An Improved Convolutional Neural Network-Based Coal Structure Identification Method in Complex Tectonic Areas

In this paper, the depth images and the colour images provided by Kinect sensors are used to enhance the accuracy of human detection. The depth-based human detection method is fast but less accurate. On the other hand, the faster region convolutional neural network-based human detection method is accurate but requires a rather complex hardware configuration. To simultaneously leverage the advantages and relieve the drawbacks of each method, one master and one client system is proposed. The final goal is to make a novel Robot Operation System (ROS)-based Perception Sensor Network (PSN) system, which is more accurate and ready for the real time application. The experimental results demonstrate the outperforming of the proposed method compared with other conventional methods in the challenging scenarios.

This paper considers a task of visual object tracking with application in embedded systems with limited computational power. The complexity of the task lies in finding the proper balance between algorithm result quality and its runtime efficiency. To select the tracking method to be used in embedded systems multiple machine learning approaches were analyzed: convolutional neural network-based methods, recurrent neural network-based methods, one-shot learning-based methods, siamese neural networks and transformers. The method nanotrack was selected for further research and analysis. To perform runtime performance and algorithm accuracy evaluation the test environment was developed using C++ programming language which was deployed on Raspberry Pi hardware. Performance analysis showed the method is suitable for real time object tracking on Raspberry Pi 5 as it allows to process more than 25 frames per second, additionally leaving the room for usage of a more complex backbone model if needed. Accuracy was evaluated using LaSOT dataset. The main types of challenging situations for the tracking algorithm were identified and corresponding videos from LaSOT dataset were selected. Based on visually observing tracking results on these videos, the conclusions about overall sufficient adaptive qualities of the algorithm were made. To evaluate overall algorithm quality the accuracy metric was calculated on LaSOT dataset and compared to other state-of-the-art tracking methods. Accuracy metrics were computed on LaSOT dataset, showing good performance for some object classes and worse scores for others. Based on the analysis, it is expected that training neural network on a data representing limited target set of object classes will lead to satisfactory accuracy for these classes while preserving original runtime performance. The further research directions are experimenting with different backbone models for the Nanotrack method and evaluating their influence on accuracy and runtime performance.

Intrusion detection algorithms based on deep learning are currently a hot topic in the field of intrusion detection research, but most of the research focuses on how to improve the algorithms to improve the accuracy of intrusion detection, while ignoring the problem that the limited labeled data generated by a single organization is not enough to train a deep model with high accuracy in practice. The paper proposes a federal learning and convolutional neural network-based intrusion detection method that can expand the data volume by jointly training the model with data sets from multiple participants. The method uses a federation learning framework to design a deep learning-based intrusion detection model. The data dimensionality is first reconstructed by data padding to form two-dimensional data, then the DCNN network is used for feature extraction and learning under the mechanism of federation learning, and finally the model is trained with a softmax classifier for detection. In addition, aiming at the over-fitting problem caused by the compression and over-parameterization of deep neural networks, this paper proposes a model pruning method based on sparse convolutional neural network according to the weight parameters of the convolutional layer and the Batch Normalization layer (BN). This section will introduce the implementation details of this method. The experimental results show that this method largely reduces the training time and maintains a high detection rate. In addition, the model ensures data security and privacy compared to typical intrusion detection models.

This paper proposes a deep convolutional neural network-based low-light image enhancement method. In order to adaptively enhance the image brightness, a convolutional neural network with convolutional modules is designed. Lowlight image is firstly down-sampled into sub-images. Then an illumination map is obtained from the input image to provide additional information to the network. The network works on a tensor that consists of sub-images and illumination map, achieving a good performance in brightness increasing and structure preservation. The enhanced result is reconstructed from the output sub-images. Experimental results demonstrate the effectiveness of the proposed method in low-light image enhancement.

