Yu Bai

Dr. Yu Bai

Computer Engineering Program, California State University Fullerton, CA, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
9 March 2018 in IEEE Access
Verified
Journal Article
Open access
YGYanhui Guo
Yanhui Guo
SHSiming Han
Siming Han
CSChuanhe Shen
Chuanhe Shen
YLYing Li
Ying Li
XYXijie Yin
Xijie Yin
YBYu Bai
Yu Bai
In order to mitigate investmentsk, stock price forecasting has attracted more attention in recent years. Aiming at the discreteness, non-normality, high-noise in high-frequency data, a support vector machine regression(SVR) algorithm is introduced in this paper. However, the characteristics in different periods of the same stock, or the same periods of different stocks are significantly different. So, SVR with fixed parameters is difficult to satisfy with the constantly changing data flow. To tackle this problem, an adaptive SVR was proposed for stock data at three different time scales, including daily data, 30-minute data, and 5-minute data. Experiments show that the improved SVR with dynamic optimization of learning parameters by Particle Swarm Optimization(PSO) can get a better result than compared methods including SVR and Back-propagation neural network(BPNN).

8 March 2019 in EURASIP Journal on Wireless Communications and Networking
Verified
Journal Article
Open access
PDF file
YGYanhui Guo
Yanhui Guo
XYXijie Yin
Xijie Yin
XZXuechen Zhao
Xuechen Zhao
DYDongxin Yang
Dongxin Yang
YBYu Bai
Yu Bai
Hyperspectral image (HSI) classification has been long envisioned in the remote sensing community. Many methods have been proposed for HSI classification. Among them, the method of fusing spatial features has been widely used and achieved good performance. Aiming at the problem of spatial feature extraction in spectral-spatial HSI classification, we proposed a guided filter-based method. We attempted two fusion methods for spectral and spatial features. In order to optimize the classification results, we also adopted a guided filter to obtain better results. We apply the support vector machine (SVM) to classify the HSI. Experiments show that our proposed methods can obtain very competitive results than compared methods on all the three popular datasets. More importantly, our methods are fast and easy to implement.

28 March 2018 in IEEE Access
Verified
Journal Article
Open access
YGYanhui Guo
Yanhui Guo
HCHan Cao
Han Cao
SHSiming Han
Siming Han
YSYunchuan Sun
Yunchuan Sun
YBYu Bai
Yu Bai
Explosive growth of applications in hyperspectral image (HSI) has made HSI classification a hot topic in the remote sensing community. The key to improve classification accuracy is how to make full use of the spectral and spatial information. We combine k-nearest neighbor (KNN) algorithm with guided filter which can extract spatial context information and denoise the classification results by edge-preserving filtering. To solve the problem of dimension disaster, we also take dimensionality reduction into account for HSI classification. To verify the feasibility of our proposed methods, we evaluate the performance over four widely used hyperspectral data sets. The experimental results show that with only 5% of samples, our method obtained better performance than improved support vector machine and KNN methods.

4 January 2019 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Closed access
YGYanhui Guo
Yanhui Guo
HCHan Cao
Han Cao
JBJianjun Bai
Jianjun Bai
YBYu Bai
Yu Bai

8 May 2019 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
ASAshkan Samiee
Ashkan Samiee
PBPayal Borulkar
Payal Borulkar
RDRonald F. DeMara
Ronald F. DeMara
PZPeiyi Zhao
Peiyi Zhao
YBYu Bai
Yu Bai
Deep Learning (DL) offers the advantages of high accuracy performance at tasks such as image recognition, learning of complex intelligent behaviors, and large-scale information retrieval problems such as intelligent web search. To attain the benefits of DL, the high computational and energy-consumption demands imposed by the underlying processing, interconnect, and memory devices on which software-based DL executes can benefit substantially from innovative hardware implementations. Logic-in-Memory (LIM) architectures offer potential approaches to attaining such throughput goals within area and energy constraints starting with the lowest layers of the hardware stack. In this paper, we develop a Spintronic Logic-in-Memory (S-LIM) XNOR neural network (S-LIM XNN) which can perform binary convolution with reconfigurable in-memory logic without supplementing distinct logic circuits for computation within the memory module itself. Results indicate that the proposed S-LIM XNN designs achieve 1.2-fold energy reduction, 1.26-fold throughput increase, and 1.4-fold accuracy improvement compared to the state-of-the-art binarized convolutional neural network hardware. Design considerations, architectural approaches, and the impact of process variation on the proposed hybrid spin-CMOS design are identified and assessed, including comparisons and recommendations for future directions with respect to LIM approaches for neuromorphic computing.

22 July 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
RTRui Tian
Rui Tian
DLDanqing Liu
Danqing Liu
YBYu Bai
Yu Bai
YJYu Jin
Yu Jin
GWGuanliang Wan
Guanliang Wan
YGYanhui Guo
Yanhui Guo
Deep Learning has found widespread application in Hyperspectral Image (HSI) classification, where Transformer architectures based on self-attention have emerged as state-of-the-art (SOTA). The Swin-MAE framework utilizes a masked autoencoder approach with Shifted Windows Transformer as its backbone, demonstrating strong representational power and performance. This study proposes a Shifted Windows Masking Spectral Pretraining (Swin-MSP) model, which achieves hierarchical modeling of hyperspectral data from local to global scales by introducing spectral masking pretraining techniques and a hierarchical architecture. To fit with this pretraining, we introduce the Uniaxial Continuous Cross-Correlation Layer (UC3L), a straightforward yet effective solution tailored for hyperspectral imagery masking. And we design the Shift Frequency Band Transformer (SFBT) to hierarchically characterize spectral features. Experiments with publicly available datasets establish that our pretrained network significantly improves classification efficiency compared with SOTA networks. Furthermore, we systematically investigate the sensitivity of various datasets to pretraining hyper-parameters. The results underscore that the universal spectral representation acquired during the pretraining phase serves as a robust initialization for subsequent task-specific fine-tuning. It is noted that this work breaks from traditional ViT approaches, offering a new perspective on hyperspectral dataset pretraining. Code is available at https://github.com/teaRRe/Swin-MSP.