scholarly journals Non-Intrusive Load Disaggregation by Linear Classifier Group Considering Multi-Feature Integration

2019 ◽  
Vol 9 (17) ◽  
pp. 3558 ◽  
Author(s):  
Jinying Yu ◽  
Yuchen Gao ◽  
Yuxin Wu ◽  
Dian Jiao ◽  
Chang Su ◽  
...  
Keyword(s):  
Identification Accuracy ◽  
Data Set ◽  
Linear Discriminant ◽  
Practical Applications ◽  
Core Technology ◽  
Open Source Data ◽  
Source Data ◽  
Load Monitoring ◽  
Global Similarity ◽  
Linear Discriminant Classifier

Non-intrusive load monitoring (NILM) is a core technology for demand response (DR) and energy conservation services. Traditional NILM methods are rarely combined with practical applications, and most studies aim to disaggregate the whole loads in a household, which leads to low identification accuracy. In this method, the event detection method is used to obtain the switching event sets of all loads, and the power consumption curves of independent unknown electrical appliances in a period are disaggregated by utilizing comprehensive features. A linear discriminant classifier group based on multi-feature global similarity is used for load identification. The uniqueness of our algorithm is that it designs an event detector based on steady-state segmentation and a linear discriminant classifier group based on multi-feature global similarity. The simulation is carried out on an open source data set. The results demonstrate the effectiveness and high accuracy of the multi-feature integrated classification (MFIC) algorithm by using the state-of-the-art NILM methods as benchmarks.

scholarly journals Non-Intrusive Load Disaggregation by Linear Classifier Group Considering Multi-Feature Integration

2019 ◽  
Author(s):  
Jinying Yu ◽  
Yuxin Wu ◽  
Chang Su
Keyword(s):  
Identification Accuracy ◽  
Linear Discriminant ◽  
Practical Applications ◽  
Usage Frequency ◽  
Core Technology ◽  
Load Monitoring ◽  
Load Disaggregation ◽  
Event Based ◽  
Global Similarity ◽  
Linear Discriminant Classifier

Non-intrusive load monitoring (NILM) is a core technology for demand response (DR) and energy conservation services. Traditional NILM methods are rarely combined with practical applications, and most studies aim to decompose the whole loads in a household, which leads to low identification accuracy. In this paper, an NILM approach based on multi-feature integrated classification (MFIC) is explored, which combines some non-electrical features such as ON/OFF duration, usage frequency of appliances, and usage period to improve load differentiability. The implementation of MFIC algorithm is consistent with traditional event-based method. The uniqueness of our algorithm is that it designs an event detector based on steady-state segmentation and a linear discriminant classifier group based on multi-feature global similarity. Simulation results using an open-access dataset demonstrate the effectiveness and high accuracy of MFIC algorithm, with the state-of-the-art NILM methods as benchmarks.

Workshop Preview: Data Analytics and Machine Learning Hackathon 2021: A deep dive into the open-source data challenge for E&P

2021 ◽  
Vol 40 (1) ◽  
pp. 68-71
Author(s):  
Haibin Di ◽  
Anisha Kaul ◽  
Leigh Truelove ◽  
Weichang Li ◽  
Wenyi Hu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Analytics ◽  
Learning Experience ◽  
Data Set ◽  
Deep Dive ◽  
Open Source Data ◽  
Research Workshop ◽  
Hands On ◽  
Source Data ◽  
Exploration And Production

We present a data challenge as part of the hackathon planned for the August 2021 SEG Research Workshop on Data Analytics and Machine Learning for Exploration and Production. The hackathon aims to provide hands-on machine learning experience for beginners and advanced practitioners, using a relatively well-defined problem and a carefully curated data set. The seismic data are from New Zealand's Taranaki Basin. The labels for a subset of the data have been generated by an experienced geologist. The objective of the challenge is to develop innovative machine learning solutions to identify key horizons.

scholarly journals A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements

Energies ◽  
2021 ◽  
Vol 14 (21) ◽  
pp. 7410
Author(s):  
Netzah Calamaro ◽  
Moshe Donko ◽  
Doron Shmilovitz
Keyword(s):  
Sampling Rate ◽  
Identification Accuracy ◽  
Spectral Space ◽  
Data Set ◽  
Device Identification ◽  
Fast Training ◽  
Electrical Devices ◽  
Load Monitoring ◽  
Spectral Algorithm ◽  
Recorded Data

