the Arduino code. The Arduino-based RADAR system with size classification has been implemented using two IR sensors, an ultrasonic sensor, an LCD, and a servo motor. Two IR sensors have been used at different heights to classify the size of an object. A Java application is used to visualize the RADAR system on a PC in a graphical user interface (GUI), which shows the moving object in real-time. The ultrasonic range is programmed at 40 cm to detect objects. The system can detect objects in the 40 cm range and between 0 and 180° angles
Implikasi Alat Peraga Fluida Dinamis (Asas Bernoulli) Terintegrasi TPACK terhadap Keterampilan Proses Sains Peserta Didik Kelas XI IPA MA Al-Bairuny
Full text linkKeterampilan Proses Sains (KPS) siswa sangat penting dalam proses pembelajaran dan sesuai dengan keterampilan abad 21 yaitu berpikir kritis, berpikir kreatif, komunikasi dan kolaborasi. Tujuan penelitian ini adalah mengetahui KPS siswa menggunakan media alat peraga fluida dinamis terintegrasi TPACK. Jenis penelitian ini menggunakan metode penelitian kuantitatif deskriptif. Sampel penelitian ini adalah siswa kelas XI IPA MA Al-Bairuny sejumlah 20 siswa dengan teknik pengambilan sampel yaitu teknik sampel jenuh karena jumlah sampel yang dipilih sama dengan jumlah populasi. Penelitian dilaksanakan dengan menggunakan one-shot case study. Teknik pengumpulan data yang digunakan adalah observasi dengan mempertimbangkan rubrik penilaian KPS. Data hasil penelitian dianalisis dengan menggunakan persentase kategori KPS. Berdasarkan analisis data menunjukkan implikasi produk penelitian di lapangan dapat mengembangkan KPS siswa berdasarkan persentase KPS siswa dengan hasil 82.5 % dalam kategori baik. Penelitian ini memberikan implikasi dalam mengembangkan keterampilan proses sains peserta didik melalui penggunaan alat peraga yang interaktif dengan mengintegrasikan TPACK dalam pembelajaran fisika
Analisis Kuantitatif Model SEMF: Studi Perbandingan Terhadap Data Eksperimen Massa Nuklida
Full text linkSemiempirical Mass Formula (SEMF) merupakan salah satu model teoretis yang digunakan untuk memperkirakan massa inti dan energi ikat nuklida. Meskipun sederhana, akurasi SEMF sangat bergantung pada nilai parameter yang digunakan. Penelitian ini bertujuan mengevaluasi kinerja beberapa set parameter SEMF dari literatur berbeda dalam memprediksi massa nuklida ringan stabil. Data eksperimen diambil dari Atomic Mass Evaluation (AME2020), sedangkan perhitungan teoretis dilakukan menggunakan SEMF dengan empat set parameter berbeda. Seluruh perhitungan dilakukan menggunakan Microsoft Excel 2021 dengan presisi bawaan double-precision, tanpa pembulatan manual maupun penggunaan makro, sehingga operasi aritmetika berlangsung konsisten melalui formula standar spreadsheet. Hasil analisis menunjukkan adanya variasi akurasi antar model. Model IV memberikan performa terbaik dengan nilai MAE terkecil, yaitu 0,00199 u, yang konsisten dengan kecenderungan selisih massa dan error absolut yang lebih kecil. Temuan ini menunjukkan bahwa untuk nuklida ringan stabil pada rentang A = 1 hingga A = 55, model tanpa suku pairing justru menghasilkan prediksi massa yang lebih baik. Secara keseluruhan, penelitian ini menegaskan bahwa SEMF tetap relevan digunakan dalam studi massa nuklida, dan bahwa pembaruan atau reevaluasi parameter perlu dilakukan untuk memastikan ketepatan model dalam era data massa berpresisi tinggi
Travel Package Recommendation System Using Collaborative Filtering Method at Loka Travel
