Search

Informative and accurate survival prediction with individualized dynamic risk profiles over time is critical for personalized disease prevention and clinical management. The massive genetic data, such as SNPs from genome-wide association studies (GWAS), together with well-characterized time-to-event phenotypes provide unprecedented opportunities for developing effective survival prediction models. Recent advances in deep learning have made extraordinary achievements in establishing powerful prediction models in the biomedical field. However, the applications of deep learning approaches in survival prediction are limited, especially with utilizing the wealthy GWAS data. Motivated by developing powerful prediction models for the progression of an eye disease, age-related macular degeneration (AMD), we develop and implement a multilayer deep neural network (DNN) survival model to effectively extract features and make accurate and interpretable predictions. Various simulation studies are performed to compare the prediction performance of the DNN survival model with several other machine learning-based survival models. Finally, using the GWAS data from two large-scale randomized clinical trials in AMD with over 7800 observations, we show that the DNN survival model not only outperforms several existing survival prediction models in terms of prediction accuracy (eg, c-index =0.76), but also successfully detects clinically meaningful risk subgroups by effectively learning the complex structures among genetic variants. Moreover, we obtain a subject-specific importance measure for each predictor from the DNN survival model, which provides valuable insights into the personalized early prevention and clinical management for this disease., (© 2020 John Wiley & Sons Ltd.)

In recent years, deep learning (DL) networks have been widely used in super-resolution (SR) and exhibit improved performance. In this paper, an image quality assessment (IQA)-guided single image super-resolution (SISR) method is proposed in DL architecture, in order to achieve a nice tradeoff between perceptual quality and distortion measure of the SR result. Unlike existing DL-based SR algorithms, an IQA net is introduced to extract perception features from SR results, calculate corresponding loss fused with original absolute pixel loss, and guide the adjustment of SR net parameters. To solve the problem of heterogeneous datasets used by IQA and SR networks, an interactive training model is established via cascaded network. We also propose a pairwise ranking hinge loss method to overcome the shortcomings of insufficient samples during training process. The performance comparison between our proposed method with recent SISR methods shows that the former achieves a better tradeoff between perceptual quality and distortion measure than the latter. Extensive benchmark experiments and analyses also prove that our method provides a promising and opening architecture for SISR, which is not confined to a specific network model., Competing Interests: The authors have declared that no competing interests exist.

Stochastic gradient descent (SGD) algorithms, with constant momentum and its variants such as Adam, are the optimization methods of choice for training deep neural networks (DNNs). There is great interest in speeding up the convergence of these methods due to their high computational expense. Nesterov accelerated gradient with a time-varying momentum (NAG) improves the convergence rate of gradient descent for convex optimization using a specially designed momentum; however, it accumulates error when the stochastic gradient is used, slowing convergence at best and diverging at worst. In this paper, we propose scheduled restart SGD (SRSGD), a new NAG-style scheme for training DNNs. SRSGD replaces the constant momentum in SGD by the increasing momentum in NAG but stabilizes the iterations by resetting the momentum to zero according to a schedule. Using a variety of models and benchmarks for image classification, we demonstrate that, in training DNNs, SRSGD significantly improves convergence and generalization; for instance, in training ResNet-200 for ImageNet classification, SRSGD achieves an error rate of 20.93% versus the benchmark of 22.13%. These improvements become more significant as the network grows deeper. Furthermore, on both CIFAR and ImageNet, SRSGD reaches similar or even better error rates with significantly fewer training epochs compared to the SGD baseline. Our implementation of SRSGD is available at https://github.com/minhtannguyen/SRSGD.

