Blaž Bertalanič

Blaž Bertalanič, Carolina Fortuna

Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{eff}/N = 1/(1+c(N-1)N^{-β})$ where the regime exponent $β$ classifies any configuration into one of three asymptotic regimes -- hard-ceiling at $1/c$ ($β= 0$), sublinear at $N^β/c$ ($0 < β< 1$), or linear ($β\ge 1$), and a mean-field theorem predicts that peer count $k$ and rounds $τ$ during agent debate enter the dynamics only through their product $kτ$. The law applies at two levels: answer diversity and correctness redundancy. Across 44 (model $\times$ task $\times$ condition) cells spanning peer debate, self-correction, random-noise placebo, self-consistency, three open-weight families (Qwen, Llama, Ministral) at scales from 7B to 32B with a frontier API check (Gemini), thinking models, heterogeneous teams, and sparse communication, the functional form fits every condition at $R^2 > 0.99$; only $(c, β)$ shifts. On free-form math, dense peer influence collapses the answer-level regime from sublinear into hard-ceiling; correctness-level fits remain hard-ceiling throughout. Three findings have practical implications. \emph{(i)}~Thirty dense debating agents produce no more answer diversity than one on MMLU-Hard. \emph{(ii)}~A noise placebo tracks self-correction on free-form math and at $4\times$ scale, so within homogeneous teams the gain commonly attributed to ``debate'' comes from re-evaluation, not peer content. \emph{(iii)}~A single $N \le 5$ pilot predicts the $N=30$ structural ceiling, and within the configurations tested only architectural diversity (heterogeneous teams) lowers $c$ and escapes the hard-ceiling regime, communication-mode interventions do not.

Gregor Cerar, Blaž Bertalanič, Anže Pirnat et al.

The digital transformation of the energy infrastructure enables new, data driven, applications often supported by machine learning models. However, domain specific data transformations, pre-processing and management in modern data driven pipelines is yet to be addressed. In this paper we perform a first time study on generic data models that are able to support designing feature management solutions that are the most important component in developing ML-based energy applications. We first propose a taxonomy for designing data models suitable for energy applications, explain how this model can support the design of features and their subsequent management by specialized feature stores. Using a short-term forecasting dataset, we show the benefits of designing richer data models and engineering the features on the performance of the resulting models. Finally, we benchmark three complementary feature management solutions, including an open-source feature store suitable for time series.

Ljupcho Milosheski, Gregor Cerar, Blaž Bertalanič et al.

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, technology classification and device fingerprinting. Most of the solutions are based on labeled data, created in a controlled manner and processed with supervised learning approaches. However, spectrum data measured in real-world environment is highly nondeterministic, making its labeling a laborious and expensive process, requiring domain expertise, thus being one of the main drawbacks of using supervised learning approaches in this domain. In this paper, we investigate the use of self-supervised learning (SSL) for exploring spectrum activities in a real-world unlabeled data. In particular, we compare the performance of two SSL models, one based on a reference DeepCluster architecture and one adapted for spectrum activity identification and clustering, and a baseline model based on K-means clustering algorithm. We show that SSL models achieve superior performance regarding the quality of extracted features and clustering performance. With SSL models we achieve reduction of the feature vectors size by two orders of magnitude, while improving the performance by a factor of 2 to 2.5 across the evaluation metrics, supported by visual assessment. Additionally we show that adaptation of the reference SSL architecture to the domain data provides reduction of model complexity by one order of magnitude, while preserving or even improving the clustering performance.

Anže Pirnat, Blaž Bertalanič, Gregor Cerar et al.

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 response applications and energy management systems as well as for awareness raising and motivation for improvements in energy efficiency. Recently, classical machine learning and deep learning (DL) techniques became very popular and proved as highly effective for NILM classification, but with the growing complexity these methods are faced with significant computational and energy demands during both their training and operation. In this paper, we introduce a novel DL model aimed at enhanced multi-label classification of NILM with improved computation and energy efficiency. We also propose an evaluation methodology for comparison of different models using data synthesized from the measurement datasets so as to better represent real-world scenarios. Compared to the state-of-the-art, the proposed model has its energy consumption reduced by more than 23% while providing on average approximately 8 percentage points in performance improvement when evaluating on data derived from REFIT and UK-DALE datasets. We also show a 12 percentage point performance advantage of the proposed DL based model over a random forest model and observe performance degradation with the increase of the number of devices in the household, namely with each additional 5 devices, the average performance degrades by approximately 7 percentage points.

