Wenan Tan

Wenan Tan

Auto-generated profile, based on publicly available information

Wenan Tan

School of Computer and Information Engineering, Shanghai Polytechnic University, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
11 October 2022 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
YSYong Sun
Yong Sun
WTWenan Tan
Wenan Tan
LHLi Huang
Li Huang
NXNa Xie
Na Xie
LRLing Ruan
Ling Ruan
Lida XuLida Xu
Lida Xu
Reliable Internet of Things (IoT) service discovery is a significant task in intelligent service-oriented IoT systems. Collaborative Filtering (CF) turns out to be an effective solution to IoT service discovery. However, the traditional CF framework is facing the following challenges: inefficiency in learning the high-order interactions between users and IoT services and ineffectively making use of geographical location information. Moreover, deploying a CF framework in real-world distributed IoT systems poses another significant challenge in terms of reliability assurance and privacy protection. For bridging this gap, we propose an innovative Integrated Collaborative Filtering framework (ICF) with incorporating the location-aware quality of IoT services into a heterogeneous graph embedding model. Meanwhile, a Geohash-based privacy-preservation mechanism is introduced to encoding the location information into a short string for protecting the sensitive location information. The proposed ICF framework is an integrated architecture combining advanced graph embedding learning and heterogeneous side information. And a joint objective optimization function is designed in the graph embedding learning to qualify automatic IoT service features. In this way, the hidden user-service interaction information and location-aware quality semantic features can be explored in an effective and reliable way. Furthermore, the learned location-aware quality embedding vector is incorporated to discover the reliable services among all IoT services with the mini-batch online clustering-based CF algorithm. The experimental findings illustrate the significant efficacy and reliability of our proposed ICF framework in large scale IoT service discovery scenarios.

1 May 2021
Verified
Conference Paper
Closed access
WTWenan Tan
Wenan Tan
YWYiting Wang
Yiting Wang
Aiming at the low accuracy of photovoltaic power prediction, a photovoltaic power prediction algorithm based on empirical mode decomposition algorithm and integrated neural network is proposed. First, the empirical mode decomposition algorithm decomposes the historical photovoltaic power data into a series of stationary sequences, and then a prediction model is constructed using multiple backpropagation (BP) neural networks. Finally, these models’ predicted values are weighted and fused, forming the final photovoltaic power prediction algorithm. The experimental results show that the proposed model herein has higher prediction accuracy and fewer prediction errors than the single BP neural network model and the Autoregressive Integrated Moving Average (ARIMA) model.

22 October 2021
Verified
Conference Paper
Open access
TWTong Wang
Tong Wang
WTWenan Tan
Wenan Tan
JXJianxin Xue
Jianxin Xue
SNSen Niu
Sen Niu
YDYi Du
Yi Du
XCXiaoxia Cao
Xiaoxia Cao
The composition of proteins nearly correlated with its function. Therefore, it is very important to discuss a method that can automatically forecast protein quaternary structure. The fusion encoding method of PseAA and DC was adopted to describe the protein features. Using this encoding method to express protein sequences will produce higher dimensional feature vectors. This paper uses the algorithm of predigesting the characteristic dimension. By extracting significant feature vectors from the primitive feature vectors, eigenvectors with high dimensions are changed to eigenvectors with low dimensions. The experimental method of jackknife test is adopted. The consequences indicate that the arithmetic put forwarded here is appropriate for protein quaternary structure forecast.

21 October 2022
Verified
Conference Paper
Open access
TWTong Wang
Tong Wang
WTWenan Tan
Wenan Tan
JXJianxin Xue
Jianxin Xue
SNSen Niu
Sen Niu
YDYi Du
Yi Du
XCXiaoxia Cao
Xiaoxia Cao
DR (Dimensional Decrease) arithmetic is a tool. Initially, DR arithmetic was used to solve problems in computer vision. Here, DR arithmetic is used to decrease the number of features. Contrast among various DR arithmetics is executed to face discrimination. Contrast among various DR arithmetics is executed to face discrimination. Tall order of dimension face pictures is low order of dimension manifolds in nature. The manifold learning arithmetic can decrease the order of dimension by digging the essential structure of the data, draw the inherent features of tall order of dimension face image data, and find the low order of dimension embedded manifold equivalent to the tall order of dimension original data. Contrast among LLE, Isomap arithmetic and modified Isomap arithmetic are performed to face discrimination. The outcomes of the test are gratifying, which it makes clear that DR arithmetic can settle face discrimination problems well.