Search

Accurate crop type mapping using satellite imagery is crucial for food security, yet accurately distinguishing between crops with similar spectral signatures is challenging. This study assessed the performance of Sentinel-2 (S2) time series (spectral bands and vegetation indices), Sentinel-1 (S1) time series (backscattering coefficients and polarimetric parameters), alongside phenological features derived from both S1 and S2 time series (harmonic coefficients and median features), for classifying sunflower, soybean, and maize. Random Forest (RF), Multi-Layer Perceptron (MLP), and XGBoost classifiers were applied across various dataset configurations and train-test splits over two study sites and years in France. Additionally, the InceptionTime classifier, specifically designed for time series data, was tested exclusively with time series datasets to compare its performance against the three general machine learning algorithms (RF, XGBoost, and MLP). The results showed that XGBoost outperformed RF and MLP in classifying the three crops. The optimal dataset for mapping all three crops combined S1 backscattering coefficients with S2 vegetation indices, with comparable results between phenological features and time series data (mean F1 scores of 89.9% for sunflower, 76.6% for soybean, and 91.1% for maize). However, when using individual satellite sensors, S1 phenological features and time series outperformed S2 for sunflower, while S2 was superior for soybean and maize. Both phenological features and time series data produced close mean F1 scores across spatial, temporal, and spatiotemporal transfer scenarios, though median features dataset was the best choice for spatiotemporal transfer. Polarimetric S1 data did not yield effective results. The InceptionTime classifier further improved classification accuracy over XGBoost for all crops, with the degree of improvement varying by crop and dataset (the highest mean F1 scores of 90.6% for sunflower, 86.0% for soybean, and 93.5% for maize). [ABSTRACT FROM AUTHOR]

Accurate crop type mapping using satellite imagery is crucial for food security, yet accurately distinguishing between crops with similar spectral signatures is challenging. This study assessed the performance of Sentinel-2 (S2) time series (spectral bands and vegetation indices), Sentinel-1 (S1) time series (backscattering coefficients and polarimetric parameters), alongside phenological features derived from both S1 and S2 time series (harmonic coefficients and median features), for classifying sunflower, soybean, and maize. Random Forest (RF), Multi-Layer Perceptron (MLP), and XGBoost classifiers were applied across various dataset configurations and train-test splits over two study sites and years in France. Additionally, the InceptionTime classifier, specifically designed for time series data, was tested exclusively with time series datasets to compare its performance against the three general machine learning algorithms (RF, XGBoost, and MLP). The results showed that XGBoost outperformed RF and MLP in classifying the three crops. The optimal dataset for mapping all three crops combined S1 backscattering coefficients with S2 vegetation indices, with comparable results between phenological features and time series data (mean F1 scores of 89.9% for sunflower, 76.6% for soybean, and 91.1% for maize). However, when using individual satellite sensors, S1 phenological features and time series outperformed S2 for sunflower, while S2 was superior for soybean and maize. Both phenological features and time series data produced close mean F1 scores across spatial, temporal, and spatiotemporal transfer scenarios, though median features dataset was the best choice for spatiotemporal transfer. Polarimetric S1 data did not yield effective results. The InceptionTime classifier further improved classification accuracy over XGBoost for all crops, with the degree of improvement varying by crop and dataset (the highest mean F1 scores of 90.6% for sunflower, 86.0% for soybean, and 93.5% for maize).

Introduction: Freezing of gait (FOG) is one of the most debilitating motor symptoms experienced by patients with Parkinson's disease (PD). FOG detection is possible using acceleration data from wearable sensors, and a convolutional neural network (CNN) is often used to determine the presence of FOG epochs. We compared the performance of a standard CNN for the detection of FOG with two more complex networks, which are well suited for time series data, the MiniRocket and the InceptionTime. Methods: We combined acceleration data of people with PD across four studies. The final data set was split into a training (80%) and hold-out test (20%) set. A fifth study was included as an unseen test set. The data were windowed (2s) and five-fold cross-validation was applied. The CNN, MiniRocket, and InceptionTime models were evaluated using a receiver operating characteristic (ROC) curve and its area under the curve (AUC). Multiple sensor configurations were evaluated for the best model. The geometric mean was subsequently calculated to select the optimal threshold. The selected model and threshold were evaluated on the hold-out and unseen test set. Results: A total of 70 participants (23.7h, 9% FOG) were included in this study for training and testing, and in addition, 10 participants provided an unseen test set (2.4h, 11% FOG). The CNN performed best (AUC= 0.86) in comparison to the InceptionTime (AUC= 0.82) and MiniRocket (AUC= 0.76) models. For the CNN, we found a similar performance for a seven-sensor configuration (lumbar, upper and lower legs and feet; AUC= 0.86), six-sensor configuration (upper and lower legs and feet; AUC= 0.87), and two-sensor configuration (lower legs; AUC= 0.86). The optimal threshold of 0.45 resulted in a sensitivity of 77% and a specificity of 58% for the hold-out set (AUC= 0.72), and a sensitivity of 85% and a specificity of 68% for the unseen test set (AUC= 0.90). Conclusion: We confirmed that deep learning can be used to detect FOG in a large, heterogeneous dataset. The CNN model outperformed more complex networks. This model could be employed in future personalized interventions, with the ultimate goal of using automated FOG detection to trigger real-time cues to alleviate FOG in daily life. [ABSTRACT FROM AUTHOR]

