Mei Song's research while affiliated with Beijing University of Posts and Telecommunications and other places

Publications (312)

Chapter
The phenomenon of long-tailed data distribution widely exists in every corner of life. And in fact, the fundamental solution to long-tailed distribution problem is actually the combination of imbalanced classification and few-shot learning. At present, the mainstream methods under the framework of deep learning are re-sampling, re-weighting and oth...
Preprint
Effective control of time-sensitive industrial applications depends on the real-time transmission of data from underlying sensors. Quantifying the data freshness through age of information (AoI), in this paper, we jointly design sampling and non-slot based scheduling policies to minimize the maximum time-average age of information (MAoI) among sens...
Article
The evaluation of node importance is a critical research topic in network science, widely applied in social networks, transport systems, and computer networks. Prior works addressing this topic either consider a single metric or assign weights for multiple metrics or select features by handcraft, which exist one-sidedness and subjectivity issues. I...
Article
Traveling by high-speed rail and railway transportation have become an important part of people's life and social production. Track is the basic equipment of railway transportation, and its performance directly affects the service lifetime of railway lines and vehicles. The anomaly detection of rail fasteners is in a priority, while the traditional...
Chapter
With the increasing number of people accessing the Internet, attacks against users or web servers have become a serious threat to network security. Network traffic can record network behavior, which is an important data source for analyzing network behavior. Using machine learning algorithm to analyze network behavior is one of the effective method...
Article
Many multiplex systems have hierarchical structures, such as communication networks. In this paper, we construct a cascading failure model on multilayer networks with dependence groups and hierarchical structure. We propose a new connection method between layers after generalizing the previous papers. Theoretical solutions of cascading model could...
Article
Full-text available
Network intrusion detection systems (IDSs) based on deep learning have reached fairly accurate attack detection rates. But these deep learning approaches usually have been performed in a closed-set protocol that only known classes appear in training are considered during classification, the existing IDSs will fail to detect the unknown attacks and...
Chapter
This paper proposes a channel estimation scheme for large-scale multiple-input multiple-output (MIMO) systems in high-speed train (HST) scenarios. On the premise that the priori velocity is accurate, we introduce fuzzy prior spatial knowledge and design a sparse received signal model with dynamic grids. After reconstructing the channel estimation i...
Article
Recent work on the cascading failure of networks with dependence groups assumes that the number of nodes in each dependence group is equal. In this paper, we construct a model on interdependent networks with dependence groups against cascading failure. The size of dependence group is supposed to obey the Poisson Distribution and the Truncated Norma...
Article
Full-text available
Human activity recognition (HAR) using body-worn sensors is an active research area in human-computer interaction and human activity analysis. The traditional methods use hand-crafted features to classify multiple activities, which is both heavily dependent on human domain knowledge and results in shallow feature extraction. Rapid developments in d...
Article
The rapid expansion of Machine Type Communication (MTC) has brought many challenges, such as sporadic uplink transmission congestion and energy consumption of battery limited nodes. To address these challenges, we consider a green energy harvesting massive MTC (mMTC) system that each device is equipped with a local cache and a rechargeable battery...
Article
Blockchain technology is reshaping the video streaming industry by changing how humans create, distribute and consume videos. Leveraging blockchain technology, some emerging video streaming platforms aim to eliminate the centralized video streaming servers by building peer-to-peer content distribution architectures and cryptocurrency-based payment...
Article
Full-text available
Human activity recognition (HAR) is a popular and challenging research topic, driven by a variety of applications. More recently, with significant progress in the development of deep learning networks for classification tasks, many researchers have made use of such models to recognise human activities in a sensor-based manner, which have achieved g...
Article
The boom of video streaming industry has resulted in the increasing demands for transcoding services from heterogeneous users. Recent advances of blockchain technology allow some startups to realize decentralized collaborative transcoding through device-to-device (D2D) networks, where a group of transcoders are selected to perform transcoding coope...
