Ensemble deep transfer learning model for Arabic (Indian) handwritten digit recognition

A Hybrid Rule-Based and Machine Learning System for Arabic Check Courtesy Amount Recognition

Courtesy amount recognition from bank checks is an important application of pattern recognition. Although much progress has been made on isolated digit recognition for Indian digits, there is no work reported in the literature on courtesy amount recognition for Arabic checks using Indian digits. Arabic check courtesy amount recognition comes with its own unique challenges that are not seen in isolated digit recognition tasks and, accordingly, need specific approaches to deal with them. This paper presents an end-to-end system for courtesy amount recognition starting from check images as input to recognizing amounts as a sequence of digits. The system is a hybrid system, combining rule-based modules as well as machine learning modules. For the amount recognition system, both segmentation-based and segmentation-free approaches were investigated and compared. We evaluated our system on the CENPARMI dataset of real bank checks in Arabic. We achieve 67.4% accuracy at the amount level and 87.15% accuracy at the digit level on the test set consisting of 626 check images. The results are presented with detailed analysis, and some possible future work is identified. This work can be used as a baseline to benchmark future research in Arabic check courtesy amount recognition.

EM-TSA: An ensemble machine learning-based transient stability assessment approach for operation of power systems

The transient stability of power systems plays the key role in their smooth operation, which is influenced by many working condition factors. To automatically evaluate transient stability status precisely for power systems remains a practical issue. To realize data-driven evaluation for the transient stability of the power systems, this paper proposes an ensemble machine learning-based assessment approach for transient stability status of power systems, which is named as EM-TSA for short. The experiments prove that the proposed model outperforms each secondary learning model and the traditional deep learning model in terms of accuracy and safety indexes. Considering the effect of noise, the experiments are repeated by adding Gaussian noise to the original test set. The results show that the ensemble learning model can maintain 98.4% accuracy under various noisy environments. In addition, the proposed model is combined with the sample transfer learning algorithm when the system topology is changed. An online update method for transient stability models is proposed, and compared with the previous approaches, the proposed algorithm can adapt to the online update of transient stability assessment models.