Search results

With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its training process requires a large amount of data to improve model performance. However, labeled data is expensive and not readily available.

To address the above problem, researchers have integrated semi-supervised and deep learning, using a limited number of labeled data and many unlabeled data to train models. In this paper, Generative Adversarial Networks (GANs) are analyzed as an entry point. Firstly, we discuss the current research on GANs in image super-resolution applications, including supervised, unsupervised, and semi-supervised learning approaches. Secondly, based on semi-supervised learning, different optimization methods are introduced as an example of image classification. Eventually, experimental comparisons and analyses of existing semi-supervised optimization methods based on GANs will be performed.

Following the analysis of the selected studies, we summarize the problems that existed during the research process and propose future research directions.

This paper reviews and analyzes research on generative adversarial networks for image super-resolution and classification from various learning approaches. The comparative analysis of experimental results on current semi-supervised GAN optimizations is performed to provide a reference for further research.

Based on the strong feature representation ability of the convolutional neural network (CNN), generous object detection methods in remote sensing (RS) have been proposed one after another. However, due to the large variation in scale and the omission of relevant relationships between objects, there are still great challenges for object detection in RS. Most object detection methods fail to take the difficulties of detecting small and medium-sized objects and global context into account. Moreover, inference time and lightness are also major pain points in the field of RS.

To alleviate the aforementioned problems, this study proposes a novel method for object detection in RS, which is called lightweight object detection with a multi-receptive field and long-range dependency in RS images (MFLD). The multi-receptive field extraction (MRFE) and long-range dependency information extraction (LDIE) modules are put forward.

To concentrate on the variability of objects in RS, MRFE effectively expands the receptive field by a combination of atrous separable convolutions with different dilated rates. Considering the shortcomings of CNN in extracting global information, LDIE is designed to capture the relationships between objects. Extensive experiments over public datasets in RS images demonstrate that our MFLD method surpasses the state-of-the-art methods. Most of all, on the NWPU VHR-10 dataset, our MFLD method achieves 94.6% mean average precision with 4.08 M model volume.

This paper proposed a method called lightweight object detection with multi-receptive field and long-range dependency in RS images.

Light field images (LFIs) have gained popularity as a technology to increase the field of view (FoV) of plenoptic cameras since they can capture information about light rays with a large FoV. Wide FoV causes light field (LF) data to increase rapidly, which restricts the use of LF imaging in image processing, visual analysis and user interface. Effective LFI coding methods become of paramount importance. This paper aims to eliminate more redundancy by exploring sparsity and correlation in the angular domain of LFIs, as well as mitigate the loss of perceptual quality of LFIs caused by encoding.

This work proposes a new efficient LF coding framework. On the coding side, a new sampling scheme and a hierarchical prediction structure are used to eliminate redundancy in the LFI's angular and spatial domains. At the decoding side, high-quality dense LF is reconstructed using a view synthesis method based on the residual channel attention network (RCAN).

In three different LF datasets, our proposed coding framework not only reduces the transmitted bit rate but also maintains a higher view quality than the current more advanced methods.

(1) A new sampling scheme is designed to synthesize high-quality LFIs while better ensuring LF angular domain sparsity. (2) To further eliminate redundancy in the spatial domain, new ranking schemes and hierarchical prediction structures are designed. (3) A synthetic network based on RCAN and a novel loss function is designed to mitigate the perceptual quality loss due to the coding process.

The aim of this study is to offer valuable insights to businesses and facilitate better understanding on transformer-based models (TBMs), which are among the widely employed generative artificial intelligence (GAI) models, garnering substantial attention due to their ability to process and generate complex data.

Existing studies on TBMs tend to be limited in scope, either focusing on specific fields or being highly technical. To bridge this gap, this study conducts robust bibliometric analysis to explore the trends across journals, authors, affiliations, countries and research trajectories using science mapping techniques – co-citation, co-words and strategic diagram analysis.

Identified research gaps encompass the evolution of new closed and open-source TBMs; limited exploration across industries like education and disciplines like marketing; a lack of in-depth exploration on TBMs' adoption in the health sector; scarcity of research on TBMs' ethical considerations and potential TBMs' performance research in diverse applications, like image processing.

The study offers an updated TBMs landscape and proposes a theoretical framework for TBMs' adoption in organizations. Implications for managers and researchers along with suggested research questions to guide future investigations are provided.

The anomaly detection task for oil and gas pipelines based on acoustic signals faces issues such as background noise coverage, lack of effective features, and small sample sizes, resulting in low fault identification accuracy and slow efficiency. The purpose of this paper is to study an accurate and efficient method of pipeline anomaly detection.

