Towards instance-dependent label noise-tolerant classification: a probabilistic approach

Pattern Analysis and Applications - Learning from labelled data is becoming more and more challenging due to inherent imperfection of training labels. Existing label noise-tolerant learning...     

Evaluation of pomelo maturity based on acoustic response and peel properties

This research investigated the maturity assessment of pomelo using acoustic properties obtained from an impact of fruit, optical properties of the peel and variables related to oil glands from peel images. Pomelo samples were harvested at 5.5, 6.0, 6.5 and 7.0 months after anthesis. All nondestructive variables were used to build qualitative models with partial least squares discriminant analysis. The classification model based on the nondestructive variables showed that fruits could be separated into immature, early‐mature and late‐mature groups with an accuracy of 96.7%. The important variables contributing to the classification were the impact response based on the second‐order resonant frequency and the difference of green colour between the oil gland and the peel.     

Recognition-based character segmentation for multi-level writing style

International Journal on Document Analysis and Recognition (IJDAR) - Character segmentation is an important task in optical character recognition (OCR). The quality of any OCR system is highly...     

An iterative bidirectional heuristic placement algorithm for solving the two-dimensional knapsack packing problem

This article presents an efficient heuristic placement algorithm, namely, a bidirectional heuristic placement, for solving the two-dimensional rectangular knapsack packing problem. The heuristic demonstrates ways to maximize space utilization by fitting the appropriate rectangle from both sides of the wall of the current residual space layer by layer. The iterative local search along with a shift strategy is developed and applied to the heuristic to balance the exploitation and exploration tasks in the solution space without the tuning of any parameters. The experimental results on many scales of packing problems show that this approach can produce high-quality solutions for most of the benchmark datasets, especially for large-scale problems, within a reasonable duration of computational time.