Single Convolutional Neural Network Research Articles

EEG-Centered Parkinson's Disease Prediction System Using Gaussian Kernel Discrete Wavelet Transform and Leaky Single Peak Triangle Context Convolutional Neural Network Deep Learning Technique

Parkinson's disease (PD), a neurodegenerative illness where dopamine-producing brain cells are destroyed, slows down motor performance. To identify PD, numerous techniques have recently been established. In this research, a novel idiosyncratic Gaussian Kernel Discrete Wavelet Transform (GKDWT) and a Leaky Single Peak Triangle Context Convolutional Neural Network (LeakySPTC-CNN)-centered effective Deep Learning (DL) model have been developed for the prediction of PD. The Electroencephalogram (EEG) signal is first acquired and then divided into one-second segments. The model then carried out signal filtering and spectrogram conversion. The features are then extracted with the support of GKDWT, and feature selection and ranking are carried out using the Quadratic Chimp Optimization Algorithm (QChOA). The LeakySPTC-CNN is used to categorize both ill and healthy people. The model has a promising future, according to the experiential evaluation, and it also offers a better way to diagnose Parkinson's disease (PD) early.

Comprehensive Review of Machine Learning-Based Methods for Electricity Load Forecasting

With the improvement of data processing power and the continuous development of modern power grids, there is an increasing demand for accuracy in predicting power load. To study the field of power load forecasting, this article summarizes and categorizes different models into three types: traditional models, single machine learning models, and hybrid models, based on previous literature. Firstly, a general overview is provided of the application of different models in power load forecasting. Secondly, typical models from three categories are selected for a detailed introduction. In traditional models, the ARIMA model is chosen, while in single machine learning models, CNN, and LSTM are chosen. For the hybrid model, the ResNet-LSTM mixed neural network is selected for the introduction. Finally, four different datasets were used to test different models. The differences and patterns of the models were summarized, and suggestions were proposed for future research directions in the field of power load forecasting.

Simple is best: A single-CNN method for classifying remote sensing images

<abstract> <p>Recently, researchers have proposed a lot of methods to boost the performance of convolutional neural networks (CNNs) for classifying remote sensing images (RSI). However, the methods' performance improvements were insignificant, while time and hardware costs increased dramatically due to re-modeling. To tackle this problem, this study sought a simple, lightweight, yet more accurate solution for RSI semantic classification (RSI-SC). At first, we proposed a set of mathematical derivations to analyze and identify the best way among different technical roadmaps. Afterward, we selected a simple route that can significantly boost a single CNN's performance while maintaining simplicity and reducing costs in time and hardware. The proposed method, called RE-EfficientNet, only consists of a lightweight EfficientNet-B3 and a concise training algorithm named RE-CNN. The novelty of RE-EfficientNet and RE-CNN includes the following: First, EfficientNet-B3 employs transfer learning from ImageNet-1K and excludes any complicated re-modeling. It can adequately utilize the easily accessible pre-trained weights for time savings and avoid the pre-training effect being weakened due to re-modeling. Second, RE-CNN includes an effective combination of data augmentation (DA) transformations and two modified training tricks (TTs). It can alleviate the data distribution shift from DA-processed training sets and make the TTs more effective through modification according to the inherent nature of RSI. Extensive experimental results on two RSI sets prove that RE-EfficientNet can surpass all 30 cutting-edge methods published before 2023. It gives a remarkable improvement of 0.50% to 0.75% in overall accuracy (OA) and a 75% or more reduction in parameters. The ablation experiment also reveals that RE-CNN can improve CNN OA by 0.55% to 1.10%. All the results indicate that RE-EfficientNet is a simple, lightweight and more accurate solution for RSI-SC. In addition, we argue that the ideas proposed in this work about how to choose an appropriate model and training algorithm can help us find more efficient approaches in the future.</p> </abstract>

A Runtime Switchable Multi-Phase Convolutional Neural Network for Resource-Constrained Systems

