Search Results - "Liang, Daojun"

Understanding Mixup Training Methods by Liang, Daojun, Yang, Feng, Zhang, Tian, Yang, Peter

“…Mixup is a neural network training method that generates new samples by linear interpolation of multiple samples and their labels. The mixup training method…”
Get full text

Multi‐sample inference network by Daojun Liang, Feng Yang, Xiuping Wang, Xiaohui Ju

“…This study explores whether neural networks can classify multiple samples simultaneously in a forward process. Therefore, a multi‐input multi‐prediction…”
Get full text

LightNets: The Concept of Weakening Layers by Ju, Xiaohui, Yang, Feng, Liang, Daojun

“…Deep neural networks generally use the information fusion at the front and back layers because the traditional convolutional networks that stack convolutional…”
Get full text

WPNets and PWNets: From the Perspective of Channel Fusion by Liang, Daojun, Yang, Feng, Zhang, Tian, Tian, Jie, Yang, Peter

“…The performance and parameters of neural networks have a positive correlation, and there are a lot of parameter redundancies in the existing neural network…”
Get full text

Progressive Supervision via Label Decomposition: An long-term and large-scale wireless traffic forecasting method by Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng, Zhang, Minggao

“…Long-term and Large-scale Wireless Traffic Forecasting (LL-WTF) is pivotal for strategic network management and comprehensive planning on a macro scale…”
Get full text

Periodformer: An efficient long-term time series forecasting method based on periodic attention by Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng, Zhang, Minggao

“…As Transformer-based models have achieved impressive performance across various time series tasks, Long-Term Series Forecasting (LTSF) has garnered extensive…”
Get full text

User Preference Learning-based Proactive Edge Caching for D2D-Assisted Wireless Networks by Li, Dongyang, Zhang, Haixia, Ding, Hui, Li, Tiantian, Liang, Daojun, Yuan, Dongfeng

“…This work investigates proactive edge caching for device-to-device (D2D) assisted wireless networks, where user equipment (UE) can be selected as caching nodes…”
Get full text

STeP-UNet: Prediction of Moving and Communication Behaviors of Vehicles by Liang, Daojun, Zhang, Haixia, Zhou, Xiaotian, Li, Dongyang, Yuan, Dongfeng, Zhang, Minggao

“…Wireless traffic prediction has drawn increasing research interests as it can provide guidance to the network optimization. With the predicted information, one…”
Get full text

DistPred: A Distribution-Free Probabilistic Inference Method for Regression and Forecasting by Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng

“…Traditional regression and prediction tasks often only provide deterministic point estimates. To estimate the uncertainty or distribution information of the…”
Get full text

Time-Sensitive Semantic Communication Using Dynamic Spiking Neural Networks by Liang, Daojun, Zhang, Bingzheng, Yuan, Dongfeng

“…Semantic communication aims to extract and trans-mit the semantic information of objects to greatly reduce the transmission of redundant information. This…”
Get full text

Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals by Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng, Zhang, Bingzheng, Zhang, Minggao

“…In this paper, we find that ubiquitous time series (TS) forecasting models are prone to severe overfitting. To cope with this problem, we embrace a…”
Get full text

Does Long-Term Series Forecasting Need Complex Attention and Extra Long Inputs? by Liang, Daojun, Zhang, Haixia, Yuan, Dongfeng, Ma, Xiaoyan, Li, Dongyang, Zhang, Minggao

“…As Transformer-based models have achieved impressive performance on various time series tasks, Long-Term Series Forecasting (LTSF) tasks have also received…”
Get full text

Personnel Scheduling of Machine Tool Assembly Workshop Based on Hybrid Discrete Particle Swarm Optimization Algorithm by Zheng, Anzhu, Yuan, Dongfeng, Liang, Daojun, Zhou, Xiaotian

“…Personnel scheduling in assembly workshop is a kind of problem widely existing in machine tool manufacturing industry. In this paper, according to the actual…”
Get full text

Comprehensive Practice Course Construction of Internet of Things Technology by Yang, Feng, Liang, Daojun, Zhai, Linbo

“…The Internet of Things (IoT) specialty belongs to the discipline of engineering application, requiring students to have strong practical and innovative…”
Get full text

Tool Fault Diagnosis Method Based on Multiscale-Channel Attention Network by Di, Zijun, Yuan, Dongfeng, Li, Dongyang, Liang, Daojun, Zhou, Xiaotian, Xin, Miaomiao, Cao, Feng, Lei, Tengfei

“…In the modern machine tool manufacturing scene, as the milling tool of CNC machine tool, the health of the tool directly affects the processing efficiency and…”
Get full text

Tool Fault Diagnosis Based on Improved Multiscale Network and Feature Fusion by Li, Dongyang, Yuan, Dongfeng, Liang, Daojun, Di, Zijun, Zhang, Mingqiang, Cao, Feng, Xin, Miaomiao, Lei, Tengfei, Jiang, Mingyan

“…Prognostic and health management is a key issue in the field of machine tool manufacturing. As the "teeth" of CNC machine tools, their health status directly…”
Get full text

LightNets: The Concept of Weakening Layers by Ju, Xiaohui, Yang, Feng, Liang, Daojun

“…Deep neural networks generally use the information fusion at the front and back layers because the traditional convolutional networks that stack convolutional…”
Get full text