Weighted Error Entropy-Based Information Theoretic Learning for Robust Subspace Representation

Li, Yuanman; Zhou, Jiantao; Jing-zhen, Tian; Zheng, Xianwei; Tang, Yuan Yan

doi:10.1109/tnnls.2021.3056188

Cited by 16 publications

(10 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…μ WiFi for WiFi AP 11,13,14,16,12, and 15 are set to 2.39 and 1.43 (ms), respectively. These average packet arrival intervals correspond to LTE subframe numbers 3 and 5, respectively.…”

Section: Existing Problems and The Enhanced Proposed Schemementioning

confidence: 99%

“…To solve this problem, we further propose an enhanced joint channel/subframe number selection scheme to deal with this undesired frequent channel switches. In the enhanced proposed scheme, after the action selection probability is derived based on Equation (5), if the channel switch happens, the Q value is further updated by Equation (12).…”

Section: Existing Problems and The Enhanced Proposed Schemementioning

confidence: 99%

“…The goal is to achieve fair medium access by giving more transmission opportunities to WiFi systems. Based on [11] and recent advances in learning techniques [12][13][14], a Q-learning-based muting period selection scheme was proposed for fair LTE-WiFi coexistence in [15]. However, it focuses on maximizing the LTE throughput and can only work in single channel scenario.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reinforcement Learning for Joint Channel/Subframe Selection of LTE in the Unlicensed Spectrum

Kishimoto

Wang

Umehira

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In recent years, to cope with the rapid growth in mobile data traffic, increasing the capacity of cellular networks is receiving more and more attention. To this end, offloading the current LTE-advanced or 5G system’s data traffic from licensed spectrum to the unlicensed spectrum that is used by WiFi systems, i.e., LTE-Licensed-Assisted-Access (LTE-LAA), has been extensively investigated. In the current LTE-LAA system, a Listen-Before-Talk (LBT) approach is implemented, which requires the LTE user also perform carrier sense before the transmission. However, fair LTE-WiFi coexistence is still hard to guarantee due to their unbalanced frame sizes and traffic loads. In the LTE-LAA system, the optimal channel selection and subframe number adjustment are the keys to realize efficient spectrum utilization and fair system coexistence. To this end, in this paper, we propose a reinforcement learning-based joint channel/subframe selection scheme for LTE-LAA. The proposed approach is implemented at the LTE access points with zero knowledge of the WiFi systems. The results of extensive simulations verify that the proposed approach can significantly improve the fairness and packet loss rate compared with baseline schemes.

show abstract

“…μ WiFi for WiFi AP 11,13,14,16,12, and 15 are set to 2.39 and 1.43 (ms), respectively. These average packet arrival intervals correspond to LTE subframe numbers 3 and 5, respectively.…”

Section: Existing Problems and The Enhanced Proposed Schemementioning

confidence: 99%

Section: Existing Problems and The Enhanced Proposed Schemementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning for Joint Channel/Subframe Selection of LTE in the Unlicensed Spectrum

Kishimoto

Wang

Umehira

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…ey have developed advanced smart service systems and platforms and built an ecological smart logistics supply chain. Some intelligent algorithms such as machine learning methods have been developed [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Impact of Logistics Development on Economic Growth: An Empirical Research from Guangdong Province in China

Chen

2021

Complexity

View full text Add to dashboard Cite

This paper evaluates the impact of the development of the logistics industry on economic growth based on panel data of 21 cities in Guangdong Province in China from 2007 to 2019. Using the overall entropy method, the comprehensive development index of the logistics industry is constructed to capture the performance of the logistics industry. On this basis, by using Moran’s index, we measure the spatial agglomeration effect of the logistics industry. Furthermore, direct and spatial spillover effects are also obtained. The estimation results of the spatial Durbin model (SDM) reveal that the elasticity coefficient of the effect of the comprehensive development level of the logistics industry on economic growth is 0.2590, which is significant at the 1% level. In addition, the coefficient of the direct effect of the logistics industry on local economic growth is 0.4074, and the coefficient of the spatial spillover effect on the economic growth of the surrounding areas is 0.3596, which are both significant at the 1% level. These results indicate that the development of the logistics industry can not only improve local economic growth but also promote the economic growth of the surrounding regions.

show abstract

“…However, DTL usually fails to reduce the requirement of parameters, which results in too large models to deploy on low-computing-power hardware systems. For (2), the network structure is optimized [24,25], and particular structures of small efficient CNNs are usually designed with less computation and small volume that is easy to popularize in application. Rahman [26] proposes a twostage small CNN architecture, which reduced the model size by 99% compared to VGG-16 while remaining an accuracy of 93.3%.…”

mentioning

confidence: 99%

A Sparse Deep Transfer Learning Model and Its Application for Smart Agriculture

Chen

Zhang

Chen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The introduction of deep transfer learning (DTL) further reduces the requirement of data and expert knowledge in various uses of applications, helping DNN-based models effectively reuse information. However, it often transfers all parameters from the source network that might be useful to the task. The redundant trainable parameters restrict DTL in low-computing-power devices and edge computing, while small effective networks with fewer parameters have difficulty transferring knowledge due to structural differences in design. For the challenge of how to transfer a simplified model from a complex network, in this paper, an algorithm is proposed to realize a sparse DTL, which only transfers and retains the most necessary structure to reduce the parameters of the final model. Sparse transfer hypothesis is introduced, in which a compressing strategy is designed to construct deep sparse networks that distill useful information in the auxiliary domain, improving the transfer efficiency. The proposed method is evaluated on representative datasets and applied for smart agriculture to train deep identification models that can effectively detect new pests using few data samples.

show abstract

Weighted Error Entropy-Based Information Theoretic Learning for Robust Subspace Representation

Cited by 16 publications

References 52 publications

Reinforcement Learning for Joint Channel/Subframe Selection of LTE in the Unlicensed Spectrum

Reinforcement Learning for Joint Channel/Subframe Selection of LTE in the Unlicensed Spectrum

Impact of Logistics Development on Economic Growth: An Empirical Research from Guangdong Province in China

A Sparse Deep Transfer Learning Model and Its Application for Smart Agriculture

Contact Info

Product

Resources

About