Massimiliano Ruocco

Sondre Sørbø, Massimiliano Ruocco

The field of time series anomaly detection is constantly advancing, with several methods available, making it a challenge to determine the most appropriate method for a specific domain. The evaluation of these methods is facilitated by the use of metrics, which vary widely in their properties. Despite the existence of new evaluation metrics, there is limited agreement on which metrics are best suited for specific scenarios and domain, and the most commonly used metrics have faced criticism in the literature. This paper provides a comprehensive overview of the metrics used for the evaluation of time series anomaly detection methods, and also defines a taxonomy of these based on how they are calculated. By defining a set of properties for evaluation metrics and a set of specific case studies and experiments, twenty metrics are analyzed and discussed in detail, highlighting the unique suitability of each for specific tasks. Through extensive experimentation and analysis, this paper argues that the choice of evaluation metric must be made with care, taking into account the specific requirements of the task at hand.

Espen Haugsdal, Erlend Aune, Massimiliano Ruocco

Time series forecasting is an important problem, with many real world applications. Ensembles of deep neural networks have recently achieved impressive forecasting accuracy, but such large ensembles are impractical in many real world settings. Transformer models been successfully applied to a diverse set of challenging problems. We propose a novel adaptation of the original Transformer architecture focusing on the task of time series forecasting, called Persistence Initialization. The model is initialized as a naive persistence model by using a multiplicative gating mechanism combined with a residual skip connection. We use a decoder Transformer with ReZero normalization and Rotary positional encodings, but the adaptation is applicable to any auto-regressive neural network model. We evaluate our proposed architecture on the challenging M4 dataset, achieving competitive performance compared to ensemble based methods. We also compare against existing recently proposed Transformer models for time series forecasting, showing superior performance on the M4 dataset. Extensive ablation studies show that Persistence Initialization leads to better performance and faster convergence. As the size of the model increases, only the models with our proposed adaptation gain in performance. We also perform an additional ablation study to determine the importance of the choice of normalization and positional encoding, and find both the use of Rotary encodings and ReZero normalization to be essential for good forecasting performance.

Simen Kristoffersen, Peter Skaar Nordby, Sara Malacarne et al.

We introduce SiamTST, a novel representation learning framework for multivariate time series. SiamTST integrates a Siamese network with attention, channel-independent patching, and normalization techniques to achieve superior performance. Evaluated on a real-world industrial telecommunication dataset, SiamTST demonstrates significant improvements in forecasting accuracy over existing methods. Notably, a simple linear network also shows competitive performance, achieving the second-best results, just behind SiamTST. The code is available at https://github.com/simenkristoff/SiamTST.

Sara Malacarne, Eirik Hoel-Høiseth, Erlend Aune et al.

Mobile network operators must monitor thousands of heterogeneous network elements across the radio access network and the packet core, each exposing high-dimensional KPI time series. The scale and cost of incident labelling make supervised approaches impractical, motivating unsupervised anomaly detection robust to context shifts and nonstationarity. We propose \textbf{C-MTAD-GAT} (\emph{Context-aware Multivariate Time-series Anomaly Detection with Graph Attention}), an anomaly detection framework designed to operate as a single shared model across large populations of network elements. The model combines temporal and feature-wise graph attention with lightweight static and dynamic context conditioning and a dual-head decoder for reconstruction and multi-step forecasting. It produces per-element, per-feature anomaly scores, converted to alerts via fully unsupervised thresholds calibrated from validation residuals. On the TELCO dataset released with DC-VAE \cite{garcia2023onemodel}, C-MTAD-GAT improves event-level affiliation and pointwise F1 while generating fewer alarms than prior graph-attention and VAE-based baselines. We then apply the same system to nation-scale radio access and evolved packet core control-plane counter data from a mobile network operator, where it is deployed. Operator feedback indicates the alerts are actionable and support daily monitoring, showing scalability across domains without relying on labelled incidents.