Convolutional Neural Networks (CNNs) are widely used in various systems, including resource-constrained embedded systems or IoT devices. In such systems, it is typical to deploy compressed or pruned CNNs, instead of original ones, at the cost of reduced accuracy. Existing CNN pruning techniques have primarily focused on minimizing resource requirements. However, today’s embedded systems are increasingly dynamic in both resource demands and availability. Thus, the previous techniques that only consider given static cases are no longer efficient. In this paper, we propose a novel multi-phase CNN that enables a multi-objective exploration of a number of pruning candidates out of a single CNN. In the proposed technique, a CNN can operate in various versions depending on which subsets of weights are used and can be transformed to the one best matches to the given constraint adaptively and efficiently. For that, a CNN is first pruned to the sparsest form; then a set of parameters (sub-network) is additionally supplemented as the phase goes by. As a result, a number of network versions for all different phases can be represented by a single network and they form a pareto solution over the accuracy and resource usage trade-off. In this work, we target CPU-based CNN inference engines as most embedded systems do not have the luxury of specialized co-processor support such as GPUs or HW accelerators. The proposed technique has been implemented in a publicly available CPU inference engine, Darknet, and its effectiveness has been validated with a popular CNN in terms of design space exploration capability and runtime switchability.

Multi-Classification of Brain Tumors on Magnetic Resonance Images Using an Ensemble of Pre-Trained Convolutional Neural Networks.

Automatic classification of brain tumors is an important issue in computeraided diagnosis (CAD) for medical applications since it can efficiently improve the clinician's diagnostic performance and the current study focused on the CAD system of the brain tumors. Existing studies mainly focused on a single classifier either based on traditional machinelearning algorithms or deep learning algorithms with unsatisfied results. In this study, we proposed an ensemble of pre-trained convolutional neural networks to classify brain tumors into three types from their T1-weighted contrast-enhanced MRI (CE-MRI) images, which are meningioma, glioma, and pituitary tumor. Three pre-trained convolutional neural networks (Inception-v3, Resnet101, Densenet201) with the best classification performance (i.e. accuracy of 96.21%, 97.00%, 96.54%, respectively) on the CE-MRI benchmark dataset were selected as backbones of the ensemble model. The features extracted by backbone networks in the ensemble model were further classified by a support vector machine. The ensemble system achieved an average classification accuracy of 98.14% under a five-fold cross-validation process, outperforming any single deep learning model in the ensemble system and other methods in the previous studies. Performance metrics for each brain tumor type, including area under the curve, sensitivity, specificity, precision, and F-score, were calculated to show the ensemble system's performance. Our work addressed a practical issue by evaluating the model with fewer training samples. The classification accuracy was reduced to 97.23%, 96.87%, and 93.96% when 75%, 50%, and 25% training data was used to train the ensemble model, respectively. Our ensemble model has a great capacity and achieved the best performance in any single convolutional neural networks for brain tumors classification and is potentially applicable in real clinical practice.

CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data

This paper aims to establish a driving style recognition method that is highly accurate, fast and generalizable, considering the lack of data types in driving style classification task and the low recognition accuracy of widely used unsupervised clustering algorithms and single convolutional neural network methods. First, we propose a method to collect the information on driver’s operation time sequence in view of the imperfect driving data, and then extract the driver’s style features through convolutional neural network. Then, for the collected temporal data, the Long Short Term Memory networks (LSTM) module is added to encode and transform the driving features, to achieve the driving style classification. The results show that the accuracy of driving style recognition reaches over 93%, while the speed is improved significantly.

A NEW APPROACH TO IMPROVE CNN PERFORMANCE IN ANOMALY DETECTION FOR IOT NETWORKS BASED ON THE ALGORITHM ADABOOST

Since the increase in internet attacks brings much damage, it is essential to take care of the security of network activities. networks must use different security systems, such as intrusion detection systems, to deal with attacks. This research proposes a reliable approach for intrusion detection systems based on anomaly networks. The network traffic data sets are large and unbalanced, affecting intrusion detection systems' performance. The imbalance has caused the minority class to be incorrectly identified by conventional data mining algorithms. By ignoring the example of this class, we tried to increase the overall accuracy, while the correct example of the minority class protocols is also essential. In the proposed method, network penetration detection based on the combination of multi-dimensional features and homogeneous cumulative set learning was proposed, which has three stages: the first stage, based on the characteristics of the data, several original datasets of raw data or datasets criteria are extracted. Then, the original feature datasets are combined to form multiple comprehensive feature datasets. Finally, the same basic algorithm is used to train different comprehensive feature datasets for the multi-dimensional subspace of features. An initial classifier is trained, and the predicted probabilities of all the basic classifiers are entered into a meta-module. In this research, an AdaBoost meta-algorithm has been used for unbalanced data according to a suitable design. Also, various single CNN models and multi-CNN fusion models have been proposed, implemented, and trained. This evaluation is done with the NSL-KDD dataset to solve some of the inherent problems of the KDD'99 dataset. Simulations were performed to evaluate the performance of the proposed model on the mentioned data sets. This proposed method's accuracy and detection rate obtained better results than other methods.