Aiming at the problem of micro-cracks detection of photovoltaic modules in industrial production line, in order to reduce labor cost, improve detection efficiency and quickly adapt to the micro-cracks detection of new products with the support of a few number of samples, a micro-cracks detection algorithm of solar cells based on few shot samples with multi-loss is proposed. Firstly, in order to enrich the semantic information extracted by convolutional neural network, Transformer’s multi-head attention mechanism is introduced to alleviate the impact of the distribution difference of each batch of products on crack detection, and promote the model to focus on crack information from diversified products. Secondly, the strategy of combining multiple loss functions to constrain the model training is used to optimize feature extraction. On the basis of direct classification loss, the triplet loss is used to shorten the feature distance between cracked samples. In addition, the implicit classification loss is designed to adapt to the characteristics of type differences between the two types of cells with or without cracks, and fully learn the diversity of historical component data. This algorithm can use a small number of samples to quickly extract the features of new components and detect micro-crack defects of new products accurately. The experimental results on the actual industrial production data sets show that the recall of the algorithm can be improved by 10 percentage points compared with other baseline models. This algorithm can effectively alleviate the problem of scarce samples with hidden cracks and greatly reduce the cost of frequent data labeling and model training for each batch of new products.

Deep learning has been increasingly popular in omics data analysis. Recent works incorporating variable selection into deep learning have greatly enhanced the model's interpretability. However, because deep learning desires a large sample size, the existing methods may result in uncertain findings when the dataset has a small sample size, commonly seen in omics data analysis. With the explosion and availability of omics data from multiple populations/studies, the existing methods naively pool them into one dataset to enhance the sample size while ignoring that variable structures can differ across datasets, which might lead to inaccurate variable selection results. We propose a penalized integrative deep neural network (PIN) to simultaneously select important variables from multiple datasets. PIN directly aggregates multiple datasets as input and considers both homogeneity and heterogeneity situations among multiple datasets in an integrative analysis framework. Results from extensive simulation studies and applications of PIN to gene expression datasets from elders with different cognitive statuses or ovarian cancer patients at different stages demonstrate that PIN outperforms existing methods with considerably improved performance among multiple datasets. The source code is freely available on Github (rucliyang/PINFunc). We speculate that the proposed PIN method will promote the identification of disease‐related important variables based on multiple studies/datasets from diverse origins. [ABSTRACT FROM AUTHOR]

B-mode ultrasound has emerged as a prevalent tool for observing tongue motion in speech production, gaining traction in speech therapy applications. However, the effective analysis of ultrasound tongue image frame sequences (UTIFs) encounters many challenges, such as the presence of high levels of speckle noise and obscured views. Recently, the application of machine learning, especially deep learning techniques, to UTIF interpretation has shown promise in overcoming these hurdles. This paper presents a thorough examination of the existing literature, focusing on UTIF analysis. The scope of our work encompasses four key areas: a foundational introduction to deep learning principles, an exploration of motion tracking methodologies, a discussion of feature extraction techniques, and an examination of cross-modality mapping. The paper concludes with a detailed discussion of insights gleaned from the comprehensive literature review, outlining potential trends and challenges that lie ahead in the field. [ABSTRACT FROM AUTHOR]

Background: Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) stand as pivotal diagnostic tools for brain disorders, offering the potential for mutually enriching disease diagnostic perspectives. However, the costs associated with PET scans and the inherent radioactivity have limited the widespread application of PET. Furthermore, it is noteworthy to highlight the promising potential of high‐field and ultra‐high‐field neuroimaging in cognitive neuroscience research and clinical practice. With the enhancement of MRI resolution, a related question arises: can high‐resolution MRI improve the quality of PET images? Purpose: This study aims to enhance the quality of synthesized PET images by leveraging the superior resolution capabilities provided by high‐field and ultra‐high‐field MRI. Methods: From a statistical perspective, the joint probability distribution is considered the most direct and fundamental approach for representing the correlation between PET and MRI. In this study, we proposed a novel model, the joint diffusion attention model, namely, the joint diffusion attention model (JDAM), which primarily focuses on learning information about the joint probability distribution. JDAM consists of two primary processes: the diffusion process and the sampling process. During the diffusion process, PET gradually transforms into a Gaussian noise distribution by adding Gaussian noise, while MRI remains fixed. The central objective of the diffusion process is to learn the gradient of the logarithm of the joint probability distribution between MRI and noise PET. The sampling process operates as a predictor‐corrector. The predictor initiates a reverse diffusion process, and the corrector applies Langevin dynamics. Results: Experimental results from the publicly available Alzheimer's Disease Neuroimaging Initiative dataset highlight the effectiveness of the proposed model compared to state‐of‐the‐art (SOTA) models such as Pix2pix and CycleGAN. Significantly, synthetic PET images guided by ultra‐high‐field MRI exhibit marked improvements in signal‐to‐noise characteristics when contrasted with those generated from high‐field MRI data. These results have been endorsed by medical experts, who consider the PET images synthesized through JDAM to possess scientific merit. This endorsement is based on their symmetrical features and precise representation of regions displaying hypometabolism, a hallmark of Alzheimer's disease. Conclusions: This study establishes the feasibility of generating PET images from MRI. Synthesis of PET by JDAM significantly enhances image quality compared to SOTA models. [ABSTRACT FROM AUTHOR]

