Ning Hou

Ning Hou

Auto-generated profile, based on publicly available information

Ning Hou

School of Electrical and Control Engineering, Henan University of Urban Construction, Pingdingshan, Henan, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
15 April 2024 in IEEE Access
Verified
Journal Article
Open access
CLChengwu Liang
Chengwu Liang
JYjie yang
jie yang
DRDu ruolin
Du ruolin
WHWei Hu
Wei Hu
NHNing Hou
Ning Hou
Human Action Recognition (HAR) based on skeleton sequences has attracted much attention due to the robustness and background insensitivity of skeletal data. The convolutional neural network (CNN) for spatio-temporal representation learning has been widely utilized for skeleton-based HAR. However, the long-term spatio-temporal modeling and action category-specific feature attention have not been fully exploited. In order to explore the current potential of CNNs for skeleton-based HAR, a novel CNN architecture with temporal-channel attention and convolution fusion is proposed. Specially, the network architecture is composed of two novel modules, the Temporal-Channels Attention Module (TCA) and Multiscale Temporal Convolution Fusion module (MTCF). TCA module is designed to generate a temporal-channel attention matrix for different visual channels and temporal features, motivating the CNN to focus on the critical category-associated feature representation learning. Along the channels, MTCF module adapts the grouped residual connections to flexibly extend the convolutional temporal receptive field, without introducing additional parameters. By reverse stacking, MTCF module creates a bidirectional information interaction among inter-channels, compensating for the receptive field and information imbalance between subgroups from different branches. The proposed method was evaluated on three benchmark datasets, including NTU RGB-D, NTU RGB-D120 and FineGYM. The results show that the proposed TCA-MTCF method improves the CNNs’ ability to model long-term temporal features of skeleton sequences, achieving the state-of-the-art performance for HAR.

1 January 2024 in International Journal of RF and Microwave Computer-Aided Engineering
Verified
Journal Article
Open access
YGYang Gao
Yang Gao
DWDanyang Wang
Danyang Wang
HYHuilong Yu
Huilong Yu
THTao Hua
Tao Hua
NHNing Hou
Ning Hou
YLYapeng Lu
Yapeng Lu
Machine learning‐assisted electromagnetic simulation has become an effective acceleration tool for designing microwave components by introducing high‐precision models and optimization algorithms, featuring fast design and high efficiency. However, enormous amount of data generated from the blind preliminary and computationally expensive simulation is required to predict the accuracy response. An efficient geometric parameter optimization method for microstrip bandpass filter (BPF) based on a one‐dimensional convolutional neural network is proposed. Nonlinear convergence factor, adaptive weight, and Gaussian difference mutation strategies are integrated using the whale optimization algorithm to avoid the local optimum and improve optimization accuracy. Computational efficiency is improved significantly with small‐scale training data. The validity and efficiency of the proposed method are confirmed by fifth‐order microstrip BPFs, and the performance of the predicted structure parameters is significantly improved, which shows great promise for application in optimization and performance improvement in microwave electromagnetic simulation.