The central problems of some of the existing Non-Intrusive Load Monitoring (NILM) algorithms are indicated as: (1) higher required electrical device identification accuracy; (2) the fact that they enable training over a larger device count; and (3) their ability to be trained faster, limiting them from usage in industrial premises and external grids due to their sensitivity to various device types found in residential premises. The algorithm accuracy is higher compared to previous work and is capable of training over at least thirteen electrical devices collaboratively, a number that could be much higher if such a dataset is generated. The algorithm trains the data around 1.8×108 faster due to a higher sampling rate. These improvements potentially enable the algorithm to be suitable for future “grids and industrial premises load identification” systems. The algorithm builds on new principles: an electro-spectral features preprocessor, a faster waveform sampling sensor, a shorter required duration for the recorded data set, and the use of current waveforms vs. energy load profile, as was the case in previous NILM algorithms. Since the algorithm is intended for operation in any industrial premises or grid location, fast training is required. Known classification algorithms are comparatively trained using the proposed preprocessor over residential datasets, and in addition, the algorithm is compared to five known low-sampling NILM rate algorithms. The proposed spectral algorithm achieved 98% accuracy in terms of device identification over two international datasets, which is higher than the usual success of NILM algorithms.

Understanding the Role of Language in Conflict

2019 ◽  
Vol 64 (1) ◽  
pp. 97-117 ◽  
Author(s):  
William A. Donohue ◽  
Qi Hao ◽  
Richard Spreng ◽  
Charles Owen
Keyword(s):  
Text Analysis ◽  
Word Count ◽  
Data Set ◽  
Open Source Data ◽  
Communication Events ◽  
Source Data ◽  
Linguistic Inquiry ◽  
Mind Set ◽  
The Mind

The purpose of this article is to illustrate innovations in text analysis associated with understanding conflict-related communication events. Two innovations will be explored: LIWC (Linguistic Inquiry and Word Count), the text modeling program from the open-source data analysis software program R, and SPSS Modeler. The LIWC analysis revisits the 2009 study by Donohue and Druckman and the 2014 study by Donohue, Liang, and Druckman focusing on text analyses of the Oslo I Accords between the Palestinians and Israelis to illustrate this approach. The R and SPSS modeling of text analysis use the same data set as the LIWC analysis to provide a different set of pictures associated with each leader’s rhetoric during the period in which the Oslo I accords were being negotiated. Each innovation provides different insights into the mind-set of the two groups of leaders as the secret talks were emerging. The implications of each approach in establishing an understanding of the communication exchanges are discussed to conclude the article.

scholarly journals Transfreq: a Python package for computing the theta-to-alpha transition frequency from resting state EEG data

2021 ◽  
Author(s):  
Elisabetta Vallarino ◽  
Sara Sommariva ◽  
Dario Arnaldi ◽  
Francesco Famà ◽  
Michele Piana ◽  
...  
Keyword(s):  
Resting State ◽  
Transition Frequency ◽  
Data Set ◽  
Open Source Data ◽  
Eeg Data ◽  
Source Data ◽  
Classic Approach ◽  
Spectral Profiles ◽  
Eeg Recordings ◽  
The Individual

AbstractA classic approach to estimate the individual theta-to-alpha transition frequency requires two electroencephalographic (EEG) recordings, one acquired in restingstate condition and one showing an alpha de-synchronisation due e.g. to task execution. This translates into longer recording sessions that my be cumbersome in studies involving patients. Moreover, incomplete de-synchronisation of the alpha rhythm may compromise the final estimation of the transition frequency. Here we present transfreq, a Python library that allows the computation of the transition frequency from resting-state data by clustering the spectral profiles at different EEG channels based on their content in the alpha and theta bands. We first provide an overview of the transfreq core algorithm and of the software architecture. Then we demonstrate its feasibility and robustness across different experimental setups on a publicly available EEG data set and on in-house recordings. A detailed documentation of transfreq and the codes for reproducing the analysis of the paper with the open-source data set are available online at https://elisabettavallarino.github.io/transfreq/

scholarly journals LTmatch: A Method to Abstract Pattern from Unstructured Log

2021 ◽  
Vol 11 (11) ◽  
pp. 5302
Author(s):  
Xiaodong Wang ◽  
Yining Zhao ◽  
Haili Xiao ◽  
Xiaoning Wang ◽  
Xuebin Chi
Keyword(s):  
Longest Common Subsequence ◽  
Practical Significance ◽  
Pattern Extraction ◽  
Data Set ◽  
Log Files ◽  
Open Source Data ◽  
Average Accuracy ◽  
Source Data ◽  
Matching Efficiency ◽  
Common Subsequence