Ljupcho Milosheski, Gregor Cerar, Blaž Bertalanič et al.

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 conducted in automatic learning of feature representations for domain-related challenges. However, most of the existing works assume some supervision along the learning process by using labels to optimize the model. In this paper, we investigate an approach to learning feature representations for wireless transmission clustering in a completely unsupervised manner, i.e. requiring no labels in the process. We propose a model based on convolutional neural networks that automatically learns a reduced dimensionality representation of the input data with 99.3% less components compared to a baseline principal component analysis (PCA). We show that the automatic representation learning is able to extract fine-grained clusters containing the shapes of the wireless transmission bursts, while the baseline enables only general separability of the data based on the background noise.

Gregor Cerar, Blaž Bertalanič, Carolina Fortuna

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 very well in wireless fingerprinting localization based on extensive indoor radio measurement data. However, with the increasing complexity these methods become computationally very intensive and energy hungry, both for their training and subsequent operation. Considering only mobile users, estimated to exceed 7.4 billion by the end of 2025, and assuming that the networks serving these users will need to perform only one localization per user per hour on average, the machine learning models used for the calculation would need to perform $65 \times 10^{12}$ predictions per year. Add to this equation tens of billions of other connected devices and applications that rely heavily on more frequent location updates, and it becomes apparent that localization will contribute significantly to carbon emissions unless more energy-efficient models are developed and used. In this Chapter, we discuss the latest results and trends in wireless localization and look at paths towards achieving more sustainable AI. We then elaborate on a methodology for computing DL model complexity, energy consumption and carbon footprint and show on a concrete example how to develop a more resource-aware model for fingerprinting. We finally compare relevant works in terms of complexity and training CO$_2$ footprint.

Blaž Bertalanič, Jakob Jenko, Carolina Fortuna

Energy management systems (EMS) rely on (non)-intrusive load monitoring (N)ILM to monitor and manage appliances and help residents be more energy efficient and thus more frugal. The robustness as well as the transfer potential of the most promising machine learning solutions for (N)ILM is not yet fully understood as they are trained and evaluated on relatively limited data. In this paper, we propose a new approach for load monitoring in building EMS based on dimensionality expansion of time series and transfer learning. We perform an extensive evaluation on 5 different low-frequency datasets. The proposed feature dimensionality expansion using video-like transformation and resource-aware deep learning architecture achieves an average weighted F1 score of 0.88 across the datasets with 29 appliances and is computationally more efficient compared to the state-of-the-art imaging methods. Investigating the proposed method for cross-dataset intra-domain transfer learning, we find that 1) our method performs with an average weighted F1 score of 0.80 while requiring 3-times fewer epochs for model training compared to the non-transfer approach, 2) can achieve an F1 score of 0.75 with only 230 data samples, and 3) our transfer approach outperforms the state-of-the-art in precision drop by up to 12 percentage points for unseen appliances.

Jože M. Rožanec, Gašper Petelin, João Costa et al.

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, such as lumpy and intermittent demands, power consumption for home appliances being turned on and off, impurities measurement in distillation processes, and even airport shuttle demand prediction. The presence of zeroes affects the models' learning and may result in poor performance. Furthermore, zeroes also distort the metrics used to compute the model's prediction quality. This paper showcases two real-world use cases (home appliances classification and airport shuttle demand prediction) where a hierarchical model applied in the context of zero-inflated data leads to excellent results. In particular, for home appliances classification, the weighted average of Precision, Recall, F1, and AUC ROC was increased by 27%, 34%, 49%, and 27%, respectively. Furthermore, it is estimated that the proposed approach is also four times more energy efficient than the SOTA approach against which it was compared to. Two-fold models performed best in all cases when predicting airport shuttle demand, and the difference against other models has been proven to be statistically significant.