Short-term performance degradation prediction of a commercial vehicle fuel cell system based on CNN and LSTM hybrid neural network

Short-term performance degradation prediction is significant for fuel cell system control and health management. This paper presents a hybrid deep learning method by combining the convolutional neural network (CNN) and long short-term memory (LSTM) network to predict the short-term degradation of a 110 kW fuel cell system used for the commercial vehicle. First, the complete ensemble empirical mode decomposition (CEEMD) is applied to decompose the nonlinear and non-stationary voltage sequence extracted by the sliding window into modality sequences with different characteristic time scales. Then, these modality sequences are input into the corresponding CNN-LSTM for voltage prediction. Experimental results show that the proposed CNN-LSTM can reduce the root mean square error (RMSE) by 13.55% and 34.40%, respectively, compared to the single CNN and LSTM because it combines the spatial feature extraction ability of CNN and the powerful prediction ability of LSTM. Furthermore, the CEEMD–CNN–LSTM can reduce RMSE by 36.92% compared to CNN-LSTM since the impact of exogenous factors on the recoverable decay and intrinsic decay of the fuel cell can be separated easily for better model learning. The CEEMD–CNN–LSTM is also compared with other recently published deep learning models based on the same data set, and the results show that the prediction framework in this paper has higher accuracy.

Piston Sensing for Golay-6 Sparse Aperture System with Double-Defocused Sharpness Metrics via ResNet-34

In pursuit of high imaging quality, optical sparse aperture systems must correct piston errors quickly within a small range. In this paper, we modified the existing deep-learning piston detection method for the Golay-6 array, by using a more powerful single convolutional neural network based on ResNet-34 for feature extraction; another fully connected layer was added, on the basis of this network, to obtain the best results. The Double-defocused Sharpness Metric (DSM) was selected first, as a feature vector to enhance the model performance; the average RMSE of the five sub-apertures for valid detection in our study was only 0.015λ (9 nm). This modified method has higher detecting precision, and requires fewer training datasets with less training time. Compared to the conventional approach, this technique is more suitable for the piston sensing of complex configurations.

Deep learning for cancer tumor classification using transfer learning and feature concatenation

<span lang="EN-US">Deep convolutional neural networks (CNNs) represent one of the <br /> state-of-the-art methods for image classification in a variety of fields. Because the number of training dataset images in biomedical image classification is limited, transfer learning with CNNs is frequently applied. Breast cancer is one of most common types of cancer that causes death in women. Early detection and treatment of breast cancer are vital for improving survival rates. In this paper, we propose a deep neural network framework based on the transfer learning concept for detecting and classifying breast cancer histopathology images. In the proposed framework, we extract features from images using three pre-trained CNN architectures: VGG-16, ResNet50, and Inception-v3, and concatenate their extracted features, and then feed them into a fully connected (FC) layer to classify benign and malignant tumor cells in the histopathology images of the breast cancer. In comparison to the other CNN architectures that use a single CNN and many conventional classification methods, the proposed framework outperformed all other deep learning architectures and achieved an average accuracy of 98.76%.</span>

Interactive local and global feature coupling for EEG-based epileptic seizure detection

Automatic seizure detection based on scalp electroencephalogram (EEG) can accelerate the progress of epilepsy diagnosis. Current seizure detection methods based on deep learning usually rely on single convolutional neural network (CNN) or recurrent neural network (RNN) models. In terms of feature extraction, single model often has limitations. Since CNN is good at extracting local features, and Transformer can capture global information, we put forward a seizure detection method based on interactive local and global feature coupling. Local feature and global representation of the EEG are respectively extracted by convolution operation and self-attention mechanism. To make up of the shortcomings of local feature and global representation, a feature coupling block (FCB) is utilized to fuse the two kinds of information in an interactive way. The enhanced feature representation is fed to the classifier for seizure and normal EEG classification. Extensive experiments are conducted on CHB-MIT and Siena scalp EEG datasets. Experimental results demonstrate that the method can effectively perform epileptic seizure detection from the original EEG signals without extra feature extraction.