Logs record valuable data from different software and systems. Execution logs are widely available and are helpful in monitoring, examination, and system understanding of complex applications. However, log files usually contain too many lines of data for a human to deal with, therefore it is important to develop methods to process logs by computers. Logs are usually unstructured, which is not conducive to automatic analysis. How to categorize logs and turn into structured data automatically is of great practical significance. In this paper, LTmatch algorithm is proposed, which implements a log pattern extracting algorithm based on a weighted word matching rate. Compared with our preview work, this algorithm not only classifies the logs according to the longest common subsequence(LCS) but also gets and updates the log template in real-time. Besides, the pattern warehouse of the algorithm uses a fixed deep tree to store the log patterns, which optimizes the matching efficiency of log pattern extraction. To verify the advantages of the algorithm, we applied the proposed algorithm to the open-source data set with different kinds of labeled log data. A variety of state-of-the-art log pattern extraction algorithms are used for comparison. The result shows our method is improved by 2.67% in average accuracy when compared with the best result in all the other methods.

scholarly journals An open-source data set of anti-VEGF therapy in diabetic macular oedema patients over 4 years and their visual acuity outcomes

Eye ◽  
2020 ◽  
Author(s):  
Christoph Kern ◽  
Dun Jack Fu ◽  
Josef Huemer ◽  
Livia Faes ◽  
Siegfried K. Wagner ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Open Source ◽  
Macular Oedema ◽  
Diabetic Macular Oedema ◽  
Data Set ◽  
Anti Vegf ◽  
Open Source Data ◽  
Source Data

scholarly journals Personal Identification Based on Brain Networks of EEG Signals

2018 ◽  
Vol 28 (4) ◽  
pp. 745-757 ◽  
Author(s):  
Wanzeng Kong ◽  
Bei Jiang ◽  
Qiaonan Fan ◽  
Li Zhu ◽  
Xuehui Wei
Keyword(s):  
Motor Imagery ◽  
Phase Synchronization ◽  
Brain Networks ◽  
Personal Identification ◽  
Clustering Coefficient ◽  
Identification Accuracy ◽  
Imagery Task ◽  
Eeg Signals ◽  
Data Set ◽  
Linear Discriminant

Abstract Personal identification is particularly important in information security. There are numerous advantages of using electroencephalogram (EEG) signals for personal identification, such as uniqueness and anti-deceptiveness. Currently, many researchers focus on single-dataset personal identification, instead of the cross-dataset. In this paper, we propose a method for cross-dataset personal identification based on a brain network of EEG signals. First, brain functional networks are constructed from the phase synchronization values between EEG channels. Then, some attributes of the brain networks including the degree of a node, the clustering coefficient and global efficiency are computed to form a new feature vector. Lastly, we utilize linear discriminant analysis (LDA) to classify the extracted features for personal identification. The performance of the method is quantitatively evaluated on four datasets involving different cognitive tasks: (i) a four-class motor imagery task dataset in BCI Competition IV (2008), (ii) a two-class motor imagery dataset in the BNCI Horizon 2020 project, (iii) a neuromarketing dataset recorded by our laboratory, (iv) a fatigue driving dataset recorded by our laboratory. Empirical results of this paper show that the average identification accuracy of each data set was higher than 0.95 and the best one achieved was 0.99, indicating a promising application in personal identification.

scholarly journals Impact of Kernel-PCA on Different Features for Person Re-Identification

2021 ◽  
Vol 10 (11) ◽  
pp. 76-81
Author(s):  
Md Kamal Uddin ◽  
◽  
Amran Bhuiyan ◽  
Mahmudul Hasan ◽  
◽  
...  
Keyword(s):  
Computational Cost ◽  
Feature Learning ◽  
Prediction Method ◽  
Principal Component ◽  
Feature Space ◽  
Identification Accuracy ◽  
High Dimensional ◽  
Data Set ◽  
Practical Applications ◽  
Feature Dimension

In the driving field of computer vision, re-identification of an individual in a camera network is very challenging task. Existing methods mainly focus on strategies based on feature learning, which provide feature space and force the same person to be closer than separate individuals. These methods rely to a large extent on high-dimensional feature vectors to achieve high re-identification accuracy. Due to computational cost and efficiency, they are difficult to achieve in practical applications. We comprehensively analyzed the effect of kernel-based principal component analysis (PCA) on some existing high-dimensional person re-identification feature extractors to solve these problems. We initially formulate a kernel function on the extracted features and then apply PCA, significantly reducing the feature dimension. After that, we have proved that the kernel is very effective on different state-of-the-art high-dimensional feature descriptors. Finally, a thorough experimental evaluation of the reference person re-identification data set determined that the prediction method was significantly superior to more advanced techniques and computationally feasible.

Sign in / Sign up

Export Citation Format

Share Document