First, to address the impact of background noise on the accuracy of anomaly signals, the adaptive multi-threshold center frequency variational mode decomposition method(AMTCF-VMD) method is used to eliminate strong noise in pipeline signals. Secondly, to address the strong data dependency and loss of local features in the Swin Transformer network, a Hybrid Pyramid ConvNet network with an Agent Attention mechanism is proposed. This compensates for the limitations of CNN’s receptive field and enhances the Swin Transformer’s global contextual feature representation capabilities. Thirdly, to address the sparsity and imbalance of anomaly samples, the SpecAugment and Scaper methods are integrated to enhance the model’s generalization ability.

In the pipeline anomaly audio and environmental datasets such as ESC-50, the AMTCF-VMD method shows more significant denoising effects compared to wavelet packet decomposition and EMD methods. Additionally, the model achieved 98.7% accuracy on the preprocessed anomaly audio dataset and 99.0% on the ESC-50 dataset.

This paper innovatively proposes and combines the AMTCF-VMD preprocessing method with the Agent-SwinPyramidNet model, addressing noise interference and low accuracy issues in pipeline anomaly detection, and providing strong support for oil and gas pipeline anomaly recognition tasks in high-noise environments.

The safety of high-speed rail operation environments is an important guarantee for the safe operation of high-speed rail. The operating environment of the high-speed rail is complex, and the main factors affecting the safety of high-speed rail operating environment include meteorological disasters, perimeter intrusion and external environmental hazards. The purpose of the paper is to elaborate on the current research status and team research progress on the perception of safety situation in high-speed rail operation environment and to propose directions for further research in the future.

In terms of the mechanism and spatio-temporal evolution law of the main influencing factors on the safety of high-speed rail operation environments, the research status is elaborated, and the latest research progress and achievements of the team are introduced. This paper elaborates on the research status and introduces the latest research progress and achievements of the team in terms of meteorological, perimeter and external environmental situation perception methods for high-speed rail operation.

Based on the technical route of “situational awareness evaluation warning active control,” a technical system for monitoring the safety of high-speed train operation environments has been formed. Relevant theoretical and technical research and application have been carried out around the impact of meteorological disasters, perimeter intrusion and the external environment on high-speed rail safety. These works strongly support the improvement of China’s railway environmental safety guarantee technology.

With the operation of CR450 high-speed trains with a speed of 400 km per hour and the application of high-speed train autonomous driving technology in the future, new and higher requirements have been put forward for the safety of high-speed rail operation environments. The following five aspects of work are urgently needed: (1) Research the single factor disaster mechanism of wind, rain, snow, lightning, etc. for high-speed railways with a speed of 400 kms per hour, and based on this, study the evolution characteristics of multiple safety factors and the correlation between the high-speed driving safety environment, revealing the coupling disaster mechanism of multiple influencing factors; (2) Research covers multi-source data fusion methods and associated features such as disaster monitoring data, meteorological information, route characteristics and terrain and landforms, studying the spatio-temporal evolution laws of meteorological disasters, perimeter intrusions and external environmental hazards; (3) In terms of meteorological disaster situation awareness, research high-precision prediction methods for meteorological information time series along high-speed rail lines and study the realization of small-scale real-time dynamic and accurate prediction of meteorological disasters along high-speed rail lines; (4) In terms of perimeter intrusion, research a multi-modal fusion perception method for typical scenarios of high-speed rail operation in all time, all weather and all coverage and combine artificial intelligence technology to achieve comprehensive and accurate perception of perimeter security risks along the high-speed rail line and (5) In terms of external environment, based on the existing general network framework for change detection, we will carry out research on change detection and algorithms in the surrounding environment of high-speed rail.

This paper aims to estimate contact location from sparse and high-dimensional soft tactile array sensor data using the tactile image. The authors used three feature extraction methods: handcrafted features, convolutional features and autoencoder features. Subsequently, these features were mapped to contact locations through a contact location regression network. Finally, the network performance was evaluated using spherical fittings of three different radii to further determine the optimal feature extraction method.

This paper aims to estimate contact location from sparse and high-dimensional soft tactile array sensor data using the tactile image.

This research indicates that data collected by probes can be used for contact localization. Introducing a batch normalization layer after the feature extraction stage significantly enhances the model’s generalization performance. Through qualitative and quantitative analyses, the authors conclude that convolutional methods can more accurately estimate contact locations.

The paper provides both qualitative and quantitative analyses of the performance of three contact localization methods across different datasets. To address the challenge of obtaining accurate contact locations in quantitative analysis, an indirect measurement metric is proposed.