Accurate extraction of farmland boundaries is crucial for improving the efficiency of farmland surveys, achieving precise agricultural management, enhancing farmers’ production conditions, protecting the ecological environment, and promoting local economic development. Remote sensing and deep learning are feasible methods for creating large-scale farmland boundary maps. However, existing neural network models have limitations that restrict the accuracy and reliability of agricultural parcel extraction using remote sensing technology. In this study, we used high-resolution satellite images (2 m, 1 m, and 0.8 m) and the U2-Net++ model based on the RSU module, deep separable convolution, and the channel-spatial attention mechanism module to extract different types of fields. Our model exhibited significant improvements in farmland parcel extraction compared with the other models. It achieved an F1-score of 97.13%, which is a 7.36% to 17.63% improvement over older models such as U-Net and FCN and a more than 2% improvement over advanced models such as DeepLabv3+ and U2-Net. These results indicate that U2-Net++ holds the potential for widespread application in the production of large-scale farmland boundary maps.

The main cause of corneal blindness worldwide is keratitis, especially the infectious form caused by bacteria, fungi, viruses, and Acanthamoeba. The key to effective management of infectious keratitis hinges on prompt and precise diagnosis. Nevertheless, the current gold standard, such as cultures of corneal scrapings, remains time-consuming and frequently yields false-negative results. Here, using 23,055 slit-lamp images collected from 12 clinical centers nationwide, this study constructed a clinically feasible deep learning system, DeepIK, that could emulate the diagnostic process of a human expert to identify and differentiate bacterial, fungal, viral, amebic, and noninfectious keratitis. DeepIK exhibited remarkable performance in internal, external, and prospective datasets (all areas under the receiver operating characteristic curves > 0.96) and outperformed three other state-of-the-art algorithms (DenseNet121, InceptionResNetV2, and Swin-Transformer). Our study indicates that DeepIK possesses the capability to assist ophthalmologists in accurately and swiftly identifying various infectious keratitis types from slit-lamp images, thereby facilitating timely and targeted treatment. [ABSTRACT FROM AUTHOR]

The quantification of absorbed light is essential for understanding laser-material interactions and melt pool dynamics in order to minimize defects in additively manufactured metal components. The geometry of a vapor depression formed during laser melting is closely related to laser energy absorption. This relationship has been observed by the state-of-the-art in situ high-speed synchrotron X-ray visualization and integrating sphere radiometry. These two techniques create a temporally resolved dataset consisting of vapor depression images and corresponding laser absorptance. In this work, we propose two different approaches to predict instantaneous laser absorptance. The end-to-end approach uses deep convolutional neural networks to learn implicit features of X-ray images automatically and predict the laser energy absorptance. The two-stage approach uses a semantic segmentation model to engineer geometric features and predict absorptance using classical regression models. While having distinct advantages, both approaches achieved a consistently low mean absolute error of less than 3.3%. [ABSTRACT FROM AUTHOR]

