Search

In aerospace, marine, and other heavy industries, bearing fault diagnosis has been an essential part of improving machine life, reducing economic losses, and avoiding safety problems caused by machine bearing failures. Most existing bearing fault diagnosis methods face challenges in extracting the fault features from raw bearing fault data. Compared with traditional methods for bearing fault characteristics extraction, deep neural networks can automatically extract intrinsic features without expert knowledge. The convolutional neural network (CNN) was utilized most widely in extracting representative features of bearing faults. Fundamental to this, the hybrid models based on the CNN and individual classifiers were proposed to diagnose bearing faults. However, CNN may not be suitable for all bearing fault classifiers. It is crucial to identify the classifiers which can maximize the CNN feature extraction ability. In this paper, four hybrid models based on CNN were built, and their fault detection accuracy and efficiency were compared. The comparative analysis showed that the random forest (RF) and support vector machine (SVM) could make full use of the CNN feature extraction ability. [ABSTRACT FROM AUTHOR]

The vibration signals for offshore wind-turbine high-speed bearings are often contaminated with noises due to complex environmental and structural loads, which increase the difficulty of fault detection and diagnosis. In view of this problem, we propose a fault-diagnosis strategy with good noise immunity in this paper by integrating the two-dimensional convolutional neural network (2DCNN) with random forest (RF), which is supposed to utilize both CNN's automatic feature-extraction capability and the robust discrimination performance of RF classifiers. More specifically, the raw 1D time-domain bearing-vibration signals are transformed into 2D grayscale images at first, which are then fed to the 2DCNN-RF model for fault diagnosis. At the same time, three procedures, including exponential linear unit (ELU), batch normalization (BN), and dropout, are introduced in the model to improve feature-extraction performance and the noise immune capability. In addition, when the 2DCNN feature extractor is trained, the obtained feature vectors are passed to the RF classifier to improve the classification accuracy and generalization ability of the model. The experimental results show that the diagnostic accuracy of the 2DCNN-RF model could achieve 99.548% on the CWRU high-speed bearing dataset, which outperforms the standard CNN and other standard machine-learning and deep-learning algorithms. Furthermore, when the vibration signals are polluted with noises, the 2DCNN-RF model, without retraining the model or any denoising process, still achieves satisfying performance with higher accuracy than the other methods. [ABSTRACT FROM AUTHOR]

Detecting road cracks is essential for inspecting and assessing the integrity of concrete pavement structures. Traditional image-based methods often require complex preprocessing to extract crack features, making them challenging when dealing with noisy concrete surfaces in diverse real-world scenarios, such as autonomous vehicle road detection. This study introduces an image-based crack detection approach that combines a Random Forest machine learning classifier with a deep convolutional neural network (CNN) to address these challenges. Three state-of-the-art models, namely MobileNet, InceptionV3, and Xception, were employed and trained using a dataset of 30,000 images to build an effective CNN. A systematic comparison of validation accuracy across various base learning rates identified a base learning rate of 0.001 as optimal, achieving a maximum validation accuracy of 99.97%. This optimal learning rate was then applied in the subsequent testing phase. The robustness and flexibility of the trained models were evaluated using 6,000 test photos, each with a resolution of 224 × 224 pixels, which were not part of the training or validation sets. The outstanding results, boasting a remarkable 99.95% accuracy, 99.95% precision, 99.94% recall, and a matching 99.94% F1 Score, unequivocally affirm the efficacy of the proposed technique in precisely identifying road fractures in photographs taken on real concrete surfaces. [ABSTRACT FROM AUTHOR]

