Ensemble solar forecasting and post-processing using dropout neural network and information from neighboring satellite pixels

AbstractEstablishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.

Download Full-text

Enhanced Convolutional-Neural-Network Architecture for Crop Classification

Applied Sciences ◽

10.3390/app11094292 ◽

2021 ◽

Vol 11 (9) ◽

pp. 4292

Author(s):

Mónica Y. Moreno-Revelo ◽

Lorena Guachi-Guachi ◽

Juan Bernardo Gómez-Mendoza ◽

Javier Revelo-Fuelagán ◽

Diego H. Peluffo-Ordóñez

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Architecture ◽

Classification Model ◽

Classification Error ◽

Small Scale ◽

Post Processing ◽

Average Accuracy ◽

Processing Step ◽

Crop Classification

Automatic crop identification and monitoring is a key element in enhancing food production processes as well as diminishing the related environmental impact. Although several efficient deep learning techniques have emerged in the field of multispectral imagery analysis, the crop classification problem still needs more accurate solutions. This work introduces a competitive methodology for crop classification from multispectral satellite imagery mainly using an enhanced 2D convolutional neural network (2D-CNN) designed at a smaller-scale architecture, as well as a novel post-processing step. The proposed methodology contains four steps: image stacking, patch extraction, classification model design (based on a 2D-CNN architecture), and post-processing. First, the images are stacked to increase the number of features. Second, the input images are split into patches and fed into the 2D-CNN model. Then, the 2D-CNN model is constructed within a small-scale framework, and properly trained to recognize 10 different types of crops. Finally, a post-processing step is performed in order to reduce the classification error caused by lower-spatial-resolution images. Experiments were carried over the so-named Campo Verde database, which consists of a set of satellite images captured by Landsat and Sentinel satellites from the municipality of Campo Verde, Brazil. In contrast to the maximum accuracy values reached by remarkable works reported in the literature (amounting to an overall accuracy of about 81%, a f1 score of 75.89%, and average accuracy of 73.35%), the proposed methodology achieves a competitive overall accuracy of 81.20%, a f1 score of 75.89%, and an average accuracy of 88.72% when classifying 10 different crops, while ensuring an adequate trade-off between the number of multiply-accumulate operations (MACs) and accuracy. Furthermore, given its ability to effectively classify patches from two image sequences, this methodology may result appealing for other real-world applications, such as the classification of urban materials.

Download Full-text

Copy-Move Forgery Localization Using Convolutional Neural Networks and CFA Features

International Journal of Digital Crime and Forensics ◽

10.4018/ijdcf.2018100110 ◽

2018 ◽

Vol 10 (4) ◽

pp. 140-155 ◽

Cited By ~ 2

Author(s):

Lu Liu ◽

Yao Zhao ◽

Rongrong Ni ◽

Qi Tian

Keyword(s):

Neural Network ◽

Neural Networks ◽

Image Processing ◽

Color Filter ◽

Interpolation Algorithm ◽

Post Processing ◽

Classification Result ◽

Filter Array ◽

Cfa Interpolation ◽

Learned Features

This article describes how images could be forged using different techniques, and the most common forgery is copy-move forgery, in which a part of an image is duplicated and placed elsewhere in the same image. This article describes a convolutional neural network (CNN)-based method to accurately localize the tampered regions, which combines color filter array (CFA) features. The CFA interpolation algorithm introduces the correlation and consistency among the pixels, which can be easily destroyed by most image processing operations. The proposed CNN method can effectively distinguish the traces caused by copy-move forgeries and some post-processing operations. Additionally, it can utilize the classification result to guide the feature extraction, which can enhance the robustness of the learned features. This article, per the authors, tests the proposed method in several experiments. The results demonstrate the efficiency of the method on different forgeries and quantifies its robustness and sensitivity.

Download Full-text

ScoreNet: A neural network-based post-processing model for identifying epileptic seizure onset and offset in EEGs

10.1101/2020.12.21.423728 ◽

2020 ◽

Author(s):

Poomipat Boonyakitanont ◽

Apiwat Lek-uthai ◽

Jitkomut Songsiri

Keyword(s):

Neural Network ◽

Epileptic Seizure ◽

False Positive Rate ◽

Imbalanced Data ◽

Detection Algorithm ◽

Processing Technique ◽

Post Processing ◽

Scalp Eeg ◽

Positive Rate ◽

Eeg Recordings

AbstractThis article aims to design an automatic detection algorithm of epileptic seizure onsets and offsets in scalp EEGs. A proposed scheme consists of two sequential steps: the detection of seizure episodes, and the determination of seizure onsets and offsets in long EEG recordings. We introduce a neural network-based model called ScoreNet as a post-processing technique to determine the seizure onsets and offsets in EEGs. A cost function called a log-dice loss that has an analogous meaning to F1 is proposed to handle an imbalanced data problem. In combination with several classifiers including random forest, CNN, and logistic regression, the ScoreNet is then verified on the CHB-MIT Scalp EEG database. As a result, in seizure detection, the ScoreNet can significantly improve F1 to 70.15% and can considerably reduce false positive rate per hour to 0.05 on average. In addition, we propose detection delay metric, an effective latency index as a summation of the exponential of delays, that includes undetected events into account. The index can provide a better insight into onset and offset detection than conventional time-based metrics.

