Deep Convolutional Neural Network Framework Research Articles

Attention-Guided Sample-Based Feature Enhancement Network for Crowded Pedestrian Detection Using Vision Sensors.

Occlusion presents a major obstacle in the development of pedestrian detection technologies utilizing computer vision. This challenge includes both inter-class occlusion caused by environmental objects obscuring pedestrians, and intra-class occlusion resulting from interactions between pedestrians. In complex and variable urban settings, these compounded occlusion patterns critically limit the efficacy of both one-stage and two-stage pedestrian detectors, leading to suboptimal detection performance. To address this, we introduce a novel architecture termed the Attention-Guided Feature Enhancement Network (AGFEN), designed within the deep convolutional neural network framework. AGFEN improves the semantic information of high-level features by mapping it onto low-level feature details through sampling, creating an effect comparable to mask modulation. This technique enhances both channel-level and spatial-level features concurrently without incurring additional annotation costs. Furthermore, we transition from a traditional one-to-one correspondence between proposals and predictions to a one-to-multiple paradigm, facilitating non-maximum suppression using the prediction set as the fundamental unit. Additionally, we integrate these methodologies by aggregating local features between regions of interest (RoI) through the reuse of classification weights, effectively mitigating false positives. Our experimental evaluations on three widely used datasets demonstrate that AGFEN achieves a 2.38% improvement over the baseline detector on the CrowdHuman dataset, underscoring its effectiveness and potential for advancing pedestrian detection technologies.

Galaxy mergers in UNIONS – I. A simulation-driven hybrid deep learning ensemble for pure galaxy merger classification

Abstract Merging and interactions can radically transform galaxies. However, identifying these events based solely on structure is challenging as the status of observed mergers is not easily accessible. Fortunately, cosmological simulations are now able to produce more realistic galaxy morphologies, allowing us to directly trace galaxy transformation throughout the merger sequence. To advance the potential of observational analysis closer to what is possible in simulations, we introduce a supervised deep learning Convolutional Neural Network (CNN) and Vision Transformer (ViT) hybrid framework, Mummi (MUlti Model Merger Identifier). Mummi is trained on realism-added synthetic data from IllustrisTNG100-1, and is comprised of a multi-step ensemble of models to identify mergers and non-mergers, and to subsequently classify the mergers as interacting pairs or post-mergers. To train this ensemble of models, we generate a large imaging dataset of 6.4 million images targeting UNIONS with RealSimCFIS. We show that Mummi offers a significant improvement over many previous machine learning classifiers, achieving 95% pure classifications even at Gyr long timescales when using a jury-based decision making process, mitigating class imbalance issues that arise when identifying real galaxy mergers from z = 0 to 0.3. Additionally, we can divide the identified mergers into pairs and post-mergers at 96% success rate. We drastically decrease the false positive rate in galaxy merger samples by 75%. By applying Mummi to the UNIONS DR5-SDSS DR7 overlap, we report a catalog of 13,448 high confidence galaxy merger candidates. Finally, we demonstrate that Mummi produces powerful representations solely using supervised learning, which can be used to bridge galaxy morphologies in simulations and observations.

Geometrically-informed predictive modeling of melt pool depth in laser powder bed fusion using deep MLP-CNN and metadata integration

