Original Form Research Articles

Image Dehazing Technique Based on DenseNet and the Denoising Self-Encoder

The application value of low-quality photos taken in foggy conditions is significantly lower than that of clear images. As a result, restoring the original image information and enhancing the quality of damaged images on cloudy days are crucial. Commonly used deep learning techniques like DehazeNet, AOD-Net, and Li have shown encouraging progress in the study of image dehazing applications. However, these methods suffer from a shallow network structure leading to limited network estimation capability, reliance on atmospheric scattering models to generate the final results that are prone to error accumulation, as well as unstable training and slow convergence. Aiming at these problems, this paper proposes an improved end-to-end convolutional neural network method based on the denoising self-encoder-DenseNet (DAE-DenseNet), where the denoising self-encoder is used as the main body of the network structure, the encoder extracts the features of haze images, the decoder performs the feature reconstruction to recover the image, and the boosting module further performs the feature fusion locally and globally, and finally outputs the dehazed image. Testing the defogging effect in the public dataset, the PSNR index of DAE-DenseNet is 22.60, which is much higher than other methods. Experiments have proved that the dehazing method designed in this paper is better than other algorithms to a certain extent, and there is no color oversaturation or an excessive dehazing phenomenon in the image after dehazing. The dehazing results are the closest to the real image and the viewing experience feels natural and comfortable, with the image dehazing effect being very competitive.

Dynamic Process Fault Detection and Diagnosis Method Based on Factor Analysis: Application on the Three‐Tank System Process

ABSTRACTTo address the issue of underreporting faults in the detection of tiny faults by dynamic factor analysis (DFA), a novel fault detection and diagnosis method based on DFA‐sliding window combined with mean square error (DFA‐SWMSE) is proposed. Firstly, the data matrix is augmented by introducing time lag shifts. Secondly, factor analysis (FA) is applied to the augmented data matrix, achieving dimensionality reduction and feature extraction while retaining most of the original data's information. Then, the sliding window technique is applied to calculate the mean square error of the dimensionally reduced data, allowing for the monitoring of the system's current state and the detection of tiny faults. Finally, effective fault diagnosis is achieved through the analysis of fault factors and variable contributions. The proposed method is validated using a complex dynamic numerical example and a three‐tank system process named Sim3Tanks. This system has gained widespread application in the field of process fault detection due to its ability to simulate and generate various types of faults. The proposed method is compared with principal component analysis (PCA), dynamic principal component analysis (DPCA), PCA similarity factor (SPCA), FA, and DFA. The experimental results thoroughly validate the effectiveness of the proposed method in detecting and diagnosing tiny faults in dynamic processes.

Prior-guided restoration of intense local specular highlight in fringe projection profilometry images

This paper presents a novel prior-guided restoration method, to our knowledge, aimed at removing and recovering intense local specular highlight in fringe projection profilometry (FPP) images of specular objects. Local reflections, caused by the direct reflection of the projector on smooth surfaces, often saturate pixel intensities, posing a significant obstacle to 3D shape reconstruction. The proposed method combines sinusoidal fringe projection principles with improved fitting techniques. By analyzing fringe patterns in non-highlight regions, the constant and amplitude parameters of the fringes are determined by non-highlight regions. For the critical initial phase parameter, the continuity of highlight regions and the fixed relative geometry between the projector and object are leveraged, which enables an iterative calculation strategy that progressively estimates fringe intensity within specular regions. The results show a seamless integration of the restored fringe data with the original non-highlight information, ensuring global consistency and continuity. 3D measurement experiments demonstrate effective restoration of morphological distortions and filling of point cloud holes.