Abdulmajid Murad, Massimiliano Ruocco

In modern air traffic management, generating synthetic flight trajectories has emerged as a promising solution for addressing data scarcity, protecting sensitive information, and supporting large-scale analyses. In this paper, we propose a novel method for trajectory synthesis by adapting the Time-Based Vector Quantized Variational Autoencoder (TimeVQVAE). Our approach leverages time-frequency domain processing, vector quantization, and transformer-based priors to capture both global and local dynamics in flight data. By discretizing the latent space and integrating transformer priors, the model learns long-range spatiotemporal dependencies and preserves coherence across entire flight paths. We evaluate the adapted TimeVQVAE using an extensive suite of quality, statistical, and distributional metrics, as well as a flyability assessment conducted in an open-source air traffic simulator. Results indicate that TimeVQVAE outperforms a temporal convolutional VAE baseline, generating synthetic trajectories that mirror real flight data in terms of spatial accuracy, temporal consistency, and statistical properties. Furthermore, the simulator-based assessment shows that most generated trajectories maintain operational feasibility, although occasional outliers underscore the potential need for additional domain-specific constraints. Overall, our findings underscore the importance of multi-scale representation learning for capturing complex flight behaviors and demonstrate the promise of TimeVQVAE in producing representative synthetic trajectories for downstream tasks such as model training, airspace design, and air traffic forecasting.

Alfredo V Clemente, Alessandro Nocente, Massimiliano Ruocco

A thorough regulation of building energy systems translates in relevant energy savings and in a better comfort for the occupants. Algorithms to predict the thermal state of a building on a certain time horizon with a good confidence are essential for the implementation of effective control systems. This work presents a global Transformer architecture for indoor temperature forecasting in multi-room buildings, aiming at optimizing energy consumption and reducing greenhouse gas emissions associated with HVAC systems. Recent advancements in deep learning have enabled the development of more sophisticated forecasting models compared to traditional feedback control systems. The proposed global Transformer architecture can be trained on the entire dataset encompassing all rooms, eliminating the need for multiple room-specific models, significantly improving predictive performance, and simplifying deployment and maintenance. Notably, this study is the first to apply a Transformer architecture for indoor temperature forecasting in multi-room buildings. The proposed approach provides a novel solution to enhance the accuracy and efficiency of temperature forecasting, serving as a valuable tool to optimize energy consumption and decrease greenhouse gas emissions in the building sector.

Olav Finne Praesteng Larsen, Massimiliano Ruocco, Michail Spitieris et al.

Access to trajectory data is a key requirement for developing and validating Air Traffic Management (ATM) solutions, yet many secondary and regional airports face severe data scarcity. This limits the applicability of machine learning methods and the ability to perform large-scale simulations or "what-if" analyses. In this paper, we investigate whether generative models trained on data-rich airports can be efficiently adapted to data-scarce airports using transfer learning. We adapt state-of-the-art diffusion- and flow-matching-based architectures to the aviation domain and evaluate their transferability between Zurich (source) and Dublin (target) landing trajectory datasets. Models are pretrained on Zurich and fine-tuned on Dublin with varying amounts of local data, ranging from 0% to 100%. Results show that diffusion-based models achieve competitive performance with as little as 5% of the Dublin data and reach baseline-level performance around 20%, consistently outperforming models trained from scratch across metrics and visual inspections. Latent flow matching and latent diffusion models also benefit from pretraining, though with more variable gains, while flow matching models show weaker generalization. Despite challenges in capturing rare trajectory patterns, these findings demonstrate the potential of transfer learning to substantially reduce data requirements for trajectory generation in ATM, enabling realistic synthetic data generation even in environments with limited historical records.

Sara Malacarne, Eirik Hoel-Høiseth, Erlend Aune et al.

