A5101926179- Mobile Ad Hoc Networks
- Cooperative Communication and Network Coding
- Opportunistic and Delay-Tolerant Networks
- Error Correcting Code Techniques
- Advanced Wireless Communication Techniques
- Industrial Vision Systems and Defect Detection
- Vehicular Ad Hoc Networks (VANETs)
- Software-Defined Networks and 5G
- Internet Traffic Analysis and Secure E-voting
- Advanced Wireless Network Optimization
- Advanced Neural Network Applications
- Coding theory and cryptography
- Wireless Networks and Protocols
- Security in Wireless Sensor Networks
- Real-Time Systems Scheduling
- Energy Efficient Wireless Sensor Networks
- Interconnection Networks and Systems
- Advanced Image and Video Retrieval Techniques
- Network Traffic and Congestion Control
- Machine Learning and ELM
- DNA and Biological Computing
- Domain Adaptation and Few-Shot Learning
- Network Security and Intrusion Detection
Beijing Jiaotong University
2019-2023
University of Southern Queensland
2006-2007
Carnegie Mellon University
2004
Constrained optimization demands highly efficient solvers which promotes the development of learn-to-optimize (L2O) approaches. As a data-driven method, L2O leverages neural networks to efficiently produce approximate solutions. However, significant challenge remains in ensuring both optimality and feasibility networks' output. To tackle this issue, we introduce Homeomorphic Polar Learning (HoP) solve star-convex hard-constrained by embedding homeomorphic mapping networks. The bijective...
In this paper, we propose a linear complexity encoding method for arbitrary LDPC codes. We start from simple graph-based ``label-and-decide.'' prove that the ``label-and-decide'' is applicable to Tanner graphs with hierarchical structure--pseudo-trees-- and resulting code block length. Next, define second type of graphs--the stopping set. The set encoded in by revised label-and-decide algorithm--the ``label-decide-recompute.'' Finally, any graph can be partitioned into sets pseudo-trees. By...
Encryption mechanisms improve the security of transmitting data. Nevertheless, attackers might silently eavesdrop packets to crack sensitive information or launch cyberattacks damage network performance victims. In this paper, we propose a learning based adaptive immune mechanism (LANIM) prevent eavesdropping attacks. Specifically, LANIM is equipped with three <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">defense lines</i> and one...
A new innovative deployment of wireless technology is mobile ad hoc network (MANET). MANET characterized by no fixed infrastructure or varying topologized structure. This feature allows to be deployed within many circumstances where traditional IP networks are constrained too expensive in terms time and resources. Adversely, the mobility node renders MANETs vulnerable malicious attacks. Security mechanism usually contains secure routing secures data transmission. There already some...
The paper presents a low-complexity encoding algorithm for cycle codes-low-density parity-check (LDPC) codes with column weight j = 2. For code of block length n, the complexity is O(n) whereas conventional method has O(n/sup 2/). We achieve linear-complexity encoder through graph analysis. First, we introduce particular Tanner graphs named pseudo-trees and prove that any pseudo-tree can be encoded in linear time. Second, show represented by union pseudo-trees. combining these two ideas, are...
Heterogeneous networks offer multipath transmission through various protocol stacks which allow multiplexing of packet for high throughput and enhanced security as prevents sniffing full information from a single point. However, often lead to arriving out-of-order issue due the different characteristics paths. The immediate consequence is lengthening delay buffering at receivers. This paper proposes lightweight novel Delay-Programmable Scheduling (DPS) mechanism mitigate problem, while...
Abstract Because of the popularisation high‐resolution images, detecting objects in these images quickly and accurately has attracted increasing attention recent studies. Current convolutional neural networks (CNN)‐based detection methods have limitations small owing to interference scale variation. In this work, we propose an improved generic framework based on YOLOv3. Equipped with multiresolution supervision for training aggregation inference, method can deal challenge variation images....
Mobile ad-hoc networks operate in the absence of any supporting infrastructure. The fixed infrastructure mobile makes it difficult to utilize existing techniques for network services, and poses number various challenges area. discovery maintenance secure route is most flinty challenge. In this paper, we deliberate implement one routing protocol FLSL (Adaptive Fuzzy Logic Based Security Level Routing Protocol) study its performance under different scenarios. implementation has been carried...