We present an evaluation of different deep learning and machine learning approaches for tree health classification in the Black Forest, the Harz Mountains, and the Göttinger Forest on a unique, highly accurate tree-level dataset. The multispectral UAV data were collected from eight forest plots with diverse tree species, mostly conifers. As ground truth data (GTD), nearly 1500 tree polygons with related attribute information on the health status of the trees were used. This data were collected during extensive fieldwork using a mobile application and subsequent individual tree segmentation. Extensive preprocessing included normalization, NDVI calculations, data augmentation to deal with the underrepresented classes, and splitting the data into training, validation, and test sets. We conducted several experiments using a classical machine learning approach (random forests), as well as different convolutional neural networks (CNNs)—ResNet50, ResNet101, VGG16, and Inception-v3—on different datasets and classes to evaluate the potential of these algorithms for tree health classification. Our first experiment was a binary classifier of healthy and damaged trees, which did not consider the degree of damage or tree species. The best results of a 0.99 test accuracy and an F1 score of 0.99 were obtained with ResNet50 on four band composites using the red, green, blue, and infrared bands (RGBI images), while VGG16 had the worst performance, with an F1 score of only 0.78. In a second experiment, we also distinguished between coniferous and deciduous trees. The F1 scores ranged from 0.62 to 0.99, with the highest results obtained using ResNet101 on derived vegetation indices using the red edge band of the camera (NDVIre images). Finally, in a third experiment, we aimed at evaluating the degree of damage: healthy, slightly damaged, and medium or heavily damaged trees. Again, ResNet101 had the best performance, this time on RGBI images with a test accuracy of 0.98 and an average F1 score of 0.97. These results highlight the potential of CNNs to handle high-resolution multispectral UAV data for the early detection of damaged trees when good training data are available. [ABSTRACT FROM AUTHOR]

Existing accelerometer-based human activity recognition (HAR) benchmark datasets that were recorded during free living suffer from non-fixed sensor placement, the usage of only one sensor, and unreliable annotations. We make two contributions in this work. First, we present the publicly available Human Activity Recognition Trondheim dataset (HARTH). Twenty-two participants were recorded for 90 to 120 min during their regular working hours using two three-axial accelerometers, attached to the thigh and lower back, and a chest-mounted camera. Experts annotated the data independently using the camera's video signal and achieved high inter-rater agreement (Fleiss' Kappa = 0.96 ). They labeled twelve activities. The second contribution of this paper is the training of seven different baseline machine learning models for HAR on our dataset. We used a support vector machine, k-nearest neighbor, random forest, extreme gradient boost, convolutional neural network, bidirectional long short-term memory, and convolutional neural network with multi-resolution blocks. The support vector machine achieved the best results with an F1-score of 0.81 (standard deviation: ± 0.18 ), recall of 0.85 ± 0.13 , and precision of 0.79 ± 0.22 in a leave-one-subject-out cross-validation. Our highly professional recordings and annotations provide a promising benchmark dataset for researchers to develop innovative machine learning approaches for precise HAR in free living. [ABSTRACT FROM AUTHOR]

The last decade has seen exponential growth in the field of deep learning with deep learning on microcontrollers a new frontier for this research area. This paper presents a case study about machine learning on microcontrollers, with a focus on human activity recognition using accelerometer data. We build machine learning classifiers suitable for execution on modern microcontrollers and evaluate their performance. Specifically, we compare Random Forests (RF), a classical machine learning technique, with Convolutional Neural Networks (CNN), in terms of classification accuracy and inference speed. The results show that RF classifiers achieve similar levels of classification accuracy while being several times faster than a small custom CNN model designed for the task. The RF and the custom CNN are also several orders of magnitude faster than state-of-the-art deep learning models. On the one hand, these findings confirm the feasibility of using deep learning on modern microcontrollers. On the other hand, they cast doubt on whether deep learning is the best approach for this application, especially if high inference speed and, thus, low energy consumption is the key objective. [ABSTRACT FROM AUTHOR]