In recent years, huge volumes of healthcare data are getting generated in various forms. The advancements made in medical imaging are tremendous owing to which biomedical image acquisition has become easier and quicker. Due to such massive generation of big data, the utilization of new methods based on Big Data Analytics (BDA), Machine Learning (ML), and Artificial Intelligence (AI) have become essential. In this aspect, the current research work develops a new Big Data Analytics with Cat Swarm Optimization based deep Learning (BDA-CSODL) technique for medical image classification on Apache Spark environment. The aim of the proposed BDA-CSODL technique is to classify the medical images and diagnose the disease accurately. BDA-CSODL technique involves different stages of operations such as preprocessing, segmentation, feature extraction, and classification. In addition, BDA-CSODL technique also follows multi-level thresholding-based image segmentation approach for the detection of infected regions in medical image. Moreover, a deep convolutional neural network-based Inception v3 method is utilized in this study as feature extractor. Stochastic Gradient Descent (SGD) model is used for parameter tuning process. Furthermore, CSO with Long Short-Term Memory (CSO-LSTM) model is employed as a classification model to determine the appropriate class labels to it. Both SGD and CSO design approaches help in improving the overall image classification performance of the proposed BDA-CSODL technique. A wide range of simulations was conducted on benchmark medical image datasets and the comprehensive comparative results demonstrate the supremacy of the proposed BDA-CSODL technique under different measures.

The patent database is often used in searches of inspirational stimuli for innovative design opportunities because of its large size, extensive variety and rich design information in patent documents.However, most patent mining research only focuses on textual information and ignores visual information.Herein, we propose a convolutional neural network (CNN)-based patent image retrieval method.The core of this approach is a novel neural network architecture named Dual-VGG that is aimed to accomplish two tasks: visual material type prediction and international patent classification (IPC) class label prediction.In turn, the trained neural network provides the deep features in the image embedding vectors that can be utilized for patent image retrieval and visual mapping.The accuracy of both training tasks and patent image embedding space are evaluated to show the performance of our model.This approach is also illustrated in a case study of robot arm design retrieval.Compared to traditional keyword-based searching and Google image searching, the proposed method discovers more useful visual information for engineering design.

With the growing development of remote sensors, huge volumes of remote sensing data are being utilized in related applications, bringing new challenges to the efficiency and capability of processing huge datasets. Spatiotemporal remote sensing data fusion can restore high spatial and high temporal resolution remote sensing data from multiple remote sensing datasets. However, the current methods require long computing times and are of low efficiency, especially the newly proposed deep learning-based methods. Here, we propose a fast three-dimensional convolutional neural network-based spatiotemporal fusion method (STF3DCNN) using a spatial-temporal-spectral dataset. This method is able to fuse low-spatial high-temporal resolution data (HTLS) and high-spatial low-temporal resolution data (HSLT) in a four-dimensional spatial-temporal-spectral dataset with increasing efficiency, while simultaneously ensuring accuracy. The method was tested using three datasets, and discussions of the network parameters were conducted. In addition, this method was compared with commonly used spatiotemporal fusion methods to verify our conclusion.

Driver drowsiness is the leading cause of accidents worldwide. Due to lack of sleep and fatigue, many motorists often experience fatigue and drowsiness, which often leads to traffic accidents. Warn the driver early is the best way to avoid traffic accidents caused by drowsiness. There are numerous techniques to detect sleepiness. In this article, we presented a deep learning-based approach to detect driver drowsiness. We used the convolutional neural network-based transfer learning method (MobileNet), a class of deep learning. We used the eye region- based dataset to predict sleepiness.

In recent years, the performance of the convolutional neural network-based pedestrian detection method has improved significantly. However, an imbalance remains between detection accuracy and speed. In this paper, we employ a one-stage object detection framework and propose a pedestrian detection method based on the multi-scale attention mechanism of a convolutional neural network to improve the imbalance between accuracy and speed. First, a multi-scale convolution module is designed to extract corresponding features at different scales. Second, using the attention module, association information between features is mined from space and channel perspectives to strengthen the original features. Then, the enhanced features are passed through a classification and regression module to perform object positioning and bounding box regression. Finally, to learn more pedestrian location information, we improve the loss function to realise better network training. The proposed method achieved considerable results on the challenging CityPersons and Caltech pedestrian detection datasets.

