High-dimensional time series increasingly arise in the Internet of Energy (IoE), given the use of multi-sensor environments and the two way communication between energy consumers and the smart grid. ...Therefore, methods that are capable of computing high-dimensional time series are of great value in smart building and IoE applications. Fuzzy Time Series (FTS) models stand out as data-driven non-parametric models of easy implementation and high accuracy. Unfortunately, the existing FTS models can be unfeasible if all variables were used to train the model. We present a new methodology named Embedding Fuzzy Time Series (EFTS), by applying a combination of data embedding transformation and FTS methods. The EFTS is an explainable and data-driven approach, which is flexible and adaptable for many smart building and IoE applications. The experimental results with three public datasets show that our methodology outperforms several machine learning based forecasting methods (LSTM, GRU, TCN, RNN, MLP and GBM), and demonstrates the accuracy and parsimony of the EFTS in comparison to the baseline methods and the results previously published in the literature, showing an enhancement greater than 80%. Therefore, EFTS has a great value in high-dimensional time series forecasting in IoE applications.
•New methods for handling high-dimensional time series in IoE.•Combining data embedding transformation and fuzzy time series.•Proposed methods outperform several machine learning methods.•Enhancement greater than 80% in skill score compared to other methods.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Fuzzy cognitive maps (FCMs) have demonstrated considerable success in time series forecasting and are adept at handling uncertainties and capturing the dynamics of complex systems. Nevertheless, ...challenges still remain in the handling of multivariate high-dimensional time series using a time-effective learning algorithm. This article introduces multiple-input multiple-output randomized high-order FCM (MRHFCM), a new methodology for predicting high-dimensional time series in multiple-input-multiple-output systems. MRHFCM represents a hybrid method that combines data embedding transformation, randomized high-order FCM (R-HFCM), and an echo state network. The core of MRHFCM involves a cascade of R-HFCMs termed the CR-HFCM model. Each CR-HFCM comprises three layers: 1) the input layer, 2) reservoir (internal layer), and 3) output layer. Notably, only the output layer is trainable, employing the least squares minimization algorithm. The weights within each subreservoir are randomly chosen and remain unchanged throughout the training procedure. Three real-world high-dimensional datasets are utilized to assess the performance of the proposed MRHFCM method. The results obtained reveal that our approach outperforms some existing baseline and state-of-the-art machine learning and deep learning forecasting techniques in terms of both accuracy and parsimony.
Deep learning has revolutionized medical image segmentation, but it relies heavily on high-quality annotations. The time, cost and expertise required to label images at the pixel-level for each new ...task has slowed down widespread adoption of the paradigm. We propose Pix2Rep, a self-supervised learning (SSL) approach for few-shot segmentation, that reduces the manual annotation burden by learning powerful pixel-level representations directly from unlabeled images. Pix2Rep is a novel pixel-level loss and pre-training paradigm for contrastive SSL on whole images. It is applied to generic encoder-decoder deep learning backbones (e.g., U-Net). Whereas most SSL methods enforce invariance of the learned image-level representations under intensity and spatial image augmentations, Pix2Rep enforces equivariance of the pixel-level representations. We demonstrate the framework on a task of cardiac MRI segmentation. Results show improved performance compared to existing semi- and self-supervised approaches; and a 5-fold reduction in the annotation burden for equivalent performance versus a fully supervised U-Net baseline. This includes a 30% (resp. 31%) DICE improvement for one-shot segmentation under linear-probing (resp. fine-tuning). Finally, we also integrate the novel Pix2Rep concept with the Barlow Twins non-contrastive SSL, which leads to even better segmentation performance.
In the internet of things (IoT), high-dimensional time series data are generated continuously and recorded from different data sources; moreover, these time series are characterized by intrinsic ...changes known as concept drifts. Beside, decision-making in IoT applications may often involve multiple factors and criteria. Therefore, methods capable of handling high-dimensional non-stationary time series and many outputs are of great value in IoT applications. An important gap in the literature is the absence of fuzzy time series (FTS) multiple-input multiple-output (MIMO) methods. To fill this gap, we present a new methodology for forecasting high-dimensional non-stationary time series called MO-ENSFTS (multiple output embedding non-stationary fuzzy time series). MO-ENSFTS is a first-order MIMO multivariate model. We apply a combination of data embedding transformation and a non-stationary FTS model. We tested the proposed methodology on four real-world high-dimensional IoT time-series data sets. The proposed approach is a data-driven method, which is flexible and adaptable for many IoT applications. The computational results show that the proposed method outperforms recurrent neural networks, random forests and support vector regression methods, and is more parsimonious than deep learning methods.
Full text
Available for:
DOBA, EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, IZUM, KILJ, KISLJ, MFDPS, NLZOH, NUK, ODKLJ, OILJ, PILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UILJ, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
The prediction of residential power usage is essential in assisting a smart grid to manage and preserve energy to ensure efficient use. An accurate energy forecasting at the customer level will ...reflect directly into efficiency improvements across the power grid system, however forecasting building energy use is a complex task due to many influencing factors, such as meteorological and occupancy patterns. In addiction, high-dimensional time series increasingly arise in the Internet of Energy (IoE), given the emergence of multi-sensor environments and the two way communication between energy consumers and the smart grid. Therefore, methods that are capable of computing high-dimensional time series are of great value in smart building and IoE applications. Fuzzy Time Series (FTS) models stand out as data-driven non-parametric models of easy implementation and high accuracy. Unfortunately, the existing FTS models can be unfeasible if all features were used to train the model. We present a new methodology for handling high-dimensional time series, by projecting the original high-dimensional data into a low dimensional embedding space and using multivariate FTS approach in this low dimensional representation. Combining these techniques enables a better representation of the complex content of multivariate time series and more accurate forecasts.