This paper proposes an end-to-end neural network model that fully utilizes the characteristic of uneven fog distribution to estimate visibility in fog images. Firstly, we transform the original single labels into discrete label distributions and introduce discrete label distribution learning on top of the existing classification networks to learn the difference in visibility information among different regions of an image. Then, we employ the bilinear attention pooling module to find the farthest visible region of fog in the image, which is incorporated into an attention-based branch. Finally, we conduct a cascaded fusion of the features extracted from the attention-based branch and the base branch. Extensive experimental results on a real highway dataset and a publicly available synthetic road dataset confirm the effectiveness of the proposed method, which has low annotation requirements, good robustness, and broad application space. [ABSTRACT FROM AUTHOR]

In the non-intrusive automated testing system for Internet of Vehicles (IoV) applications, automatic recognition of text and icons on vehicle central control screens is of paramount importance. However, the detection and recognition of content on vehicle central control screens are inherently complex. Additionally, during non-intrusive vehicle central control screen image testing, there is a deficiency of suitable datasets and detection methods. This deficiency renders information within vehicle application images difficult to be accurately extracted by the detection network. To address this problem, this study first constructs a dataset tailored for text detection and recognition on vehicle screens. This dataset encompasses a variety of vehicle central control images, enabling the generic text detection and recognition network to more effectively identify and interpret text within vehicle screens. Subsequently, this research proposes an enhanced Fully Convolutional Networks for Text Detection (FOTS) method for vehicle central control screen text detection and recognition. This method elevates the semantic expression capabilities of features by sharing vehicle central control screen text detection and recognition features. Furthermore, it improves multi-scale feature processing capabilities through the utilization of a feature transformation module. Validation through visual and quantitative experiments demonstrates that the proposed method can effectively accomplish text detection and recognition tasks on vehicle screens. This achievement bears significant implications for the field of automated testing in IoV applications. [ABSTRACT FROM AUTHOR]

Deep learning is being increasingly employed for hyperspectral classification, although such use is often predicated on the availability of a sufficiently large set of labeled samples for training. To improve classification performance under a limited training-set size, a semi-supervised network with end-to-end local–global active learning (AL) based on graph convolutional networks (GCNs) is proposed. The proposed AL extracts both global as well as local graph-based features to gauge the discriminative information in unlabeled samples, while semi-supervised classification expands the training set of a fully supervised classifier by attaching pseudo-labels to high-confidence unlabeled samples. Experimental results demonstrate that the proposed network outperforms not only other approaches to semi-supervised classification but also several existing fully supervised methods. The source code of this method can be found at https://github.com/XtaoS/semi-LG-AGCN. [ABSTRACT FROM AUTHOR]

To improve the prediction accuracy of milling tool wear, a prediction method based on Attention-LSTM is proposed. In the training phase, first, the data are pre-processed by truncation, downsampling, and the Hampel filtering method, and then features are extracted by the time domain, frequency domain, and time-frequency domain analysis methods. Second, a deep neural network is designed to describe the complex nonlinear function between features and tool wear. Last, aiming at the insufficient prediction accuracy due to the LSTM lacking feature extraction and enhancement, the Attention mechanism is introduced to optimize the model. The results suggest that this prediction method provides an efficient strategy for milling tool wear prediction. [ABSTRACT FROM AUTHOR]

