Yan Liang

Yan Liang

Auto-generated profile, based on publicly available information

Yan Liang

School of Computer Engineering, Chengdu Technological University, Chengdu, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 November 2023 in Journal of Engineering Research
Verified
Journal Article
Open access
XDXin Dong
Xin Dong
YLYan Liang
Yan Liang
SMShoichiro Miyamoto
Shoichiro Miyamoto
Shingo YamaguchiShingo Yamaguchi
Shingo Yamaguchi

3 February 2025 in IEEE Access
Verified
Journal Article
Open access
XDXin Dong
Xin Dong
JWJie Wang
Jie Wang
YLYan Liang
Yan Liang
The presence of software defects significantly impacts the quality of software systems and increases development and maintenance costs. To improve system quality and reduce costs, it is necessary to predict software defects in the early stages of the software development lifecycle. This paper proposes Double Fault Disagreement (DFD), a novel diversity metric and method for selecting competent base classifiers for ensemble learning-based software defect prediction. To consider the diversity features of the base learners, several base learners with strong diversity are chosen to build ensemble learning. This method makes full use of the diversity characteristics of base learners, leverages their classification ability, optimizes the selection method for ensemble learning, and enhances the predictive performance of the ensemble model. The experimental results demonstrate that the DFD ensemble learning-based software defect prediction model outperforms the ten other models, including five common machine learning (ML) classification algorithms (logistic regression (LR), naïve Bayes (NB), K-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM)), two deep learning (DL) algorithms (multi-layer perceptron (MLP) and convolutional neural network (CNN)), and three ensemble learning algorithms (random forest (RF), extreme gradient boosting (XGB), and stacking). The DFD model achieves superior performance on eight public NASA and PROMISE datasets (six of which are imbalanced) across five performance indicators, including area under the curve (AUC), geometric mean (G-Mean), F1 score, Matthews correlation coefficient (MCC), and Balance. Furthermore, the DFD method is not only highly performant but also requires a small number of base learners to converge rapidly, thereby reducing the amount of data and computation time required.

15 December 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
HLHai Liao
Hai Liao
SCSong Chen
Song Chen
YLYan Liang
Yan Liang
FMfan min
fan min
Drone-view object detection (DroneDet) is a computer vision method for locating objects and predicting their categories in aerial images. Popular methods are often plagued by high energy consumption and severe noise interference in dynamic aerial environments. In this study, we propose a novel integer-valued spiking neural network (SNN)-based approach called SNN-Drone to optimize both energy consumption and performance. Regarding high energy consumption, a new integer-valued encoding (IVE) scheme transforms YOLOv8 features into high-fidelity integer spike trains. The IVE effectively reduces the high energy consumption associated with conventional binary spike encoding. For noise interference, our dual-branch SNN block (DBSB) enhances feature representation by separating spatial and semantic processing, while the normalized Wasserstein distance (NWD) loss refines localization accuracy for small and densely packed targets. These modules significantly improve detection performance. In addition, we construct UAVDT-SNN, the first large-scale neuromorphic dataset for uncrewed aerial vehicle (UAV) object detection with temporally encoded motion and diverse aerial scenes. Extensive experiments on the VisDrone 2019, UAVDT, and UAVDT-SNN datasets demonstrate that SNN-Drone achieves state-of-the-art performance, outperforming both baseline artificial neural networks (ANNs) and advanced YOLOv8–v12 variants. Notably, SNN-Drone-s improves the energy efficiency by $7.7\times $ compared to YOLOv8s. This work is the first to show that SNNs can serve as an energy-efficient yet competitive solution for drone-view object detection, narrowing the performance–energy gap with ANNs. Our code is available at https://github.com/iliaohai/SNN-Drone

4 March 2024 in Applied Artificial Intelligence
Verified
Journal Article
Open access
HLHai Liao
Hai Liao
YLYan Liang
Yan Liang
SCSong Chen
Song Chen
LXLingyun Xiang
Lingyun Xiang
ZCZhimin Chang
Zhimin Chang
YXYun Xiao
Yun Xiao

25 March 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
HLHai Liao
Hai Liao
SCSong Chen
Song Chen
YLYan Liang
Yan Liang
HZHang Zhou
Hang Zhou
FMfan min
fan min
Remote sensing object detection under haze extends traditional tasks to extreme scenes with low visibility and image degradation. Its key issues include feature loss during dehazing, inconsistency between the dehazing and detection stages, and limited datasets. In this study, we propose a novel two-stage framework called HAE-Net that integrates a structure-aware dehazing module with a YOLO11s-based object detector. For feature loss during dehazing, our Local and Global Defogging (LGD) network balances global context and local detail restoration to minimize feature loss. Unlike conventional methods, it preserves semantic integrity critical for downstream detection. Regarding inconsistency between the dehazing and detection stages, our Haze-Aware Detector (HAD) employs multi-scale feature fusion and the NWD Loss to optimize dehazed outputs for detection tasks. This enhances feature consistency across stages. For limited datasets, we present a new dataset, HAE-DIOR. It comprises 23,463 high-resolution hazy images and 192,472 annotated targets, spanning 20 object categories. Extensive experiments were conducted on the DIOR dataset, the real hazy datasets Hazy-DIOR and HazyDet, and the synthetic hazy dataset HAE-DIOR.Our method achieves competitive performance across all datasets, with an mAP$_{50}$ of 68.3% on HAE-DIOR, which is 22.7 points higher than YOLO12.

4 March 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
SCSong Chen
Song Chen
HLHai Liao
Hai Liao
YLYan Liang
Yan Liang
HZHang Zhou
Hang Zhou
FMfan min
fan min
Log anomaly detection is the most important method for identifying potential system failure. However, current Artificial Neural Networks (ANNs) based methods significantly increase the energy consumption of the system while improving the accuracy of log classification. In this paper, we present a novel SNN framework specifically designed for system log anomaly detection, offering distinct advantages in energy efficiency and temporal information processing. First, we introduce a new LLMs-based Spike Feature Encoding (LSFE) method, which encodes word embeddings from a pre-trained T5-base model into spatiotemporal spike sequences. This approach bridge the gap between high accuracy and low energy consumption in SNNs. Second, we propose an SNN Fine-Tuning (SFT) method that integrates SNN with the T5-base model, allowing supervised fine-tuning to enhance the learning capabilities of the network. This fine-tuning process addresses the accuracy limitations typically encountered in traditional SNNs. Experimental results demonstrate that 1) LogSNN consumes only 23\% of the energy required by UniLog and LogBERT; and 2) LogSNN achieves the highest performance with an F1-score of 0.9951 on the HDFS dataset and 0.9948 on the BGL dataset. This work presents a breakthrough in the application of SNNs to log anomaly detection, positioning SNNs as a competitive solution in resource-constrained environments.