Full text linkThe rapid development of information technology drives the need for a system that can help tourists in determining the choice of tourist destinations that suit their preferences. The Loka Travel application was developed as a web-based platform that provides various tour packages and is equipped with a recommendation system to suggest relevant destinations for users. This study aims to design and implement a tour package recommendation system using the Collaborative Filtering method with a memory-based approach. This method works by calculating the similarity between users based on their rating or booking history for tour packages, allowing the system to suggest packages that are preferred by other users who have similar preferences. The cosine similarity algorithm is used in the process of calculating the similarity between users, with interaction data obtained from booking and payment activities in the application. The implementation of this system is carried out using the Laravel framework and MySQL database. The results of the system test show that the system is able to provide recommendations with an accuracy level of 80.63%, based on the calculation of Mean Absolute Error (MAE). Thus, this system can help users find suitable tourist destinations and improve their experience in using the Loka Travel application
Implementation of Neural Collaborative Filtering for Social Aid Recipient Recommendation
Full text linkSocial assistance needs system accurate recommendations for ensure distribution appropriate target. Research This aims to implement Neural Collaborative Filtering (NCF) to recommend recipient help social based on integration of dynamic parameters of poverty data. The NCF method was chosen Because his ability combines Generalized Matrix Factorization (GMF) and Multi-Layer Perceptron (MLP) to catch non-linear relationship between data. The dataset is taken from 845 recipients assistance in Cijulang Village, District Ciamis, with criteria covering employment, income, health, and family history assistance. The preprocessing stage includes data cleaning, label encoding, one-hot encoding, and data splitting (training-validation 80:20). The NCF architecture is built with embedding layer (dimension 32), hidden layer MLP (128-64-32 neurons), and output layer that combines GMF and MLP. Evaluation using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results show that the model achieves RMSE 0.63 and MAE 0.47 on the training data, but overfitting occurred with a validation RMSE of 1.40 and MAE of 1.24. Analysis indicates the need for hyperparameter optimization (e.g., regulation, dropout rate) for an increase in generalization. Findings This prove NCF potential in increase accuracy recommendation help social, at the same time highlight importance data handling no balance and sparsity in context poverty. Implications study covers improvement transparency distribution assistance and reduction jealousy social through recommendation data -based. This study gives contribution methodological in NCF adaptation for sector public
Dampak Media Sosial Terhadap Partisipasi Politik Pemilih Milenial Dalam Percaturan Politik Lokal
Full text linkPercaturan politik lokal kini tidak hanya diwarnai oleh peran elit politik dan masyarakat lokal namun lebih mencerminkan peran besar pemilih milenial melalui penggunaan media sosial. Pemilih milenial acapkali dianggap tidak peduli dengan politik namun melalui media sosial nampak fenomena keterlibatan dalam politik. Tujuan penelitian, mengukur dampak media sosial terhadap partisipasi politik pemilih milenial. Metode yang digunakan adalah deskriptif kuantitatif dimana data diperoleh melalui studi survei terhadap populasi atau seluruh pemilih milenial pada pemilukada Kabupaten TTU Tahun 2020 berjumlah 90.245 orang dan sampel 200 orang dengan penyebaran kuesioner secara online, wawancara dan dokumentasi. Setelah itu, dilakukan tabulasi silang, dianalisis menggunakan teknik statistik inferensial jenis analisis regresi. Terdapat hubungan yang signifikan antara penggunaan media sosial terhadap partisipasi politik pemilih milenial. Dimana pemilih milenial berperan sebagai penonton, pembagi informasi, komentator dan pembuat konten informasi secara simultan dalam kegiatan pemilihan, lobby, kegiatan organisasi, contacting dan tindakan kekerasan. Pada variabel media sosial (X), pemilih milenial menggunakan media sosial dengan tinggi maka variabel partisipasi politik (Y) mengalami peningkatan yang signifikan dengan nilai koefisien regresi: 0,136 atau 13,6%. Artinya penggunaan media sosial yang tinggi dapat meningkatkan partisipasi politik pemilih milenial yang tinggi pul