The laser powder bed fusion (LPBF) process has the ability to manufacture intricate geometries. However, the fabrication of complex geometries using the LPBF process for industrial applications remains challenging in terms of achieving consistent microstructure and mechanical properties. Experimental investigations show that in addition to process parameters, geometrical factors such as shape and size of parts impact the thermal history, microstructure, defect structure, and thus mechanical and fatigue properties. As a result, the standardization, qualification, and certification of additively manufactured (AM-ed) parts encounters substantial obstacles posed by the obscure impact of design parameters on component quality. In this paper, an artificial intelligence framework is proposed to predict the melt pool depth of the additively manufactured parts considering the geometrical information of the parts. More specifically, a deep Multilayer Perceptron and Convolutional Neural Network (MLP-CNN) framework is designed to predict melt pool depth for any part geometries when printing metallic parts via LPBF using metadata (i.e., numerical and image data). Quite often the melt pool depth generated during the AM processes is employed as a surrogate for thermal, defect- and micro-structural signatures. In melt pool depth prediction of complex geometries in LPBF, a digital twin environment using a finite element model (FEM) is developed and validated using experimental melt pool measurements for different geometries within multi-tracks and layers. The FEM was in agreement with experimentation with an error of less than 15%. Through the process simulation, a large dataset of melt pool depths was obtained for various part geometries and different process parameters. Next, the MLP-CNN framework was established to identify the parallel impact of part design and process parameters on melt pool depths. To enhance the performance and robustness of this model, data augmentation has been implemented by rotating and transferring geometries to artificially expand the dataset. Data augmentation helps to mitigate overfitting and promote better generalization, especially in the context of limited training data. After training, the proposed model is found to give accurate melt pool prediction even for new geometries not considered during training. The fusion of CNN and MLP has led the melt pool predictions for unseen geometries with an accuracy of 95%.

Deep convolutional neural network framework with multi-modal fusion for Alzheimer’s detection

The biomedical profession has gained importance due to the rapid and accurate diagnosis of clinical patients using computer-aided diagnosis (CAD) tools. The diagnosis and treatment of Alzheimer’s disease (AD) using complementary multimodalities can improve the quality of life and mental state of patients. In this study, we integrated a lightweight custom convolutional neural network (CNN) model and nature-inspired optimization techniques to enhance the performance, robustness, and stability of progress detection in AD. A multi-modal fusion database approach was implemented, including positron emission tomography (PET) and magnetic resonance imaging (MRI) datasets, to create a fused database. We compared the performance of custom and pre-trained deep learning models with and without optimization and found that employing natureinspired algorithms like the particle swarm optimization algorithm (PSO) algorithm significantly improved system performance. The proposed methodology, which includes a fused multimodality database and optimization strategy, improved performance metrics such as training, validation, test accuracy, precision, and recall. Furthermore, PSO was found to improve the performance of pre-trained models by 3-5% and custom models by up to 22%. Combining different medical imaging modalities improved the overall model performance by 2-5%. In conclusion, a customized lightweight CNN model and nature-inspired optimization techniques can significantly enhance progress detection, leading to better biomedical research and patient care.

A single-stage anchor-free rotating target visual detection algorithm suitable for flexible body vibration displacement measurement

The phenomenon of angular inclination of flexible structures during vibration poses a significant challenge to the applicability of visual vibration measurement methods because the target locked in the captured image will produce unknown geometric deformations such as scale, displacement, and angle in the time domain space, and the horizontal rectangular frame used for matching during target detection will also increase the false detection rate of the target due to the introduction of more background information. Such subtle geometric deformations and false detections can lead to severe fit errors in the displacement curves regressed by the visual vibration measurement algorithm. To effectively improve the accuracy and robustness of vibration image target recognition, this article takes the flexible body captured by a high-speed camera as the target of vibration displacement measurement. It introduces the rotating target detection method based on deep learning into the field of visual vibration measurement, which verifies the feasibility of the deep learning method in flexible body vibration measurement, and based on the deep convolutional neural network framework, a high-precision displacement measurement algorithm based on single-stage anchor-free rotating target detection is proposed. The algorithm in this article first uses the CSPDarknet backbone network to extract multi-scale features of flexible structural image sequences. It then uses PANet to fuse the top-down and bottom-up bidirectional feature maps of the four bridge target feature maps obtained through the backbone network. The shallow and deep information is used for semantic feature fusion and combined with the Coordinate Attention mechanism to achieve target finding and fine positioning on the feature map. Finally, we use the coordinates of the bounding box obtained from the test to regress the position offset of the object’s center point. To verify the accuracy of the algorithm in this article, we conducted experimental validation on the cable-stayed bridge model and the actual bridge and compared the performance with the traditional template matching algorithm, differential optical flow method, and various deep learning algorithms with different localization principles, as well as the displacement signals collected and processed by accelerometers. The experimental results of time-frequency characteristics analysis show that the vibration displacement trajectories regressed by the algorithm in this paper have the best overlap with the displacement measurements collected by the accelerometer, which verifies that the algorithm in this article has good application potential and implementation space in the field of condition monitoring of flexible structural bodies.

