Claim Missing Document
Check
Articles

Found 23 Documents
Search

Prediksi Sebaran Hama Tikus Pada Tanaman Padi Menggunakan Metode Backpropagation Neural Network Arimawarni, Rafika; Sugiartawan, Putu; Murpratiwi, Santi Ika
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 5 No 1 (2022): September
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.175

Abstract

OPT (Plant Pest Organisms) is any activity or activities that damage and kill plants, one of which is caused by pests, diseases, viruses, etc. In Bali, especially in Tabanan Regency, OPT cases are still very high. OPT in rice plants caused by rats is a problem faced by farmers and in the future, it must be prevented by knowing the spread of rats. Therefore, the purpose of this research is to help farmers prevent pest attacks so that rice productivity can be increased. In this study, the backpropagation neural network method was used to predict the distribution of rat pests on rice plants. This method uses previous data, namely from 2012-2021 when the data is processed and calculated until the smallest error value is obtained. In this study, data were obtained from calculating the distribution of pests in hectares which showed a percentage difference in accuracy error of 16.2%, which means that the prediction of this calculation is good enough to be used as a reference for further research
Prediksi Sebaran Hama Padi Dengan Metode LSTM Pada Pertanian Padi Di Buleleng Negara, I Gede Sunia; Sugiartawan, Putu; Murpratiwi, Santi Ika
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 5 No 1 (2022): September
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.176

Abstract

Prediction is a systematic process of estimating future values based on patterns contained in data that has been converted into numerical form. In this study, the aim was to predict the distribution of rice borer in Buleleng district which could endanger the productivity of the rice agricultural sector. One of the methods used in this research is Long Short Term Memory (LSTM), a form of development of Recurrent Neural Network (RNN) which is suitable for processing and predicting time series data. The data used in this study is rice borer attack data for the last ten years, from 2012 to 2021. The results show that the LSTM model has an MAE data testing of 16.8149 and MAPE data testing of 2.356%, and MAE data training of 16.8149 and MAPE data training of 2,356%. These values measure the prediction error with the MAE and MAPE techniques. With these results, the agricultural service can recognize the pattern of distribution of rice borer attacks in the region and take appropriate action to overcome them.
Incremental CNN-k-NN Hybrid Facial Recognition for Helmeted Facial Recognition in IoT-Enabled Smart Parking: A Case Study at Universitas Mataram Widiartha, Ida Bagus Ketut; Husodo, Ario Yudo; Thuy, Tran Thi Thanh; Murpratiwi, Santi Ika
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 6 (2025): JUTIF Volume 6, Number 6, Desember 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.6.5447

Abstract

Helmeted rider identification challenges traditional facial recognition, especially in Indonesian campuses like UNRAM, where motorbike use is prevalent and theft risks are high. This study develops a hybrid CNN-k-NN system for secure parking access. The dataset contains 2,800 augmented images (Haar Cascade crop, 224x224 grayscale), with features extracted via VGG16/ResNet and classified using k-NN (k=1, Euclidean/Cosine). The system achieves 95.62% accuracy, with precision, recall, and F1 scores of 0.96. Incremental retraining reduces processing time to under 1 second, compared to 30 minutes for full retraining. The use of cosine similarity improves accuracy slightly over Euclidean distance. This solution enhances IoT-based smart campuses by enabling efficient, real-time identification and reducing theft by improving access control. It is adaptable to low-resource environments, supporting scalable deployments in smart parking and campus security systems.