Distributed Acoustic Sensing (DAS) enables large-scale monitoring through optical fibers, but its high dimensionality and complex spatio-temporal patterns make event classification demanding. Existing deep learning approaches–CNNs, recurrent models, and Transformer variants–either fail to capture long-range dependencies or require processing raw DAS matrices at prohibitive cost. We propose DAStatFormer, a hybrid multibranch Transformer that combines compact multidomain statistical features with Gated Transformer Networks. Instead of raw signals, we extract 24 ANOVA-selected attributes per channel from the temporal, waveform, and spectral domains, reducing data size by orders of magnitude while preserving discriminative information. Each domain is processed via dedicated step-wise and channel-wise attention branches, fused by an adaptive gating mechanism. Experiments on the open ϕ -OTDR benchmark and a real-scenario DAS dataset show that DAStatFormer achieves up to 99.4 https://github.com/MichelD-git/DAStatFormer

Distributed Acoustic Sensing (DAS) technology has emerged as a powerful tool for large-scale acoustic monitoring, transforming standard fiber optic cables into dense arrays of virtual microphones. When combined with artificial intelligence, particularly deep learning, DAS enables scalable and automated detection of acoustic events, making it a promising solution for whale monitoring across vast marine environments. In the field of marine bioacoustics, DAS provides significant advantages in terms of spatial coverage and robustness compared to traditional hydrophone arrays. This paper presents a novel deep learning-based approach to detect whale vocalizations from DAS data. The proposed method leverages a hybrid architecture combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks to extract both spatial and temporal features from waterfall diagrams derived from DAS recordings. A multi-stage preprocessing pipeline including frequency filtering and frequency-wavenumber (f-k) filtering is applied to enhance signal quality and isolate whale calls from background noise. Each DAS recording is treated as a spatio-temporal matrix, and sequences of such matrices are sequentially analyzed capturing temporal dependencies. Experimental evaluations on a public dataset from the Ocean Observatories Initiative (OOI) RCA North Cable demonstrate that the CNN-BiLSTM model outperforms CNN and CNN-LSTM baselines, achieving a F1-score of 96

Associative classification models are valuable for discovering relationships within heterogeneous data systems, making them particularly useful for data integration tasks. However, they struggle with imbalanced and sparse data. This paper addresses the problem of imbalanced classification in building maintenance data by providing several updates based both on algorithms and preprocessing. Experiments conducted on real maintenance datasets demonstrate significant improvements in accuracy and precision.

Distributed Acoustic Sensing (DAS) offers a scalable and resilient solution for real-time perimeter security by transforming optical fibers into dense arrays of vibration sensors. However, its high-dimensional, noisy, and spatio-temporally complex data make accurate event recognition challenging. Conventional deep learning models, such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, often struggle to capture long-range dependencies and rely heavily on handcrafted or single-domain features, limiting their effectiveness in complex intrusion scenarios. Designing compact and discriminative feature representations remains a critical challenge. To address these issues, we propose DASViT1D, a novel intrusion detection framework that integrates a one-dimensional Vision Transformer (ViT1D) with fused multi-domain features. Specifically, we extract and combine Mel-Frequency Cepstral Coefficients (MFCC), Redundant Discrete Fourier Transform (RDFT), and Discrete Wavelet Transform (DWT) features to capture complementary spectral and temporal characteristics. ViT1D then leverages self-attention to model long-range dependencies across time. Evaluated on a public.-OTDR DAS dataset with nine event classes, our approach achieves 93.5% accuracy, outperforming CNN-based baselines by nearly 8 points, with a false negative rate (FNR) of 0.009, a nuisance alarm rate (NAR) of 0.005, and fast inference (0.13 s/sample), demonstrating its suitability for real-time DAS-based intrusion detection.

Gradual patterns, capturing intricate attribute co-variations expressed as ”when X increases/decreases, Y increases/decreases” in numerical data, play a vital role in managing vast volumes of complex numerical data in real-world applications. Recently, the data science community has focused on efficient extraction methods for gradual patterns from temporal data. However, there is a notable gap in approaches addressing the extraction of gradual patterns that capture seasonality from the graduality point of view in the temporal data sequences, despite their potential to yield valuable insights in applications such as e-commerce. This paper proposes a new method for extracting co-variations of periodically repeating attributes termed as seasonal gradual patterns. To achieve this, we formulate the task of mining seasonal gradual patterns as the problem of mining periodic patterns in multiple sequences and then, leverage periodic pattern mining algorithms to extract seasonal gradual patterns. Additionally, we propose a new antimonotonic support definition associated with these seasonal gradual patterns. Illustrative results from real-world datasets demonstrate the efficiency of the proposed approach and its ability to sift through numerous non-seasonal patterns to identify the seasonal ones.