Cross-domain prediction approach of human lower limb voluntary movement intention for exoskeleton robot based on EEG signals.

Exoskeleton robot control should ideally be based on human voluntary movement intention. The readiness potential (RP) component of the motion-related cortical potential is observed before movement in the electroencephalogram and can be used for intention prediction. However, its single-trial features are weak and highly variable, and existing methods cannot achieve high cross-temporal and cross-subject accuracies in practical online applications. Therefore, this work aimed to combine a deep convolutional neural network (CNN) framework with a transfer learning (TL) strategy to predict the lower limb voluntary movement intention, thereby improving the accuracy while enhancing the model generalization capability; this would also provide sufficient processing time for the response of the exoskeleton robotic system and help realize robot control based on the intention of the human body. The signal characteristics of the RP for lower limb movement were analyzed, and a parameter TL strategy based on CNN was proposed to predict the intention of voluntary lower limb movements. We recruited 10 subjects for offline and online experiments. Multivariate empirical-mode decomposition was used to remove the artifacts, and the moment of onset of voluntary movement was labeled using lower limb electromyography signals during network training. The RP features can be observed from multiple data overlays before the onset of voluntary lower limb movements, and these features have long latency periods. The offline experimental results showed that the average movement intention prediction accuracy was 95.23% ± 1.25% for the right leg and 91.21% ± 1.48% for the left leg, which showed good cross-temporal and cross-subject generalization while greatly reducing the training time. Online movement intention prediction can predict results about 483.9 ± 11.9ms before movement onset with an average accuracy of 82.75%. The proposed method has a higher prediction accuracy with a lower training time, has good generalization performance for cross-temporal and cross-subject aspects, and is well-prioritized in terms of the temporal responses; these features are expected to lay the foundation for further investigations on exoskeleton robot control.

RiceNet: A deep convolutional neural network approach for classification of rice varieties

The cultivation of desired grain varieties holds immense significance as about 67% of the world’s population is associated with the agriculture sector. Unknowingly sowing the wrong variety of seeds may lead to a colossal waste of effort and money. Furthermore, the growing issue of rice grain adulteration in high-quality rice poses a threat to the trust of rice importers and exporters. While traditional methods are expensive, laborious, and error-prone, Computer Vision provides a good alternative that constitutes a current, advanced technology for image processing and data evaluation that holds tremendous promise and potential. In this research study, five varieties of rice grains including Jehlum Sr-1, Mushkibudji, Sr-2, and Sr-4 were collected from local grain and were used for research analysis. A computer vision system “RiceNet” contingent upon Deep Convolutional Neural Network (DCNN) framework has been designed for ameliorating the accuracy of identifying five unique groups of rice grain varieties. Deep Learning (DL) based pre-trained architectures including InceptionV3 and InceptionResNetV2 models were also adopted for classifying five specific groups of rice species. To optimize model parameters and alleviate back-propagation error during training, the Adam optimizer with a learning rate (lr) of 0.00003 has been employed to fine-tune the pre-trained InceptionV3 and ResNetInceptionV2 models. The proposed RiceNet architecture and pre-trained models were also compared with traditional ML approaches of HOG-SVM, SIFT-SVM, HOG-Logistic Regression(HOG-LR), SIFT-Logistic Regression(SIFT-LR), HOG-KNN, and SIFT-KNN for rice grain classification. With these experimentations at hand, it was observed that our proposed model “RiceNet” outperformed other approaches in similar computer vision tasks. The prediction accuracy outcome for the test dataset by HOG-SVM, SIFT-SVM, HOG-LR, SIFT-LR, HOG-KNN, and SIFT-KNN models were 66.0%, 65.33%, 62.67%, 65.0%, 54.0%, and 52.0% respectively. RiceNet, InceptionV3 and ResNetInceptionV2 have the best prediction accuracy of 94%, 84% and 81.333%. The remarkably high success rate of DCNN models makes them highly valuable and can be extended to endorse an integrated grain identification system that can operate in real-world situations.