Robust image watermarking that can resist camera shooting has gained considerable attention in recent years due to the need to protect sensitive printed information from being captured and reproduced without authorization. Indeed, the evolution of smartphones has made identity watermarking a feasible and convenient process. However, this process also introduces challenges like perspective distortions, which can significantly impair the effectiveness of watermark detection on freehandedly digitized images. To meet this challenge, ResNet50-based ensemble of randomized neural networks (ReRNet), a recursive convolutional neural network-based correction method, is presented for the print-cam process, specifically applied to identity images. Therefore, this paper proposes an improved Fourier watermarking method based on ReRNet to rectify perspective distortions. Experimental results validate the robustness of the enhanced scheme and demonstrate its superiority over existing methods, especially in handling perspective distortions encountered in the print-cam process.

Protein-RNA interactions play a critical role in various biological processes. The accurate prediction of RNA-binding residues in proteins has been one of the most challenging and intriguing problems in the field of computational biology. The existing methods still have a relatively low accuracy especially for the sequence-based ab-initio methods. In this work, we propose an approach aPRBind, a convolutional neural network-based ab-initio method for RNA-binding residue prediction. aPRBind is trained with sequence features and structural ones (particularly including residue dynamics information and residue-nucleotide propensity developed by us) that are extracted from the predicted structures by I-TASSER. The analysis of feature contributions indicates the sequence features are most important, followed by dynamics information, and the sequence and structural features are complementary in binding site prediction. The performance comparison of our method with other peer ones on benchmark dataset shows that aPRBind outperforms some state-of-the-art ab-initio methods. Additionally, aPRBind can give a better prediction for the modeled structures with TM-score≥0.5, and meanwhile since the structural features are not very sensitive to the refined 3D structures, aPRBind has only a marginal dependence on the accuracy of the structure model, which allows aPRBind to be applied to the RNA-binding site prediction for the modeled or unbound structures. The source code is available at https://github.com/ChunhuaLiLab/aPRbind. Supplementary data are available at Bioinformatics online.

Deep learning-based segmentation algorithms for medical image require massive training datasets with accurate annotations, which is costly since it takes much human effort to manually labeling from scratch. Therefore, interactive image segmentation is important and may greatly improve the efficiency and accuracy of medical image labeling. Some interactive segmentation methods (e.g. Deep Extreme Cut and Deepgrow) may improve the labeling through minimal interactive input. However these methods only utilize the initial manually input information, while existing segmentation results (such as annotations produced by nonprofessionals or conventional segmentation algorithms) cannot be utilized. In this paper, an interactive segmentation method is proposed to make use of both existing segmentation results and human interactive information to optimize the segmentation results progressively. In this framework, the user only needs to click on the foreground or background of the target individual on the medical image, the algorithm could adaptively learn the correlation between them, and automatically completes the segmentation of the target. The main contributions of this paper are: (1) We adjusted and applied a convolutional neural network which takes medical image data and user's clicks information as input to achieve more accurate segmentation of medical images. (2) We designed an iterative training strategy to realize the applicability of the model to deal with different number of clicks data input. (3) We designed an algorithm based on false positive and false negative regions to simulate the user's clicks, so as to provide enough training data. By applying the proposed method, users can easily extract the region of interest or modify the segmentation results by multiple clicks. The experimental results of 6 medical image segmentation tasks show that the proposed method achieves more accurate segmentation results by at most five clicks.