Blockchain Based Proxy Re-Encryption for Secure Data Sharing

This paper proposes a solution to secure data sharing within the Internet of Things (IoT) by combining Proxy Re-Encryption (PRE) and Blockchain. In IoT networks, data must often be shared across multiple devices and users, raising concerns over data privacy and security. Proxy Re-Encryption enables controlled data sharing without disclosing original information, while Blockchain technology offers an immutable, transparent ledger for tracking data transactions. Together, these technologies ensure data integrity, privacy, and efficient access control, making them suitable for modern IoT applications

Abstract 4116844: Simplifying Cardiology Research Abstracts: Assessing ChatGPT's Readability and Comprehensibility for Non-Medical Audiences

Background: Artificial Intelligence (AI)-powered chatbots like ChatGPT are increasingly used in academic medical settings to help with tasks such as evidence synthesis and manuscript drafting. They have shown potential in simplifying complex medical texts for non-medical audiences like patients and journalists. However, less is known about whether simplified texts may exclude important information or be of interest to patients or other non-medically-trained people such as journalists. Objective: This study aims to assess ChatGPT's capacity to simplify cardiology research abstracts by eliminating jargon and enhancing universal comprehension. Methods: We analyzed all abstracts and scientific statements published from July to November 2023 in Circulation (n=113). These abstracts were processed through ChatGPT with the prompt: "Please rewrite the following text to be comprehensible at a 5th-grade reading level. Retain all original information and exclude nothing". We assessed the readability of both original and simplified texts using Flesch-Kincaid Grade Level (FKGL) and Reading Ease (FKRE) scores. Additionally, a panel of five physicians and five laypeople evaluated these texts for completeness, accuracy, and understandability. Results: ChatGPT transformation or abstracts reduced the required reading level from a college graduate to 8-9th grade by both FKGL (18.3 to 8.6; p<.001) and FKRE (14.6 to 68.5; p<.001). The physician panel generally found that the simplified abstracts retained all essential information without introducing errors. Both physicians and laypeople found the simplified texts more comprehensible. Laypeople appreciated the ease of understanding but did not strongly express a desire for more such simplified texts, and some still worried about the simplified abstracts missing important details. Conclusion: ChatGPT simplifies medical research abstracts to a level understandable by those with less than a high school education without excluding important information. This approach may be useful to communicate new research findings to patients and other non-medically-trained people.

A temporal convolution network-based just-in-time learning method for industrial quality variable prediction

Real-time acquisition of quality variables is paramount for enhancing control and optimization of industrial processes. Process modeling methods, such as soft sensors, offer a means to predict difficult-to-obtain quality variables using easily measurable process parameters. However, the dynamic nature of industrial processes poses significant challenges to modeling. For instance, conventional models are typically trained offline using historical data, rendering them incapable of adapting to real-time changes in data distribution or environmental conditions. To tackle this challenge, we introduce a novel approach termed the Residual Temporal Attention Temporal Convolution Network (RTA-TCN) and propose a just-in-time learning method based on RTA-TCN for industrial process modeling. The RTA-TCN model incorporates temporal attention into TCN, enabling the integration of previous time-step process variables into the current ones, as well as the fusion of internally relevant features among inputs. Moreover, to prevent the partial loss of original information during feature integration, residual connections are introduced into the temporal attention mechanism. These connections facilitate the retention of original feature information to a maximal extent while integrating relevant features. Consequently, the proposed RTA-TCN demonstrates significant advantages in handling the non-linearity and long-term dynamic dependencies inherent in industrial variables. Additionally, the proposed just-in-time learning method leverages RTA-TCN as a local model and updates it in real-time using online industrial data. This just-in-time learning method enables effective adaptation to varying data distributions and environmental conditions. We validate the performance of our method using two industrial datasets (Debutanizer Column and Sulfur Recovery Unit).