In-situ enhanced anchor-free deep CNN framework for a high-speed human-machine interaction

Human-Robot Interaction (HRI) constitutes a demanding research field that integrates artificial intelligence, informatics, robotics, engineering, and human-machine interaction. In the present era, there is an increased focus on natural user interfaces, with particular attention to gestural modalities. This leads to the coordination of modern robotic systems, where real-time integration and interpretation of manual gestures play a vital role in facilitating effective manipulation. Hand gesture recognition holds a crucial role in the field of machine vision, perhaps greatly exacerbated with varying lighting conditions and backgrounds. In this paper, first an Enhanced Anchor-free Network (EAF-Net) is proposed to perform hand gesture recognition in real-time. The EAF-Net is deep single-stage Convolutional Neural Network (CNN) based architecture. The Custom Precise Prediction Function (CPPF) is utilized for a continuous recognition of a specific gesture from a video feed. Then, the 6-axis collaborative Robot is manipulated using the predicted gesture. The EAF-Net model utilizes the Enriched Hourglass as a backbone feature extraction network. The proposed EAF-Net model undergoes training and assessment using the MITI HD-II dataset. The performance of the model is also analyzed for the standard benchmark datasets (NUSHP-II and Senz-3D). The evaluation of the EAF-Net model’s performance spans a range of IoU values from 0.5 to 0.95. The EAF-Net model led to higher precision values (AP0.5) as 99.22%, recall values (AR0.5) as 98.20%, and F1-Score0.5 as 98.64% on the MITI HD-II dataset. The EAF-Net model consumed a prediction time of 259 ms on NVIDIA Jetson Nano Processor and 14 ms on NVIDIA Titan X GPU. It aided in implementing a portable high-speed 6-axis Robot control framework to pick and place operation in 3D space. The robot would be able to imitate human hand activities such as hand rotation, hand tilting, picking and arranging items, and so on in the near future. Further reduction in prediction time of the model on the portable processors (NVIDIA Jetson Nano, Raspberry-Pi) could enhance the speed of the Human Machine Interaction process.

A unified prediction approach of fatigue life suitable for diversified engineering materials

Investigation on fatigue life prediction approaches for welded joints of different materials was of great significance for the reliability and safety of engineering structures. A fatigue performance dataset with sufficient characteristics was established via data processing and augmentation. The modification of loss function and the physics-informed influencing factors was used to realize the multi-level physical intervention on the prediction model. The importance of physics-informed influencing factors under mechanical-properties dataset was analyzed and integrated into the deep convolutional neural network (DCNN) framework via attention model. The significance of the intervention using physics-informed influencing factors and the identification using mechanical properties was proved via the comparison of different prediction methods. Further, a mechanical properties-based prediction method for fatigue life of multiple materials was established, and the average prediction error (30.5%) and standard deviation of prediction error (16.1%) of the proposed approach were significantly lower than that of the other prediction methods. By the identification via mechanical properties and the introduction of physics-informed influencing factors, the machine learning method can be used to evaluate the fatigue life of multiple materials in engineering with low consumption.