Ljupcho Milosheski, Kuon Akiyama, Blaž Bertalanič et al.

The growing number of smart devices supporting bandwidth-intensive and latency-sensitive applications, such as real-time video analytics, smart sensing, and Extended Reality (XR), necessitates reliable wireless connectivity in indoor environments. Therein, accurate estimation of Radio Environment Maps (REMs) enables adaptive wireless network planning and optimization of Access Point (AP) placement. However, generating realistic REMs remains challenging due to the complexity of indoor spaces. To overcome this challenge, this paper introduces a multimodal dataset that integrates high-resolution 3D LiDAR scans with Wi-Fi Received Signal Strength Indicator (RSSI) measurements collected under 20 distinct AP configurations in a multi-room indoor environment. The dataset captures two measurement scenarios: the first without human presence in the environment, and the second with human presence. Thus, the presented dataset supports the study of dynamic environmental effects on wireless signal propagation. This resource is designed to facilitate research in data-driven wireless modeling, particularly in the context of emerging high-frequency standards such as IEEE 802.11be (Wi-Fi 7), and aims to advance the development of robust, high-capacity indoor communication systems.

Blaž Bertalanič, Carolina Fortuna

Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review filters hallucinations. Yet the failure dynamics of homogeneous debate remain poorly understood, therefore we report findings from a controlled empirical study of teams of $N{=}10$ homogeneous agents (Qwen2.5-7B, Llama-3.1-8B, Ministral-3-8B) across $R{=}3$ debate rounds on two high-difficulty benchmarks (GSM-Hard and MMLU-Hard). We compare peer debate against isolated self-correction and a stochastic noise control that injects rationales from unrelated problems. We decompose debate failure into three model-dependent pathways: sycophantic conformity, where agents uncritically adopt majority answers (modal adoption up to 85.5%); contextual fragility, where peer rationales destabilize previously correct reasoning (vulnerability rate up to 70.0%); and consensus collapse, where plurality voting discards correct answers already present in the generation pool (oracle gap up to 32.3 percentage points). Ablations over communication density ($K \in \{2,4,9\}$) and sampling temperature ($T \in \{0.4, 0.7\}$) show that conformity reaches high levels at minimal peer exposure ($K{=}2$) and intensifies with greater initial diversity. Across all configurations, debate consumes 2.1-3.4$\times$ more tokens (up to 28,631 tokens per problem) than self-correction for equal or lower accuracy. Our results indicate that, within the 7-8B parameter class, homogeneous teams without structured roles do not benefit from unguided peer exchange, and that isolated self-correction consistently offers a more favorable cost-accuracy tradeoff.

Irina Barašin, Blaž Bertalanič, Mihael Mohorčič et al.

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 theoretical understanding of how and why complex architectures function remains limited, prompting the need for more interpretable models. Recently, the Kolmogorov-Arnold Networks (KANs) have been proposed as a more interpretable alternative to deep learning. While KAN-related research is significantly rising, to date, the study of KAN architectures for time series classification has been limited. In this paper, we aim to conduct a comprehensive and robust exploration of the KAN architecture for time series classification utilising 117 datasets from UCR benchmark archive, from multiple different domains. More specifically, we investigate a) the transferability of reference architectures designed for regression to classification tasks, b) identifying the hyperparameter and implementation configurations for an architecture that best generalizes across 117 datasets, c) the associated complexity trade-offs and d) evaluate KANs interpretability. Our results demonstrate that (1) the Efficient KAN outperforms MLPs in both performance and training times, showcasing its suitability for classification tasks. (2) Efficient KAN exhibits greater stability than the original KAN across grid sizes, depths, and layer configurations, especially when lower learning rates are employed. (3) KAN achieves competitive accuracy compared to state-of-the-art models such as HIVE-COTE2 and InceptionTime, while maintaining smaller architectures and faster training times, highlighting its favorable balance of performance and transparency. (4) The interpretability of the KAN model, as confirmed by SHAP analysis, reinforces its capacity for transparent decision-making.