IntroductionFreezing of gait (FOG) is one of the most debilitating motor symptoms experienced by patients with Parkinson’s disease (PD). FOG detection is possible using acceleration data from wearable sensors, and a convolutional neural network (CNN) is often used to determine the presence of FOG epochs. We compared the performance of a standard CNN for the detection of FOG with two more complex networks, which are well suited for time series data, the MiniRocket and the InceptionTime.MethodsWe combined acceleration data of people with PD across four studies. The final data set was split into a training (80%) and hold-out test (20%) set. A fifth study was included as an unseen test set. The data were windowed (2 s) and five-fold cross-validation was applied. The CNN, MiniRocket, and InceptionTime models were evaluated using a receiver operating characteristic (ROC) curve and its area under the curve (AUC). Multiple sensor configurations were evaluated for the best model. The geometric mean was subsequently calculated to select the optimal threshold. The selected model and threshold were evaluated on the hold-out and unseen test set.ResultsA total of 70 participants (23.7 h, 9% FOG) were included in this study for training and testing, and in addition, 10 participants provided an unseen test set (2.4 h, 11% FOG). The CNN performed best (AUC = 0.86) in comparison to the InceptionTime (AUC = 0.82) and MiniRocket (AUC = 0.76) models. For the CNN, we found a similar performance for a seven-sensor configuration (lumbar, upper and lower legs and feet; AUC = 0.86), six-sensor configuration (upper and lower legs and feet; AUC = 0.87), and two-sensor configuration (lower legs; AUC = 0.86). The optimal threshold of 0.45 resulted in a sensitivity of 77% and a specificity of 58% for the hold-out set (AUC = 0.72), and a sensitivity of 85% and a specificity of 68% for the unseen test set (AUC = 0.90).ConclusionWe confirmed that deep learning can be used to detect FOG in a large, heterogeneous dataset. The CNN model outperformed more complex networks. This model could be employed in future personalized interventions, with the ultimate goal of using automated FOG detection to trigger real-time cues to alleviate FOG in daily life.

This study aims to enhance rapeseed field detection accuracy using Sentinel-1 (S1) time series data and addressing challenges in collecting ground samples. The proposed solutions include model transfer between years without retraining and secondly, developing models with limited training samples. The research evaluates the performance of Random Forest (RF) and three deep learning (DL) algorithms: Long Short-Term Memory Fully Convolutional Network (LSTM-FCN), InceptionTime, and Multi-layer Perceptron (MLP). All four algorithms are evaluated initially with abundant ground samples and later with smaller sample sizes (100, 300, 500 and 1000 samples). Model transferability is tested across years. The impact of S1 image count on transfer accuracy is examined. Additionally, the effect of the phenological shift in the rapeseed growth cycle of 15 and 30 days between the training and test years was also investigated. The findings demonstrate strong model performance when training and testing occur in the same year (F1-score up to 95%). Within sample sizes of 300 to 1000, RF and InceptionTime stand out with high accuracy (F1-score>90%). When employing different years for training and testing with abundant sample sizes, all four algorithms correctly classified rapeseed (F1-score between 85.5% and 92.7%). In cases of a reduced number of images, the performance of InceptionTime and LSTM-FCN decreased (16% decrease in the F1-score), while RF and MLP maintain their performance. Notably, RF outperforms DL algorithms with an F1-score of 89.1%. In the context of a phenological shift, only InceptionTime and LSTM-FCN demonstrated strong performance (F1-score between 87.7% and 92.6%).

Precision viticulture is an area that is very dependent on methods that allow for a sustainable assessment of grape maturity and, in this work, we apply two state-of-the-art (SOTA) convolution-based networks, namely InceptionTime and OmniScale 1D-CNN, to hyperspectral images of wine grape berries to estimate sugar content. Since attaining generalization capacity and processing the information in such high-dimensional data are the two biggest challenges to overcome in problems of this nature, we also study the impact of two dimensionality reduction techniques, Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE), on the models' performance. Both models underwent different tests with different vintages and varieties of wine grapes in the training/validation steps, as to form a true test to their generalization capacity. Our results show that both PCA and t-SNE succeed in improving the performance of these deep networks when an adequate number of components is chosen that minimizes the ratio between information loss and removing redundant features: additionally, both techniques significantly reduce computational cost, a very important trait when training deep learning models. Both models showed good generalization ability with very competitive results across different varieties and vintages even despite their significant differences in variability, which is an indicator that a relationship between spectras can be found that is reflected on sugar content values.