FgbCNN: A unified bilinear architecture for learning a fine-grained feature representation in facial expression recognition

A facial expression recognition system has been proposed in this paper. The challenges of the facial expression recognition system lie due to low intra-class variance within a class of negative emotions, such as anger, disgust, and fear. A conventional Convolution Neural Network (CNN) model may extract discriminative features and has shown outstanding performance in various computer vision tasks. However, it is unable to extract the second-order feature information that demonstrates the interaction between features in the image of wild-environment datasets. This paper presents a novel method to solve the facial expression recognition problem by addressing several limitations concerning emotion recognition problems. A deep learning-based bilinear convolutional neural network framework has been proposed, termed an Fine-Grained Bilinear CNN (FgbCNN) model that consists of two branches with optimized CNN along with a normalization layer composed of batch-normalization, square-root normalization, L2-normalization, and drop-out layers. Here, local and holistic features have been aggregated using a dot-product layer to extract more discriminant features. Finally, experimenting with two wild-environments (SFEW 1.0 and SFEW 2.0) and two lab-controlled datasets (KDEF and CK+), it has been observed that the proposed model can minimize the intra-class variances and has attained outstanding performance compared to other state-of-the-art methods.

An adaptive weighted attention-enhanced deep convolutional neural network for classification of MRI images of Parkinson's disease

BackgroundParkinson's disease (PD) is the second prevalent neurological diseases with a significant growth rate in incidence. Convolutional neural networks using structural magnetic resonance images (sMRI) are widely used for PD classification. However, the areas of change in the patient's MRI images are small and unfixed. Thus, capturing the features of the areas accurately where the lesions changed became a problem. MethodWe propose a deep learning framework that combines multi-scale attention guidance and multi-branch feature processing modules to diagnose PD by learning sMRI T2 slice features. In this scheme, firstly, to achieve effective feature transfer and gradient descent, a deep convolutional neural network framework based on dense block is designed. Next, an Adaptive Weighted Attention algorithm is proposed, whose pursers is to extract multi branch and even diverse features. Finally, Dropout layer and SoftMax layer are added to the network structure to obtain good classification results and rich and diverse feature information. The Dropout layer is used to reduce the number of intermediate features to increase the orthogonality between features of each layer. The activation function SoftMax increases the flexibility of the neural network by increasing the degree of fitting to the training set and converting linear to nonlinear. ResultsThe best performance of the proposed method an accuracy of 92%, a sensitivity of 94%, specificity of 90% and a F1 score of 95% respectively for identifying PD and HC. ConclusionExperiments show that the proposed method can successfully distinguish PD and NC. Good classification results were obtained in PD diagnosis classification task and compared with advanced research methods.

A deep learning approach for multi‐stage classification of brain tumor through magnetic resonance images

AbstractBrain tumor is the 10th major cause of death among humans. The detection of brain tumor is a significant process in the medical field. Therefore, the objective of this research work is to propose a fully automated deep learning framework for multistage classification. Besides, this study focuses on to develop an efficient and reliable system using a convolutional neural network (CNN). In this study, the fast bounding box technique is used for segmentation. Moreover, the CNN layers‐based three models are developed for multistage classification through magnetic resonance images on three publicly available datasets. The first dataset is obtained from Kaggle Repository (Dataset‐1), the second dataset is known as Figshare (Dataset‐2), and the third dataset is called REMBRANDT (Dataset‐3) to classify the MR images into different grades. Different augmentation techniques are applied to increase the data size of MR images. In pre‐processing, the proposed models achieved higher Peak Signal‐to‐Noise ratio to remove noise. The first proposed deep CNN framework mentioned as Classification‐1 has obtained 99.40% accuracy, which classified MR images into two classes, that is (i) normal and (ii) abnormal, while the second proposed CNN framework mentioned as Classification‐2 has obtained 97.78% accuracy, which classified brain tumor into three types, which are meningioma, glioma, and pituitary. Similarly, the third developed CNN framework mentioned as Classification‐3 has obtained 98.91% accuracy that further classified MR images of tumors into four different classes as: Grade I, Grade II, Grade III, and Grade IV. The results demonstrate that the proposed models achieved better performance on three large and diverse datasets. The comparison of obtained outcomes shows that the developed models are more efficient and effective than state‐of‐the‐art methods.

