Xinyu Niu
YOU?
Author Swipe
View article: Single-cell analysis reveals cellular heterogeneity and molecular features during postnatal pig testis development
Single-cell analysis reveals cellular heterogeneity and molecular features during postnatal pig testis development Open
Our findings provide novel insights into the cellular dynamics of spermatogenesis and offer a valuable foundation for future research on the molecular mechanisms underlying testicular development in pigs and other mammals.
View article: Photonic transformer chip: interference is all you need
Photonic transformer chip: interference is all you need Open
As the core component of the transformer model, the attention has been proved as all you need in artificial intelligence field in recent years. However, conventional electronic processors are unable to cope with the exponentially increasin…
View article: Integrated photonic neuromorphic computing: device, architecture, chip, algorithm
Integrated photonic neuromorphic computing: device, architecture, chip, algorithm Open
Artificial intelligence (AI) has experienced explosive growth in recent years. The large models have been widely applied in various fields, including natural language processing, image generation, and complex decision-making systems, revol…
View article: A Transformer-Based Approach for Efficient Geometric Feature Extraction from Vector Shape Data
A Transformer-Based Approach for Efficient Geometric Feature Extraction from Vector Shape Data Open
The extraction of shape features from vector elements is essential in cartography and geographic information science, supporting a range of intelligent processing tasks. Traditional methods rely on different machine learning algorithms tai…
View article: Genetic algorithm-based optimal repertoire selection for music therapy on therapeutic effects
Genetic algorithm-based optimal repertoire selection for music therapy on therapeutic effects Open
In recent years, music therapy has gradually become an adjunct to conventional medicine and drug therapy. In this paper, genetic algorithms are used in conventional music therapy, and they are also used to optimize the combination of reper…
View article: E-plane waveguide bandpass filters based on high-order modes of spoof surface plasmon polaritons
E-plane waveguide bandpass filters based on high-order modes of spoof surface plasmon polaritons Open
In this paper, a new design method of E-plane waveguide bandpass filter (BPF) using high-order modes of spoof surface plasmon polaritons (SSPPs) is proposed. The high-order modes of the double-layer SSPP (DL-SSPP) unit cell can be effectiv…
View article: Multiscale 3D genome organization underlies duck fatty liver with no adipose inflammation or serious injury
Multiscale 3D genome organization underlies duck fatty liver with no adipose inflammation or serious injury Open
Non-alcoholic fatty liver disease (NAFLD) is the most common form of chronic liver disease. Little is known about how gene expression and chromatin structure are regulated in NAFLD due to lack of suitable model. Ducks naturally develop fat…
View article: A new chromosome-scale duck genome shows a major histocompatibility complex with several expanded multigene families
A new chromosome-scale duck genome shows a major histocompatibility complex with several expanded multigene families Open
View article: Simplification and Regularization Algorithm for Right-Angled Polygon Building Outlines with Jagged Edges
Simplification and Regularization Algorithm for Right-Angled Polygon Building Outlines with Jagged Edges Open
Building outlines are important for emergency response, urban planning, and change analysis and can be quickly extracted from remote sensing images and raster maps using deep learning technology. However, such building outlines often have …
View article: Regularization Algorithm for Right-Angled Polygon Building Outlines with Jagged Edges
Regularization Algorithm for Right-Angled Polygon Building Outlines with Jagged Edges Open
Building outlines extracted from remote sensing images and raster maps often have irregular boundaries, redundant points, inaccurate positions, and unclear turns due to factors such as image quality, complexity of the surrounding environme…
View article: Simple and Effective Complementary Label Learning Based on Mean Square Error Loss
Simple and Effective Complementary Label Learning Based on Mean Square Error Loss Open
In this paper, we propose a simple and effective complementary label learning approach to address the label noise problem for deep learning model. Different surrogate losses have been proposed for complementary label learning, however, are…
View article: iPSC-sEVs Alleviate Microglia Senescence to Protect Against Ischemic Stroke in Aged Mice
iPSC-sEVs Alleviate Microglia Senescence to Protect Against Ischemic Stroke in Aged Mice Open
View article: Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator
Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator Open
Recent advances in algorithm-hardware co-design for deep neural networks (DNNs) have demonstrated their potential in automatically designing neural architectures and hardware designs. Nevertheless, it is still a challenging optimization pr…
View article: A Research on Modulation in Digital Communication System
A Research on Modulation in Digital Communication System Open
With the development of network and communication technology in modern society, WiFi technology has become an indispensable part of people’s lives. WiFi shows its future application prospects with its wireless portability and multi-user ac…