Tim Strnad, Blaž Bertalanič, Carolina Fortuna

Machine learning is increasingly permeating radio-based localization services. To keep results credible and comparable, everyday workflows should make rigorous experiment specification and exact repeatability the default, without blocking advanced experimentation. However, in practice, researchers face a three-way gap that could be filled by a framework that offers (i) low coding effort for end-to-end studies, (ii) reproducibility by default including versioned code, data, and configurations, controlled randomness, isolated runs, and recorded artifacts, and (iii) built-in extensibility so new models, metrics, and stages can be added with minimal integration effort. Existing tools rarely deliver all three for machine learning in general and localization workflows in particular. In this paper we introduce LOCALIZE, a low-code, configuration-first framework for radio localization in which experiments are declared in human-readable configuration, a workflow orchestrator runs standardized pipelines from data preparation to reporting, and all artifacts, such as datasets, models, metrics, and reports, are versioned. The preconfigured, versioned datasets reduce initial setup and boilerplate, speeding up model development and evaluation. The design, with clear extension points, allows experts to add components without reworking the infrastructure. In a qualitative comparison and a head-to-head study against a plain Jupyter notebook baseline, we show that the framework reduces authoring effort while maintaining comparable runtime and memory behavior. Furthermore, using a Bluetooth Low Energy dataset, we show that scaling across training data (1x to 10x) keeps orchestration overheads bounded as data grows. Overall, the framework makes reproducible machine-learning-based localization experimentation practical, accessible, and extensible.

Ivana Kesić, Aljaž Blatnik, Carolina Fortuna et al.

Global Navigation Satellite Systems (GNSS) are increasingly disrupted by intentional jamming, degrading availability precisely when positioning and timing must remain operational. We address this by reframing jamming mitigation as dynamic graph regression and introducing a receiver-centric deep temporal graph network that predicts, and thus corrects, the receivers horizontal deviation in real time. At each 1 Hz epoch, the satellite receiver environment is represented as a heterogeneous star graph (receiver center, tracked satellites as leaves) with time varying attributes (e.g., SNR, azimuth, elevation, latitude/longitude). A single layer Heterogeneous Graph ConvLSTM (HeteroGCLSTM) aggregates one hop spatial context and temporal dynamics over a short history to output the 2D deviation vector applied for on the fly correction. We evaluate on datasets from two distinct receivers under three jammer profiles, continuous wave (cw), triple tone (cw3), and wideband FM, each exercised at six power levels between -45 and -70 dBm, with 50 repetitions per scenario (prejam/jam/recovery). Against strong multivariate time series baselines (MLP, uniform CNN, and Seq2Point CNN), our model consistently attains the lowest mean absolute error (MAE). At -45 dBm, it achieves 3.64 cm (GP01/cw), 7.74 cm (GP01/cw3), 4.41 cm (ublox/cw), 4.84 cm (ublox/cw3), and 4.82 cm (ublox/FM), improving to 1.65-2.08 cm by -60 to -70 dBm. On mixed mode datasets pooling all powers, MAE is 3.78 cm (GP01) and 4.25 cm (ublox10), outperforming Seq2Point, MLP, and CNN. A split study shows superior data efficiency: with only 10\% training data our approach remains well ahead of baselines (20 cm vs. 36-42 cm).

Athanasios Tziouvaras, Carolina Fortuna, George Floros et al.

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 infrastructure changes, user mobility, and emerging traffic patterns, induces concept drifts that can quickly degrade these model accuracies. Existing methods in general are very domain specific, or struggle with certain type of concept drift. In this paper, we introduce two unsupervised, model-agnostic, batch concept drift detectors. Both methods compute an expected-utility score to decide when concept drift occurred and if model retraining is warranted, without requiring ground-truth labels after deployment. We validate our framework on two real-world wireless use cases in outdoor fingerprinting for localization and for link-anomaly detection, and demonstrate that both methods are outperforming classical detectors such as ADWIN, DDM, CUSUM by 20-40 percentage points. Additionally, they achieve an F1-score of 0.94 and 1.00 in correctly triggering retraining alarm, thus reducing the false alarm rate by up to 20 percentage points compared to the best classical detectors.

