1. |
- Balouji, Ebrahim, 1985, et al.
(author)
-
A LSTM-based Deep Learning Method with Application to Voltage Dip Classification
- 2018
-
In: 2018 18TH INTERNATIONAL CONFERENCE ON HARMONICS AND QUALITY OF POWER (ICHQP). - Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE). - 2164-0610. - 9781538605172 - 9781538605172 ; 2018-May
-
Conference paper (peer-reviewed)abstract
- In this paper, a deep learning (DL)-based method for automatic feature extraction and classification of voltage dips is proposed. The method consists of a dedicated architecture of Long Short-Term Memory (LSTM), which is a special type of Recurrent Neural Networks (RNNs). A total of 5982 three-phase one-cycle voltage dip RMS sequences, measured from several countries, has been used in our experiments. Our results have shown that the proposedmethod is able to classify the voltage dips from learned features in LSTM, with 93.40% classification accuracy on the test data set. The developed architecture is shown to be novel for feature learning and classification of voltage dips. Different from the conventional machine learning methods, the proposed method is able to learn dip features without requiring transition-event segmentation, selecting thresholds, and using expert rules or human expert knowledge, when a large amount of measurement data is available. This opens a new possibility of exploiting deep learning technology for power quality data analytics and classification.
|
|
2. |
- Bäckström, Karl, 1994, et al.
(author)
-
An efficient 3D deep convolutional network for Alzheimer's disease diagnosis using MR images
- 2018
-
Conference paper (peer-reviewed)abstract
- Automatic extraction of features from MRI brain scans and diagnosis of Alzheimer’s Disease (AD) remain a challenging task. In this paper, we propose an efficient and simple three dimensional convolutional network (3D ConvNet) architecture that is able to achieve high performance for detection of AD on a relatively large dataset. The proposed 3D ConvNet consists of five convolutional layers for feature extraction, followed by three fully-connected layers for AD/NC classification. The main contributions of the paper include: (a) propose a novel and effective 3D ConvNet architecture; (b) study the impact of hyper-parameter selection on the performance of AD classification; (c) study the impact of pre-processing; (d) study the impact of data partitioning; (e) study the impact of dataset size. Experiments conducted on an ADNI dataset containing 340 subjects and 1198 MRI brain scans have resulted good performance (with the test accuracy of 98.74%, 100% AD detection rate and 2,4% false alarm). Comparisons with 7 existing state-of-the-art methods have provided strong support to the robustness of the proposed method.
|
|