TransformCode: a contrastive learning framework for code embedding via subtree transformation

Z **an, R Huang, D Towey, C Fang… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing
software development efficiency. The advent of pre-trained models (PTMs) leveraging …

zsllmcode: An effective approach for functional code embedding via llm with zero-shot learning

Z **an, C Cui, R Huang, C Fang, Z Chen - arxiv preprint arxiv:2409.14644, 2024‏ - arxiv.org
Regarding software engineering (SE) tasks, Large language models (LLMs) have the
capability of zero-shot learning, which does not require training or fine-tuning, unlike pre …

Convolutional Neural Network Image Classification Based on Different Color Spaces

Z **an, R Huang, D Towey… - Tsinghua Science and …, 2024‏ - ieeexplore.ieee.org
Although Convolutional Neural Networks (CNNs) have achieved remarkable success in
image classification, most CNNs use image datasets in the Red-Green-Blue (RGB) color …

Hidden Markov models with multivariate bounded asymmetric student's t-mixture model emissions

O Bouarada, M Azam, M Amayri, N Bouguila - Pattern Analysis and …, 2024‏ - Springer
Abstract Hidden Markov models (HMMs) are popular methods for continuous sequential
data modeling and classification tasks. In such applications, the observation emission …

Challenges and Future Developments in the Metaverse

S Wang, W Huang - 2024 2nd International Conference on …, 2024‏ - ieeexplore.ieee.org
This paper gives a comprehensive overview of the metaverse, focusing on its key
technologies, current challenges and future prospects. Key technologies discussed include …

Mixture-Based Clustering and Hidden Markov Models for Energy Management and Human Activity Recognition: Novel Approaches and Explainable Applications

HGA Al-Bazzaz - 2023‏ - spectrum.library.concordia.ca
In recent times, the rapid growth of data in various fields of life has created an immense
need for powerful tools to extract useful information from data. This has motivated …

Generative Models Based on the Bounded Asymmetric Student's t-Distribution

O Bouarada - 2023‏ - spectrum.library.concordia.ca
Gaussian mixture models (GMMs) are a very useful and widely popular approach for
clustering, but they have several limitations, such as low outliers tolerance and assumption …

The Impact of Color Spaces on Convolutional Neural Network Classification Performance

Z **an, R Huang, D Towey, C Yue - Available at SSRN 4442933‏ - papers.ssrn.com
Image classification has become widely used in computer vision applications in recent
years, including in intrusion detection in video surveillance. While Convolutional Neural …

Generative Models Based on the Bounded Asymmetric Gaussian Distribution

Z **an - 2021‏ - spectrum.library.concordia.ca
The bounded asymmetric Gaussian mixture model (BAGMM) has proved that it generally
performs better than the classical Gaussian mixture model. In this thesis, we investigate the …