Evaluation of Decision Fusions for Classifying Karst Wetland Vegetation Using One-Class and Multi-Class CNN Models with High-Resolution UAV Images

Combining deep learning and UAV images to map wetland vegetation distribution has received increasing attention from researchers. However, it is difficult for one multi-classification convolutional neural network (CNN) model to meet the accuracy requirements for the overall classification of multi-object types. To resolve these issues, this paper combined three decision fusion methods (Majority Voting Fusion, Average Probability Fusion, and Optimal Selection Fusion) with four CNNs, including SegNet, PSPNet, DeepLabV3+, and RAUNet, to construct different fusion classification models (FCMs) for mapping wetland vegetations in Huixian Karst National Wetland Park, Guilin, south China. We further evaluated the effect of one-class and multi-class FCMs on wetland vegetation classification using ultra-high-resolution UAV images and compared the performance of one-class classification (OCC) and multi-class classification (MCC) models for karst wetland vegetation. The results highlight that (1) the use of additional multi-dimensional UAV datasets achieved better classification performance for karst wetland vegetation using CNN models. The OCC models produced better classification results than MCC models, and the accuracy (average of IoU) difference between the two model types was 3.24–10.97%. (2) The integration of DSM and texture features improved the performance of FCMs with an increase in accuracy (MIoU) from 0.67% to 8.23% when compared to RGB-based karst wetland vegetation classifications. (3) The PSPNet algorithm achieved the optimal pixel-based classification in the CNN-based FCMs, while the DeepLabV3+ algorithm produced the best attribute-based classification performance. (4) Three decision fusions all improved the identification ability for karst wetland vegetation compared to single CNN models, which achieved the highest IoUs of 81.93% and 98.42% for Eichhornia crassipes and Nelumbo nucifera, respectively. (5) One-class FCMs achieved higher classification accuracy for karst wetland vegetation than multi-class FCMs, and the highest improvement in the IoU for karst herbaceous plants reached 22.09%.

Automatic ovarian tumors recognition system based on ensemble convolutional neural network with ultrasound imaging

BackgroundUpon the discovery of ovarian cysts, obstetricians, gynecologists, and ultrasound examiners must address the common clinical challenge of distinguishing between benign and malignant ovarian tumors. Numerous types of ovarian tumors exist, many of which exhibit similar characteristics that increase the ambiguity in clinical diagnosis. Using deep learning technology, we aimed to develop a method that rapidly and accurately assists the different diagnosis of ovarian tumors in ultrasound images.MethodsBased on deep learning method, we used ten well-known convolutional neural network models (e.g., Alexnet, GoogleNet, and ResNet) for training of transfer learning. To ensure method stability and robustness, we repeated the random sampling of the training and validation data ten times. The mean of the ten test results was set as the final assessment data. After the training process was completed, the three models with the highest ratio of calculation accuracy to time required for classification were used for ensemble learning pertaining. Finally, the interpretation results of the ensemble classifier were used as the final results. We also applied ensemble gradient-weighted class activation mapping (Grad-CAM) technology to visualize the decision-making results of the models.ResultsThe highest mean accuracy, mean sensitivity, and mean specificity of ten single CNN models were 90.51 ± 4.36%, 89.77 ± 4.16%, and 92.00 ± 5.95%, respectively. The mean accuracy, mean sensitivity, and mean specificity of the ensemble classifier method were 92.15 ± 2.84%, 91.37 ± 3.60%, and 92.92 ± 4.00%, respectively. The performance of the ensemble classifier is better than that of a single classifier in three evaluation metrics. Moreover, the standard deviation is also better which means the ensemble classifier is more stable and robust.ConclusionFrom the comprehensive perspective of data quantity, data diversity, robustness of validation strategy, and overall accuracy, the proposed method outperformed the methods used in previous studies. In future studies, we will continue to increase the number of authenticated images and apply our proposed method in clinical settings to increase its robustness and reliability.

Driver behavior model for healthy driving style using machine learning methods

Driving is a complex and dynamic task requiring drivers not only to make accurate perceptions and cognitions about the information on the driver’s driving skill but also to process this information at a high speed. This paper compared three major image processing/machine learning algorithms viz; Single Shot Multibox Detection (SSD), Convolutional Neural Networks (CNN), and support vector machine (SVM) to find the fastest and most efficient of the three with regards to the dataset from driving events (braking, speeding and safe driving) collected from Nigeria. The results analyzed showed that in an identical testing environment, Support Vector Machine outperformed Single Shot Detection and Convolutional Neural Networks.