Background: Muscle fatigue is a crucial indicator to determine whether training is in place and to protect trainers. Purpose: To make full use of morphological information of surface EMG and ECG signals in the time domain, a new idea and method for the fatigue assessment of exercise muscles based on data fusion is proposed in this paper. Methods: sEMG and ECG time series with the same length were obtained by signal preprocessing and sequence normalization, feature extraction of sequence tenses was realized by a deep learning network based on sequential convolution and signal fusion model of muscle fatigue evaluation was established by D-S evidence theory. Experiment: Thirty volunteers were recruited and divided into three groups. ECG signals and sEMG signals at the biceps brachii of the right upper limb were monitored in a 20-minute exercise cycle. Results: The prediction result of TCN based on time domain signal is better than the commonly used KNN and SVM recognition algorithm, and the recognition accuracy of relaxed, excessive and fatigue by D-S fusion was 89%, 86%, 88.5%. The accuracy was 0.9055, 0.9494 and 0.9269, respectively. The recall rates of the three conditions were 0.9303, 0.9570 and 0.9435. The F-score of the three conditions was 0.8911, 0.8764 and 0.8837, respectively. Conclusion: Based on time series and time series convolutional network, sEMG and ECG fusion of motor muscle recognition method can better distinguish different state information and has certain practical value in the fields of muscle evaluation, clinical diagnosis, wearable devices and so on. [ABSTRACT FROM AUTHOR]

A machine vision system (MVS) is a technology that can analyze and recognize still or moving pictures using a computer. It is a branch of computer vision that looks like a security camera but can automatically capture, evaluate, and analyze images. The drawbacks are obvious. In the event of a computer vision system failure, firms must have a team of highly trained people with a thorough understanding of the distinctions. Artificial neural networks with numerous layers between the input and output layers are deep neural networks (DNN). Neurons, synapses, weights, biases, and functions are all part of any neural network, regardless of the kind. Many of the challenges in computer vision revolve around using convolutional neural networks (CNN) to categorize images into predefined categories. Convolutional and pooling layers were utilized to decrease the image's size before feeding the reduced data to fully connected layers. According to the paper, the MVS-CNN algorithm can analyze a picture and determine the value of various characteristics and objects inside it. It is called convolution when combining two functions to create a third function. It is a fusion of two different datasets. A CNN performs convolution on the input data to build a feature map using a filter or kernel. Using a convolutional neural network, an inverted residual block is introduced as the basic block to balance identification accuracy and processing efficiency. The suggested method's higher inspection performance is achieved with a huge dataset of photos of faulty and defect-free bottles. The result is obtained from the proposed method, the standard deviation ratio is 83.56%, absolute error ratio is 77.26%, trajectory length difference ratio is 82.35%, source pattern radiation amplitude ratio is 86.25%, classification of accuracy ratio is 83.25%, and finally, overall percentage performance ratio is 90.26%. [ABSTRACT FROM AUTHOR]

To diagnose faulty equipments in time and save the cost of maintenance, a deep learning model of fault diagnosis based on multi-scale time serial features fusion is proposed for the operation and maintenance of photovoltaic power station. To take advantage of the different abilities of convolutional layers with different scales, the model implements the multi-scale neighborhood feature extraction, which can help the network filter the noise in input data while keep the important information. Then, considering the long time series and high dimension of monitoring data, a long short-term memory unit with attention mechanism is used to extract sequential features. Finally, to improve the discernment of the network, metric learning loss function is applied to assist training. In addition, a data normalization algorithm is designed out. It can be used to rectify the impact of devices and weather on monitoring data through comparison between data from different devices and different days. Experiments prove that the proposed model can diagnose faults of equipment more accurately compared with other time series analysis algorithms, which can achieve 95% accuracy on real monitoring data of photovoltaic power station. [ABSTRACT FROM AUTHOR]

Acquiring Electroencephalography (EEG) data is often time-consuming, laborious, and costly, posing practical challenges to train powerful but data-demanding deep learning models. This study proposes a surrogate EEG data-generation system based on cycle-consistent adversarial networks (CycleGAN) that can expand the number of training data. This study used EEG2Image based on a modified S-transform (MST) to convert EEG data into EEG-topography. This method retains the frequency-domain characteristics and spatial information of the EEG signals. Then, the CycleGAN is used to learn and generate motor-imagery EEG data of stroke patients. From the visual inspection, there is no difference between the EEG topographies of the generated and original EEG data collected from the stroke patients. Finally, we used convolutional neural networks (CNN) to evaluate and analyze the generated EEG data. The experimental results show that the generated data effectively improved the classification accuracy. [ABSTRACT FROM AUTHOR]

