Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

Download Full-text

SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

ACM Transactions on Graphics ◽

10.1145/3450284 ◽

2021 ◽

Vol 40 (3) ◽

pp. 1-13

Author(s):

Lumin Yang ◽

Jiajie Zhuang ◽

Hongbo Fu ◽

Xiangzhi Wei ◽

Kun Zhou ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Large Scale ◽

State Of The Art ◽

Semantic Segmentation ◽

Structure Information ◽

Graph Neural Networks ◽

Node Labels ◽

Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Download Full-text

Real-time data analysis for medical diagnosis using FPGA-accelerated neural networks

BMC Bioinformatics ◽

10.1186/s12859-018-2505-7 ◽

2018 ◽

Vol 19 (S18) ◽

Cited By ~ 6

Author(s):

Ahmed Sanaullah ◽

Chen Yang ◽

Yuri Alexeev ◽

Kazutomo Yoshii ◽

Martin C. Herbordt

Keyword(s):

Neural Networks ◽

Data Analysis ◽

Real Time ◽

Medical Diagnosis ◽

Time Data ◽

Real Time Data

Download Full-text

Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks

10.5753/eniac.2020.12161 ◽

2020 ◽

Author(s):

Douglas Meneghetti ◽

Reinaldo Bianchi

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Communication Channels ◽

Neural Network Architecture ◽

Graph Representations ◽

Labeled Graph ◽

Multiple Agent ◽

Multi Agent ◽

Graph Neural Networks

This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes feature vectors of different sizes for different entity classes, uses relational graph convolution layers to model different communication channels between entity types and learns distinct policies for different agent classes, sharing parameters wherever possible. Results have shown that specializing the communication channels between entity classes is a promising step to achieve higher performance in environments composed of heterogeneous entities.

Download Full-text

Status Monitoring and Fault Diagnosis Network System Based on UPnP

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.353-358.2632 ◽

2007 ◽

Vol 353-358 ◽

pp. 2632-2635

Author(s):

Pei Yu Li ◽

Da Peng Tan ◽

Tao Qing Zhou ◽

Bo Yu Lin

Keyword(s):

Fault Diagnosis ◽

Embedded System ◽

Real Time ◽

Data Storage ◽

Network Architecture ◽

Network System ◽

Time Data ◽

Status Monitoring ◽

Self Recognition ◽

Real Time Data

Aiming at some problems in the fields of industry monitoring technology (IMT) such as bad dynamic ability and poor versatility, this paper brought forward a kind of intelligent Status monitoring and Fault diagnosis Network System (SFNS) based on UPnP-Universal Plug and Play. The model for fault diagnosis network system was established according to characteristics and requirements of IMT network, and system network architecture was designed and realized by UPnP. Using embedded system technology, real-time data collection node, monitoring center node and data storage server were designed, and that supplies powerful real-time data support for SFNS. Industry fields experiments proved that this system can realize self recognition, seamless linkage and other self adapting ability, and can break through the limitation of real IP address to achieve real-time remote monitoring on line.

Download Full-text

Fast Inference of Deep Neural Networks for Real-time Particle Physics Applications

Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays ◽

10.1145/3289602.3293986 ◽

2019 ◽

Author(s):

Javier Duarte ◽

Song Han ◽

Philip Harris ◽

Sergo Jindariani ◽

Edward Kreinar ◽

...

Keyword(s):

Neural Networks ◽

Real Time ◽

Particle Physics ◽

Deep Neural Networks

Download Full-text

Comparative Performance Analysis of Neural Network Real-Time Object Detections in Different Implementations

EPJ Web of Conferences ◽

10.1051/epjconf/202022602020 ◽

2020 ◽

Vol 226 ◽

pp. 02020

Author(s):

Alexey V. Stadnik ◽

Pavel S. Sazhin ◽

Slavomir Hnatic

Keyword(s):

Neural Network ◽

Neural Networks ◽

Computer Vision ◽

Performance Analysis ◽

Object Detection ◽

Real Time ◽

Network Architecture ◽

Neural Network Architecture ◽

Comparative Performance

The performance of neural networks is one of the most important topics in the field of computer vision. In this work, we analyze the speed of object detection using the well-known YOLOv3 neural network architecture in different frameworks under different hardware requirements. We obtain results, which allow us to formulate preliminary qualitative conclusions about the feasibility of various hardware scenarios to solve tasks in real-time environments.

