Zonghua Gu
YOU?
Author Swipe
View article: Performance Measurement and Analysis ofCertifiable Defenses against Adversarial PatchAttacks
Performance Measurement and Analysis ofCertifiable Defenses against Adversarial PatchAttacks Open
We consider deep learning-based perception in real-time, safety-critical cyber-physical systems (CPS), such as autonomous driving and robotics, where embedded computing platforms typically operate under limited hardware resources due to SW…
View article: Comparative study of the effects of simple and complex neural network models on enterprise performance
Comparative study of the effects of simple and complex neural network models on enterprise performance Open
Overseas studies have shown that complex neural network models perform better in enterprise performance prediction and can accurately capture the complex relationship of data, but there are long training time, overfitting risk, and limited…
View article: DarwinSync: An adaptive time step execution framework for large‐scale neuromorphic systems
DarwinSync: An adaptive time step execution framework for large‐scale neuromorphic systems Open
The time step functions as a crucial temporal unit for simulating neuronal dynamics within spiking neural networks, which play a significant role in neuromorphic computing systems. Efficient management of these time steps is vital to ensur…
View article: Real-time Stereo-based 3D Object Detection for Streaming Perception
Real-time Stereo-based 3D Object Detection for Streaming Perception Open
The ability to promptly respond to environmental changes is crucial for the perception system of autonomous driving. Recently, a new task called streaming perception was proposed. It jointly evaluate the latency and accuracy into a single …
View article: Efficient Performance Prediction of End-to-End Autonomous Driving Under Continuous Distribution Shifts Based on Anomaly Detection
Efficient Performance Prediction of End-to-End Autonomous Driving Under Continuous Distribution Shifts Based on Anomaly Detection Open
A Deep Neural Network (DNN)’s prediction may be unreliable outside of its training distribution despite high levels of accuracy obtained during model training. The DNN may experience different degrees of accuracy degradation for different …
View article: Message from ICESS 2022 Program Chairs
Message from ICESS 2022 Program Chairs Open
It is our great pleasure to welcome you to the 18th IEEE International Conference on Embedded Software and Systems (ICESS 2022), held in Chengdu, China during December 18-21, 2022. For the IEEE ICESS 2022, the financial sponsors are IEEE a…
View article: LRP‐based network pruning and policy distillation of robust and non‐robust DRL agents for embedded systems
LRP‐based network pruning and policy distillation of robust and non‐robust DRL agents for embedded systems Open
Summary Reinforcement learning (RL) is an effective approach to developing control policies by maximizing the agent's reward. Deep reinforcement learning uses deep neural networks (DNNs) for function approximation in RL, and has achieved t…
View article: CAN Bus Intrusion Detection Based on Auxiliary Classifier GAN and Out-of-distribution Detection
CAN Bus Intrusion Detection Based on Auxiliary Classifier GAN and Out-of-distribution Detection Open
The Controller Area Network (CAN) is a ubiquitous bus protocol present in the Electrical/Electronic (E/E) systems of almost all vehicles. It is vulnerable to a range of attacks once the attacker gains access to the bus through the vehicle’…
View article: Exploiting augmented intelligence in the modeling of safety-critical autonomous systems
Exploiting augmented intelligence in the modeling of safety-critical autonomous systems Open
Machine learning (ML) is used increasingly in safety-critical systems to provide more complex autonomy to make the system to do decisions by itself in uncertain environments. Using ML to learn system features is fundamentally different fro…
View article: Out-of-Distribution Detection for Deep Neural Networks With Isolation Forest and Local Outlier Factor
Out-of-Distribution Detection for Deep Neural Networks With Isolation Forest and Local Outlier Factor Open
Deep Neural Networks (DNNs) are extensively deployed in today's safety-critical autonomous systems thanks to their excellent performance. However, they are known to make mistakes unpredictably, e.g., a DNN may misclassify an object if it i…
View article: Efficient Spiking Neural Networks With Logarithmic Temporal Coding
Efficient Spiking Neural Networks With Logarithmic Temporal Coding Open
A Spiking Neural Network (SNN) can be trained indirectly by first training an Artificial Neural Network (ANN) with the conventional backpropagation algorithm, then converting it into an equivalent SNN. To reduce the computational cost of t…
View article: Simulation Performance Enhancement in Automotive Embedded Control Using the Unscented Transform
Simulation Performance Enhancement in Automotive Embedded Control Using the Unscented Transform Open
Automotive embedded systems comprise several domains, such as in software, electrical, electronics, and control. When designing and testing functions at the top level, one generally ignores the uncertainties arising from the electrical and…
View article: Model-Based Development of an Engine Control Module for a Spark Ignition Engine
Model-Based Development of an Engine Control Module for a Spark Ignition Engine Open
A Spark ignition (SI) engine is a complex, multi-domain component of the vehicle powertrain system. The engine control module (ECM) for an SI engine must achieve both high performance and good fuel efficiency. In this paper, we present a m…
View article: Analytical and Experimental Performance Evaluations of CAN-FD Bus
Analytical and Experimental Performance Evaluations of CAN-FD Bus Open
Controller area network (CAN) is a widely-used bus protocol in automotive distributed embedded systems, but its limited communication bandwidth (up to 1 Mbps) and payload size (up to 8 Bytes) limit its applicability in today's increasingly…
View article: WCET-Aware Control Flow Checking With Super-Nodes for Resource-Constrained Embedded Systems
WCET-Aware Control Flow Checking With Super-Nodes for Resource-Constrained Embedded Systems Open
Safety-critical embedded systems in application domains, such as aerospace, automotive, and industrial automation, must satisfy dual requirements of fault-tolerance and real-time predictability. Control flow checking is an effective techni…
View article: Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices
Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices Open
With the rapid proliferation of Internet of Things and intelligent edge devices, there is an increasing need for implementing machine learning algorithms, including deep learning, on resource-constrained mobile embedded devices with limite…