Reconstruction of physical dance teaching content and movement recognition based on a machine learning model

Action recognition is an active research field that aims to recognize human actions and intentions from a series of observations of human behavior and the environment. Unlike image-based action recognition mainly using a two-dimensional (2D) convolutional neural network (CNN), one of the difficulties in video-based action recognition is that video action behavior should be able to characterize both short-term small movements and long-term temporal appearance information. Previous methods aim at analyzing video action behavior only using a basic framework of 3D CNN. However, these approaches have a limitation on analyzing fast action movements or abruptly appearing objects because of the limited coverage of convolutional filter. In this paper, we propose the aggregation of squeeze-and-excitation (SE) and self-attention (SA) modules with 3D CNN to analyze both short and long-term temporal action behavior efficiently. We successfully implemented SE and SA modules to present a novel approach to video action recognition that builds upon the current state-of-the-art methods and demonstrates better performance with UCF-101 and HMDB51 datasets. For example, we get accuracies of 92.5% (16f-clip) and 95.6% (64f-clip) with the UCF-101 dataset, and 68.1% (16f-clip) and 74.1% (64f-clip) with HMDB51 for the ResNext-101 architecture in a 3D CNN.

Electroencephalogram-based machine learning models to predict neurologic outcome after cardiac arrest: A systematic review

Intrusion detection plays a critical role in safeguarding computer networks from malicious activities and unauthorized access. Traditional machine learning (ML) models have been widely employed for intrusion detection, but their effectiveness can be limited due to the complex and evolving nature of network attacks. An efficient Convolutional Neural Network (CNN) that utilizes one-dimensional convolutions, batch normalization, and max pooling layers is designed to capture the attack patterns in network traffic data. By leveraging the inherent feature extraction capabilities of CNNs, the proposed architecture demonstrates improved performance in identifying network intrusions compared to traditional ML models. The effectiveness of the novel CNN architecture is evaluated by conducted comprehensive experiments on two benchmark intrusion detection datasets. The designed CNN performance was compared with four other ML models such as logistic regression, k-nearest neighbors, decision trees, and random forest. The experimental results revealed that the proposed CNN architecture outperformed the traditional ML models with highest accuracy of 97.68% and 97.39% and highest F1-score of 97.68% and 97.40% for. UNSW-NB15 and CICIDS2017 datasets, respectively. The proposed CNN architecture serves as a promising alternative to traditional ML models, offering improved performance in identifying and mitigating network attacks.

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

Comparison of machine learning and deep learning models for the assessment of rondo wine grape quality with a hyperspectral camera

Study question Can a machine learning (ML) model, developed using modern neural network architecture produce comparable annotation data; utilisable for algorithmic outcome prediction, to manual time-lapse annotations? Summary answer The model automatically annotated unseen embryos with comparable results to manual methods, generating morphokinetic data to enable comparably predictive outputs from an embryo selection algorithm. What is known already The application of artificial intelligence across healthcare industries, including fertility, is increasing. Several ML models are available that seek to generate or analyse embryo images and morphokinetic data, and to determine embryo viability potential. Along with photographic images, the use of time-lapse in IVF laboratories has amassed numeric data, resulting predominantly from annotated manual assessment of images over time. Embryo annotation practice is variable in quality, can be subjective and is time-consuming; commonly taking several minutes per embryo. The development of rapid, accurate automatic annotation would represent a significant time-saving as well as an increase in reproducibility and accuracy. Study design, size, duration Multicentre quality assured annotation data from 63,383 time-lapse monitored embryos (EmbryoScope®), comprising over 400 million individual images, were used to train a ML model to automatically generate morphokinetic annotations. Data was derived from 8 UK clinics within a cohesive group between 2012-2021. Accuracy was assessed using 900 unseen embryos (with live birth outcome) by comparing the output of an established in-house, prospectively validated embryo selection model when the input was either ML-automated, or manual annotations. Participants/materials, setting, methods Multi-focal plane images were processed on the Azure cloud (Microsoft) and resampled to 300x300 pixels. A Laplacian-based focal stacking algorithm merged frames into a single image. The model consisted of an EfficientNetB4 Convolutional Neural Network classifier to extract features and classify the stage of embryo images. A Temporal Convolutional Network interpreted a time-series of image features; producing annotations from pronuclear fading through to blastocyst. Soft localisation loss function used QA data to integrate annotation subjectivities. Main results and the role of chance The ML model rapidly and automatically generated annotations. Efficacy and comparability of the ML model to automate reliable, utilisable annotations was demonstrated by comparison with manual annotation data and the ML model’s ability to auto-generate annotations which could be used to predict live birth by providing annotation data to an established, validated in house embryo selection model. Live birth-predictive capability was measured, and benchmarked against manual annotation, using the area under the receiver operating characteristic curve (AUC). When tested on time-lapse images, collected from pronuclear fading to full blastulation, representing 900 previously unseen, transferred blastocysts where live birth outcomes were blinded, the in-house developed auto-annotation ML model resulted in an AUC of 0.686 compared with 0.661 for manual annotations, for live birth prediction. Auto annotation using the developed model took only milliseconds to complete per embryo. The developed auto-annotation model, built and tested on large data, is considered suitable for productionisation with the aim of being validated and integrated into an application to support IVF laboratory practice. Limitations, reasons for caution Whilst this model was trained to recognise key morphokinetic events, there are other morphokinetic variables that may be useful in the prediction of live birth and further improve embryo selection, or deselection, ability. Akin to manual interpretation, some embryos may fail to be annotated or need second opinion. Wider implications of the findings There is increasing evidence supporting the application of ML to utilise big data from time-lapse imaging and fertility care generally. Whilst promising benefits to IVF clinics and patients, responsible use of data is required alongside large high-quality datasets, and rigorous validation, to ensure safe and robust applications. Trial registration number N/A

