# A Deep Learning-Based Framework Using CNN+LSTM for Karate Kata Classification and Correctness Evaluation
> Abdulrahman N.

URL kanonis: https://discover.unhas.ac.id/publications/pub_scopus_105037952868
Jurnal / Konferensi: Engineering Technology and Applied Science Research
Tahun terbit: 2026
DOI: https://doi.org/10.48084/etasr.12147
ISSN: 22414487
Kuartil SJR: Q2
Citations: 0

## Authors
- Abdulrahman N.

## Abstract
This paper presents a deep learning-based framework for automated classification and correctness evaluation of karate kata sequences using human pose data. The method utilizes MediaPipe BlazePose to extract 3D body keypoints from video frames, which are subsequently transformed into 132-dimensional vectors and temporally normalized into fixed-length sequences. Two neural architectures are evaluated: a baseline Convolutional Neural Network (CNN) and a hybrid CNN combined with Long Short-Term Memory (CNN+LSTM). Both models perform dual-output predictions: multi-class kata identification and binary correctness classification. Experimental results demonstrate that the CNN+LSTM model performs better in classification accuracy and movement assessment, with up to 95.74% accuracy and F1-scores exceeding 95% for several kata classes on unseen data. The findings highlight the importance of temporal modeling for structured movement analysis and establish a foundation for intelligent martial arts evaluation systems.

## Keywords
- Correctness
- Convolutional neural network
- Computer science
- Artificial intelligence
- Artificial neural network
- Binary classification
- Binary number
- Deep learning
- Pattern recognition (psychology)
- Movement (music)
- Martial arts
- Identification (biology)
- Feature extraction
- Machine learning
- Feature (linguistics)
- Computer vision
- Deep neural networks
- Baseline (sea)
- Foundation (evidence)
- Key (lock)

---
Sumber: Discover Unhas — RIMS Universitas Hasanuddin.
Saat mengutip, gunakan DOI bila tersedia atau URL kanonis di atas.