Heating, ventilation, and air-conditioning (HVAC) equipment faults and operational errors result in comfort issues and waste of energy in buildings. An Automatic Fault Detection and Diagnosis (AFDD) tool could help facility managers fix comfort and energy issues more efficiently, by identifying the most probable root causes. Existing AFDD methods mostly focus on equipment-level fault detection and diagnostics ; almost no attention is given to building level fault diagnosis, considering inter-dependency between equipment through the energy distribution chain. In this work we propose a methodology to automatically derive a Bayesian network from HVAC system topology description such as Haystack. This Bayesian network models and estimates the state of all elements in the system, helping users to identify the most probable root fault. As it is able to ingest evidence from any source (field data, operators, or other models) and is capable of updating its estimates when new evidence is delivered, such a tool could have a great potential to be used interactively on the field. We applied the proposed methodology on simulated and real-world buildings and present in this paper one specific case.

Enhancing the convective heat transfer is essential in solar applications for efficiency improvement. This can be achieved using Vortex Generators (VGs). Previous studies have focused on distinguishing the best VGs design while considering single VGs row configuration. In this paper, a study is conducted on investigating the effect of using multiple VGs rows configuration with varying longitudinal pitch (LP) separating the rows at Reynolds number Re = 2000. Then, the effect of increasing the air flow rate is studied by varying Re in the range of 2000-10,000. The SST k-omega model is chosen to model the turbulence at high Re. Validation is performed by comparing the numerical results to numerical and experimental data from the open literature. The best configuration is obtained when using five VGs rows with LP = 3H which increases the thermal enhancement factor by 69 % and 90 % with respect to empty channel configuration at Re = 2000 and 10,000 respectively. Then, local analyses are performed to better understand the physics behind the heat transfer enhancement in the best configuration. Finally, Nusselt number and friction factor correlations are developed to be representative of a dynamic model of photovoltaic/thermal (PVT) systems with vortex generators.

In complex real-world decision problems, ensuring safety and addressing uncertainties are crucial aspects. In this work, we present an uncertainty-aware Reinforcement Learning agent designed for risk-sensitive applications in continuous action spaces. Our method quantifies and leverages both epistemic and aleatoric uncertainties to enhance agent's learning and to incorporate risk assessment into decision-making processes. We conduct numerical experiments to evaluate our work on a modified version of Lunar Lander with variable and risky landing conditions. We show that our method outperforms both Deep Deterministic Policy Gradient (DDPG) and TD3 algorithms by reducing collisions and having significant faster training. In addition, it enables the trained agent to learn a risk-sensitive policy that balances performance and risk based on a specific level of sensitivity to risk required for the task.

Photo-Voltaic/Thermal (PVT) system performance is defined by two main factors, the electric power generated from the Photo-Voltaic (PV) module, and the thermal power that is extracted from the PVT module. To increase the energy output, several control techniques can be applied. In the present work, a Economic model predictive Control (EMPC) strategy is used to enhance the performance of the PVT system. A dynamic model for the PVT system is developed using the Modelica language in the Dynamic Modeling Laboratory software (DYMOLA). Then, EMPC controller is defined in Matlab/Simulink. Two geometrical cases for the duct side of the PVT system are studied as different heat intensification techniques. First, an empty channel is considered and then vortex generators (VGs) are inserted into the channel. Simulations are carried out with summer and winter days in the north of France with two energy use scenarios referred to as no heat recovery (NHR) and heat recovery (HR) scenarios. The results showed that when using an EMPC controller with a heat recovery scenario the energy gain increases by 174% and 234% for empty channel and for vortex generator geometrical cases respectively. In order to better analyze the obtained results, cell temperature and mass flow rate are plotted for all the studied scenarios as a function of time. Finally, power generation as a function of irradiance is plotted in order to distinguish when the benefits of cooling out-weight its cost.

: Real-world decision problems, such as Domestic Hot Water (DHW) production, require the consideration of multiple, possibly conflicting objectives. This work suggests an adaptation of Deep Q-Networks (DQN) to solve multi-objective sequential decision problems using scalarization functions. The adaptation was applied to train multiple agents to control DHW systems in order to find possible trade-offs between comfort and energy cost reduction. Results have shown the possibility of finding multiple policies to meet preferences of different users. Trained agents were tested to ensure hot water production with variable energy prices (peak and off-peak tariffs) for several consumption patterns and they can reduce energy cost from 10.24 % without real impact on users’ comfort and up to 18 % with slight impact on comfort.