Joint Mixing Data Augmentation for Skeleton-based Action Recognition

Skeleton-based action recognition is beneficial for understanding human behavior in videos, and thus has received much attention in recent years as an important research area in action recognition. Current research focuses on designing more advanced algorithms to better extract spatio-temporal information from skeleton data. However, due to the small amount of data in the existing skeleton dataset and the lack of effective data augmentation methods, it is easy to lead to overfitting in model training. To address this challenge, we propose a mix-based data augmentation method, Joint Mixing Data Augmentation (JMDA), which can generally improve the effectiveness and robustness of various skeleton-based action recognition algorithms. In terms of spatial information, we introduce SpatialMix (SM), a method that projects the original 3D skeleton discrete information into a 2D space. Then, SM mixes the projected spatial information between two random samples during the training process to achieve the spatial-based mixing data augmentation. Concerning temporal information, we propose TemporalMix (TM). Leveraging the temporal continuity in skeleton data, we perform a temporal resize operation on the original skeleton data, and then merge two random samples during training to achieve the temporal-based mixed data augmentation. Additionally, we analyze the Feature Mismatch (FM) problem caused by introducing mix-based data augmentation into skeleton data. Then we propose a new data preprocessing method called Feature Alignment (FA) to effectively address this problem and improve model performance. Moreover, we propose a novel training pipeline, Joint Training Strategy (JTS), which combines multiple mix-based data augmentation methods for further improvement of model performance. Specifically, our proposed JMDA is plug-and-play and widely applicable to skeleton-based action recognition models. At the same time, the application of JMDA does not increase the model parameters and there is almost no additional training cost. We conduct extensive experiments on NTU RGB+D 60 and NTU RGB+D 120 datasets to demonstrate the effectiveness and robustness of the proposed JMDA on several mainstream skeleton-based action recognition algorithms.

Modeling Functional Brain Networks for ADHD via Spatial Preservation-Based Neural Architecture Search.

Modeling functional brain networks (FBNs) for attention deficit hyperactivity disorder (ADHD) has sparked significant interest since the abnormal functional connectivity is discovered in certain functional magnetic resonance imaging (fMRI)-based brain regions compared to typical developmental control (TC) individuals. However, existing models for modeling FBNs generally use dimensionality reduction techniques to process the high dimensional input data, which results in confusion and an inaccurate representation of voxel interactions between spatially close brain regions, causing misdiagnosis of the disease. To address these issues, we propose a spatial preservation-based neural architecture search (SP-NAS) for FBNs modeling in ADHD. The main work includes three-fold: 1) A spatial preservation module is designed to embed original spatial information into dimensionality reduction data, addressing the challenge of a large number of parameters in the original data and mitigating disease misdiagnosis resulting from voxel confusion between different brain regions caused by dimensionality reduction. 2) A search space using more suitable search operations is constructed to efficiently extract spatial-temporal interaction characteristics of fMRI data in ADHD while narrowing the search space. 3) Cross-regional association differences between ADHD and TC groups are explored for ADHD auxiliary diagnosis since the abnormal activation regions of ADHD relative to TC on the brain regions and the abnormal connectivity between the lesion brain regions are identified. Model validation results on the ADHD-200 dataset show that the FBNs obtained from SP-NAS not only achieve competitive results in ADHD diagnosis but also reveal abnormal connections in the lesion regions of ADHD consistent with clinical diagnosis.

Leaf cultivar identification via prototype-enhanced learning

Leaf cultivar identification, as a typical task of ultra-fine-grained visual classification (UFGVC), is facing a huge challenge due to the high similarity among different varieties. In practice, an instance may be related to multiple varieties to varying degrees, especially in the UFGVC datasets. However, deep learning methods trained on one-hot labels fail to reflect patterns shared across categories and thus perform poorly on this task. As an analogy to natural language processing (NLP), by capturing the co-relation between labels, label embedding can select the most informative words and neglect irrelevant ones when predicting different labels. Based on this intuition, we propose a novel method named Prototype-enhanced Learning (PEL), which is predicated on the assumption that label embedding encoded with the inter-class relationships would force the image classification model to focus on discriminative patterns. In addition, a new prototype update module is put forward to learn inter-class relations by capturing label semantic overlap and iteratively update prototypes to generate continuously enhanced soft targets. Prototype-enhanced soft labels not only contain original one-hot label information, but also introduce rich inter-category semantic association information, thus providing more effective supervision for deep model training. Extensive experimental results on 7 public datasets show that our method can significantly improve the performance on the task of ultra-fine-grained visual classification. The code is available at https://github.com/YIYIZH/PEL.

