arXiv subjects

Ngaiming Kwok

Publications and source records attributed to Ngaiming Kwok.

3 recordsLinked to original sources

arXiv2025

Further Commentary on the Sooty Tern Optimization Algorithm and Tunicate Swarm Algorithm

In the article (Kudela, 2022), experimental demonstrations indicated that two Bio-/Nature inspired optimization algorithms (BNIOAs), Sooty Tern Optimization Algorithm (STOA) and Tunicate Swarm Algorithm (TSA), exhibit a zero-bias, leading to the conclusion that the claims made in the original papers were overstated. In this work, we extend the analysis by investigating the source of this bias from a probabilistic perspective. Our findings suggest that operations involving exponentiation, trigonometric functions, and divisions between random numbers are the primary causes of design flaws. These operations result in probability density distributions with a noticeable shift toward zero. Therefore, the application of these two algorithms should be approached with due caution.

cs.NE↗

arXiv2025

On the Structural and Statistical Flaws of the Exponential-Trigonometric Optimizer

The proliferation of metaphor-based metaheuristics has often been accompanied by issues of symbolic inflation, benchmarking opacity, and statistical misuse. This study presents a diagnostic critique of the recently proposed Exponential Trigonometric Optimizer (ETO), exposing fundamental flaws in its algorithmic structure and the statistical reporting of its performance. Through a stripped mathematical reconstruction, we identify inert symbolic constructs, ill-defined recurrence schedules, and ineffective update mechanisms that collectively undermine the algorithm's purported balance and effectiveness. A principled benchmarking comparison against nine established metaheuristics on the CEC 2017 and 2021 suites reveals that ETO's performance claims are inflated. While it demonstrates mid-tier competitiveness, it consistently fails against top-tier algorithms, especially under high-dimensional and shift-rotated landscapes. Our statistical framework, employing rank-based non-parametric tests and effect size diagnostics, quantifies these limitations and highlights ETO's structural fragility and lack of scalability. The paper concludes by advocating for a reformist framework in metaheuristic research, emphasizing symbolic hygiene, operator attribution, and statistical transparency to mitigate misleading narratives and foster a more robust and reproducible optimization literature.

cs.NE↗

arXiv2019

Three-dimensional Backbone Network for 3D Object Detection in Traffic Scenes

The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature extraction methods. To address this issue, this study proposes a 3D backbone network to acquire comprehensive 3D feature maps for 3D object detection. It primarily consists of sparse 3D convolutional neural network operations in the point cloud. The 3D backbone network can inherently learn 3D features from the raw data without compressing the point cloud into multiple 2D images. The sparse 3D convolutional neural network takes full advantage of the sparsity in the 3D point cloud to accelerate computation and save memory, which makes the 3D backbone network feasible in a real-world application. Empirical experiments were conducted on the KITTI benchmark and comparable results were obtained with respect to the state-of-the-art performance for 3D object detection.

cs.CV↗