We propose C-MTAD-GAT, an \emph{unsupervised}, \emph{context-aware} graph-attention model for anomaly detection in multivariate time series from mobile networks. C-MTAD-GAT combines graph attention with lightweight context embeddings, and uses a deterministic reconstruction head and multi-step forecaster to produce anomaly scores. Detection thresholds are calibrated \emph{without labels} from validation residuals, keeping the pipeline fully unsupervised. On the public TELCO dataset, C-MTAD-GAT consistently outperforms MTAD-GAT and the Telco-specific DC-VAE, two state-of-the-art baselines, in both event-level and pointwise F1, while triggering substantially fewer alarms. C-MTAD-GAT is also deployed in the Core network of a national mobile operator, demonstrating its resilience in real industrial settings.

Abdulmajid Murad, Massimiliano Ruocco

Access to comprehensive flight operations data remains severely restricted in aviation due to commercial sensitivity and competitive considerations, hindering the development of predictive models for operational planning. This paper investigates whether synthetic data can effectively replace real operational data for training machine learning models in pre-tactical aviation scenarios-predictions made hours to days before operations using only scheduled flight information. We evaluate four state-of-the-art synthetic data generators on three prediction tasks: aircraft turnaround time, departure delays, and arrival delays. Using a Train on Synthetic, Test on Real (TSTR) methodology on over 1.7 million European flight records, we first validate synthetic data quality through fidelity assessments, then assess both predictive performance and the preservation of operational relationships. Our results show that advanced neural network architectures, specifically transformer-based generators, can retain 94-97% of real-data predictive performance while maintaining feature importance patterns informative for operational decision-making. Our analysis reveals that even with real data, prediction accuracy is inherently limited when only scheduled information is available-establishing realistic baselines for pre-tactical forecasting. These findings suggest that high-quality synthetic data can enable broader access to aviation analytics capabilities while preserving commercial confidentiality, though stakeholders must maintain realistic expectations about pre-tactical prediction accuracy given the stochastic nature of flight operations.

Michail Spitieris, Massimiliano Ruocco, Abdulmajid Murad et al.

Recent advances in generative AI offer promising solutions for synthetic data generation but often rely on large datasets for effective training. To address this limitation, we propose a novel generative model that learns from limited data by incorporating physical constraints to enhance performance. Specifically, we extend the VAE architecture by incorporating physical models in the generative process, enabling it to capture underlying dynamics more effectively. While physical models provide valuable insights, they struggle to capture complex temporal dependencies present in real-world data. To bridge this gap, we introduce a discrepancy term to account for unmodeled dynamics, represented within a latent Gaussian Process VAE (GPVAE). Furthermore, we apply regularization to ensure the generated data aligns closely with observed data, enhancing both the diversity and accuracy of the synthetic samples. The proposed method is applied to indoor temperature data, achieving state-of-the-art performance. Additionally, we demonstrate that PIGPVAE can produce realistic samples beyond the observed distribution, highlighting its robustness and usefulness under distribution shifts.

Zachari Thiry, Massimiliano Ruocco, Alessandro Nocente et al.

Forecasting indoor temperatures is important to achieve efficient control of HVAC systems. In this task, the limited data availability presents a challenge as most of the available data is acquired during standard operation where extreme scenarios and transitory regimes such as major temperature increases or decreases are de-facto excluded. Acquisition of such data requires significant energy consumption and a dedicated facility, hindering the quantity and diversity of available data. Cost related constraints however do not allow for continuous year-around acquisition. To address this, we investigate the efficacy of data augmentation techniques leveraging SoTA AI-based methods for synthetic data generation. Inspired by practical and experimental motivations, we explore fusion strategies of real and synthetic data to improve forecasting models. This approach alleviates the need for continuously acquiring extensive time series data, especially in contexts involving repetitive heating and cooling cycles in buildings. In our evaluation 1) we assess the performance of synthetic data generators independently, particularly focusing on SoTA AI-based methods; 2) we measure the utility of incorporating synthetically augmented data in a subsequent forecasting tasks where we employ a simple model in two distinct scenarios: 1) we first examine an augmentation technique that combines real and synthetically generated data to expand the training dataset, 2) we delve into utilizing synthetic data to tackle dataset imbalances. Our results highlight the potential of synthetic data augmentation in enhancing forecasting accuracy while mitigating training variance. Through empirical experiments, we show significant improvements achievable by integrating synthetic data, thereby paving the way for more robust forecasting models in low-data regime.