Osler and Cushing on Vesalius

Both Osler and Cushing still considered that mastering anatomy was essential to medical theory and practice. This was particularly true for a skilled surgeon, such as Cushing, but for the reputed internist Osler as well. Osler and Cushing, devoted bibliophiles, collected outstanding works, including those of Vesalius, and made up extremely valuable libraries meant to preserve original information and documents, able to convey traditions from the past to the new generations. Besides, they thoroughly discussed and interpreted the work and life of Vesalius, his importance as a trailblazer and significance for the history of medical knowledge. These two titans of modern medicine embodied the classic humanistic features of doctors and medicine, a science tightly connected with science, art, philosophy and religion, but equally with ethics and medical deontology. Not haphazardly, today, under various forms, medical «humanities», art and history of medicine are once again reconsidered and optionally included in the academic syllabus.

Analyzing vehicle path optimization using an improved genetic algorithm in the presence of stochastic perturbation matter

By analyzing the influence of stochastic perturbation matters on vehicle path optimization, a perturbation scheduling model for logistics and distribution with a carbon tax mechanism is established under the premise of time window variation and load capacity constraints. Herein, we propose an enhanced Genetic Algorithm (GA) based on a Gaussian matrix mutation (GMM) operator, which maintains the diversity of the population while speeding up the algorithm’s convergence. The model builds a Gaussian probability matrix using the site positional order distribution characteristics implied in the original site data information, and applies the Gaussian probability matrix to individual gene mutations using a roulette-wheel-selection method; thus, the study guarantees the genetic diversity of the population while guiding it to evolve in the high-fitness direction. Finally, an experimental simulation is performed using data obtained from a commercial supermarket, thereby verifying the effectiveness of the proposed algorithm and comparing it with other algorithms. The results reveal that compared with the classical GA, the average convergence speed of the improved GA can be increased by 50–60% and the consumed algorithm time can be reduced by 48% while maintaining the difference in solution accuracy within 1%.

Kinematic Constrained RRT Algorithm with Post Waypoint Shift for the Shortest Path Planning of Wheeled Mobile Robots.

This paper presents a rapidly exploring random tree (RRT) algorithm with an effective post waypoint shift, which is suitable for the path planning of a wheeled mobile robot under kinematic constraints. In the growth of the exploring tree, the nearest node that satisfies the kinematic constraints is selected as the parent node. Once the distance between the new node and the target is within a certain threshold, the tree growth stops and a target connection based on minimum turning radius arc is proposed to generate an initial complete random path. The most significant difference from traditional RRT-based methods is that the proposed method optimizes the path based on Dubins curves through a post waypoint shift after a random path is generated, rather than through parent node selection and rewiring during the exploring tree growth. Then, it is proved that the method can obtain an optimal path in terms of the shortest length. The optimized path has good convergence and almost does not depend on the state of the initial random path. The comparative test results show that the proposed method has significant advantages over traditional RRT-based methods in terms of the sampling point number, the tree node number, and the path node number. Subsequently, an efficient method is further proposed to avoid unknown obstacles, which utilizes the original path information and thus effectively improves the new path planning efficiency. Simulations and real-world tests are carried out to demonstrate the effectiveness of this method.

