- Real-Time Systems Scheduling
- Distributed and Parallel Computing Systems
- Parallel Computing and Optimization Techniques
- Embedded Systems Design Techniques
- Network Time Synchronization Technologies
- Traffic control and management
- Interconnection Networks and Systems
- Vehicle Dynamics and Control Systems
- Vehicle emissions and performance
- Geological Modeling and Analysis
- Neural Networks and Applications
- Phytochemicals and Antioxidant Activities
- Advanced machining processes and optimization
- Engineering and Test Systems
- Advanced Surface Polishing Techniques
- Lignin and Wood Chemistry
- Scheduling and Optimization Algorithms
- Free Radicals and Antioxidants
- Geochemistry and Geologic Mapping
- Embedded Systems and FPGA Design
- Fault Detection and Control Systems
- Advanced Measurement and Metrology Techniques
- Traffic Prediction and Management Techniques
- Radiation Effects in Electronics
- Petri Nets in System Modeling
Nanjing University of Posts and Telecommunications
2019-2025
Jiangnan University
2023
Hong Kong Polytechnic University
2019
Northeastern University
2015-2018
Heterogenerous multi-cores utilize the strength of different architectures for executing particular types workload, and usually offer higher performance energy efficiency. In this paper, we study worst-case response time (WCRT) analysis typed scheduling parallel DAG tasks on heterogeneous multi-cores, where workload each vertex in is only allowed to execute a type cores. The known WCRT bound problem grossly pessimistic suffers non-self-sustainability problem. propose two new bounds. first...
To highlight the advantages of autonomous vehicles (AVs) in modern traffic, it is necessary to investigate sensing requirement parameters road environment during vehicle braking process. Based on texture information obtained using a field measurement, model an AV was built Simulink and ride comfort under typical scenarios analyzed CarSim/Simulink co-simulation. The results showed that proposed brake system for displayed better performance than traditional ABS when considering pavement...
The analysis of global multiprocessor scheduling is more difficult than its uniprocessor counterpart. Due to the unknown critical instant, existing techniques use over-approximations task interference for efficient yet pessimistic analysis. In this paper, we proposed a new technique improve precision estimation. key identify and resolve contradicting assumptions made in procedure. resulting method improves at price higher complexity. Then introduce optimize better efficiency. Experiments...
The increasing demands for processor performance are driving system designers to adopt multiprocessors. In this paper, we study global fixed priority scheduling in multiprocessor real-time systems and introduce a technique improving the schedulability. key idea is construct execution dependency selected tasks leverage slack time reduce interference between high-priority low-priority tasks. Thus, more lower-priority enabled be scheduled. Further, provide response analysis method which takes...
As the main objective influencing factor on brake safety of autonomous vehicles, pavement texture information is directly related to road surface antiskid performance. However, in system influence adhesion characteristics braking stability seldomly considered. To study vehicles curved sections under different conditions, advanced close-range photogrammetry was utilized extract information. Thereafter, power spectral density (PSD) calculated by MATLAB obtain coefficient curves based Persson...
Optical fiber communication has advantages of high transmission rate, channel capacity, long distance, and strong anti-interference ability so that it been widely used in control automation systems. Meanwhile, various topological structures are required the different applications optical system. According to these demands, we propose a system named Frame Forwarding (FF) for Profibus this paper. This supports three kinds network topologies which liner, star redundant ring. Especially, could...
Heterogenerous multi-cores utilize the strength of different architectures for executing particular types workload, and usually offer higher performance energy efficiency. In this paper, we study worst-case response time (WCRT) analysis typed scheduling parallel DAG tasks on heterogeneous multi-cores, where workload each vertex in is only allowed to execute a type cores. The known WCRT bound problem grossly pessimistic suffers non-self-sustainability problem. propose two new bounds. first...
Time-Sensitive Networking (TSN) has become a popular technique in the modern Internet of Things (IoT). However, messages may encounter transient faults during transmissions, which can impact schedulability and reliability. To protect against faults, re-transmitting uncorrected received is common approach. If there are only few re-transmissions, we not guarantee network's unlimited re-transmissions cause temporary rapid increase network load or even overload, leading to situations where some...
Heterogeneous multi-cores utilize the strength of different architectures for executing particular types workload, and usually offer higher performance energy efficiency. In this paper, we study worst-case response time (WCRT) analysis \emph{typed} scheduling parallel DAG tasks on heterogeneous multi-cores, where workload each vertex in is only allowed to execute a type cores. The known WCRT bound problem grossly pessimistic suffers \emph{non-self-sustainability} problem. propose two new...
Traffic delay in arterial road is an important criterion the judgment of service level transportation. At present, there exist a certain degree congestion problems most intersections, especially holidays. In order to assess and predict intersection, traffic simulation research chosen area Jinshan was undertaken. PTV VISSIM used generate simulated flow data. Linear Regression model, SoftMax machine learning were combined process data generated from micro simulation. This aim building proper...
Heterogeneous multi-core platforms can provide diverse computing power. By using different cores to perform specific workloads, the advantages of heterogeneous multi-cores be fully utilized achieve high performance and low power consumption. In this paper, we study problem schedulability analysis parallel directed acyclic graph (DAG) tasks on platforms. The DAG task studied in paper has particularities. A vertex a is only allowed execute set cores. each task's worst-case response time(WCRT)...