Systematic Review of Machine Learning in Diagnosis of Myeloproliferative Neoplasia

In recent years, a significant amount of research has focused on analyzing the effectiveness of machine learning (ML) models for malware detection. These approaches have ranged from methods such as decision trees and clustering to more complex approaches like support vector machine (SVM) and deep neural networks. In particular, neural networks have proven to be very effective in detecting complex and advanced malware. This, however, comes with a caveat. Neural networks are notoriously complex. Therefore, the decisions that they make are often just accepted without questioning why the model made that specific decision. The black box characteristic of neural networks has challenged researchers to explore methods to explain black-box models such as SVM and neural networks and their decision-making process. Transparency and explainability give the experts and malware analysts assurance and trustworthiness about the ML models’ decisions. In addition, it helps in generating comprehensive reports that can be used to enhance cyber threat intelligence sharing. As such, this much needed analysis drives our work in this paper to explore the explainability and interpretability of ML models in the field of online malware detection. In this paper, we used the Shapley Additive exPlanations (SHAP) explainability technique to achieve efficient performance in interpreting the outcome of different ML models such as SVM Linear, SVM-RBF (Radial Basis Function), Random Forest (RF), Feed-Forward Neural Net (FFNN), and Convolutional Neural Network (CNN) models trained on an online malware dataset. To explain the output of these models, explainability techniques such as KernalSHAP, TreeSHAP, and DeepSHAP are applied to the obtained results.

With the rapid development of sequencing technology, the application of genomic prediction has become more and more common in breeding schemes of livestocks and crops. Selecting an appropriate statistical model is of central importance to achieve high prediction accuracy. Recently, machine learning models have been expected to upgrade genomic prediction into a new era. However, the perspective still suffers from lack of evidence that machine learning models can generally outperform the traditional ones on empirical data sets. In this study, we compared two machine learning models based on artificial neural network (ANN) and convolutional neural network (CNN) with four traditional models, including genomic best linear unbiased prediction (GBLUP), Bayesian ridge regression (BRR), BayesA and BayesB, using three published data sets for grain yield in wheat. For each model, we considered two variants: modeling and ignoring the genotype-by-environment ([Formula: see text]) interaction. In the comparison, we considered two strategies of cross-validation: predicting genotypes that have not been evaluated in any environment (CV1) and predicting genotypes that have been tested in other environments (CV2). Our results showed that traditional Bayesian models (BayesA, BayesB, and BRR) outperformed GBLUP, ANN and CNN when considering [Formula: see text] interaction. The accuracies of ANN and CNN were higher than traditional models only in CV1 and when [Formula: see text] interaction was ignored. It was also found that the performance of the two machine learning models was significantly affected by the interaction between the CV strategy and the way of treating the [Formula: see text] interaction, while that of the four traditional models was only influenced by whether the [Formula: see text] interaction was considered or not. Thus, machine learning models can be a powerful complementary to the traditional ones and their superiority may depend on the prediction scenario. Among the two machine learning models, we observed that the accuracy of ANN was higher than CNN in most cases, indicating that it is still challenging to adapt complex machine learning models such as CNN to genomic prediction.

