document

HAS-RL: A Hierarchical Approximate Scheme Optimized With Reinforcement Learning for NoC-Based NN Accelerators

Li, Siyue (author), Zhou, Shize (author), Xue, Yongqi (author), Fan, Wenjie (author), Cheng, Tong (author), Ji, Jinlun (author), Dai, Chenyang (author), Song, Wenqing (author), Gao, C. (author)

Network-on-Chip (NoC) is a scalable on-chip communication architecture for the NN accelerator, but with the increase in the number of nodes, the communication delay becomes higher. Applications such as machine learning have a certain resilience to noisy/erroneous transmitted data. Therefore, approximate communication becomes a promising solution...

journal article 2024

document

A Data-Driven Model for Power Loss Estimation of Magnetic Materials Based on Multi-Objective Optimization and Transfer Learning

Li, Z. (author), Wang, L. (author), Liu, R. (author), Mirzadarani, R. (author), Luo, T. (author), Lyu, D. (author), Ghaffarian Niasar, M. (author), Qin, Z. (author)

Traditional methods such as Steinmetz's equation (SE) and its improved variant (iGSE) have demonstrated limited precision in estimating power loss for magnetic materials. The introduction of Neural Network technology for assessing magnetic component power loss has significantly enhanced accuracy. Yet, an efficient method to incorporate detailed...

journal article 2024

document

Fusion of Gaze and Scene Information for Driving Behaviour Recognition: A Graph-Neural-Network- Based Framework

Yi, Yangtian (author), Lu, Chao (author), Wang, Boyang (author), Cheng, Long (author), Li, Z. (author), Gong, Jianwei (author)

Accurate recognition of driver behaviours is the basis for a reliable driver assistance system. This paper proposes a novel fusion framework for driver behaviour recognition that utilises the traffic scene and driver gaze information. The proposed framework is based on the graph neural network (GNN) and contains three modules, namely, the...

journal article 2023

document

Robust Lane Detection Through Self Pre-Training With Masked Sequential Autoencoders and Fine-Tuning With Customized PolyLoss

Li, Ruohan (author), Dong, Y. (author)

Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the valuable features and aggregate contextual information, especially the interrelationships between lane...

journal article 2023

document

DeepPick: A Deep Learning Approach to Unveil Outstanding Users Ranking with Public Attainable Features

Li, Wanda (author), Xu, Zhiwei (author), Sun, Yi (author), Gong, Qingyuan (author), Chen, Y. (author), Ding, Aaron Yi (author), Wang, Xin (author), Hui, Pan (author)

Outstanding users (OUs) denote the influential, 'core' or 'bridge' users in online social networks. How to accurately detect and rank them is an important problem for third-party online service providers and researchers. Conventional efforts, ranging from early graph-based algorithms to recent machine learning-based approaches, typically rely on...

journal article 2023

document

A Multi-Task Learning Based Runoff Forecasting Model for Multi-Scale Chaotic Hydrological Time Series

Zuo, Hui (author), Yan, Gaowei (author), Lu, Ruochen (author), Li, Rong (author), Xiao, Shuyi (author), Pang, Y. (author)

Accurately predicting runoff is crucial for managing water resources, preventing and mitigating floods, scheduling hydropower plant operations, and protecting the environment. The hydrological dynamic composite system that forms runoff is complex and random, and seemingly random behavior may be caused by nonlinear variables in a simple...

journal article 2023

document

Use Reinforcement Learning to Generate Testing Commands for Onboard Software of Small Satellites

Li, Zhuoheng (author)

Programmers usually write test cases to test onboard software. However, this procedure is time-consuming and needs sufficient prior knowledge. As a result, small satellite developers may not be able to test the software thoroughly. <br/> <br/>A promising direction to solve this problem is reinforcement learning (RL) based testing. It searches...

master thesis 2022

document

Prediction of mechanical solutions for a laminated LCEs system fusing an analytical model and neural networks

Wang, Jue (author), Yuan, Weiyi (author), Li, Z. (author), Zhu, Yingcan (author), Santos, Thebano (author), Fan, J. (author)

This paper presents a convenient and efficient method to predict the mechanical solutions of a laminated Liquid Crystal Elastomers (LCEs) system subjected to combined thermo-mechanical load, based on a back propagation (BP) neural network which is trained by machine learning from a database established by analytical solutions. Firstly, the...

journal article 2022

document

Short-Term Nationwide Airport Throughput Prediction With Graph Attention Recurrent Neural Network

Zhu, Xinting (author), Lin, Yu (author), He, Yuxin (author), Tsui, Kwok Leung (author), Chan, Pak Wai (author), Li, L. (author)

With the dynamic air traffic demand and the constrained capacity resources, accurately predicting airport throughput is essential to ensure the efficiency and resilience of air traffic operations. Many research efforts have been made to predict traffic throughputs or flight delays at an airport or over a network. However, it is still a...

journal article 2022

document

A multiple spiking neural network architecture based on fuzzy intervals for anomaly detection: a case study of rail defects

Phusakulkajorn, W. (author), Hendriks, J.M. (author), Moraal, J. (author), Dollevoet, R.P.B.J. (author), Li, Z. (author), Nunez, Alfredo (author)

In this paper, a fuzzy interval-based method is proposed for solving the problem of rail defect detection relying on an on-board measurement system and a multiple spiking neural network architecture. Instead of outputting binary values (defect or not defect), all data will belong to both classes with different spreads that are given by two fuzzy...