Breast Cancer Tumor Classification Using a Bag of Deep Multi-Resolution Convolutional Features

Breast cancer accounts for 30% of all female cancers. Accurately distinguishing dangerous malignant tumors from benign harmless ones is key to ensuring patients receive lifesaving treatments on time. However, as doctors currently do not identify 10% to 30% of breast cancers during regular assessment, automated methods to detect malignant tumors are desirable. Although several computerized methods for breast cancer classification have been proposed, convolutional neural networks (CNNs) have demonstrably outperformed other approaches. In this paper, we propose an automated method for the binary classification of breast cancer tumors as either malignant or benign that utilizes a bag of deep multi-resolution convolutional features (BoDMCF) extracted from histopathological images at four resolutions (40×, 100×, 200× and 400×) by three pre-trained state-of-the-art deep CNN models: ResNet-50, EfficientNetb0, and Inception-v3. The BoDMCF extracted by the pre-trained CNNs were pooled using global average pooling and classified using the support vector machine (SVM) classifier. While some prior work has utilized CNNs for breast cancer classification, they did not explore using CNNs to extract and pool a bag of deep multi-resolution features. Other prior work utilized CNNs for deep multi-resolution feature extraction from chest X-ray radiographs to detect other conditions such as pneumoconiosis but not for breast cancer detection from histopathological images. In rigorous evaluation experiments, our deep BoDMCF feature approach with global pooling achieved an average accuracy of 99.92%, sensitivity of 0.9987, specificity (or recall) of 0.9797, positive prediction value (PPV) or precision of 0.99870, F1-Score of 0.9987, MCC of 0.9980, Kappa of 0.8368, and AUC of 0.9990 on the publicly available BreaKHis breast cancer image dataset. The proposed approach outperforms the prior state of the art for histopathological breast cancer classification as well as a comprehensive set of CNN baselines, including ResNet18, InceptionV3, DenseNet201, EfficientNetb0, SqueezeNet, and ShuffleNet, when classifying images at any individual resolutions (40×, 100×, 200× or 400×) or when SVM is used to classify a BoDMCF extracted using any single pre-trained CNN model. We also demonstrate through a carefully constructed set of experiments that each component of our approach contributes non-trivially to its superior performance including transfer learning (pre-training and fine-tuning), deep feature extraction at multiple resolutions, global pooling of deep multiresolution features into a powerful BoDMCF representation, and classification using SVM.

Ensemble Learning of Lightweight Deep Convolutional Neural Networks for Crop Disease Image Detection

The application of convolutional neural networks (CNNs) to plant disease recognition is widely considered to enhance the effectiveness of such networks significantly. However, these models are nonlinear and have a high bias. To address the high bias of the single CNN model, the authors proposed an ensemble method of three lightweight CNNs models (MobileNetv2, NasNetMobile and a simple CNN model from scratch) based on a stacking generalization approach. This method has two-stage training, first, we fine-tuned and trained the base models (level-0) to make predictions, then we passed these predictions to XGBoost (level-1 or meta-learner) for training and making the final prediction. Furthermore, a search grid algorithm was used for the hyperparameter tuning of the XGBoost. The proposed method is compared to the majority voting approach and all base learner models (MobileNetv2, NasNetMobile and simple CNN model from scratch). The proposed ensemble method significantly improved the performance of plant disease classification. Experiments show that the ensemble approach achieves higher prediction accuracy (98% for majority voting and 99% for staking method) than a single CNN learner. Furthermore, the proposed ensemble method has a lightweight size (e.g., 10[Formula: see text] smaller than VGG16), allowing farmers to deploy it on devices with limited resources such as cell phones, internet of things (IoT) devices, unmanned aerial vehicles (UAVs) and so on.

Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN

The noise attenuation of seismic data is an indispensable part of seismic data processing, directly impacting the following inversion and imaging. This paper focuses on two bottlenecks in the AI-based denoising method of seismic data: the destruction of structural information of seismic data and the inferior generalizability. We propose a flexible attention-CNN (FACNN) and realized the denoising work of seismic data. This paper’s main work and advantages were concentrated on the following three aspects: (i) We propose attention gates (AGs), which progressively suppressed features in irrelevant background parts and improved the denoising performance. (ii) We added a noise level map M as an additional channel, making a single CNN model expected to inherit the flexibility of handling noise models with different parameters, even spatially variant noises. (iii) We propose a mixed loss function based on MS_SSIM to improve the performance of FACNN further. Adding the noise level map can improve the network’s generalization ability, and adding the attention structure with the mixed loss function can better protect the structural information of the seismic data. The numerical tests showed that our method has better generalization and can better protect the details of seismic events.

Gamma function based ensemble of CNN models for breast cancer detection in histopathology images

Breast cancer is the second deadliest disease amongst women worldwide. Breast histopathology image analysis is one of the most powerful ways used for the detection of tumour malignancies. Manual breast histopathology image analysis is, however, subjective, time-consuming and prone to human errors. Computer-aided diagnosis (CAD) has become a popular and viable solution for medical image analysis due to recent advances in computer power and memory. However, the performance of the CAD models needs to be improved to use for practical purposes. Convolutional neural network (CNN) based models have achieved promising results for breast histopathological image classification. In this paper, instead of relying on a single CNN model, we have proposed a novel rank-based ensemble method by combining outcomes of three transfer learning CNN models, namely GoogleNet, VGG11 and MobileNetV3_Small. The proposed ensemble model is designed using the Gamma function for solving a 2-class classification problem of breast histopathological images. In comparison to state-of-the-art approaches, our method produces better classification results, with 99.16%, 98.24%, 98.67%, and 96.16% for 40X, 100X, 200X, and 400X levels of magnification, respectively, on a publicly accessible standard dataset called BreakHis and 96.95% on another well-known dataset called ICIAR-2018.

Data augmentation in extreme ultraviolet lithography simulation using convolutional neural network

BackgroundIn the previous work, we developed a convolutional neural network (CNN), which reproduces the results of the rigorous electromagnetic (EM) simulations in a small mask area. The prediction time of CNN was 5000 times faster than the calculation time of EM simulation. We trained the CNN using 200,000 data, which were the results of EM simulation. Although the prediction time of CNN was very short, it took a long time to build a huge amount of the training data. Especially when we enlarge the mask area, the calculation time to prepare the training data becomes unacceptably long.AimReducing the calculation time to prepare the training data.ApproachWe apply data augmentation technique to increase the number of training data using limited original data. The training data of our CNN are the diffraction amplitudes of mask patterns. Assuming a periodic boundary condition, the diffraction amplitudes of the shifted or flipped mask pattern can be easily calculated using the diffraction amplitudes of the original mask pattern.ResultsThe number of training data after the data augmentation is multiplied by 200 from 2500 to 500,000. Using a large amount of training data, the validation loss of CNN was reduced. The accuracy of CNN with augmented data is verified by comparing the CNN predictions with the results of EM simulation.ConclusionsData augmentation technique is applied to the diffraction amplitude of the mask pattern. The data preparation time is reduced by a factor of 200. Our CNN almost reproduces the results of EM simulation. In this work, the mask patterns are restricted to line and space patterns. It is a challenge to build several CNNs for specific mask patterns or ultimately a single CNN for arbitrary mask patterns.

Feasibility and validity of a single camera CNN driven musculoskeletal model for muscle force estimation during upper extremity strength exercises: Proof-of-concept.

Muscle force analysis can be essential for injury risk estimation and performance enhancement in sports like strength training. However, current methods to record muscle forces including electromyography or marker-based measurements combined with a musculoskeletal model are time-consuming and restrict the athlete's natural movement due to equipment attachment. Therefore, the feasibility and validity of a more applicable method, requiring only a single standard camera for the recordings, combined with a deep-learning model and musculoskeletal model is evaluated in the present study during upper-body strength exercises performed by five athletes. Comparison of muscle forces obtained by the single camera driven model against those obtained from a state-of-the art marker-based driven musculoskeletal model revealed strong to excellent correlations and reasonable RMSD's of 0.4–2.1% of the maximum force (Fmax) for prime movers, and weak to strong correlations with RMSD's of 0.4–0.7% Fmax for stabilizing and secondary muscles. In conclusion, a single camera deep-learning driven model is a feasible method for muscle force analysis in a strength training environment, and first validity results show reasonable accuracies, especially for prime mover muscle forces. However, it is evident that future research should investigate this method for a larger sample size and for multiple exercises.