Chapter
Extracting sports highlights and summarizing the most exciting moments of the match is an important task for the broadcast media. However, it requires intensive video editing. We propose a Multimodal Analysis Approach (MAA) for auto-curating sports highlights, and use it to create a real-world system for editing aids of soccer highlight reels. MAA...
Chapter
The massive growth of mobile vehicles arises immense mobile traffic demand on the current cellular communication system. To cope with this challenge, a new transmission pattern that vehicle nodes cache some data contents in advance and provide data access for future requests via direct contacts has become an appealing solution for data offloading....
Conference Paper
Full-text available
Proactively caching content at the edge is a promising way of alleviating the traffic load in the core networks, especially for latency sensitive video services. The content popularity herein is an effective measure for making efficient cache placement decisions. Most state-of-the-art works design the caching strategies under the assumption that vi...
Article
Full-text available
Network attack behavior detection using deep learning is an important research topic in the field of network security. Currently, there are still many challenges in detecting multi-class imbalanced abnormal traffic data. This paper proposed a new intrusion detection network based on deep learning, named parallel cross convolutional neural network (...
Article
Nowadays, wireless communication has become a fabric of our daily life, and it has been a universal demand for higher capacity and longer battery lifetime. For the sake of solving these problems, this paper considers taking the advantage of cooperative communication with the assistance of green relays. So, in this paper, we design an auction market...
Conference Paper
In some special application environments, network fault can lead to loss of important information or even mission failures, resulting in unpredictable losses. Therefore, it has certain research significance and practical value to evaluate the network status and predict the possible faults before performing the key tasks. Based on the logs collected...
Chapter
In order to utilize renewable energy and save traditional energy, many literatures in recent years have drawn attention to content caching in wireless communications. In this article, we focus on content push and cache to increase green energy utilization and save traditional energy. The state transition probability and future rewards in the mobile...
Article
Cascading failure is widespread in the networks. In order to solve practical problems, it is necessary to study the cascading failure in the complex network. In this paper, we mainly focus on the cascading failure in multilayer networks with asymmetric dependence group and discuss the influence factors of networks’ robustness. We build a model with...
Article
Full-text available
This paper conducts mobility analysis in Coordinated multipoint (CoMP) based ultra-dense networks (UDNs) where channel state information (CSI) is outdated due to feedback delay. To depict the impact of mobility on CoMP-based UDNs, related analyses are carried out from two perspectives. For one thing, we define CoMP handover probability as the proba...
Article
Full-text available
Cryptographic cores integrated with self-test ability fulfill data security as well as reliability requirements of the Internet of Things (IoT) network. However from IoT perspective where most devices are resource constrained, a fundamental problem associated with most of the self-test architectures is high hardware overhead due to the additional c...
Chapter
In order to ensure the performance of cell edge users and meet the explosive growth of people’s data services, Coordinated Multiple Points technology (CoMP) has become a key technology in the evolution of wireless networks. Cooperative cell selection is a major support point of CoMP multi-point collaboration technology. However, multi-differentiate...
Chapter
Machine learning becomes an effective method to detect malicious traffic. With the proliferation of network traffic, malicious traffic categories are greatly increased, which puts forward higher requirements for the computation time and detection accuracy of machine learning. A feature selection framework is proposed to balance the computation time...
Article
Blockchain-based video streaming systems aim to build decentralized peer-to-peer networks with flexible monetization mechanisms for video streaming services. On these blockchain-based platforms, video transcoding, which is computational intensive and time consuming, is still a major challenge. Meanwhile, the block size of the underlying blockchain...
Article
The cloud-based Internet of things (IoT) develops rapidly but suffer from large latency and back-haul bandwidth requirement, the technology of fog computing and caching has emerged as a promising paradigm for IoT to provide proximity services, and thus reduce service latency and save back-haul bandwidth. However, the performance of the fog-enabled...