With the development of our society, unmanned aerial vehicles (UAVs) appear more frequently in people's daily lives, which could become a threat to public security and privacy, especially at night. At the same time, laser active imaging is an important detection method for night vision. In this paper, we implement a UAV detection model for our laser active imaging system based on deep learning and a simulated dataset that we constructed. Firstly, the model is pre-trained on the largest available dataset. Then, it is transferred to a simulated dataset to learn about the UAV features. Finally, the trained model is tested on real laser active imaging data. The experimental results show that the performance of the proposed method is greatly improved compared to the model not trained on the simulated dataset, which verifies the transferability of features learned from the simulated data, the effectiveness of the proposed simulation method, and the feasibility of our solution for UAV detection in the laser active imaging domain. Furthermore, a comparative experiment with the previous method is carried out. The results show that our model can achieve high-precision, real-time detection at 104.1 frames per second (FPS). [ABSTRACT FROM AUTHOR]

In recent years, internal short circuits have frequently been the cause of safety accidents, and traditional diagnosis methods for such problem have limitations that prevent their application under complex working conditions. Furthermore, due to the scarcity of real internal short circuit data, it is difficult to obtain a large amount of real vehicle data, which makes internal short circuit fault diagnosis even more challenging. In this paper, fault batteries with unknown parameters are diagnosed using a residual network based on multi-label processed battery data and transfer learning is utilized to optimize the diagnosis effect for fault localization and fault degree identification, thus increasing the information richness of the training model samples and improving the training effect. Accuracy, recall, and false positive rate are used to evaluate the diagnosis results of the residual network. The results demonstrate that the accuracy rate increased by 11.1% after transfer learning, indicating a significant reduction in misdiagnoses. The proposed fault diagnosis method using residual network and transfer learning has practical significance for enhancing battery fault detection accuracy and efficiency. Especially in areas such as electric vehicles and energy storage systems, it can provide effective technical support for battery health monitoring and early warning. [ABSTRACT FROM AUTHOR]

Incorporating various modes of information into the machine learning procedure is becoming a new trend And data from various source can provide more information than single one no matter they are heterogeneous or homogeneous. Existing deep learning based algorithms usually directly concatenate features from each domain to represent the input data. Seldom of them take the quality of data into consideration which is a key issue in related multimodal problems. In this paper, we propose an efficient quality-aware deep neural network to model the weight of data from each domain using deep reinforcement learning (DRL). Specifically, we take the weighting of each domain as a decision-making problem and teach an agent learn to interact with the environment. The agent can tune the weight of each domain through discrete action selection and obtain a positive reward if the saliency results are improved. The target of the agent is to achieve maximum rewards after finished its sequential action selection. We validate the proposed algorithms on dual-modal saliency detection in a coarse-to-fine way. The coarse saliency maps are generated from an encoder–decoder framework which is trained with content loss and adversarial loss. The final results can be obtained via adaptive weighting of maps from each domain. Extensive experiments on two kinds of salient object detection benchmarks all obtained a significant gain by fusing two-modalities with our proposed quality-aware deep neural network. • We introduce a novel and general quality estimation network using DRL. • We apply it on the dual-modal saliency detection successfully and further propose a coarse-to-fine salient object detection framework based on GAN. • Extensive experiments on two public dual-modal saliency detection dataset validated the effectiveness of the introduced algorithm. [ABSTRACT FROM AUTHOR]