This study aims to present a new rapid enhancement digital elevation model (DEM) framework using Google Earth Engine (GEE), machine learning, weighted interpolation and spatial interpolation techniques with ground control points (GCPs), where high-resolution DEMs are crucial spatial data that find extensive use in many analyses and applications.

First, rapid-DEM imports Shuttle Radar Topography Mission (SRTM) data and Sentinel-2 multispectral imagery from a user-defined time and area of interest into GEE. Second, SRTM with the feature attributes from Sentinel-2 multispectral imagery is generated and used as input data in support vector machine classification algorithm. Third, the inverse probability weighted interpolation (IPWI) approach uses 12 fixed GCPs as additional input data to assign the probability to each pixel of the image and generate corrected SRTM elevations. Fourth, gridding the enhanced DEM consists of regular points (E, N and H), and the contour interval is 5 m. Finally, densification of enhanced DEM data with GCPs is obtained using global positioning system technique through spatial interpolations such as Kriging, inverse distance weighted, modified Shepard’s method and triangulation with linear interpolation techniques.

The results were compared to a 1-m vertically accurate reference DEM (RD) obtained by image matching with Worldview-1 stereo satellite images. The results of this study demonstrated that the root mean square error (RMSE) of the original SRTM DEM was 5.95 m. On the other hand, the RMSE of the estimated elevations by the IPWI approach has been improved to 2.01 m, and the generated DEM by Kriging technique was 1.85 m, with a reduction of 68.91%.

A comparison with the RD demonstrates significant SRTM improvements. The suggested method clearly reduces the elevation error of the original SRTM DEM.

This study aims to offer an effective nanocomposite for potential use to consolidate and protect deteriorated archaeological pottery.

Three nanocomposites were used in the experimental study. This study used nano Primal AC33, silicon dioxide (SiO₂) and montmorillonite (MMT) nanoparticles to protect and consolidate pottery specimens. Pottery specimens were made at 800°C for this investigation. Consolidation materials were applied with a brush. The properties of the treated pottery specimens were assessed using several methods such as digital and scanning electron microscopes, static water contact angle, color alteration, physical properties and compressive strength.

Microscopic examination indicated the ability of the nano Primal AC33/MMT nanocomposites to cover the outer surface well and bind the inner granules. Concerning specimens with code F treated with nano Primal AC33 5%/MMT 3% nanocomposites, it achieved an increase in contact angle (120°), density (1.23 g/cm³) and compressive strength (561 kg/cm²), as well as a decrease in color change (ΔE = 2.62), water absorption (4.45%) and porosity (5.46%). The novelty of the results is due to the characteristics of nano Primal AC33 5%/MMT 3% nanocomposites used in the current study.

This study describes the significant results of the analytical methods used for evaluating consolidation materials used in this study. The findings offer useful information for the protection of archaeological pottery. The investigation indicated that nano Primal AC33 5%/MMT 3% nanocomposites gave the best results. Therefore, it is recommended to use this nanocomposite to consolidate archaeological pottery. As a result, the current work provides a promising first step in conserving archaeological pottery for future studies.

Physics-informed neural networks (PINNs) have become a new tendency in flow simulation, because of their self-advantage of integrating both physical and monitored information of fields in solving the Navier–Stokes equation and its variants. In view of the strengths of PINN, this study aims to investigate the impact of spatially embedded data distribution on the flow field results around the train in the crosswind environment reconstructed by PINN.

PINN can integrate data residuals with physical residuals into the loss function to train its parameters, allowing it to approximate the solution of the governing equations. In addition, with the aid of labelled training data, PINN can also incorporate the real site information of the flow field in model training. In light of this, the PINN model is adopted to reconstruct a two-dimensional time-averaged flow field around a train under crosswinds in the spatial domain with the aid of sparse flow field data, and the prediction results are compared with the reference results obtained from numerical modelling.

The prediction results from PINN results demonstrated a low discrepancy with those obtained from numerical simulations. The results of this study indicate that a threshold of the spatial embedded data density exists, in both the near wall and far wall areas on the train’s leeward side, as well as the near train surface area. In other words, a negative effect on the PINN reconstruction accuracy will emerge if the spatial embedded data density exceeds or slips below the threshold. Also, the optimum arrangement of the spatial embedded data in reconstructing the flow field of the train in crosswinds is obtained in this work.

In this work, a strategy of reconstructing the time-averaged flow field of the train under crosswind conditions is proposed based on the physics-informed data-driven method, which enhances the scope of neural network applications. In addition, for the flow field reconstruction, the effect of spatial embedded data arrangement in PINN is compared to improve its accuracy.