Major depressive disorder (MDD) has been considered a severe and common ailment with effects on functional frailty, while its clear manifestations are shrouded in mystery. Hence, manual detection of MDD is a challenging and subjective task. Although Electroencephalogram (EEG) signals have shown promise in aiding diagnosis, further enhancement is required to improve accuracy, clinical utility, and efficiency. This study focuses on the automated detection of MDD using EEG data and deep neural network architecture. For this aim, first, a customized InceptionTime model is recruited to detect MDD individuals via 19-channel raw EEG signals. Then a channel-selection strategy, which comprises three channel-selection steps, is conducted to omit redundant channels. The proposed method achieved 91.67% accuracy using the full set of channels and 87.5% after channel reduction. Our analysis shows that i) only the first minute of EEG recording is sufficient for MDD detection, ii) models based on EEG recorded in eyes-closed resting-state outperform eyes-open conditions, and iii) customizing the InceptionTime model can improve its efficiency for different assignments. The proposed method is able to help clinicians as an efficient, straightforward, and intelligent diagnostic tool for the objective detection of MDD.

Damage detection and the classification of carbon fiber-reinforced composites using non-destructive testing (NDT) techniques are of great importance. This paper applies an acoustic emission (AE) technique to obtain AE data from three tensile damage tests determining fiber breakage, matrix cracking, and delamination. This article proposes a deep learning approach that combines a state-of-the-art deep learning technique for time series classification: the InceptionTime model with acoustic emission data for damage classification in composite materials. Raw AE time series and frequency-domain sequence data are used as the input for the InceptionTime network, and both obtain very high classification performances, achieving high accuracy scores of about 99%. The InceptionTime network produces better training, validation, and test accuracy with the raw AE time series data than it does with the frequency-domain sequence data. Simultaneously, the InceptionTime model network shows its potential in dealing with data imbalances. [ABSTRACT FROM AUTHOR]

Motion or inertial sensors such as gyroscope and accelerometer commonly found in smartwatches and smartphones can measure characteristics such as acceleration and angular velocity of movements in the human body and use them to learn models capable of identifying human activities, that has applicability in various fields such as biometrics, remote patient health monitoring, etc. Recently deep learning-based methods have become popular for human activity recognition because they use representation learning techniques that can automatically generate optimal features from raw input data generated from sensors without any human intervention and can identify hidden patterns in data. This work proposes a novel hybrid deep neural network model, CNN-GRU that combines convolutional and gated recurrent units for human activity recognition. This model was successfully validated on WISDM dataset and produced accuracy that is suggestively better than other state-of-the-art deep neural network models such as Inception Time and DeepConvLSTM created using AutoML.

Introduction: Freezing of gait (FOG) is one of the most debilitating motor symptoms experienced by patients with Parkinson's disease (PD). FOG detection is possible using acceleration data from wearable sensors, and a convolutional neural network (CNN) is often used to determine the presence of FOG epochs. We compared the performance of a standard CNN for the detection of FOG with two more complex networks, which are well suited for time series data, the MiniRocket and the InceptionTime., Methods: We combined acceleration data of people with PD across four studies. The final data set was split into a training (80%) and hold-out test (20%) set. A fifth study was included as an unseen test set. The data were windowed (2 s) and five-fold cross-validation was applied. The CNN, MiniRocket, and InceptionTime models were evaluated using a receiver operating characteristic (ROC) curve and its area under the curve (AUC). Multiple sensor configurations were evaluated for the best model. The geometric mean was subsequently calculated to select the optimal threshold. The selected model and threshold were evaluated on the hold-out and unseen test set., Results: A total of 70 participants (23.7 h, 9% FOG) were included in this study for training and testing, and in addition, 10 participants provided an unseen test set (2.4 h, 11% FOG). The CNN performed best (AUC = 0.86) in comparison to the InceptionTime (AUC = 0.82) and MiniRocket (AUC = 0.76) models. For the CNN, we found a similar performance for a seven-sensor configuration (lumbar, upper and lower legs and feet; AUC = 0.86), six-sensor configuration (upper and lower legs and feet; AUC = 0.87), and two-sensor configuration (lower legs; AUC = 0.86). The optimal threshold of 0.45 resulted in a sensitivity of 77% and a specificity of 58% for the hold-out set (AUC = 0.72), and a sensitivity of 85% and a specificity of 68% for the unseen test set (AUC = 0.90)., Conclusion: We confirmed that deep learning can be used to detect FOG in a large, heterogeneous dataset. The CNN model outperformed more complex networks. This model could be employed in future personalized interventions, with the ultimate goal of using automated FOG detection to trigger real-time cues to alleviate FOG in daily life., Competing Interests: JN serves on the advisory board of Cue2Walk and Ceriter. He also reports grants from ZonMW, Ipsen Pharmaceuticals, Parkinson Foundation, and Gossweiler Foundation outside the submitted work. RW serves on the board of the hemianopia stichting. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Klaver, Heijink, Silvestri, van Vugt, Janssen, Nonnekes, van Wezel and Tjepkema-Cloostermans.)