Low-dose radiographic inspection of welding by a novel aperiodic reverse stochastic resonance method

Abstract Low-dose radiographic inspection is a growing trend in industry to minimize radiation risks to humans and the environment. However, reduction in radiation dose often introduces significant noise, which affects image quality and hinders accurate identification of subtle defects. This study addresses this issue by introducing a novel phenomenon called aperiodic reverse stochastic resonance (ARSR), observed in nonlinear systems excited by aperiodic binary signals. ARSR enables simultaneous amplitude amplification and reversal of signals under specific noise conditions. Leveraging ARSR, we propose an image denoising framework for low-dose radiographic inspections. First, a set of projection data is obtained by using Radon transform to reduce the dimensionality of X-ray images from different angles. Then, the projection data is modulated based on the ARSR system. Finally, the image is reconstructed based on the inverse Radon transform. Simulations and experimental comparison results in welding applications validate the effectiveness of the framework, demonstrating significant improvements in image quality for low-dose radiographic defect detection. Unlike advanced methods such as Gaussian filtering, BM3D, and DnCNN, which operate at the pixel level, ARSR performs denoising at the projection data stage, reducing noise impact, preserving original information, and focusing on physical data processing during imaging. This approach enhances the detection of subtle defects, highlighting the potential of stochastic resonance in image processing.

Variational quantum algorithm for designing quantum information maskers

Abstract Since the concept of quantum information masking was proposed by Modi et al. [Phys. Rev. Lett. 120, 230501 (2018)], many interesting and significant results have been reported, both theoretically and experimentally. However, designing a quantum information masker is not an easy task, especially for larger systems. In this paper, we propose a variational quantum algorithm to resolve this problem. Specifically, our algorithm is a hybrid quantum-classical model, where the quantum device with adjustable parameters tries to mask quantum information and the classical device evaluates the performance of the quantum device and optimizes its parameters. After optimization, the quantum device behaves as an optimal masker. The loss value during optimization can be used to characterize the performance of the masker. In particular, if the loss value converges to zero, we obtain a perfect masker that masks completely the quantum information generated by the quantum information source, otherwise, the perfect masker does not exist and the subsystems always contain the original information. Nevertheless, these resulting maskers are still optimal. Quantum parallelism is utilized to reduce quantum state preparations and measurements. Our work paves the way for the wide applications of quantum information masking, and some of the techniques used in this work may have potential applications in quantum information processing.

Self-supervised image change detection method based on lightweight capsule network

In response to the significant impact of speckle noise on the accuracy of SAR image change detection, the high complexity of existing capsule network based image change detection methods, and the loss of a large amount of original image information in training samples, this paper proposes a self supervised image change detection method based on the Light Capsule Network (SCapsNet). First, the log ratio operator difference graph is generated, and the "pseudo label" of training samples with high confidence is obtained through the maximum inter class variance method and fuzzy C-means clustering method, which lays the foundation for self-supervised learning; Secondly, construct a three channel training sample based on the difference map of two temporal SAR images and logarithmic ratio operators to maximize the preservation of sample information; Then, SCapsNet is designed to extract training sample features through single scale convolution, and a single scale capsule network is used to mine spatial relationships between features; Finally, comparative experiments and ablation experiments were set up and tested on 5 real SAR Datasets. The experimental results show that the The advantage of this method is to improve the operational efficiency of the method while reducing model complexity, obtain stronger robust features, suppress the adverse impact of speckle noise on change detection performance, and improve change detection performance.

Image segmentation of tunnel water leakage defects in complex environments using an improved Unet model

Computer vision technology provides an intelligent means for detecting tunnel water leakage areas. However, the accuracy of defect feature extraction and segmentation is limited by factors such as insufficient lighting and environmental interference inside tunnels. To address the problem, this paper proposes a tunnel water leakage area segmentation network model called Customized Side Guided-Unet (CSG-Unet), using Unet as the baseline model. The main contributions are: (1) To improve the accuracy of water leakage area extraction, a customized side guided term is introduced to direct the net’s attention to the changes in light and shade within the image. A parallel attention network module is designed to extract internal information from the guided term. Subsequently, a strengthened channel attention module aggregates the guided term and the original information to achieve accurate segmentation of water leakage areas; (2) To address the scarcity of tunnel water leakage area datasets, a basic dataset is constructed by collecting data from open-source datasets and manually gathered data in tunnels. On this basis, perspective transformation is used to change the camera viewpoint, gaussian noise is randomly added to the images in the dataset to simulate images taken in dimly lit scenes, thereby expanding the dataset and enhancing the network’s generalization. The CSG-Unet network was trained using the constructed training set, achieving a mean Intersection over Union (mi IoU) of 85.54%, a mean Dice coefficient (mi Dice) of 85.26%, and a mean Pixel Accuracy (mi PA) of 90.85%. Compared to its baseline network, U-Net (tiny), these metrics show an improvement of over 3.2% in each indicator. Finally, a visual comparison between the improved network and the baseline network further confirms that the proposed model can effectively adapt to the segmentation of water leakage areas in complex environments.

