Blaž Bertalanič
YOU?
Author Swipe
View article: JaGuard: Jamming Correction of GNSS Deviation with Deep Temporal Graphs
JaGuard: Jamming Correction of GNSS Deviation with Deep Temporal Graphs Open
Global Navigation Satellite Systems (GNSS) are increasingly exposed to intentional jamming, threatening reliability when accurate positioning and timing are most critical. We address this problem by formulating interference mitigation as a…
View article: Towards Reliable AI in 6G: Detecting Concept Drift in Wireless Network
Towards Reliable AI in 6G: Detecting Concept Drift in Wireless Network Open
AI-native 6G networks promise unprecedented automation and performance by embedding machine-learning models throughout the radio access and core segments of the network. However, the non-stationary nature of wireless environments due to in…
View article: Multi-Agent Reinforcement Learning-Based In-Place Scaling Engine for Edge-Cloud Systems
Multi-Agent Reinforcement Learning-Based In-Place Scaling Engine for Edge-Cloud Systems Open
Modern edge-cloud systems face challenges in efficiently scaling resources to handle dynamic and unpredictable workloads. Traditional scaling approaches typically rely on static thresholds and predefined rules, which are often inadequate f…
View article: Data Model Design for Explainable Machine Learning-based Electricity Applications
Data Model Design for Explainable Machine Learning-based Electricity Applications Open
The transition from traditional power grids to smart grids, significant increase in the use of renewable energy sources, and soaring electricity prices has triggered a digital transformation of the energy infrastructure that enables new, d…
View article: A Representation Learning Approach to Feature Drift Detection in Wireless Networks
A Representation Learning Approach to Feature Drift Detection in Wireless Networks Open
AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of AI models …
View article: Exploring Kolmogorov–Arnold Networks for Interpretable Time Series Classification
Exploring Kolmogorov–Arnold Networks for Interpretable Time Series Classification Open
Time‐series classification is a relevant step supporting decision‐making processes in various domains, and deep neural models have shown promising performance in this respect. Despite significant advancements in deep learning, the theoreti…
View article: Exploring Kolmogorov-Arnold Networks for Interpretable Time Series Classification
Exploring Kolmogorov-Arnold Networks for Interpretable Time Series Classification Open
Time series classification is a relevant step supporting decision-making processes in various domains, and deep neural models have shown promising performance in this respect. Despite significant advancements in deep learning, the theoreti…
View article: Explainable semantic wireless anomaly characterization for digital twins
Explainable semantic wireless anomaly characterization for digital twins Open
The shift towards software-centric network infrastructures is driven by the increasing need for networks to be responsive, flexible, and scalable in the face of an expanding set of connected devices. The digital twin (DT) approach, mirrori…
View article: An Overview and Solution for Democratizing AI Workflows at the Network Edge
An Overview and Solution for Democratizing AI Workflows at the Network Edge Open
With the process of democratization of the network edge, hardware and software for networks are becoming available to the public, overcoming the confines of traditional cloud providers and network operators. This trend, coupled with the in…
View article: Natural Language Interaction with a Household Electricity Knowledge-based Digital Twin
Natural Language Interaction with a Household Electricity Knowledge-based Digital Twin Open
Domain specific digital twins, representing a digital replica of various segments of the smart grid, are foreseen as able to model, simulate, and control the respective segments. At the same time, knowledge-based digital twins, coupled wit…
View article: Towards Data-Driven Electricity Management: Multi-Region Harmonized Data and Knowledge Graph
Towards Data-Driven Electricity Management: Multi-Region Harmonized Data and Knowledge Graph Open
Due to growing population and technological advances, global electricity consumption, and consequently also CO2 emissions are increasing. The residential sector makes up 25% of global electricity consumption and has great potential to incr…
View article: Energy Efficient Deep Multi-Label ON/OFF Classification of Low Frequency Metered Home Appliances
Energy Efficient Deep Multi-Label ON/OFF Classification of Low Frequency Metered Home Appliances Open
Non-intrusive load monitoring (NILM) is the process of obtaining appliance-level data from a single metering point, measuring total electricity consumption of a household or a business. Appliance-level data can be directly used for demand …