When using convolutional neural networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice [two-dimensional (2D)] or whole volumes [three-dimensional (3D)]. One common alternative, in this study denoted as pseudo-3D, is to use a stack of adjacent slices as input and produce a prediction for at least the central slice. This approach gives the network the possibility to capture 3D spatial information, with only a minor additional computational cost. In this study, we systematically evaluate the segmentation performance and computational costs of this pseudo-3D approach as a function of the number of input slices, and compare the results to conventional end-to-end 2D and 3D CNNs, and to triplanar orthogonal 2D CNNs. The standard pseudo-3D method regards the neighboring slices as multiple input image channels. We additionally design and evaluate a novel, simple approach where the input stack is a volumetric input that is repeatably convolved in 3D to obtain a 2D feature map. This 2D map is in turn fed into a standard 2D network. We conducted experiments using two different CNN backbone architectures and on eight diverse data sets covering different anatomical regions, imaging modalities, and segmentation tasks. We found that while both pseudo-3D methods can process a large number of slices at once and still be computationally much more efficient than fully 3D CNNs, a significant improvement over a regular 2D CNN was only observed with two of the eight data sets. triplanar networks had the poorest performance of all the evaluated models. An analysis of the structural properties of the segmentation masks revealed no relations to the segmentation performance with respect to the number of input slices. A post hoc rank sum test which combined all metrics and data sets yielded that only our newly proposed pseudo-3D method with an input size of 13 slices outperformed almost all methods. In the general case, multislice inputs appear not to improve segmentation results over using 2D or 3D CNNs. For the particular case of 13 input slices, the proposed novel pseudo-3D method does appear to have a slight advantage across all data sets compared to all other methods evaluated in this work.

Over large areas, land cover classification has conventionally been undertaken using satellite time series. Typically temporal metric percentiles derived from single pixel location time series have been used to take advantage of spectral differences among land cover classes over time and to minimize the impact of missing observations. Deep convolutional neural networks (CNNs) have demonstrated potential for land cover classification of single date images. However, over large areas and using time series their application is complicated because they are sensitive to missing observations and they may misclassify small and spatially fragmented surface features due to their spatial patch-based implementation. This study demonstrates, for the first time, a one-dimensional (1D) CNN single pixel time series land classification approach that uses temporal percentile metrics and that does not have these issues. This is demonstrated for all the Conterminous United States (CONUS) considering two different 1D CNN structures with 5 and 8 layers, respectively. CONUS 30 m land cover classifications were derived using all the available Landsat-5 and -7 imagery over a seven-month growing season in 2011 with 3.3 million 30 m land cover class labelled samples extracted from the contemporaneous CONUS National Land Cover Database (NLCD) 16 class land cover product. The 1D CNNs and, a conventional random forest model, were trained using 10%, 50% and 90% samples, and the classification accuracies were evaluated with an independent 10% proportion. Temporal metrics were classified using 5, 7 and 9 percentiles for each of five Landsat reflective wavelength bands and their eight band ratios. The CONUS and detailed 150 × 150 km classification results demonstrate that the approach is effective at scale and locally. The 1D CNN classification land cover class boundaries were preserved for small axis dimension features, such as roads and rivers, with no stripes or anomalous spatial patterns. The 8-layer 1D CNN provided the highest overall classification accuracies and both the 5-layer and 8-layer 1D CNN architectures provided higher accuracies than the random forest by 1.9% - 2.8% which as all the accuracies were > 83% is a meaningful increase. The CONUS overall classification accuracies increased marginally with the number of percentiles (86.21%, 86.40%, and 86.43% for 5, 7 and 9 percentiles, respectively) using the 8-layer 1D-CNN. Class specific producer and user accuracies were quantified, with lower accuracies for the developed land, crop and pasture/hay classes, but no systematic pattern among classes with respect to the number of temporal percentiles used. Application of the trained model to a different year of CONUS Landsat ARD showed moderately decreased accuracy (80.79% for 7 percentiles) that we illustrate is likely due to different intra-annual surface variations between years. These encouraging results are discussed with recommended research for deep learning using temporal metric percentiles.

Recently, three dimensional (3D) convolutional neural networks (CNNs) have emerged as dominant methods to capture spatiotemporal representations in videos, by adding to pre-existing 2D CNNs a third, temporal dimension. Such 3D CNNs, however, are anti-causal (i.e., they exploit information from both the past and the future frames to produce feature representations, thus preventing their use in online settings), constrain the temporal reasoning horizon to the size of the temporal convolution kernel, and are not temporal resolution-preserving for video sequence-to-sequence modelling, as, for instance, in action detection. To address these serious limitations, here we present a new 3D CNN architecture for the causal/online processing of videos. Namely, we propose a novel Recurrent Convolutional Network (RCN), which relies on recurrence to capture the temporal context across frames at each network level. Our network decomposes 3D convolutions into (1) a 2D spatial convolution component, and (2) an additional hidden state 1 × 1 convolution, applied across time. The hidden state at any time t is assumed to depend on the hidden state at t - 1 and on the current output of the spatial convolution component. As a result, the proposed network: (i) produces causal outputs, (ii) provides flexible temporal reasoning, (iii) preserves temporal resolution. Our experiments on the largescale large Kinetics and MultiThumos datasets show that the proposed method performs comparably to anti-causal 3D CNNs, while being causal and using fewer parameters.