Deep Convolutional Network Based Machine Intelligence Model for Satellite Cloud Image Classification

As a huge number of satellites revolve around the earth, a great probability exists to observe and determine the change phenomena on the earth through the analysis of satellite images on a real-time basis. Therefore, classifying satellite images plays strong assistance in remote sensing communities for predicting tropical cyclones. In this article, a classification approach is proposed using Deep Convolutional Neural Network (DCNN), comprising numerous layers, which extract the features through a downsampling process for classifying satellite cloud images. DCNN is trained marvelously on cloud images with an impressive amount of prediction accuracy. Delivery time decreases for testing images, whereas prediction accuracy increases using an appropriate deep convolutional network with a huge number of training dataset instances. The satellite images are taken from the Meteorological & Oceanographic Satellite Data Archival Centre, the organization is responsible for availing satellite cloud images of India and its subcontinent. The proposed cloud image classification shows 94% prediction accuracy with the DCNN framework.

Classification of Tumor in Brain MR Images Using Deep Convolutional Neural Network and Global Average Pooling

Brain tumors can cause serious health complications and lead to death if not detected accurately. Therefore, early-stage detection of brain tumors and accurate classification of types of brain tumors play a major role in diagnosis. Recently, deep convolutional neural network (DCNN) based approaches using brain magnetic resonance imaging (MRI) images have shown excellent performance in detection and classification tasks. However, the accuracy of DCNN architectures depends on the training of data samples since it requires more precise data for better output. Thus, we propose a transfer learning-based DCNN framework to classify brain tumors for example meningioma tumors, glioma tumors, and pituitary tumors. We use a pre-trained DCNN architecture VGGNet which is previously trained on huge datasets and used to transfer its learning parameters to the target dataset. Also, we employ transfer learning aspects such as fine-tune the convolutional network and freeze the layers of the convolutional network for better performance. Further, this proposed approach uses a Global Average Pooling (GAP) layer at the output to avoid overfitting issues and vanishing gradient problems. The proposed architecture is assessed and compared with competing deep learning based brain tumor classification approaches on the Figshare dataset. Our proposed approach produces 98.93% testing accuracy and outperforms the contemporary learning-based approaches.

Toward a generalizable deep CNN for neural drive estimation across muscles and participants

Objective. High-density electromyography (HD-EMG) decomposition algorithms are used to identify individual motor unit (MU) spike trains, which collectively constitute the neural code of movements, to predict motor intent. This approach has advanced from offline to online decomposition, from isometric to dynamic contractions, leading to a wide range of neural-machine interface applications. However, current online methods need offline retraining when applied to the same muscle on a different day or to a different person, which limits their applications in a real-time neural-machine interface. We proposed a deep convolutional neural network (CNN) framework for neural drive estimation, which takes in frames of HD-EMG signals as input, extracts general spatiotemporal properties of MU action potentials, and outputs the number of spikes in each frame. The deep CNN can generalize its application without retraining to HD-EMG data recorded in separate sessions, muscles, or participants. Approach. We recorded HD-EMG signals from the vastus medialis and vastus lateralis muscles from five participants while they performed isometric contractions during two sessions separated by ∼20 months. We identified MU spike trains from HD-EMG signals using a convolutive blind source separation (BSS) method, and then used the cumulative spike train (CST) of these MUs and the HD-EMG signals to train and validate the deep CNN. Main results. On average, the correlation coefficients between CST from the BSS and that from deep CNN were for leave-one-out across-sessions-and-muscles validation and for leave-one-out across-participants validation. When trained with more than four datasets, the performance of deep CNN saturated at for cross validations across muscles, sessions, and participants. Significance. We can conclude that the deep CNN is generalizable across the aforementioned conditions without retraining. We could potentially generate a robust deep CNN to estimate neural drive to muscles for neural-machine interfaces.