Several works have been conducted to promote a standard for exchanging building data. However, during the operation and maintenance phase of a building, there is still no emerging standard. Existing solutions continue to require manual tasks to match and share data and information among various actors such as owners, service providers, and occupants. This process becomes tedious due to the large volume of exchanged data, hence there is a need to find other ways of matching and identifying association rules between data of different views. In this paper we propose a new associative classification approach that integrates multi-criteria analysis at the association rule ranking level, and some application for data matching and system interoperability. We conducted experiments on both real building maintenance data sets and some UCI Machine Learning data sets, and the results show that our approach achieves good precision/accuracy and produces a less complex classifier that is easily exploitable by business experts.

This paper proposes a data-driven method for the detection and isolation of open-circuit faults in multi-phase inverters using measurements of the motor currents. First, feature variables are formulated in terms of the averages of the phase currents and their absolute values. Next, by using an AUto-adaptive and Dynamical Clustering (AUDyC) based on Gaussian Mixture Models, feature data is clustered into different classes characterizing normal and faulty operation modes. Afterwards, these classes are used for deriving appropriate conditions for detecting and labelling faults. The proposed method requires minimal knowledge about the system operation. Furthermore, it allows us to update our knowledge of existing faults online, thus making it possible to detect unknown faults. Moreover, conditions are formulated to describe the influence of the method parameters on the detection time. Once parameters are tuned, the accuracy of the proposed method is illustrated on various experimental data sets, where single and double faults are detected with detection times in the order of the fundamental signal period.

Simulating human activities remains a challenging problem because the decision-making mechanisms underlying these activities are difficult to reproduce and mimic. In this article, we are interested in the simulation of in-store shoppers whose activities are generally divided into two parts: a walking activity and a purchase activity. Since the act of buying is more complex than simply following a shopping list, we propose here to model the attraction relationships that can exist between a product and a customer. This attraction model is used to build a multi-agent simulation whose realism is evaluated through various experiments.

In building simulation, internal heat gains correspond to heat production by human metabolism or electrical devices use. It is one of the most uncertain model inputs and could have an important impact on building simulation results. This study proposes a method to investigate the influence of the internal heat gains uncertainties by separating the uncertainty on the internal heat gains of the entire building, the uncertainty on the spatial distribution and its evolution on time. The uncertainty sources are propagated independently in a dynamic thermal simulation (DTS). The temperature of each zone at each moment is analyzed. In order to simplify this study, the most representing temperatures are selected with a method based on cumulative variances and a clustering algorithm. This approach is applied on an office building in France. The data coming from a one year monitoring period, provide information to reduce the uncertainties about the real internal heat gains. The results indicate that the effects of the internal heat gains uncertainties are time dependent. They also depend on the heating scenario of the thermal zone (heated or not-heated). At last, the temperatures are mainly influenced by the uncertainty on the internal heat gains of the entire building.

Gradual patterns that capture co-variation of complex attributes in the form “when X increases/decreases, Y increases/decreases” play an important role in many real world applications where huge volumes of complex numerical data must be handled. More recently, they have received attention from the data mining community for exploring temporal data and methods have been defined to automatically extract gradual patterns from temporal data. However, to the best of our knowledge, no method has been proposed to extract gradual patterns that always appear at the identical time intervals in the sequences of temporal data, despite the knowledge that such patterns may bring for certain applications such as e-commerce. This paper proposes to extract co-variations of periodically repeating attributes from the sequences of temporal data that we call seasonal gradual patterns. We discuss the specific features of these patterns and propose an approach for their extraction by exploiting a motif mining algorithm in a sequence, and justify its applicability to the gradual case. Illustrative results obtained from a real world data set are described and show the interest for such patterns.

Considerable efforts have been made to find a reliable model able to accurately describe and predict the thermal behavior of the indoor environment of a building. Such a model is essential, in particular, for designing climate control strategies for optimizing both the comfort level and the energy consumption. However, a building is a complex system characterized by a nonlinear thermal behavior, so the task to find such a reliable model is rather difficult. This paper aims at overcoming some of these difficulties by presenting a data driven approach based on a switched system identification to detect and model the thermal behavior of a building zone during normal usage. The proposed technique relies on a PieceWise AutoRegressive model with eXogeneous inputs (PWARX) consisting of a set of sub-models with each one of them describing a certain configuration/state of the dwelling, e.g. turning the heating ON/OFF or opening/closing windows, doors and shutters. The approach is data-driven, easy to implement and its computational time is inferior to creating a detailed model under a specialized software. Therefore, it is particularly suitable for providing a quick description of the thermal behavior of existing buildings for which it is possible to install sensors and perform measurements. Using the available measurements, the algorithm is able to detect various configurations as will be shown by two numerical examples. Such a collection of sub-models provides a better temperature estimate than using ARX models, so it will eventually allow to select better strategies for improving energy efficiency.