Download Full-text

ARPEGE cloud cover forecast post-processing with convolutional neural network

10.5194/egusphere-egu2020-18325 ◽

2020 ◽

Author(s):

Florian Dupuy ◽

Olivier Mestre ◽

Léo Pfitzner

Keyword(s):

Neural Network ◽

Machine Learning ◽

Convolutional Neural Network ◽

Random Forests ◽

Cloud Cover ◽

Spatial Information ◽

Weather Prediction ◽

Excellent Result ◽

Machine Learning Algorithms ◽

Post Processing

<p>Cloud cover is a crucial information for many applications such as planning land observation missions from space. However, cloud cover remains a challenging variable to forecast, and Numerical Weather Prediction (NWP) models suffer from significant biases, hence justifying the use of statistical post-processing techniques. In our application, the ground truth is a gridded cloud cover product derived from satellite observations over Europe, and predictors are spatial fields of various variables produced by ARPEGE (M&#233;t&#233;o-France global NWP) at the corresponding lead time.</p><p>In this study, ARPEGE cloud cover is post-processed using a convolutional neural network (CNN). CNN is the most popular machine learning tool to deal with images. In our case, CNN allows to integrate spatial information contained in NWP outputs. We show that a simple U-Net architecture produces significant improvements over Europe. Compared to the raw ARPEGE forecasts, MAE drops from 25.1 % to 17.8 % and RMSE decreases from 37.0 % to 31.6 %. Considering specific needs for earth observation, special interest was put on forecasts with low cloud cover conditions (< 10 %). For this particular nebulosity class, we show that hit rate jumps from 40.6 to 70.7 (which is the order of magnitude of what can be achieved using classical machine learning algorithms such as random forests) while false alarm decreases from 38.2 to 29.9. This is an excellent result, since improving hit rates by means of random forests usually also results in a slight increase of false alarms.</p>

Download Full-text

An Improved Fully Convolutional Network Based on Post-Processing with Global Variance Equalization and Noise-Aware Training for Speech Enhancement

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2021.p0130 ◽

2021 ◽

Vol 25 (1) ◽

pp. 130-137

Author(s):

Wenlong Li ◽

◽

Kaoru Hirota ◽

Yaping Dai ◽

Zhiyang Jia

Keyword(s):

Neural Network ◽

Speech Enhancement ◽

Deep Neural Network ◽

Voice Conversion ◽

Post Processing ◽

Generalization Capability ◽

Convolutional Network ◽

Fully Convolutional Network ◽

Subjective Score ◽

Model Training

An improved fully convolutional network based on post-processing with global variance (GV) equalization and noise-aware training (PN-FCN) for speech enhancement model is proposed. It aims at reducing the complexity of the speech improvement system, and it solves overly smooth speech signal spectrogram problem and poor generalization capability. The PN-FCN is fed with the noisy speech samples augmented with an estimate of the noise. In this way, the PN-FCN uses additional online noise information to better predict the clean speech. Besides, PN-FCN uses the global variance information, which improve the subjective score in a voice conversion task. Finally, the proposed framework adopts FCN, and the number of parameters is one-seventh of deep neural network (DNN). Results of experiments on the Valentini-Botinhaos dataset demonstrate that the proposed framework achieves improvements in both denoising effect and model training speed.

Download Full-text

A Green Prospective for Learned Post-processing in Sparse-view Tomographic Reconstruction

10.20944/preprints202107.0265.v1 ◽

2021 ◽

Author(s):

Elena Morotti ◽

Davide Evangelista ◽

Elena Loli Piccolomini

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Tomographic Reconstruction ◽

Research Field ◽

Filtered Backprojection ◽

Post Processing ◽

Training Set ◽

Imaging Reconstruction ◽

Active Research

Deep Learning is developing interesting tools which are of great interest for inverse imaging applications. In this work, we consider a medical imaging reconstruction task from subsampled measurements, which is an active research field where Convolutional Neural Networks have already revealed their great potential. However, the commonly used architectures are very deep and, hence, prone to overfitting and unfeasible for clinical usages. Inspired by the ideas of the green-AI literature, we here propose a shallow neural network to perform an efficient Learned Post-Processing on images roughly reconstructed by the filtered backprojection algorithm. The results obtained on images from the training set and on unseen images, using both the non-expensive network and the widely used very deep ResUNet show that the proposed network computes images of comparable or higher quality in about one fourth of time.

Download Full-text

Artificial intelligence techniques applied to predict teams position of the Brazilian football championship

Journal of Physical Education ◽

10.4025/jphyseduc.v32i1.3254 ◽

1989 ◽

Author(s):

Mariana Kleina ◽

◽

Mateus Noronha dos Santos ◽

Tiago Noronha dos Santos ◽

Marcos Augusto Mendes Marques ◽

...

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Group Classification ◽

Support Vector ◽

Multi Layer Perceptron ◽

Post Processing ◽

Specific Training ◽

Reasonable Prediction ◽

True Group ◽

Better Than

This study presents a classifier prediction in groups for the Brazilian Football Championship of both A and B leagues, from the results of the first half of each championship. With assertive predictions of the group where a team will end the championship, strategic planning can be performed in the squad, such as new hiring, specific training for athletes, and possible championships that the team will be entitled to participate in according to the group classification. In order to find the predictions, two techniques of artificial intelligence were applied: Multi-Layer Perceptron (MLP), which is a type of artificial neural network, and Support Vector Machine (SVM). Preliminary results show that the proposed methodology is very promising, with more than 40% successful cases with MLP and almost 50% with SVM. Moreover, results indicate that the methodology is able to make a reasonable prediction by missing one group of the true group at the end of the championship. The SVM technique was slightly better than MLP. A post-processing analysis of the SVM results was applied to the 2018 A league data from the Brazilian championship, resulting in 85% success indicator of groups.

Download Full-text