• Three types of rural building roof were determined as main detection targets. • A revised U-net model was proposed to detect building roofs at the macro level. • Potential PV panel area at micro level was calculated using 2 installation methods. • The spatial distribution of solar PV power generation was obtained. Rooftop photovoltaic (PV) power generation is an important form of solar energy development, especially in rural areas where there is a large quantity of idle rural building roofs. Existing methods to estimate the spatial distribution of PV power generation potential are either unable to obtain spatial information or are too expensive to be applied in rural areas. Herein, we propose a novel approach to estimate the spatial distribution of the general potential of rural rooftop power from publicly available satellite images. We divide rural building roofs into three categories based on their orientation and roof angle and propose a revised U-Net deep learning network to extract roof images from satellite images at the macro level. Based on the rooftop detection, a calculation method for the potential area of the installed PV panel at the micro level was developed, considering different types of PV panels and their maintenance methods. By combining the above results and setting the solar radiation parameters and PV system efficiency, we can obtain the spatial distribution of the rooftop PV power generation potential in rural areas. This method is applied in northern China on a village and a town scale, and the overall accuracy of the revised U-Net model can reach over 92%. The spatial distribution information was analyzed and displayed. The annual average PV power generation potential ranges from 26.5 to 36.2 MWh per household and from 7.3 to 10 GWh per village. [ABSTRACT FROM AUTHOR]

Ship type classification is an essential task in maritime navigation domains, contributing to shipping monitoring, analysis, and forecasting. Presently, with the development of ship positioning and monitoring systems, many ship trajectory acquisitions make it possible to classify ships according to their movement pattern. Existing methods of ship classification based on trajectory include classical sequence analysis and deep learning methods. However, the real ship trajectories are unevenly distributed in geographical space, which leads to many problems in inferring the ship movement mode on the original ship trajectory. This paper proposes a hierarchical spatial-temporal embedding method based on enhanced trajectory features for ship type classification. We first preprocess the trajectory and combine the port information to transform the original ship trajectory into the moored records of ships, removing the unevenly distributed points in the trajectory data and enhancing key points' semantic information. Then, we propose a Hierarchical Spatial-Temporal Embedding Method (Hi-STEM) for ship classification. Hi-STEM maps moored records in the original geographical space into the feature space and can efficiently find the classification plane in the feature space. Experiments are conducted on real-world datasets and compared with several existing methods. The result shows that our approach has high accuracy in ship classification on ship moored records. We make the source code and datasets publicly available. [ABSTRACT FROM AUTHOR]

Magnetic anomaly detection is becoming increasingly prevalent for detecting and locating the buried pipelines. The detection performance is often hindered by adjacent pipeline, near-field ferromagnetic objects and random noises. In order to overcome these obstacles, a magnetic anomaly detection method based on deep learning neural networks (DLNN) is proposed to decouple and denoise the integrated detection to accurately extract the magnetic anomaly of single pipeline. The theoretical derivation of the vertical component of magnetic anomaly was executed based on Poisson's equation. Then the integrated detection was simulated by summing magnetic anomalies of parallel pipelines and metal sphere, as well as white Gaussian noise. The DLNN was constructed with improved optimization design, and trained using supervised learning method. The results show that the proposed method exhibits almost immune to random noises, the prediction accuracy approaches to 90% with signal to noise ratio (SNR) of 30 dB. Meanwhile, the predictive accuracy is still above 80% with interferences both from near-field ferromagnetic objects and random noises with SNR of 30 dB. The method becomes practically significant in the development of geomagnetic inspection instruments for the adjacent parallel pipelines. • The expressions of magnetic anomaly are derived based on Poisson's equation. • A deep learning neural networks is constructed with improved design. • Extracting magnetic anomaly of single pipeline accurately. • Prediction accuracy approaches to 90% with signal to noise ratio drops to 30 dB. [ABSTRACT FROM AUTHOR]