<p>Earthquake Early Warning System (EEW) is a technology that calculates earthquake parameter using P-wave that arrives earlier and warns the expected damage area before the arrival of destructive S wave. Therefore, many countries are operating EEW to mitigate damage from earthquake shaking. Especially an on-site EEW is drawn attention as it can reduce blind zones due to using only a single or minimum station. In the on-site EEW, it is important to quickly predict the seismic intensity, which indicates the degree of ground damage, response of structures and ground shaking felt by people at a given location, rather than information on the magnitude or distance of the earthquake.</p><p>In this study, we suggest a machine learning (ML) model that can directly estimate the seismic intensity scale from initial P-waveforms of three-component acceleration data measured at a single station. We used 1D-Convolutional Neural Networks (1D-CNN), which have been shown good performance in signal processing of speech and medical data which are similar to earthquake signals. K-Net and KiK-net datasets, recorded at stations in Japan, were used for training the ML model. Since the amount of data is enough and all of data are labeled with Japan Meteorological Agency Seismic Intensity Scale (I<sub>JMA</sub>), the datasets were used as training data in this study. The developed model produced fast and accurate results using only the three-component acceleration field data at a single station.</p><p>In order to test applicability of the trained model to the new dataset acquired from other regions, the trained model was applied to the STEAD data which were recorded at stations distributed globally. When the trained model was applied to STEAD data directly, the prediction results were worse than those of K-Net and KiK-net data. The reason is that the characteristics of the ground and waveforms are different depending on the region. Therefore, to solve this problem, transfer learning was applied, and only the parameters of a fully connected layer of pretrained ML model were fine-tuned using small number of both labeled target dataset and training dataset used for pretraining. Moreover, by considering the imbalance problem of the training data for transfer learning, it was able to obtain better prediction results. Ultimately, this study shows the pretrained model with a specific region dataset can provide reasonable prediction of seismic intensity to new dataset acquired from other regions using transfer learning.</p>

Recent advances in land use and land cover (LULC) classification with remote sensing imagery are driven by state-of-the-art models such as Convolutional Neural Networks (CNNs). Advanced CNN architecture like ResNet can enhance overall classification performance by incorporating residual skip connections. The integration of 3D feature extraction and ResNet architecture suggests a potential improvement in classification tasks. This paper explores the potential of the 3D ResNet model for LULC classification, comparing it with baseline approaches (Support Vector Machine, Random Forest, XGBoost, 1D CNN, 3D CNN) and state-of-the-art 3D models (3D VGG, 3D DenseNet) using WorldView-2 satellite imagery. The 3D ResNet-18 model, fine-tuned via transfer learning on multispectral images, demonstrates significant improvements in classification performance over machine learning models. It achieves the highest Overall Accuracy (OA) of 99.66% and Kappa Accuracy (KA) of 99.39% on the primary dataset. Despite having slightly lower performance on the external validation dataset (OA:82.89%, KA:80.05%) than 3D DenseNet, it is highly efficient with processing times of 490.2 minutes and 3.6 minutes for both datasets respectively. McNemar’s test results show 3D ResNet and 3D DenseNet have significant differences in classification performance (p<0.05) against other models consistently for both datasets.

For effective management of water quantity and quality, it is absolutely essential to estimate the pollution level of the existing surface water. This case study aims to evaluate the performance of twelve machine learning (ML) models, including five boosting-based algorithms (adaptive boosting, gradient boosting, histogram-based gradient boosting, light gradient boosting, and extreme gradient boosting), three decision tree-based algorithms (decision tree, extra trees, and random forest), and four ANN-based algorithms (multilayer perceptron, radial basis function, deep feed-forward neural network, and convolutional neural network), in estimating the surface water quality of the La Buong River in Vietnam. Water quality data at four monitoring stations alongside the La Buong River for the period 2010–2017 were utilized to calculate the water quality index (WQI). Prediction performance of the ML models was evaluated by using two efficiency statistics (i.e., R2 and RMSE). The results indicated that all twelve ML models have good performance in predicting the WQI but that extreme gradient boosting (XGBoost) has the best performance with the highest accuracy (R2 = 0.989 and RMSE = 0.107). The findings strengthen the argument that ML models, especially XGBoost, may be employed for WQI prediction with a high level of accuracy, which will further improve water quality management.