Abstract 10580: Machine Learning-Assisted Echocardiographic Identification of Children at High Risk for Treatment-Related Cardiomyopathy: A Proof-of-Concept Study

Introduction: Childhood cancer survivors require life-long surveillance for treatment-related cardiomyopathy/heart failure (CHF). Ultimately, we aim to use machine learning to aid in echocardiographic discrimination of survivors more likely to develop future CHF. For this feasibility pilot, we built two proof-of-concept deep convolutional neural networks (DCNNs) tasked with binary classification of present/future CHF versus no CHF with the aim of assessing optimal data input format and model architecture. Methods: From a robust multi-institutional surveillance echo dataset, we selected pilot data comprising 171 parasternal short axis echo clips, 52 from 5 CHF+ (present and future CHF) and 119 from 21 CHF- patients. We built two DCNN models differing in frame selection for input data (Fig. 1), both tasked with binary classification of CHF+ vs. CHF-. We used holdout subsets in a 10-fold cross-validation framework to test model performance and Student’s t test (paired) to compare model performance. Results: Classification performance was similar, with mean AUROC values of 0.59 ± 0.09 and 0.53 ± 0.11 (p=0.14) for the models trained on Type I and Type II montages, respectively (Fig. 2). Conclusions: The DCNN framework is feasible for a model tasked with classifying CHF status, and we are optimistic that a similar model can be trained with pre-CHF diagnosis (case) vs control patient images to facilitate machine learning-assisted identification of childhood cancer survivors more likely to develop CHF in the future.

Hybrid InceptionV3-SVM-Based Approach for Human Posture Detection in Health Monitoring Systems

Posture detection targets toward providing assessments for the monitoring of the health and welfare of humans have been of great interest to researchers from different disciplines. The use of computer vision systems for posture recognition might result in useful improvements in healthy aging and support for elderly people in their daily activities in the field of health care. Computer vision and pattern recognition communities are particularly interested in fall automated recognition. Human sensing and artificial intelligence have both paid great attention to human posture detection (HPD). The health status of elderly people can be remotely monitored using human posture detection, which can distinguish between positions such as standing, sitting, and walking. The most recent research identified posture using both deep learning (DL) and conventional machine learning (ML) classifiers. However, these techniques do not effectively identify the postures and overfits of the model overfits. Therefore, this study suggested a deep convolutional neural network (DCNN) framework to examine and classify human posture in health monitoring systems. This study proposes a feature selection technique, DCNN, and a machine learning technique to assess the previously mentioned problems. The InceptionV3 DCNN model is hybridized with SVM ML and its performance is compared. Furthermore, the performance of the proposed system is validated with other transfer learning (TL) techniques such as InceptionV3, DenseNet121, and ResNet50. This study uses the least absolute shrinkage and selection operator (LASSO)-based feature selection to enhance the feature vector. The study also used various techniques, such as data augmentation, dropout, and early stop, to overcome the problem of model overfitting. The performance of this DCNN framework is tested using benchmark Silhouettes of human posture and classification accuracy, loss, and AUC value of 95.42%, 0.01, and 99.35% are attained, respectively. Furthermore, the results of the proposed technology offer the most promising solution for indoor monitoring systems.