Background: the credit scoring model is an effective tool for banks and other financial institutions to distinguish potential default borrowers. The credit scoring model represented by machine learning methods such as deep learning performs well in terms of the accuracy of default discrimination, but the model itself also has many shortcomings such as many hyperparameters and large dependence on big data. There is still a lot of room to improve its interpretability and robustness. Methods: the deep forest or multi-Grained Cascade Forest (gcForest) is a decision tree depth model based on the random forest algorithm. Using multidimensional scanning and cascading processing, gcForest can effectively identify and process high-dimensional feature information. At the same time, gcForest has fewer hyperparameters and has strong robustness. So, this paper constructs a two-stage hybrid default discrimination model based on multiple feature selection methods and gcForest algorithm, and at the same time, it optimizes the parameters for the lowest type II error as the first principle, and the highest AUC and accuracy as the second and third principles. GcForest can not only reflect the advantages of traditional statistical models in terms of interpretability and robustness but also take into account the advantages of deep learning models in terms of accuracy. Results: the validity of the hybrid default discrimination model is verified by three real open credit data sets of Australian, Japanese, and German in the UCI database. Conclusions: the performance of the gcForest is better than the current popular single classifiers such as ANN, and the common ensemble classifiers such as LightGBM, and CNNs in type II error, AUC, and accuracy. Besides, in comparison with other similar research results, the robustness and effectiveness of this model are further verified. [ABSTRACT FROM AUTHOR]

Global carbon fluxes describe the carbon exchange between land and atmosphere. However, already available global carbon fluxes datasets have not been adjusted by the available site data and deep learning tools. In this work, a global carbon fluxes dataset (named as GCFD) of gross primary productivity (GPP), terrestrial ecosystem respiration (RECO), and net ecosystem exchange (NEE) has been developed via a deep learning based convolutional neural network (CNN) model. The dataset has a spatial resolution of 1 km at three time steps per month from January 1999 to June 2020. Flux measurements were used as a training target while remote sensing of vegetation conditions and meteorological data were used as predictors. The results showed that CNN could outperform other commonly used machine learning methods such as random forest (RF) and artificial neural network (ANN) by leading to satisfactory performance with R2 values of the validation stage as 0.82, 0.72 and 0.62 for GPP, RECO, and NEE modelling, respectively. Thus, CNN trained using reanalysis meteorological data and remote sensing data was chosen to produce the global dataset. GCFD showed higher accuracy and more spatial details than some other global carbon flux datasets with reasonable spatial pattern and temporal variation. GCFD is also in accordance with vegetation conditions detected by remote sensing. Owing to the obtained results, GCFD can be a useful reference for various meteorological and ecological analyses and modelling, especially when high resolution carbon flux maps are required. [ABSTRACT FROM AUTHOR]

Downward short-wave (SW) solar radiation is the only essential energy source powering the atmospheric dynamics, ocean dynamics, biochemical processes, and so forth on our planet. Clouds are the main factor limiting the SW flux over the land and the Ocean. For the accurate meteorological measurements of the SW flux one needs expensive equipment-pyranometers. For some cases where one does not need golden-standard quality of measurements, we propose estimating incoming SW radiation flux using all-sky optical RGB imagery which is assumed to incapsulate the whole information about the downward SW flux. We used DASIO all-sky imagery dataset with corresponding SW downward radiation flux measurements registered by an accurate pyranometer. The dataset has been collected in various regions of the World Ocean during several marine campaigns from 2014 to 2021, and it will be updated. We demonstrate the capabilities of several machine learning models in this problem, namely multilinear regression, Random Forests, Gradient Boosting and convolutional neural networks (CNN). We also applied the inverse target frequency (ITF) re-weighting of the training subset in an attempt of improving the SW flux approximation quality. We found that the CNN is capable of approximating downward SW solar radiation with higher accuracy compared to existing empiric parameterizations and known algorithms based on machine learning methods for estimating downward SW flux using remote sensing (MODIS) imagery. The estimates of downward SW radiation flux using all-sky imagery may be of particular use in case of the need for the fast radiative budgets assessment of a site. [ABSTRACT FROM AUTHOR]