Article
Driven by the explosive data traffic and new quality of service (QoS) requirement of mobile users, the communication industry has been experiencing a new evolution by means of network infrastructure densification. With the increase of the density as well as the variety of access points (APs), the network benefits from proximal transmissions and inc...
Article
Full-text available
Blockchain technology has been applied in a variety of fields due to its capability of establishing trust in a decentralized fashion. However, the application of blockchain in wireless mobile networks is hindered by a major challenge brought by the proof-of-work (PoW) puzzle during the mining process, which sets a high demand for the computational...
Conference Paper
Full-text available
In this paper, we investigate the issue of resource allocation for secure communications in an orthogonal frequency division multiplexing (OFDM) based full-duplex (FD) relaying network, for maximizing the overall secure energy efficiency. Under the power constraint and minimum secrecy requirement, the resource allocation problem involves the subcar...
Article
The robust beamforming problem in multiple-input single-output (MISO) downlink networks of simultaneous wireless information and power transfer (SWIPT) is studied in this paper. Adopting the time switching fashion to perform energy harvesting and information decoding respectively, we aim at maximizing the sum rate under imperfect channel state info...
Conference Paper
Full-text available
Small cells are widely being deployed to enhance the performance of cellular networks, which results in a random distribution of base stations as well as a complex interference problem. Therefore, it becomes considerably challenging to derive a closed-form expression for the capacity of small cell enhanced heterogeneous cellular network especially...
Conference Paper
Full-text available
In the Long Term Evolution-Advanced (LTE-A) systems, coordinated Multi-Point (CoMP) transmission/reception technology is widely used to improve cell-edge throughput and system throughput. With the introduction of CoMP technology, handover scenes have changed and traditional handover algorithms are no longer able to meet the requirements of current...
Chapter
© Springer International Publishing AG 2018. The increasing traffic demands in the past few years require further expansion of cellular network capacity. Densely deployed base stations may cause a large amount of energy consumption and lots of environmental problems. Relaying is considered as a promising cost-efficient solution for capacity expansi...
Article
This paper considers the queue-aware optimal energy minimisation sparse beamforming design (QESB) in a downlink cloud radio access network (C-RAN) system where multi-RRH communicates with multi-user through a central computing cloud via digital front-haul links. The problem is formulated as the joint optimisation problem of the transmission energy...
Article
Software defined networking (SDN) is revolutionizing the telecommunication networking industry by providing flexible and efficient management. Because of energy cost and environmental concerns, green networking technologies are being developed to increasing energy efficiency and making use of renewable energy, for both wired and wireless networks....
Article
The rapid expansion of mobile communication networks has led to a significant increase of energy consumption, and the energy consumption of wireless access networks accounted for nearly 90%. As an important form of the wireless access networks, multi-hop relay networks have been widely deployed in the existing cellular networks. Consequently, impro...
Article
Densely deployment of various small-cell base stations in cellular networks to increase capacity will lead to heterogeneous networks (HetNets), and meanwhile, embedding the energy harvesting capabilities in base stations as an alternative energy supply is becoming reality. How to make efficient utilization of radio resource and renewable energy is...
Article
Virtual network embedding problem which is NP-hard is a key issue for implementing software-defined network which is brought about by network virtualization. Compared with other studies which focus on designing heuristic algorithms to reduce the hardness of the NP-hard problem we propose a robust VNE algorithm based on component connectivity in lar...
Article
The paper studies the robustness of the network in terms of the network structure. We define a strongly dominated relation between nodes and then we use the relation to merge the network. Based on that, we design a dominated clustering algorithm aiming at finding the critical nodes in the network. Furthermore, this merging process is lossless which...
Article
Full-text available
We consider an ultra-dense network (UDN) where each mobile is attached to the access point (AP) which provides the best reference signal received power (RSRP) according to both path-loss and small scale fading. In order to evaluate the effect of outdated channel state information (CSI) brought by feedback delay on handover decisions, we first deriv...