Claim Missing Document
Check
Articles

Found 22 Documents
Search

Deteksi Bahasa Isyarat Berdasarkan Abjad Menggunakan Metode LSTM (Long Short Term Memory) Syanti Irviantina; Dela Agustri Wijaya; Desiana R. Situmorang; Nazhiifah Mawaddah Juliyanda Nasution
Majalah Ilmiah METHODA Vol. 14 No. 3 (2024): Majalah Ilmiah METHODA
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methoda.Vol14No3.pp371-376

Abstract

The LSTM based sign language detection system combined with the use of mediapipe can recognize hand gestures in real time with high accuracy. Alphabet based sign language can use this model to collect temporal patterns of hand gestures. The data used in this study are 30 sample for each alphabet based on American Sign Language (ASL). The data is processed through landmark detection on the hand using mediapipe and opencv, keypoints extraction, folder creation and pre – processing with 80% data divisior for training data and 20 % data for testing data. Using Adam optimization, categorical crossentropy loss function and evaluation metric. The model was trained with 100 epochs and evaluated using confusion matrix. The evaluation results showed that the LSTM model performed well with an accuracy of 98%.
Identifikasi Potensi Penipuan pada Transaksi Bank Menggunakan K-Means Clustering Jessica Uly Sari Hutagalung; Kristin Trivena Sihombing; Michael Owen Hutabarat; Syanti Irviantina
Majalah Ilmiah METHODA Vol. 14 No. 3 (2024): Majalah Ilmiah METHODA
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methoda.Vol14No3.pp392-395

Abstract

Increasing cases of fraud in bank transactions are a serious concern for financial institutions, resulting in significant economic losses and undermining customer trust. This calls for identifying suspicious transaction patterns through machine-learning approaches to mitigate the risk of fraud. The methods used include problem identification, transaction data collection, and preprocessing to clean and prepare the data and after that, applying the K-Means Clustering algorithm to group transactions based on similar characteristics. The evaluation result obtained in this study using the Silhouette Score is 0.42, indicating a fairly good separation between normal and suspicious transactions. This research is expected to contribute to the development of a more accurate and efficient machine learning-based fraud detection system in banking institutions.