Henrik Hoeiness, Kristoffer Gjerde, Luca Oggiano et al.

Approximating wind flows using computational fluid dynamics (CFD) methods can be time-consuming. Creating a tool for interactively designing prototypes while observing the wind flow change requires simpler models to simulate faster. Instead of running numerical approximations resulting in detailed calculations, data-driven methods and deep learning might be able to give similar results in a fraction of the time. This work rephrases the problem from computing 3D flow fields using CFD to a 2D image-to-image translation-based problem on the building footprints to predict the flow field at pedestrian height level. We investigate the use of generative adversarial networks (GAN), such as Pix2Pix [1] and CycleGAN [2] representing state-of-the-art for image-to-image translation task in various domains as well as U-Net autoencoder [3]. The models can learn the underlying distribution of a dataset in a data-driven manner, which we argue can help the model learn the underlying Reynolds-averaged Navier-Stokes (RANS) equations from CFD. We experiment on novel simulated datasets on various three-dimensional bluff-shaped buildings with and without height information. Moreover, we present an extensive qualitative and quantitative evaluation of the generated images for a selection of models and compare their performance with the simulations delivered by CFD. We then show that adding positional data to the input can produce more accurate results by proposing a general framework for injecting such information on the different architectures. Furthermore, we show that the models performances improve by applying attention mechanisms and spectral normalization to facilitate stable training.

Andreas Kvistad, Massimiliano Ruocco, Eliezer de Souza da Silva et al.

One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are continuously made available to the learner that have to decide whether to request a label or to make a prediction. The goal is to reduce the request rate while at the same time maximize prediction performance. In previous research, reinforcement learning has been used for learning the AL request/prediction strategy. In our work, we propose to equip a reinforcement learning process with memory augmented neural networks, to enhance the one-shot capabilities. Moreover, we introduce Class Margin Sampling (CMS) as an extension of the standard margin sampling to the reinforcement learning setting. This strategy aims to reduce training time and improve sample efficiency in the training process. We evaluate the proposed method on a classification task using empirical accuracy of label predictions and percentage of label requests. The results indicates that the proposed method, by making use of the memory augmented networks and CMS in the training process, outperforms existing baselines.

Johan Phan, Massimiliano Ruocco, Francesco Scibilia

Recently, Convolutional Neural Networks (CNNs) have shown unprecedented success in the field of computer vision, especially on challenging image classification tasks by relying on a universal approach, i.e., training a deep model on a massive dataset of supervised examples. While unlabeled data are often an abundant resource, collecting a large set of labeled data, on the other hand, are very expensive, which often require considerable human efforts. One way to ease out this is to effectively select and label highly informative instances from a pool of unlabeled data (i.e., active learning). This paper proposed a new method of batch-mode active learning, Dual Active Sampling(DAS), which is based on a simple assumption, if two deep neural networks (DNNs) of the same structure and trained on the same dataset give significantly different output for a given sample, then that particular sample should be picked for additional training. While other state of the art methods in this field usually require intensive computational power or relying on a complicated structure, DAS is simpler to implement and, managed to get improved results on Cifar-10 with preferable computational time compared to the core-set method.

Bjørnar Vassøy, Massimiliano Ruocco, Eliezer de Souza da Silva et al.