FFSCN: Frame Fusion Spectrum Center Net for Carrier Signal Detection

Carrier signal detection is a complicated and essential task in many domains because it demands a quick response to the existence of several carriers in the wideband, while also precisely predicting each carrier signal’s frequency centers and bandwidths, including single-carrier and multi-carrier modulation signals. Multi-carrier modulation signals, such as FSK and OFDM, could be incorrectly recognized as several single-carrier signals by using the spectrum center net (SCN) or FCN-based method. This paper designed a deep convolutional neural network (CNN) framework for multi-carrier signal detection by fusing the features of multiple consecutive frames of the broadband power spectra and estimating the information of each single-carrier or multi-carrier modulation signal in the broadband, called frame fusion spectrum center net (FFSCN), including FFSCN-R, FFSCN-MN, and FFSCN-FMN. FFSCN includes three base parts, the deep CNN-based backbone, the feature pyramid network (FPN) neck, and the regression network (RegNet) head. FFSCN-R and FFSCN-MN fusing the FPN out features, which use the Residual and MobileNetV3 backbone, respectively, and FFSCN-MN cost less inference time. To further reduce the complexity of FFSCN-MN, the designed FFSCN-FMN modifies the MobileNet blocks and fuses the features at each block of the backbone. The multiple consecutive frames of broadband power spectra not only preserve the high-resolution ratio of the broadband frequency, but also add the features of the signal changes in the time dimension. Extensive experimental results demonstrate that the proposed FFSCN can effectively detect multi-carrier and single-carrier modulation signals in the broadband power spectrum and outperform SCN in accuracy and efficiency.

Key frames assisted hybrid encoding for high-quality compressive video sensing.

Snapshot compressive imaging (SCI) encodes high-speed scene video into a snapshot measurement and then computationally makes reconstructions, allowing for efficient high-dimensional data acquisition. Numerous algorithms, ranging from regularization-based optimization and deep learning, are being investigated to improve reconstruction quality, but they are still limited by the ill-posed and information-deficient nature of the standard SCI paradigm. To overcome these drawbacks, we propose a new key frames assisted hybrid encoding paradigm for compressive video sensing, termed KH-CVS, that alternatively captures short-exposure key frames without coding and long-exposure encoded compressive frames to jointly reconstruct high-quality video. With the use of optical flow and spatial warping, a deep convolutional neural network framework is constructed to integrate the benefits of these two types of frames. Extensive experiments on both simulations and real data from the prototype we developed verify the superiority of the proposed method.

Modern Crack Detection for Bridge Infrastructure Maintenance Using Machine Learning

Manual investigation of damages incurred to infrastructure is a challenging process, in that it is not only labour-intensive and expensive but also inefficient and error-prone. To automate the process, a method that is based on computer vision for automatically detecting cracks from 2D images is a viable option. Amongst the different methods of deep learning that are commonly used, the convolutional neural network (CNNs) is one that provides the opportunity for end-to-end mapping/learning of image features instead of using the manual suboptimal image feature extraction. Specifically, CNNs do not require human supervision and are more suitable to be used for indoor and outdoor applications requiring image feature extraction and are less influenced by internal and external noise. Additionally, the CNN’s are also computationally efficient since they are based on special convolution layers and pooling operations that enable the full execution of CNN frameworks on several hardware devices. Keeping this in mind, we propose a deep CNN framework that is based on 10 different convolution layers along with a cycle GAN (Generative Adversarial Network) for predicting the crack segmentation pixel by pixel in an end-to-end manner. The methods proposed here include the Deeply Supervised Nets (DSN) and Fully Convolutional Networks (FCN). The use of DSN enables integrated feature supervision for each stage of convolution. Furthermore, the model has been designed intricately for learning and aggregating multi-level and multiscale features while moving from the lower to higher convolutional layers through training. Hence, the architecture in use here is unique from the ones in practice which just use the final convolution layer. In addition, to further refine the predicted results, we have used a guided filter and CRFs (Conditional Random Fields) based methods. The verification step for the proposed framework was carried out with a set of 537 images. The deep hierarchical CNN framework of 10 convolutional layers and the Guided filtering achieved high-tech and advanced performance on the acquired dataset, showing higher F-score, Recall and Precision values of 0.870, 0.861, and 0.881 respectively, as compared to the traditional methods such as SegNet, Crack-BN, and Crack-GF.