相关论文: A Model Drift Detection and Adaptation Framework f…

Continuous learning from an immense volume of data streams becomes exceptionally critical in the internet era. However, data streams often do not conform to the same distribution over time, leading to a phenomenon called concept drift.…

This paper studies change point detection on networks with community structures. It proposes a framework that can detect both local and global changes in networks efficiently. Importantly, it can clearly distinguish the two types of…

This study is a first attempt to experimentally explore the range of performance bottlenecks that 5G mobile networks can experience. To this end, we leverage a wide range of measurements obtained with a prototype testbed that captures the…

ML models are increasingly being pushed to mobile devices, for low-latency inference and offline operation. However, once the models are deployed, it is hard for ML operators to track their accuracy, which can degrade unpredictably (e.g.,…

Concept drift refers to the change of data distributions over time. While drift poses a challenge for learning models, requiring their continual adaption, it is also relevant in system monitoring to detect malfunctions, system failures, and…

We consider the problem of energy-efficient network management in 5G systems, where backhaul and fronthaul nodes have both networking and computational capabilities. We devise an optimization model accounting for the main features of 5G…

Visual change detection, aiming at segmentation of video frames into foreground and background regions, is one of the elementary tasks in computer vision and video analytics. The applications of change detection include anomaly detection,…

The evolution of mobile wireless systems into Heterogeneous Networks, along with the introduction of the 5th Generation (5G) systems, significantly increased the complexity of radio resource management. The current mobile networks consist…

The sharing of mobile network infrastructure has become a key topic with the introduction of 5G due to the high costs of deploying such infrastructures, with neutral host models coupled with features such as network function virtualization…

A trained ML model is deployed on another `test' dataset where target feature values (labels) are unknown. Drift is distribution change between the training and deployment data, which is concerning if model performance changes. For a…

The last decade has seen a surge of interest in adaptive learning algorithms for data stream classification, with applications ranging from predicting ozone level peaks, learning stock market indicators, to detecting computer security…

In the past few decades, the world has witnessed a rapid growth in mobile communication and reaped great benefits from it. Even though the fourth generation (4G) mobile communication system is just being deployed worldwide, proliferating…

To accommodate various use cases with differing characteristics, the Fifth Generation (5G) mobile communications system intends to utilize network slicing. Network slicing enables the creation of multiple logical networks over a shared…

Intrusion Detection Systems (IDS) are critical components in safeguarding 5G/6G networks from both internal and external cyber threats. While traditional IDS approaches rely heavily on signature-based methods, they struggle to detect novel…

With a plethora of new connections, features, and services introduced, the 5th generation (5G) wireless technology reflects the development of mobile communication networks and is here to stay for the next decade. The multitude of services…

Discriminative correlation filters show excellent performance in object tracking. However, in complex scenes, the apparent characteristics of the tracked target are variable, which makes it easy to pollute the model and cause the model…

Flexible management is one of the key components of next-generation 5G networks. Currently, many approaches focus on network functionality (services) and translate it afterward into end-user requirements, which slightly constrains the…

The availability of different paths to communicate to a user or device introduces several benefits, from boosting enduser performance to improving network utilization. Hybrid access is a first step in enabling convergence of mobile and…

Recent technological improvements in vehicle manufacturing may greatly improve safety however, the individuals' driving behaviour still remains a factor of paramount importance with aggressiveness, lack of focus and carelessness being the…

The proposed 3GPP's 5G Next-generation (NextGen) Core architecture (5GC) enables the ability to introduce new user and control plane functions within the context of network slicing to allow greater flexibility in handling of heterogeneous…