In recent years session-based recommendation has emerged as an increasingly applicable type of recommendation. As sessions consist of sequences of events, this type of recommendation is a natural fit for Recurrent Neural Networks (RNNs). Several additions have been proposed for extending such models in order to handle specific problems or data. Two such extensions are 1.) modeling of inter-session relations for catching long term dependencies over user sessions, and 2.) modeling temporal aspects of user-item interactions. The former allows the session-based recommendation to utilize extended session history and inter-session information when providing new recommendations. The latter has been used to both provide state-of-the-art predictions for when the user will return to the service and also for improving recommendations. In this work we combine these two extensions in a joint model for the tasks of recommendation and return-time prediction. The model consists of a Hierarchical RNN for the inter-session and intra-session items recommendation extended with a Point Process model for the time-gaps between the sessions. The experimental results indicate that the proposed model improves recommendations significantly on two datasets over a strong baseline, while simultaneously improving return-time predictions over a baseline return-time prediction model.

Silje Christensen, Simen Johnsrud, Massimiliano Ruocco et al.

This work proposes a novel approach based on sequence-to-sequence (seq2seq) models for context-aware conversational systems. Exist- ing seq2seq models have been shown to be good for generating natural responses in a data-driven conversational system. However, they still lack mechanisms to incorporate previous conversation turns. We investigate RNN-based methods that efficiently integrate previous turns as a context for generating responses. Overall, our experimental results based on human judgment demonstrate the feasibility and effectiveness of the proposed approach.

Basant Agarwal, Heri Ramampiaro, Helge Langseth et al.

This paper is concerned with paraphrase detection. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship authentication and question answering. Given two sentences, the objective is to detect whether they are semantically identical. An important insight from this work is that existing paraphrase systems perform well when applied on clean texts, but they do not necessarily deliver good performance against noisy texts. Challenges with paraphrase detection on user generated short texts, such as Twitter, include language irregularity and noise. To cope with these challenges, we propose a novel deep neural network-based approach that relies on coarse-grained sentence modeling using a convolutional neural network and a long short-term memory model, combined with a specific fine-grained word-level similarity matching model. Our experimental results show that the proposed approach outperforms existing state-of-the-art approaches on user-generated noisy social media data, such as Twitter texts, and achieves highly competitive performance on a cleaner corpus.

Massimiliano Ruocco, Ole Steinar Lillestøl Skrede, Helge Langseth

In recent years, research has been done on applying Recurrent Neural Networks (RNNs) as recommender systems. Results have been promising, especially in the session-based setting where RNNs have been shown to outperform state-of-the-art models. In many of these experiments, the RNN could potentially improve the recommendations by utilizing information about the user's past sessions, in addition to its own interactions in the current session. A problem for session-based recommendation, is how to produce accurate recommendations at the start of a session, before the system has learned much about the user's current interests. We propose a novel approach that extends a RNN recommender to be able to process the user's recent sessions, in order to improve recommendations. This is done by using a second RNN to learn from recent sessions, and predict the user's interest in the current session. By feeding this information to the original RNN, it is able to improve its recommendations. Our experiments on two different datasets show that the proposed approach can significantly improve recommendations throughout the sessions, compared to a single RNN working only on the current session. The proposed model especially improves recommendations at the start of sessions, and is therefore able to deal with the cold start problem within sessions.

Massimiliano Ruocco, Heri Ramampiaro

Media sharing applications, such as Flickr and Panoramio, contain a large amount of pictures related to real life events. For this reason, the development of effective methods to retrieve these pictures is important, but still a challenging task. Recognizing this importance, and to improve the retrieval effectiveness of tag-based event retrieval systems, we propose a new method to extract a set of geographical tag features from raw geo-spatial profiles of user tags. The main idea is to use these features to select the best expansion terms in a machine learning-based query expansion approach. Specifically, we apply rigorous statistical exploratory analysis of spatial point patterns to extract the geo-spatial features. We use the features both to summarize the spatial characteristics of the spatial distribution of a single term, and to determine the similarity between the spatial profiles of two terms -- i.e., term-to-term spatial similarity. To further improve our approach, we investigate the effect of combining our geo-spatial features with temporal features on choosing the expansion terms. To evaluate our method, we perform several experiments, including well-known feature analyses. Such analyses show how much our proposed geo-spatial features contribute to improve the overall retrieval performance. The results from our experiments demonstrate the effectiveness and viability of our method.