Power Quality Disturbance Monitoring and Classification Based on Improved PCA and Convolution Neural Network for Wind-Grid Distribution Systems

Shen, Yue; Abubakar, Muhammad; Liu, Hui; Hussain, Fida

doi:10.3390/en12071280

Cited by 95 publications

(57 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, we only compared recent related work based on conventional machine learning methods for END PCA is commonly used to reduce the high-dimensional space of the deep features extracted using DCNNs. It was used extensively in References [39][40][41][42][43][44][45][46] to lower the dimension of deep features used in training SVM classifiers and to also lower the SVM's complexity. SVM classifiers have very effective performance in classification tasks with limited training samples.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Techniques for Automatic Detection of Embryonic Neurodevelopmental Disorders

2020

View full text Add to dashboard Cite

The increasing rates of neurodevelopmental disorders (NDs) are threatening pregnant women, parents, and clinicians caring for healthy infants and children. NDs can initially start through embryonic development due to several reasons. Up to three in 1000 pregnant women have embryos with brain defects; hence, the primitive detection of embryonic neurodevelopmental disorders (ENDs) is necessary. Related work done for embryonic ND classification is very limited and is based on conventional machine learning (ML) methods for feature extraction and classification processes. Feature extraction of these methods is handcrafted and has several drawbacks. Deep learning methods have the ability to deduce an optimum demonstration from the raw images without image enhancement, segmentation, and feature extraction processes, leading to an effective classification process. This article proposes a new framework based on deep learning methods for the detection of END. To the best of our knowledge, this is the first study that uses deep learning techniques for detecting END. The framework consists of four stages which are transfer learning, deep feature extraction, feature reduction, and classification. The framework depends on feature fusion. The results showed that the proposed framework was capable of identifying END from embryonic MRI images of various gestational ages. To verify the efficiency of the proposed framework, the results were compared with related work that used embryonic images. The performance of the proposed framework was competitive. This means that the proposed framework can be successively used for detecting END.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning Techniques for Automatic Detection of Embryonic Neurodevelopmental Disorders

2020

View full text Add to dashboard Cite

show abstract

“…The study [9] by Yue Shen et al, "Power Quality Disturbance Monitoring and Classification Based on Improved PCA and Convolution Neural Network for Wind-Grid Distribution Systems", falls within the set "statistical signal processing (SSP) and intelligent methods for PQ analysis". The authors made a deep revision on signal processing and the multivariate techniques applied to feature extraction in PQ contexts.…”

Section: A Short Review Of the Contributions In This Issuementioning

confidence: 99%

Special Issue “Analysis for Power Quality Monitoring”

de-la-Rosa

Pérez-Donsión

2020

Energies

View full text Add to dashboard Cite

We are immersed in the so-called digital energy network, continuously introducing new technological advances for a better way of life. As a consequence, numerous emerging words are relevant to this point: Internet of Things (IoT), big data, smart cities, smart grid, industry 4.0, etc. To achieve this formidable goal, systems should work more efficiently, a fact that inevitably leads to power quality (PQ) assurance. Apart from its economic losses, a bad PQ implies serious risks for machines and, consequently, for people. Many researchers are endeavouring to develop new analysis techniques, instruments, measurement methods, and new indices and norms that match and fulfil the requirements regarding the current operation of the electrical network. This book, and its associated Special Issue, offer a compilation of some of the recent advances in this field. The chapters range from computing to technological implementation, going through event detection strategies and new indices and measurement methods that contribute significantly to the advance of PQ analysis and regulation. Experiments have been developed within the frameworks of research units and projects and deal with real data from industry practice and public buildings. Human beings have an unavoidable commitment to sustainability, which implies adapting PQ monitoring techniques to our dynamic world, defining a digital and smart concept of quality for electricity.

show abstract

“…To assess the quality of the release signal, utility providers may be interested in several different indicators. These include, for instance, the mean, skewness, kurtosis, standard deviation to mean ratio, and maximum to mean ratio [48]. Thus, for completeness, we present these indicators in Table II for three different cases along the privacy-utility trade off curve.…”

Section: ) Inference Of Households Occupancymentioning

confidence: 99%

Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release

Shateri

Messina

Piantanida

et al. 2019

2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

View full text Add to dashboard Cite

Smart Meters (SMs) are an important component of smart electrical grids, but they have also generated serious concerns about privacy data of consumers. In this paper, we present a general formulation of the privacy-preserving problem in SMs from an information-theoretic perspective. In order to capture the casual time series structure of the power measurements, we employ Directed Information (DI) as an adequate measure of privacy. On the other hand, to cope with a variety of potential applications of SMs data, we study different distortion measures along with the standard squared-error distortion. This formulation leads to a quite general training objective (or loss) which is optimized under a deep learning adversarial framework where two Recurrent Neural Networks (RNNs), referred to as the releaser and the attacker, are trained with opposite goals. An exhaustive empirical study is then performed to validate the proposed approach for different privacy problems in three actual data sets. Finally, we study the impact of the data mismatch problem, which occurs when the releaser and the attacker have different training data sets and show that privacy may not require a large level of distortion in real-world scenarios.

show abstract

Power Quality Disturbance Monitoring and Classification Based on Improved PCA and Convolution Neural Network for Wind-Grid Distribution Systems

Cited by 95 publications

References 64 publications

Deep Learning Techniques for Automatic Detection of Embryonic Neurodevelopmental Disorders

Deep Learning Techniques for Automatic Detection of Embryonic Neurodevelopmental Disorders

Special Issue “Analysis for Power Quality Monitoring”

Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release

Contact Info

Product

Resources

About