Di Wu

Dr. Di Wu

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
17 March 2022 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
GLGuanzhi Li
Guanzhi Li
AZAining Zhang
Aining Zhang
QZQizhi Zhang
Qizhi Zhang
Di WuDi Wu
Di Wu
CZChou-Jun Zhan
Chou-Jun Zhan
Accurate prediction of a stock price is a challenging task due to the complexity, chaos, and non-linearity nature of financial systems. In this brief, we proposed a multi-indicator feature selection method for stock price prediction based on Pearson correlation coefficient (PCC) and Broad Learning System (BLS), named the PCC-BLS framework. Firstly, PCC was used to select the input features from 35 features, including original stock price, technical indicators, and financial indicators. Secondly, these screened input features were used for rapid information feature extraction and training a BLS. Four stocks recorded on the Shanghai Stock Exchange or Shenzhen Stock Exchange were adopted to evaluate the performance of the proposed method. In addition, we compared the forecasting results with ten machine learning methods, including Support Vector Regression (SVR), Adaptive Boosting (Adaboost), Bootstrap aggregating (Bagging), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Broad Learning System (BLS). Among all algorithms used in this brief, the proposed model showed the best performance with the highest model fitting ability.

5 August 2019 in IEEE Transactions on Sustainable Computing
Verified
Journal Article
Open access
Di WuDi Wu
Di Wu
Hao WangHao Wang
Hao Wang
HMHadi Mohammed
Hadi Mohammed
RSRazak Seidu
Razak Seidu
Constructing Sustainable Smart Water Supply systems are facing serious challenges all around the world with the fast expansion of modern cities. Water quality is influencing our life ubiquitously and prioritizing all the urban management. Traditional urban water quality control mostly focused on routine tests of quality indicators, which include physical, chemical, and biological groups. However, the inevitable delay for biological indicators has increased the health risk and leads to accidents such as massive infections in many big cities. In this paper, we first analyze the problem, technical challenges, and research questions. Then, we provide a possible solution by building a risk analysis framework for the urban water supply system. It takes indicator data we collected from industrial processes to perceive water quality changes, and further for risk detection. In order to provide explainable results, we propose an Adaptive Frequency Analysis (Adp-FA) method to resolve the data using indicators' frequency domain information for their inner relationships and individual prediction. We also investigate the scalability properties of this method from indicator, geography, and time domains. For the application, we select industrial quality data sets collected from a Norwegian project in four different urban water supply systems, as Oslo, Bergen, Strømmen, and Ålesund. We employ the proposed method to test spectrogram, prediction accuracy, and time consumption, comparing with classical Artificial Neural Network and Random Forest methods. The results show our method better perform in most of the aspects. It is feasible to support industrial water quality risk early warnings and further decision support.

16 May 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
ZLZuhe Li
Zuhe Li
ZHZhenwei Huang
Zhenwei Huang
YPYushan Pan
Yushan Pan
JYJun Yu
Jun Yu
WLWeihua Liu
Weihua Liu
Hao WangHao Wang
Hao Wang

26 February 2020 in Sensors
Verified
Journal Article
Open access
PDF file
ZYZhaolin Yuan
Zhaolin Yuan
JHJinlong Hu
Jinlong Hu
Di WuDi Wu
Di Wu
Xiaojuan BanXiaojuan Ban
Xiaojuan Ban
This paper focuses on the time series prediction problem for underflow concentration of deep cone thickener. It is commonly used in the industrial sedimentation process. In this paper, we introduce a dual attention neural network method to model both spatial and temporal features of the data collected from multiple sensors in the thickener to predict underflow concentration. The concentration is the key factor for future mining process. This model includes encoder and decoder. Their function is to capture spatial and temporal importance separately from input data, and output more accurate prediction. We also consider the domain knowledge in modeling process. Several supplementary constructed features are examined to enhance the final prediction accuracy in addition to the raw data from sensors. To test the feasibility and efficiency of this method, we select an industrial case based on Industrial Internet of Things (IIoT). This Tailings Thickener is from FLSmidth with multiple sensors. The comparative results support this method has favorable prediction accuracy, which is more than 10% lower than other time series prediction models in some common error indices. We also try to interpret our method with additional ablation experiments for different features and attention mechanisms. By employing mean absolute error index to evaluate the models, experimental result reports that enhanced features and dual-attention modules reduce error of fitting ~5% and ~11%, respectively.

26 April 2024 in Water
Verified
Journal Article
Open access
PDF file
JLJincheng Liu
Jincheng Liu
Di WuDi Wu
Di Wu
HMHadi Mohammed
Hadi Mohammed
RSRazak Seidu
Razak Seidu
Water quality monitoring plays a crucial role in urban water supply systems for the production of safe drinking water. However, the traditional approach to water monitoring in Norway relies on a periodic (weekly/biweekly/monthly) sampling and analysis of biological indicators, which fails to provide a timely response to changes in water quality. This research addresses this issue by proposing a data-driven solution that enhances the timeliness of water quality monitoring. Our research team applied a case study in Ålesund Kommune. A sensor platform has been deployed at Lake Brusdalsvatnet, the water source reservoir in Ålesund. This sensor module is capable of collecting data for 10 different physico-chemical indicators of water quality. Leveraging this sensor platform, we developed a CNN-AutoEncoder-SOM solution to automatically monitor, process, and evaluate water quality evolution in the lake. There are three components in this solution. The first one focuses on anomaly detection. We employed a recurrence map to encode the temporal dynamics and sensor correlations, which were then fed into a convolutional neural network (CNN) for classification. It is noted that this network achieved an impressive accuracy of up to 99.6%. Once an anomaly is detected, the data are calibrated in the second component using an AutoEncoder-based network. Since true values for calibration are unavailable, the results are evaluated through data analysis. With high-quality calibrated data in hand, we proceeded to cluster the data into different categories to establish water quality standards in the third component, where a self-organizing map (SOM) is applied. The results revealed that this solution demonstrated significant performance, with a silhouette score of 0.73, which illustrates a small in-cluster distance and large intra-cluster distance when the water was clustered into three levels. This system not only achieved the objective of developing a comprehensive solution for continuous water quality monitoring but also offers the potential for integration with other cyber–physical systems (CPSs) in urban water management.

3 April 2018 in Symmetry
Verified
Journal Article
Open access
PDF file
XWXiaokun Wang
Xiaokun Wang
Xiaojuan BanXiaojuan Ban
Xiaojuan Ban
RHRunzi He
Runzi He
Di WuDi Wu
Di Wu
XLXing Liu
Xing Liu
YXYuting Xu
Yuting Xu
In order to simulate fluid-solid boundary interaction for non-Newtonian Smoothed Particle Hydrodynamics (SPH) fluids, we present a steady and realistic fluid-solid boundary handling method using symmetrical interaction forces. Firstly, we use the improved SPH method to model the non-Newtonian fluid. Secondly, the density of boundary particle is created into the calculation of fluid-solid interaction forces. Besides, we apply friction conditions to constrain the fluid particles at the boundary. Finally, we apply the predictive-corrective scheme to correct the density deviation and improve boundary computing efficiency. The experiment confirms the feasibility for the interaction between non-Newtonian fluid and solid objects with this method. At the same time, it reflects the viscous characteristics and ensures the physical properties of non-Newtonian fluid. In addition, compared to existing methods, this method is more stable and easier to implement.