View article: The Fusion Strategy of 2D and 3D Information Based on Deep Learning: A Review
The Fusion Strategy of 2D and 3D Information Based on Deep Learning: A Review Open
Recently, researchers have realized a number of achievements involving deep-learning-based neural networks for the tasks of segmentation and detection based on 2D images, 3D point clouds, etc. Using 2D and 3D information fusion for the adv…
View article: High-Performance FPGA-based Accelerator for Bayesian Neural Networks
High-Performance FPGA-based Accelerator for Bayesian Neural Networks Open
Neural networks (NNs) have demonstrated their potential in a wide range of applications such as image recognition, decision making or recommendation systems. However, standard NNs are unable to capture their model uncertainty which is cruc…
View article: Improving Performance Estimation for Design Space Exploration for Convolutional Neural Network Accelerators
Improving Performance Estimation for Design Space Exploration for Convolutional Neural Network Accelerators Open
Contemporary advances in neural networks (NNs) have demonstrated their potential in different applications such as in image classification, object detection or natural language processing. In particular, reconfigurable accelerators have be…
View article: Mapping Large LSTMs to FPGAs with Weight Reuse
Mapping Large LSTMs to FPGAs with Weight Reuse Open
Long-Short Term Memory (LSTM) can retain memory and learn from data sequences. It gives state-of-the-art accuracy in many applications such as speech recognition, natural language processing and video classifications. Field-Programmable Ga…
View article: Effects of exogenous melatonin and abscisic acid on osmotic adjustment substances of ‘Summer Black’ grape under drought stress
Effects of exogenous melatonin and abscisic acid on osmotic adjustment substances of ‘Summer Black’ grape under drought stress Open
In this study, seedlings of grape 'Summer Black' were used as the experimental materials to investigate the effects of melatonin (MT) and abscisic acid (ABA) on osmotic adjustment substances under drought stress, by root irrigating 100μmol…
View article: Deep Neural Network Approximation for Custom Hardware
Deep Neural Network Approximation for Custom Hardware Open
Deep neural networks have proven to be particularly effective in visual and audio recognition tasks. Existing models tend to be computationally expensive and memory intensive, however, and so methods for hardware-oriented approximation hav…
View article: Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Going
Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Going Open
Deep neural networks have proven to be particularly effective in visual and audio recognition tasks. Existing models tend to be computationally expensive and memory intensive, however, and so methods for hardware-oriented approximation hav…
View article: Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA
Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA Open
FPGA becomes a popular technology for implementing Convolutional Neural Network (CNN) in recent years. Most CNN applications on FPGA are domain-specific, e.g., detecting objects from specific categories, in which commonly-used CNN models p…
View article: Exploiting the chaotic behaviour of atmospheric models with reconfigurable architectures
Exploiting the chaotic behaviour of atmospheric models with reconfigurable architectures Open
Reconfigurable architectures are becoming mainstream: Amazon, Microsoft and IBM are supporting such architectures in their data centres. The computationally intensive nature of atmospheric modelling is an attractive target for hardware acc…
View article: EXTRA: Towards an Efficient Open Platform for Reconfigurable High Performance Computing
EXTRA: Towards an Efficient Open Platform for Reconfigurable High Performance Computing Open
To handle the stringent performance requirements of future exascale-class applications, High Performance Computing (HPC) systems need ultra-efficient heterogeneous compute nodes. To reduce power and increase performance, such compute nodes…
View article: On the use of programmable hardware and reduced numerical precision in earth‐system modeling
On the use of programmable hardware and reduced numerical precision in earth‐system modeling Open
Programmable hardware, in particular Field Programmable Gate Arrays (FPGAs), promises a significant increase in computational performance for simulations in geophysical fluid dynamics compared with CPUs of similar power consumption. FPGAs …
View article: An Experimental Study on Seismic Performance of Steel Truss Coupling Beams with Buckling-restrained Brace
An Experimental Study on Seismic Performance of Steel Truss Coupling Beams with Buckling-restrained Brace Open
Through the pseudo-static test on the steel truss coupling beams with buckling-restrained brace, the bearing capacity, deformation capacity, hysteresis curve, skeleton curve, ductility, Energy Dissipation and stiffness degradation of such …
View article: Optimising runtime reconfigurable designs for high performance applications
Optimising runtime reconfigurable designs for high performance applications Open
This thesis proposes novel optimisations for high performance runtime reconfigurable designs. For a reconfigurable design, the proposed approach investigates idle resources introduced by static design approaches, and exploits runtime recon…