Anomaly Detection and Repair for Accurate Predictions in Geo-distributed Big Data

Corizzo, Roberto; Ceci, Michelangelo; Japkowicz, Nathalie

doi:10.1016/j.bdr.2019.04.001

Cited by 50 publications

(27 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Investigators and practitioners have developed projects optimizing PV systems [19,20] and studied the influence of meteorological variables [21][22][23]. Researchers have presented procedures in photovoltaic generation forecasting to mitigate uncertainty [24][25][26], with the aim to incorporate the spatial correlation of PV modules [27] or reducing fuel consumption in a hybrid system (with a diesel generator and photovoltaic resources) [28]. In the water industry, many works have been performed in pressurized water networks [19,[29][30][31] and in pressurized irrigation networks [32][33][34] where the energy consumption profiles influence the PV installation [35][36][37].…”

Section: Introductionmentioning

confidence: 99%

Converting a Water Pressurized Network in a Small Town into a Solar Power Water System

Pardo

Fernández²,

Jódar-Abellán

2020

Energies

View full text Add to dashboard Cite

The efficient management of water and energy is one challenge for managers of water pressurized systems. In a scheme with high pressure on the environment, solar power appears as an opportunity for nonrenewable energy expenditure reduction and emissions elimination. In Spain, new legislation that eliminates old taxes associated with solar energy production, a drop in the cost of solar photovoltaic modules, and higher values of irradiance has converted solar powered water systems into one of the trendiest topics in the water industry. One alternative to store energy (compulsory in standalone photovoltaic systems) when managing pressurized urban water networks is the use of head tanks (tanks accumulate water during the day and release it at night). This work intends to compare the pressurized network running as a standalone system and a hybrid solution that incorporates solar energy supply and electricity grids. The indicator used for finding the best choice is the net present value for the solar power water system lifespan. This study analyzed the possibility of transferring the energy surplus obtained at midday to the electricity grid, a circumstance introduced in the Spanish legislation since April 2019. We developed a real case study in a small town in the Alicante Province, whose findings provide planning policymakers with very useful information in this case and similar case studies

show abstract

Section: Introductionmentioning

confidence: 99%

Converting a Water Pressurized Network in a Small Town into a Solar Power Water System

Pardo

Fernández²,

Jódar-Abellán

2020

Energies

View full text Add to dashboard Cite

show abstract

“…Some simple algorithms, such as AutoRegressive Integrated Moving Average (ARIMA) [33], k-nearest neighbors and linear regression, show a moderate computational cost and good prediction performances in many scenarios when the task is that of prediction or forecasting with a limited time horizon. Other algorithms, such as Neural Networks and deep neural networks [34], show a higher predictive accuracy and the ability to consider nonlinearity in the in data, at the cost of a higher computational complexity.…”

Section: Distributed Methods For Multi-target Regressionmentioning

confidence: 99%

DENCAST: distributed density-based clustering for multi-target regression

et al. 2019

Self Cite

View full text Add to dashboard Cite

The generation of massive amounts of data in different forms (such as activity logs and sensor measurements) has increased the need for novel data mining algorithms, which are capable of building accurate models efficiently and in a distributed fashion. In recent years, several researchers proposed novel approaches to distribute the workload among several machines for classical clustering, classification and regression tasks [1]. However, only a few of them tackle the specific problem of density-based clustering. This problem has received much attention in the last decades, because of many desirable properties of the extracted clusters (arbitrarily-shaped, noise-free, robustness to outliers) which turn out the be useful in many application domains (e.g., spatial data analysis). Starting from the seminal work of DBSCAN [2], many algorithms have been proposed, but only a few of them are distributed. Unfortunately, existing distributed methods for density-based clustering suffer from several limitations. In particular, they are limited to data organized in a specific structure (e.g., they can analyze only low-dimensional feature spaces), or they suffer from overhead and scalability issues when the number of instances and attributes increase considerably [3-5]. These limitations depend from the

show abstract

“…The rationale of this process is to use convolution as an efficient way to extract a new compact and effective feature representation from raw data, simplifying the subsequent classification task. This capability of neural networks has also been fruitfully exploited in order to extract feature vector representations for predictive tasks also in the context of graph data [18,19] and time series data [20,21]. Feature fusion can also be found in other articles [22,23].…”

Section: Introductionmentioning

confidence: 99%

“…Network training is performed on the modified deep neural network. Subsequently, we exploit fine-tuned CNNs for feature extraction and utilize the extracted features for the training of SVM classifiers, which have been successfully applied in other image classification and transfer learning problems [20,24,30]. In this paper, SVMs are implemented in two versions: with linear kernel and with Radial Basis Function (RBF) kernel.…”

Section: Introductionmentioning

confidence: 99%

Aerial Scene Classification through Fine-Tuning with Adaptive Learning Rates and Label Smoothing

Petrovska¹,

Atanasova-Pacemska

Corizzo

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained Convolutional Neural Networks (CNNs). A common approach in the literature is employing CNNs for feature extraction, and subsequently train classifiers exploiting such features. In this paper, we propose the adoption of transfer learning by fine-tuning pre-trained CNNs for end-to-end aerial image classification. Our approach performs feature extraction from the fine-tuned neural networks and remote sensing image classification with a Support Vector Machine (SVM) model with linear and Radial Basis Function (RBF) kernels. To tune the learning rate hyperparameter, we employ a linear decay learning rate scheduler as well as cyclical learning rates. Moreover, in order to mitigate the overfitting problem of pre-trained models, we apply label smoothing regularization. For the fine-tuning and feature extraction process, we adopt the Inception-v3 and Xception inception-based CNNs, as well the residual-based networks ResNet50 and DenseNet121. We present extensive experiments on two real-world remote sensing image datasets: AID and NWPU-RESISC45. The results show that the proposed method exhibits classification accuracy of up to 98%, outperforming other state-of-the-art methods.

show abstract

Anomaly Detection and Repair for Accurate Predictions in Geo-distributed Big Data

Cited by 50 publications

References 37 publications

Converting a Water Pressurized Network in a Small Town into a Solar Power Water System

Converting a Water Pressurized Network in a Small Town into a Solar Power Water System

DENCAST: distributed density-based clustering for multi-target regression

Aerial Scene Classification through Fine-Tuning with Adaptive Learning Rates and Label Smoothing

Contact Info

Product

Resources

About