Download Full-text

Design of Real-Time Database for the Vacuum Cold-Black Environment Simulator

MATEC Web of Conferences ◽

10.1051/matecconf/201823202034 ◽

2018 ◽

Vol 232 ◽

pp. 02034

Author(s):

Jingyi Shao ◽

Juan Ning ◽

Yangyang Liu

Keyword(s):

Real Time ◽

Data Storage ◽

Network Architecture ◽

Large Data ◽

Space Environment ◽

Time Data ◽

Data Volume ◽

Environment Simulation ◽

Real Time Database ◽

Interaction Efficiency

There is an urgent need to develop a real-time database (RTDB) to handle large amounts of real-time data, to realize process monitoring of vacuum cold-black environment simulation, cold-black environment data acquisition, fault processing, data storage, etc. This paper conducts real-time database design through network architecture, functional modules, communication interfaces, data management, and transaction scheduling. Simulation test and associated debugging test show that the real-time database can efficiently process large data volume, and the data interaction efficiency is greatly improved to meet the needs of space environment simulation equipment, laying a solid data foundation for subsequent applications.

Download Full-text

Rumor Detection Based on SAGNN: Simplified Aggregation Graph Neural Networks

Machine Learning and Knowledge Extraction ◽

10.3390/make3010005 ◽

2021 ◽

Vol 3 (1) ◽

pp. 84-94

Author(s):

Liang Zhang ◽

Jingqun Li ◽

Bin Zhou ◽

Yan Jia

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Network Architectures ◽

Neural Network Architecture ◽

Convolutional Networks ◽

Effective Manner ◽

Deep Learning Network ◽

Graph Neural Networks ◽

Rumor Detection

Identifying fake news on media has been an important issue. This is especially true considering the wide spread of rumors on popular social networks such as Twitter. Various kinds of techniques have been proposed for automatic rumor detection. In this work, we study the application of graph neural networks for rumor classification at a lower level, instead of applying existing neural network architectures to detect rumors. The responses to true rumors and false rumors display distinct characteristics. This suggests that it is essential to capture such interactions in an effective manner for a deep learning network to achieve better rumor detection performance. To this end we present a simplified aggregation graph neural network architecture. Experiments on publicly available Twitter datasets demonstrate that the proposed network has performance on a par with or even better than that of state-of-the-art graph convolutional networks, while significantly reducing the computational complexity.

Download Full-text

Wearable Fall Detector Using Recurrent Neural Networks

Sensors ◽

10.3390/s19224885 ◽

2019 ◽

Vol 19 (22) ◽

pp. 4885 ◽

Cited By ~ 9

Author(s):

Francisco Luna-Perejón ◽

Manuel Jesús Domínguez-Morales ◽

Antón Civit-Balcells

Keyword(s):

Neural Networks ◽

Low Power ◽

Real Time ◽

Recurrent Neural Networks ◽

Response Times ◽

Fall Detection ◽

High Energy ◽

Great Accuracy ◽

Public Health Issue ◽

Fall Detector

Falls have become a relevant public health issue due to their high prevalence and negative effects in elderly people. Wearable fall detector devices allow the implementation of continuous and ubiquitous monitoring systems. The effectiveness for analyzing temporal signals with low energy consumption is one of the most relevant characteristics of these devices. Recurrent neural networks (RNNs) have demonstrated a great accuracy in some problems that require analyzing sequential inputs. However, getting appropriate response times in low power microcontrollers remains a difficult task due to their limited hardware resources. This work shows a feasibility study about using RNN-based deep learning models to detect both falls and falls’ risks in real time using accelerometer signals. The effectiveness of four different architectures was analyzed using the SisFall dataset at different frequencies. The resulting models were integrated into two different embedded systems to analyze the execution times and changes in the model effectiveness. Finally, a study of power consumption was carried out. A sensitivity of 88.2% and a specificity of 96.4% was obtained. The simplest models reached inference times lower than 34 ms, which implies the capability to detect fall events in real-time with high energy efficiency. This suggests that RNN models provide an effective method that can be implemented in low power microcontrollers for the creation of autonomous wearable fall detection systems in real-time.

Download Full-text