conference paper 2022

document

Prior-Guided Deep Interference Mitigation for FMCW Radars

Wang, J. (author), Li, Runlong (author), He, Yuan (author), Yang, Yang (author)

In this article, the interference mitigation (IM) problem is tackled as a regression problem. A prior-guided deep learning (DL)-based IM approach is proposed for frequency-modulated continuous-wave (FMCW) radars. Considering the complex-valued nature of radar signals, a complex-valued convolutional neural network, which is different from the...

journal article 2022

document

A neural network-assisted 3D theoretical thermoelastic solution for laminated liquid crystal elastomer plate used in restoring cardiac mechanical function

Wang, Jue (author), Yuan, Weiyi (author), Li, Z. (author), Trofimov, Yuri (author), Lishik, Sergey (author), Fan, J. (author)

Some atrial contractile assist devices applied on the heart surface can be regarded as a laminated Liquid crystal elastomer (LCE) plate under steady temperature loads and a contact mechanical force. An exact solution for the deformation of the laminated LCE plate under combined thermal and mechanical loads is derived by solving the three...

journal article 2022

document

Adaptive neural sliding mode control for heterogeneous ship formation keeping considering uncertain dynamics and disturbances

You, Xu (author), Yan, Xinping (author), Liu, Jialun (author), Li, Shijie (author), Negenborn, R.R. (author)

This paper investigates the formation keeping problem of heterogeneous ships with underactuated inputs, uncertain dynamics, and environmental disturbances. The control objective is to make the heterogeneous followers keep the desired formation while tracking a leader. To solve the problem effectively, a novel virtual leader–follower formation...

journal article 2022

document

Label-Only Membership Inference Attack against \\Node-Level Graph Neural Networks

Conti, M. (author), Li, Jiaxin (author), Picek, S. (author), Xu, J. (author)

Graph Neural Networks (GNNs), inspired by Convolutional Neural Networks (CNNs), aggregate the message of nodes' neighbors and structure information to acquire expressive representations of nodes for node classification, graph classification, and link prediction. Previous studies have indicated that node-level GNNs are vulnerable to Membership...

conference paper 2022

document

Short-Term Traffic Flow Prediction Based on the Efficient Hinging Hyperplanes Neural Network

Tao, Qinghua (author), Li, Zhen (author), Xu, Jun (author), Lin, Shu (author), De Schutter, B.H.K. (author), Suykens, Johan A.K. (author)

Traffic flow (TF) prediction is an important and yet a challenging task in transportation systems, since the TF involves high nonlinearities and is affected by many elements. Recently, neural networks have attracted much attention for TF prediction, but they are commonly black boxes with complex architectures and difficult to be interpreted,...

journal article 2022

document

Model-to-Image Registration via Deep Learning towards Image-Guided Endovascular Interventions

Li, Z. (author), Mancini, Maria Elisabetta (author), Monizzi, Giovanni (author), Andreini, Daniele (author), Ferrigno, Giancarlo (author), Dankelman, J. (author), De Momi, Elena (author)

Cardiologists highlight the need for an intra-operative 3D visualization to assist interventions. The intra-operative 2D X-ray/Digital Subtraction Angiography (DSA) images in the standard clinical workflow limit cardiologists’ views significantly. Compared with image-to-image registration, model-to-image registration is an essential approach...

conference paper 2021

document

An efficient deep learning approach for ground point filtering in aerial laser scanning point clouds

Nurunnabi, A. (author), Teferle, F. N. (author), Li, J. (author), Lindenbergh, R.C. (author), Hunegnaw, A. (author)

Ground surface extraction is one of the classic tasks in airborne laser scanning (ALS) point cloud processing that is used for three-dimensional (3D) city modelling, infrastructure health monitoring, and disaster management. Many methods have been developed over the last three decades. Recently, Deep Learning (DL) has become the most dominant...

journal article 2021

document

基于Lambert-Beer理论与人工神经网络的混合荧光粉发射光谱预测

Cao, Yixing (author), Chen, Shanghuan (author), Li, Yutong (author), Du, Yunjia (author), Chen, Wei (author), Fan, J. (author), Zhang, Kouchi (author)

The emission spectra of high color rendering phosphors, mixed with the yttrium aluminium garnet, silicon based oxynitride and nitride based phosphors, were predicted by the Lambert-Beer theory and back propagation neural network (BP NN). Firstly, the modified Lambert-Beer model was used to calculate the proportional coefficient of the...

journal article 2021

document

Evaluation of short-term streamflow prediction methods in Urban river basins

Huang, Xinxing (author), Li, Yifan (author), Tian, Zhan (author), Ye, Qinghua (author), Ke, Q. (author), Fan, Dongli (author), Mao, Ganquan (author), Chen, Aifang (author), Liu, Junguo (author)

Efficient and accurate streamflow predictions are important for urban water management. Data-driven models, especially neural network (NN) models can predict streamflow fast, while the results are uncertain in some complex river systems. Physically based models can reveal the underlying physics, but it is relatively slow and computationally...

journal article 2021

document

SCIPoC: Semantic Classification of Indoor Point Cloud: A study into the possibilities of classifying indoor point cloud using a Deep Learning approach

Smit, Mels (author), Chen, Zhaiyu (author), Erbaşu, Mihai-Alexandru (author), Yustisi Ardhitasari Lumban Gaol, Yustisi (author), Li, Xiaoai (author)

With the constantly evolving range of applications for technology the quality and amount of data constantly increases as well. In this growing data environment, there is a constant search to provide more value to all data that is available for as little effort as possible. Our research tries to add such additional value by diving into the...

student report 2020