Jiaxiang Lin

Dr. Jiaxiang Lin

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
31 October 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
SLShengzeng Li
Shengzeng Li
YZYiwen Zhong
Yiwen Zhong
JLJiaxiang Lin
Jiaxiang Lin
Short-term load forecasting is a prerequisite and basis for power system planning and operation and has received extensive attention from researchers. To address the problem of concept drift caused by changes in the distribution patterns of electricity load data, researchers have proposed regular or quantitative model update strategies to cope with the concept drift; however, this may involve a large number of invalid updates, which not only have limited improvement in model accuracy, but also insufficient model response timeliness to meet the requirements of power systems. Hence, this paper proposes a novel incremental ensemble model based on sample domain adaptation (AWS-DAIE) for adapting concept drift in a timely and accurate manner and solves the problem of inadequate training of the model due to the few concept drift samples. The main idea of AWS-DAIE is to detect concept drift on current electricity load data and train a new base predictor using Tradaboost based on cumulative weighted sampling and then dynamically adjust the weights of the ensemble model according to the performance of the model under current electricity load data. For the purposes of demonstrating the feasibility and effectiveness of the proposed AWS-DAIE algorithm, we present the experimental results of the AWS-DAIE algorithm on electricity load data from four individual households and compared with several other excellent algorithms. The experimental results demonstrated that the proposed AWS-DAIE not only can adapt to the changes of the data distribution faster, but also outperforms all compared models in terms of prediction accuracy and has good practicality.

4 May 2020 in Concurrency and Computation: Practice and Experience
Verified
Journal Article
Closed access
PDF file
JLJiaxiang Lin
Jiaxiang Lin
LWLiping Wu
Liping Wu
RCRiqing Chen
Riqing Chen
JWJianwei Wu
Jianwei Wu
XWXueping Wang
Xueping Wang

15 November 2024 in IEEE Access
Verified
Journal Article
Open access
ZHZhixin Huang
Zhixin Huang
JLJiaxiang Lin
Jiaxiang Lin
LLLizheng Lin
Lizheng Lin
JCJianyun Chen
Jianyun Chen
LZLiankai Zheng
Liankai Zheng
KZKeju Zhang
Keju Zhang
The prevalence of zero values in zero-inflated time-series (ZI-TS) data poses significant challenges for traditional LSTM networks in learning long-term dependencies and trends. Specifically, the high proportion of zeros dilutes the influence of non-zero values, leading LSTM model to frequently predict zeros, which ultimately reduces prediction accuracy. A Weighted Zero-inflated Sensitive LSTM model (WZS-LSTM) which integrates both a stacked LSTM architecture and a Weighted Zero-inflated Sensitive (WZS) loss function was proposed to improve LSTM’s prediction accuracy in ZI-TS data. First, the stacked LSTM structure enhances the model’s capacity to capture long-term dependencies. Second, the model dynamically adjusts its focus towards non-zero values through the WZS loss function. Thorough experiments were conducted on UCI time-series dataset “WeatherAUS” and “Population”, and four typical time-series prediction model Prophet, ARIMA, LSTM, and the hurdle model are selected for comparative analysis of algorithm performance, while “WeatherAUS” is a zero-inflated time-series data, and “Population” is a normal time-series data. The results demonstrated that the WZS-LSTM model improved prediction accuracy, reducing errors by at least 2.38% when compared with the selected models: Prophet, ARIMA, LSTM, and the hurdle model in ZI-TS data, while the predictive performance of WZS-LSTM for general time-series data was comparable to ARIMA, Prophet and traditional LSTM. In addition, WZS reduced the error by an additional 0.21% compared to the best-performing loss function. Finally, it was demonstrated on real-world datasets that WZS-LSTM offers significant advantages in predicting ZI-TS data and holds great potential for broader application.

29 May 2017 in Concurrency and Computation: Practice and Experience
Verified
Journal Article
Closed access
PDF file
JLJiaxiang Lin
Jiaxiang Lin
RCRiqing Chen
Riqing Chen
LWLiping Wu
Liping Wu
ZSZhaogang Shu
Zhaogang Shu
CYChangcai Yang
Changcai Yang

15 September 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
LZLiankai Zheng
Liankai Zheng
JLJiaxiang Lin
Jiaxiang Lin
ZHZhixin Huang
Zhixin Huang
YLYu Lin
Yu Lin
QZQin Zheng
Qin Zheng
JCJianyun Chen
Jianyun Chen
Rainfall intensity prediction based on commercial microwave link data has received significant attention in recent years due to the higher spatial resolution and lower energy consumption. However, the predictive performance is inferior to the model based on meteorological data by reason of the high noise in commercial microwave link data, further exacerbated by the imbalance in the number of samples across different rainfall intensities. Hence, a cost-sensitive rainfall intensity prediction model (CSRFP) is proposed to achieve better predictive performance in high-noise commercial microwave link data. First, the spatiotemporal scene information is encoded, and its weights are trained to provide the model with correlations between signal data from different stations, which helps the model to better capture potential patterns between the data and thus reduce the effect of noise. Next, the rainfall cross-entropy loss based on the rainfall distribution provides the model with the probability of different rainfall intensities occurring and back-calculates the signal attenuation at a specific rainfall intensity, assigning more reasonable weights to different samples considering signal attenuation, which makes the model cost-sensitive and can address the class imbalance problem. Extensive experiments are carried out on high-noise communication data and imbalanced rainfall data in Fuzhou. Compared to typical prediction methods such as RNN applied to rainfall and communication data, CSRFP improves Recall, Precision, AUCROC, AUCPR and F1 and Accuracy by approximately 19%, 37%, 8%, 22%, 30%, and 17%, respectively. Significantly, the model’s prediction accuracy for heavy rain with the smallest number of samples improves by about 13%.

4 September 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
QZQin Zheng
Qin Zheng
KZKeju Zhang
Keju Zhang
QCQianqian Chen
Qianqian Chen
JWJianwei Wu
Jianwei Wu
JLJiaxiang Lin
Jiaxiang Lin
The majority of existing clustering algorithms, including those algorithms that focus on boundary detection, seldom account for the reasonableness and genuineness of boundaries, consequently, it is difficult to obtain well-defined boundary in clustering-based regional division. A novel boundary search Clustering algorithm integrating Direction Centrality with the Distance of K-nearest-neighbor (DKCDC) is proposed, which is capable of achieving well-defined regional boundaries, to resolve the challenges mentioned above. Firstly, the preliminary boundary of clusters are established on the basis of boundary points and initial cluster labels obtained by the Clustering algorithm using the local Direction Centrality (CDC). Secondly, all the boundary points are further processed and discriminated, to detect noise points concealed within the boundaries, which provides the essential basis for achieving more genuine and reliable cluster boundaries and regional identification. In this process, a fusion strategy is adopted, to subdivide the boundary points into true boundaries and false boundaries by combining voting method and distance metric. Thirdly, a regional division result with well-defined boundary is obtained by DKCDC. In the end, by distinguishing genuine from false boundaries using fusion strategy, DKCDC enhances regional boundary demarcation. Experiments on synthetic and UCI datasets show DKCDC improves silhouette coefficient by at least s4.88% over CDC, K-Means, DBSCAN, OPTICS and HDBSCAN, indicating its broad potential for applications in clustering-based regional division.