View article: Visibility Graph-Based Wireless Anomaly Detection for Digital Twin Edge Networks
Visibility Graph-Based Wireless Anomaly Detection for Digital Twin Edge Networks Open
Network softwarization, which shifts hardware-centric functions to software implementations, is essential for enhancing the agility of cellular and non-cellular wireless networks. This change, while raising reliability concerns, also impro…
View article: CARMEL: Capturing spatio-temporal correlations via time-series sub-window imaging for home appliance classification
CARMEL: Capturing spatio-temporal correlations via time-series sub-window imaging for home appliance classification Open
Energy management systems (EMS), as enablers of more efficient energy consumption, monitor and manage appliances to help residents be more energy efficient and thus more frugal. Recent appliance detection and identification techniques for …
View article: Self-supervised learning for clustering of wireless spectrum activity
Self-supervised learning for clustering of wireless spectrum activity Open
In recent years, much work has been done on processing of wireless spectrum data involving machine learning techniques in domain-related problems for cognitive radio networks, such as anomaly detection, modulation classification, technolog…
View article: Dealing with zero-inflated data: achieving SOTA with a two-fold machine learning approach
Dealing with zero-inflated data: achieving SOTA with a two-fold machine learning approach Open
In many cases, a machine learning model must learn to correctly predict a few data points with particular values of interest in a broader range of data where many target values are zero. Zero-inflated data can be found in diverse scenarios…
View article: Deep Feature Learning for Wireless Spectrum Data
Deep Feature Learning for Wireless Spectrum Data Open
In recent years, the traditional feature engineering process for training machine learning models is being automated by the feature extraction layers integrated in deep learning architectures. In wireless networks, many studies were conduc…
View article: Energy Efficient Deep Multi-Label ON/OFF Classification of Low Frequency Metered Home Appliances
Energy Efficient Deep Multi-Label ON/OFF Classification of Low Frequency Metered Home Appliances Open
Non-intrusive load monitoring (NILM) is the process of obtaining appliance-level data from a single metering point, measuring total electricity consumption of a household or a business. Appliance-level data can be directly used for demand …
View article: Graph Neural Networks Based Anomalous RSSI Detection
Graph Neural Networks Based Anomalous RSSI Detection Open
In today's world, modern infrastructures are being equipped with information and communication technologies to create large IoT networks. It is essential to monitor these networks to ensure smooth operations by detecting and correcting lin…
View article: XAI for Self-supervised Clustering of Wireless Spectrum Activity
XAI for Self-supervised Clustering of Wireless Spectrum Activity Open
The so-called black-box deep learning (DL) models are increasingly used in classification tasks across many scientific disciplines, including wireless communications domain. In this trend, supervised DL models appear as most commonly propo…
View article: Outdoor fingerprint localization with BLE beacons
Outdoor fingerprint localization with BLE beacons Open
Introduction The data set contains received signal strength (RSS) measurements made with Bluetooth Low Energy (BLE) technology, which can be used for outdoor fingerprint-based localization applications, as presented in an article "LOG-a-TE…
View article: Outdoor fingerprint localization with BLE beacons
Outdoor fingerprint localization with BLE beacons Open
Introduction The data set contains received signal strength (RSS) measurements made with Bluetooth Low Energy (BLE) technology, which can be used for outdoor fingerprint-based localization applications, as presented in an article "LOG-a-TE…
View article: Outdoor fingerprint localization with BLE beacons
Outdoor fingerprint localization with BLE beacons Open
Introduction The data set contains received signal strength (RSS) measurements made with Bluetooth Low Energy (BLE) technology, which can be used for outdoor fingerprint-based localization applications, as presented in an article "LOG-a-TE…
View article: Resource-aware Deep Learning for Wireless Fingerprinting Localization
Resource-aware Deep Learning for Wireless Fingerprinting Localization Open
Location based services, already popular with end users, are now inevitably becoming part of new wireless infrastructures and emerging business processes. The increasingly popular Deep Learning (DL) artificial intelligence methods perform …