Nowadays, remote sensing images are widely used in many fields. To obtain high-quality remote sensing images, remote sensing image fusion methods have attracted much attention. Although convolutional neural network-based pansharpening methods have good results, these methods focus on the forward propagation of the network, which cannot effectively seek the mapping relationship between images. Moreover, it is difficult to obtain global information due to the limitations of convolutional operations. In this paper, we propose a pansharpening method based on multiscale delayed channel attention networks. The method iteratively seeks to correlate high-resolution stage features with the original low-resolution multispectral image, providing a mechanism for error feedback to map the error of each stage. Meanwhile, it designs a multiscale feature fusion module to fuse feature information from different fields of view. The design of the delayed channel attention mechanism makes the network acquire the association relationship between low-frequency information and high-frequency information through adaptive learning, giving different weights to high-frequency information, and making it more flexible in dealing with different types of information. Finally, the feature aggregation module is used to generate fused images and adjust the corresponding feature information. The experimental results obtained from the Gaofen-2 and WorldView-2 experimental data show that the method achieves a significant improvement compared to the current fusion algorithms.

Since the tire pressure has a significant influence on driving safety, even self-driving vehicles need to be aware of their current tire pressures. Two major types of methods for estimating tire pressures exist: direct and indirect methods. In spite of recent advancements in direct Tire Pressure Monitoring Systems (TPMSs), indirect pressure monitoring systems still play a significant role due to their low costs. Indirect systems rely on the processing of signals from wheel speed sensors. In most cases, a transformation is applied to generate a frequency spectrum from which the tire pressure-dependent eigenfrequency can be extracted. The most accurate methods apply the Fourier transform, but these require the highest computational power. After the spectrum of signals from the wheel speed sensor is created, the eigenfrequency must be extracted. Several methods are available to extract significant frequency components. One of the easiest methods is peak searching, however, it is susceptible to noise. On the other hand, more accurate methods that are less sensitive to noise require more computational power. If a transform that consumes less computational power can be applied, then the freed resources can be used by a better eigenfrequency identification method. In this paper, a Hybrid Wavelet-Fourier Transform and Convolutional Neural Network-based method is presented, which exhibits a promising level of noise tolerance.

Sparse-view computed tomography (CT) has been attracting attention for its reduced radiation dose and scanning time. However, analytical image reconstruction methods suffer from streak artifacts due to insufficient projection views. Recently, various deep learning-based methods have been developed to solve this ill-posed inverse problem. Despite their promising results, they are easily overfitted to the training data, showing limited generalizability to unseen systems and patients. In this work, we propose a novel streak artifact reduction algorithm that provides a system- and patient-specificsolution. Motivated by the fact that streak artifacts are deterministic errors, we regenerate the same artifacts from a prior CT image under the same system geometry. This prior image need not be perfect but should contain patient-specific information and be consistent with full-view projection data for accurate regeneration of the artifacts. To this end, we use a coordinate-based neural representation that often causes image blur but can greatly suppress the streak artifacts while having multiview consistency. By employing techniques in neural radiance fields originally proposed for scene representations, the neural representation is optimized to the measured sparse-view projection data via self-supervised learning. Then, we subtract the regenerated artifacts from the analytically reconstructed original image to obtain the final correctedimage. To validate the proposed method, we used simulated data of extended cardiac-torso phantoms and the 2016 NIH-AAPM-Mayo Clinic Low-Dose CT Grand Challenge and experimental data of physical pediatric and head phantoms. The performance of the proposed method was compared with a total variation-based iterative reconstruction method, naive application of the neural representation, and a convolutional neural network-based method. In visual inspection, it was observed that the small anatomical features were best preserved by the proposed method. The proposed method also achieved the best scores in the visual information fidelity, modulation transfer function, and lung nodulesegmentation. The results on both simulated and experimental data suggest that the proposed method can effectively reduce the streak artifacts while preserving small anatomical structures that are easily blurred or replaced with misleading features by the existing methods. Since the proposed method does not require any additional training datasets, it would be useful in clinical practice where the large datasets cannot becollected.