Data in the form of images are now generated at an unprecedented rate. A case in point is remote sensing images (RSI), now available in large-scale RSI archives, which have attracted a considerable amount of research on image classification within the remote sensing community. The basic task of single-target multi-class image classification considers the case where each image is assigned exactly one label from a predefined finite set of class labels. Recently, however, image annotations have become increasingly complex, with images labeled with several labels (instead of just one). In other words, the goal is to assign multiple semantic categories to an image, based on its high-level context. The corresponding machine learning tasks is called multi-label classification (MLC). The classification of RSI is currently predominantly addressed by deep neural network (DNN) approaches, especially convolutional neural networks (CNNs), which can be utilized as feature extractors as well as end-to-end methods. After only considering single-target classification for a long period, DNNs have recently emerged that address the task of MLC. On the other hand, trees and tree ensembles for MLC have a long tradition and are the best-performing class of MLC methods, but need predefined feature representations to operate on. In this work, we explore different strategies for model training based on the transfer learning paradigm, where we utilize different families of (pre-trained) CNN architectures, such as VGG, EfficientNet, and ResNet. The architectures are trained in an end-to-end manner and used in two different modes of operation, namely, as standalone models that directly perform the MLC task, and as feature extractors. In the latter case, the learned representations are used with tree ensemble methods for MLC, such as random forests and extremely randomized trees. We conduct an extensive experimental analysis of methods over several publicly available RSI datasets and evaluate their effectiveness in terms of standard MLC measures. Of these, ranking-based evaluation measures are most relevant, especially ranking loss. The results show that, for addressing the RSI-MLC task, it is favorable to use lightweight network architectures, such as EfficientNet-B2, which is the best performing end-to-end approach, as well as a feature extractor. Furthermore, in the datasets with a limited number of images, using traditional tree ensembles for MLC can yield better performance compared to end-to-end deep approaches. [ABSTRACT FROM AUTHOR]

Having a high-quality historical air pollutant dataset is critical for environmental and epidemiological research. In this study, a novel deep learning model based on convolutional neural network architecture was developed to estimate ground-level ozone concentrations across eastern China. A high-resolution maximum daily average 8-h (MDA8) surface ground ozone concentration dataset was generated with the support of the total ozone column from the satellite Tropospheric Monitoring Instrument, meteorological data from the China Meteorological Administration Land Data Assimilation System, and simulations of the WRF-Chem model. The modeled results were compared with in situ measurements in five cities that were not involved in model training, and the mean R2 of predicted ozone with observed values was 0.9, indicating the good robustness of our model. In addition, we compared the model results with some widely used machine learning techniques (e.g., random forest) and recently published ozone datasets, showing that the accuracy of our model is higher and that the spatial distributions of predicted ozone are more coherent. This study provides an efficient and exact method to estimate ground-level ozone and offers a new perspective for modeling spatiotemporal air pollutants. [ABSTRACT FROM AUTHOR]

Today, excessive psychological stress has become a universal threat to humans. That stress can heavily affect work and study when a person repeatedly is exposed to high stress. If that exposure is long enough, it can even cause cardiovascular disease and cancer. Therefore, both monitoring and managing of stress is imperative to reduce the bad outcomes from excessive psychological stress. Conventional monitoring methods firstly extract the characteristics of the RR interval of an electrocardiogram (ECG) from a time domain and a frequency domain, then use machine learning models, like SVM, random forest, and decision tree, to distinguish the level of that stress. The biggest limitation of using these methods is that at least one minute of ECG data and other signals are indispensable to ensure the high accuracy of the results. This will greatly affect the real-time application of the models. To satisfy real-time detection of stress with high accuracy, we proposed a framework based on deep learning technology. The proposed monitoring framework is based on convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM). To evaluate the performance of this network, we conducted the experiments applying conventional methods. The data for the 34 subjects were collected on the server platform created by the group at the Institute of Psychology of the Chinese Academy of Sciences and our group. The accuracy of the proposed framework was up to 0.865 on three levels of stress using a 10 s ECG signal, a 0.228 improvement compared with conventional methods. Therefore, our proposed framework is more suitable for real-time applications [ABSTRACT FROM AUTHOR]