The decision-making process concerning the maintenance of equipment significantly impacts the safety and reliability of the aeroengine system. A cyber-aeroengine system (CAS) integrates intricate aeroengine components with a cyber decision-making space based on the communication network, thereby facilitating computational support for forecasting the health status of the aeroengine system. Within the cyber realm, we introduce a novel approach termed the graph spatio-temporal attention recurrent network with phase-lag index (PLI-GSTARN) to assess the degradation states of aeroengine systems. This method constructs a spatio-temporal graph based on sensor signal correlations and information reachability across distributed sensors within the physical equipment. Subsequently, the proposed framework employs a graph attention network to capture spatial features and a long short-term memory (LSTM) layer equipped with an attention mechanism to capture temporal features inherent in the constructed graph. Ultimately, this methodology is applied to cyber–physical systems within aircraft engines to manage remaining health life and diagnose faults, yielding commendable outcomes. • The cyber-aeroengine system (CAS) integrates complex aeroengine components with a cyber decision-making space facilitated by communication networks. This integration enhances computational support for predicting the health status of aeroengine systems. • Introduces the novel approach of graph spatio-temporal attention recurrent network with phase-lag index (PLI-GSTARN). This method constructs a spatio-temporal graph using sensor signal correlations across distributed sensors, enabling advanced assessment of aeroengine degradation states. • Combines a graph attention network for spatial features and an LSTM layer with attention mechanisms for temporal features. Applied to aircraft engine cyber-physical systems, this approach effectively manages remaining health life and diagnoses faults, showing significant operational benefits. [ABSTRACT FROM AUTHOR]

Predictive modelling of mineral prospectivity, a critical, but challenging procedure for delineation of undiscovered prospective targets in mineral exploration, has been spurred by recent advancements of spatial modelling techniques and machine learning algorithms. In this study, a set of machine learning methods, including random forest (RF), support vector machine (SVM), artificial neural network (ANN), and a deep learning convolutional neural network (CNN), were employed to conduct a data-driven W prospectivity modelling of the southern Jiangxi Province, China. A total of 118 known W occurrences derived from long-term exploration of this brownfield area and eight evidential layers of multi-source geoscience information related to W mineralization constituted the input datasets. This provided a data-rich foundation for training machine learning models. The optimal configuration of model parameters was trained by a grid search procedure and validated by 10-fold cross-validation. The resulting predictive models were comprehensively assessed by a confusion matrix, receiver operating characteristic curve, and success-rate curve. The modelling results indicate that the CNN model achieves the best classification performance with an accuracy of 92.38%, followed by the RF model (87.62%). In contrast, the RF model outperforms the rest of ML models in overall predictive performance and predictive efficiency. This is characterized by the highest value of area under the curve and the steepest slope of success-rate curve. The RF model was chosen as the optimal model for mineral prospectivity in this region as it is the best predictor. The prospective zones delineated by the prospectivity map occupy 9% of the study area and capture 66.95% of the known mineral occurrences. The geological interpretation of the model reveals that previously neglected Mn anomalies are significant indicators. This implies that enrichment of ore-forming material in the host rocks may play an important role in the formation process of wolframite and can represent an innovative exploration criterion for further exploration in this area. [ABSTRACT FROM AUTHOR]

• The proposed denoising method can eliminate severe noise in a wrapped phase. In the current network, noise level up to a signal to noise ratio (SNR) value of −4 dB can be successfully removed. • After CNN denoising, a wrapped phase can be easily unwrapped using an existing simple unwrapping method. • The proposed denoising method is shown to be effective through extensive comparisons with the average filter, median filter and windowed Fourier filtering. The proposed method outperforms the conventional average filter and median filter, and performs similarly to windowed Fourier filtering. The feasibility of phase unwrapping strategy is demonstrated by comparing with an existing deep learning unwrapping method. • The proposed denoising method is able to directly provide denoising result without adjusting any parameters. We propose a wrapped phase denoising method based on convolutional neural networks (CNN), which can effectively denoise a noisy wrapped phase. The noisy numerator and denominator of the arctangent function are firstly denoised by CNN, and then the filtered numerator and denominator use the arctangent function to obtain the clean wrapped phase. We experimentally verify the denoising performance using various wrapped phase that contains different noise conditions, where the denoised wrapped phase can achieve a satisfactory unwrapping performance using the existing simple unwrapping method. In addition, the proposed method is further demonstrated through the comparison of the existing methods, and shows an accurate denoising result without adjusting any parameters. [ABSTRACT FROM AUTHOR]