Ivana Kesić, Carolina Fortuna, Mihael Mohorčič et al.

Time series segmentation (TSS) is one of the time series (TS) analysis techniques, that has received considerably less attention compared to other TS related tasks. In recent years, deep learning architectures have been introduced for TSS, however their reliance on sliding windows limits segmentation granularity due to fixed window sizes and strides. To overcome these challenges, we propose a new more granular TSS approach that utilizes the Weighted Dual Perspective Visbility Graph (WDPVG) TS into a graph and combines it with a Graph Attention Network (GAT). By transforming TS into graphs, we are able to capture different structural aspects of the data that would otherwise remain hidden. By utilizing the representation learning capabilities of Graph Neural Networks, our method is able to effectively identify meaningful segments within the TS. To better understand the potential of our approach, we also experimented with different TS-to-graph transformations and compared their performance. Our contributions include: a) formulating the TSS as a node classification problem on graphs; b) conducting an extensive analysis of various TS- to-graph transformations applied to TSS using benchmark datasets from the TSSB repository; c) providing the first detailed study on utilizing GNNs for analyzing graph representations of TS in the context of TSS; d) demonstrating the effectiveness of our method, which achieves an average F1 score of 0.97 across 59 diverse TSS benchmark datasets; e) outperforming the seq2point baseline method by 0.05 in terms of F1 score; and f) reducing the required training data compared to the baseline methods.

Andrej Čop, Blaž Bertalanič, Marko Grobelnik et al.

As the complexity and number of machine learning (ML) models grows, well-documented ML models are essential for developers and companies to use or adapt them to their specific use cases. Model metadata, already present in unstructured format as model cards in online repositories such as Hugging Face, could be more structured and machine readable while also incorporating environmental impact metrics such as energy consumption and carbon footprint. Our work extends the existing State of the Art by defining a structured schema for ML model metadata focusing on machine-readable format and support for integration into a knowledge graph (KG) for better organization and querying, enabling a wider set of use cases. Furthermore, we present an example wireless localization model metadata dataset consisting of 22 models trained on 4 datasets, integrated into a Neo4j-based KG with 113 nodes and 199 relations.

Blaž Bertalanič, Matej Vnučec, Carolina Fortuna

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 link failures or abnormal network behaviour proactively, which can otherwise cause interruptions in business operations. This paper presents a novel method for detecting anomalies in wireless links using graph neural networks. The proposed approach involves converting time series data into graphs and training a new graph neural network architecture based on graph attention networks that successfully detects anomalies at the level of individual measurements of the time series data. The model provides competitive results compared to the state of the art while being computationally more efficient with ~171 times fewer trainable parameters.

Carolina Fortuna, Vid Hanžel, Blaž Bertalanič

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 with AI, may also empower humans to understand aspects of the system through natural language interaction in view of planning and policy making. This paper is the first to assess and report on the potential of Retrieval Augmented Generation (RAG) question answers related to household electrical energy measurement aspects leveraging a knowledge-based energy digital twin. Relying on the recently published electricity consumption knowledge graph that actually represents a knowledge-based digital twin, we study the capabilities of ChatGPT, Gemini and Llama in answering electricity related questions. Furthermore, we compare the answers with the ones generated through a RAG techniques that leverages an existing electricity knowledge-based digital twin. Our findings illustrate that the RAG approach not only reduces the incidence of incorrect information typically generated by LLMs but also significantly improves the quality of the output by grounding responses in verifiable data. This paper details our methodology, presents a comparative analysis of responses with and without RAG, and discusses the implications of our findings for future applications of AI in specialized sectors like energy data analysis.

Ljupcho Milosheski, Gregor Cerar, Blaž Bertalanič et al.