This study aimed to examine the potential of convolutional neural networks (CNNs) for the detection of individual trees infested by bark beetles in a multispectral high-resolution dataset acquired by an unmanned aerial system (UAS). We compared the performance of three CNN architectures and the random forest (RF) model to classify the trees into four categories: pines, sbbd (longer infested trees when needles turn yellow), sbbg (trees under green attack) and non-infested trees (sh). The best performance was achieved by the Nez4c3b CNN (kappa 0.80) and Safaugu4c3b CNN (kappa 0.76) using only RGB bands. The main misclassifications were between sbbd and sbbg because of the similar spectral responses. Merging sbbd and sbbg into a more general class of infested trees made the selection of model type less important. All tested model types, including RF, were able to detect infested trees with an F-score of the class over 0.90. Nevertheless, the best overall metrics were achieved again by the Safaugu3c3b model (kappa 0.92) and Nez3cb model (kappa 0.87) using only RGB bands. The performance of both models is comparable, but the Nez model has a higher learning rate for this task. Based on our findings, we conclude that the Nez and Safaugu CNN models are superior to the RF models and transfer learning models for the identification of infested trees and for distinguishing between different infestation stages. Therefore, these models can be used not only for basic identification of infested trees but also for monitoring the development of bark beetle disturbance. [ABSTRACT FROM AUTHOR]

In this Internet age, there are increasingly many threats to the security and safety of users daily. One of such threats is malicious software otherwise known as malware (ransomware, Trojans, viruses, etc.). The effect of this threat can lead to loss or malicious replacement of important information (such as bank account details, etc.). Malware creators have been able to bypass traditional methods of malware detection, which can be time-consuming and unreliable for unknown malware. This motivates the need for intelligent ways to detect malware, especially new malware which have not been evaluated or studied before. Machine learning provides an intelligent way to detect malware and comprises two stages: feature extraction and classification. This study suggests an ensemble learning-based method for malware detection. The base stage classification is done by a stacked ensemble of fully-connected and one-dimensional convolutional neural networks (CNNs), whereas the end-stage classification is done by a machine learning algorithm. For a meta-learner, we analyzed and compared 15 machine learning classifiers. For comparison, five machine learning algorithms were used: naïve Bayes, decision tree, random forest, gradient boosting, and AdaBoosting. The results of experiments made on the Windows Portable Executable (PE) malware dataset are presented. The best results were obtained by an ensemble of seven neural networks and the ExtraTrees classifier as a final-stage classifier. [ABSTRACT FROM AUTHOR]

Despite recent advances of deep Convolutional Neural Networks (CNNs) in various computer vision tasks, their potential for classification of multispectral remote sensing images has not been thoroughly explored. In particular, the applications of deep CNNs using optical remote sensing data have focused on the classification of very high-resolution aerial and satellite data, owing to the similarity of these data to the large datasets in computer vision. Accordingly, this study presents a detailed investigation of state-of-the-art deep learning tools for classification of complex wetland classes using multispectral RapidEye optical imagery. Specifically, we examine the capacity of seven well-known deep convnets, namely DenseNet121, InceptionV3, VGG16, VGG19, Xception, ResNet50, and InceptionResNetV2, for wetland mapping in Canada. In addition, the classification results obtained from deep CNNs are compared with those based on conventional machine learning tools, including Random Forest and Support Vector Machine, to further evaluate the efficiency of the former to classify wetlands. The results illustrate that the full-training of convnets using five spectral bands outperforms the other strategies for all convnets. InceptionResNetV2, ResNet50, and Xception are distinguished as the top three convnets, providing state-of-the-art classification accuracies of 96.17%, 94.81%, and 93.57%, respectively. The classification accuracies obtained using Support Vector Machine (SVM) and Random Forest (RF) are 74.89% and 76.08%, respectively, considerably inferior relative to CNNs. Importantly, InceptionResNetV2 is consistently found to be superior compared to all other convnets, suggesting the integration of Inception and ResNet modules is an efficient architecture for classifying complex remote sensing scenes such as wetlands. [ABSTRACT FROM AUTHOR]