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 proposed solutions to domain-related classification problems. Although they are proven to have unmatched performance, the necessity for large labeled training data and their intractable reasoning, as two major drawbacks, are constraining their usage. The self-supervised architectures emerged as a promising solution that reduces the size of the needed labeled data, but the explainability problem remains. In this paper, we propose a methodology for explaining deep clustering, self-supervised learning architectures comprised of a representation learning part based on a Convolutional Neural Network (CNN) and a clustering part. For the state of the art representation learning part, our methodology employs Guided Backpropagation to interpret the regions of interest of the input data. For the clustering part, the methodology relies on Shallow Trees to explain the clustering result using optimized depth decision tree. Finally, a data-specific visualizations part enables connection for each of the clusters to the input data trough the relevant features. We explain on a use case of wireless spectrum activity clustering how the CNN-based, deep clustering architecture reasons.

Anže Pirnat, Blaž Bertalanič, Gregor Cerar et al.

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 very well in wireless fingerprinting localization based on extensive indoor radio measurement data. However, with the increasing complexity these methods become computationally very intensive and energy hungry, both for their training and subsequent operation. Considering only mobile users, estimated to exceed 7.4billion by the end of 2025, and assuming that the networks serving these users will need to perform only one localization per user per hour on average, the machine learning models used for the calculation would need to perform 65*10^12 predictions per year. Add to this equation tens of billions of other connected devices and applications that rely heavily on more frequent location updates, and it becomes apparent that localization will contribute significantly to carbon emissions unless more energy-efficient models are developed and used. This motivated our work on a new DL-based architecture for indoor localization that is more energy efficient compared to related state-of-the-art approaches while showing only marginal performance degradation. A detailed performance evaluation shows that the proposed model producesonly 58 % of the carbon footprint while maintaining 98.7 % of the overall performance compared to state of the art model external to our group. Additionally, we elaborate on a methodology to calculate the complexity of the DL model and thus the CO2 footprint during its training and operation.

Blaž Bertalanič, Marko Meža, Carolina Fortuna

The number of end devices that use the last mile wireless connectivity is dramatically increasing with the rise of smart infrastructures and require reliable functioning to support smooth and efficient business processes. To efficiently manage such massive wireless networks, more advanced and accurate network monitoring and malfunction detection solutions are required. In this paper, we perform a first time analysis of image-based representation techniques for wireless anomaly detection using recurrence plots and Gramian angular fields and propose a new deep learning architecture enabling accurate anomaly detection. We elaborate on the design considerations for developing a resource aware architecture and propose a new model using time-series to image transformation using recurrence plots. We show that the proposed model a) outperforms the one based on Grammian angular fields by up to 14 percentage points, b) outperforms classical ML models using dynamic time warping by up to 24 percentage points, c) outperforms or performs on par with mainstream architectures such as AlexNet and VGG11 while having <10 times their weights and up to $\approx$8\% of their computational complexity and d) outperforms the state of the art in the respective application area by up to 55 percentage points. Finally, we also explain on randomly chosen examples how the classifier takes decisions.

Gregor Cerar, Halil Yetgin, Blaž Bertalanič et al.

After decades of research, the Internet of Things (IoT) is finally permeating real-life and helps improve the efficiency of infrastructures and processes as well as our health. As a massive number of IoT devices are deployed, they naturally incur great operational costs to ensure intended operations. To effectively handle such intended operations in massive IoT networks, automatic detection of malfunctioning, namely anomaly detection, becomes a critical but challenging task. In this paper, motivated by a real-world experimental IoT deployment, we introduce four types of wireless network anomalies that are identified at the link layer. We study the performance of threshold- and machine learning (ML)-based classifiers to automatically detect these anomalies. We examine the relative performance of three supervised and three unsupervised ML techniques on both non-encoded and encoded (autoencoder) feature representations. Our results demonstrate that; i) selected supervised approaches are able to detect anomalies with F1 scores of above 0.98, while unsupervised ones are also capable of detecting the said anomalies with F1 scores of, on average, 0.90, and ii) OC-SVM outperforms all the other unsupervised ML approaches reaching at F1 scores of 0.99 for SuddenD, 0.95 for SuddenR, 0.93 for InstaD and 0.95 for SlowD.