Dehazing network based on residual context attention and cross-layer fusion

Current image dehazing algorithms based on deep learning usually use traditional convolutional layers when extracting features, which easily causes the loss of image details and edge information, ignores the position information of the image when extracting features, and ignores the original information of the image when fusing features, and cannot restore high-quality haze-free images with complete structure and clarity. To address this problem, a dehazing algorithm based on residual context attention and cross-layer feature fusion is proposed. Firstly, the residual group structure is obtained by serializing the proposed residual context blocks, and the features of the first two layers of the network, i.e., the shallow layers, are extracted to obtain rich context information of the shallow layers; secondly, coordinate attention is introduced to establish an attention map with position information, and it is applied to the residual context feature extraction and placed in the third layer of the network, i.e., the deep layer, to extract deeper semantic information; then, in the middle layer of the network, feature information from different resolution streams is fused across layers to enhance the information exchange between the shallow and deep layers to achieve the purpose of feature enhancement; finally, the features with rich semantic information obtained by the network are aggregated with the original input, thereby improving the restoration effect. Experimental results on the RESIDE dataset and the Haze4K dataset show that the proposed algorithm achieves good results in both visual effects and objective indicators.

Separation of Macro- and Micro-Texture to Characterize Skid Resistance of Asphalt Pavement.

The skid resistance of asphalt pavement is an important factor affecting road safety. However, few studies have characterized the contribution of the macro- and micro-texture to the skid resistance of asphalt pavement. In this paper, the generalized extreme studentized deviate (GESD) and neighboring-region interpolation algorithm (NRIA) were used to identify and replace outliers, and median filters were used to suppress noise in texture data to reconstruct textures. On this basis, the separation of the macro- and micro-texture and the Monte Carlo algorithm were used to characterize the skid resistance of asphalt pavement. The results show that the GESD method can accurately identify outliers in the texture, and the median filtering can eliminate burrs in texture data while retaining more original detail information. The contribution of the macro-texture on the skid resistance is mainly attributed to the frictional resistance caused by the adhesion and elastic hysteresis, and the main contribution of the micro-texture is a micro-bulge cutting part in the friction mechanism. This investigation can provide inspiration for the interior mechanism and the specific relationship between the pavement textures and the skid resistance of asphalt pavement.

Origin and preservation mechanisms of organic matter in carbonate concretions from Lower Cambrian black shales in South China

Carbonate concretions are widely used in paleoclimate, paleoenvironmental, and paleontological studies, and even in the study of potential life on Mars. These petrological, elemental, isotopic, and lipid biomarker signals in Meso-Cenozoic carbonate concretions (relatively low thermal maturity) can effectively preserve details of seawater conditions and benthic ecosystems during the deposition of their host sediments/rocks. However, such research on Precambrian-Cambrian carbonate concretions under highly mature conditions remains scarce, and the ability of these ancient carbonate concretions to retain their original biogenic information remains uncertain. To achieve that, this study examines two Cambrian carbonate concretions, using samples from the center, transition, and rim of each, and their adjacent host black shales from the Lower Cambrian Qiongzhusi Formation in the Yangtze Block, South China. Organic and inorganic geochemical analyses were combined to elucidate the origin and preservation process of organic matter (OM) in these ancient Cambrian carbonate concretions. The results show that the thermal maturity of OM within these concretions (1.8 % EqVRo) is relatively low compared to their adjacent host shales (2.9 % EqVRo). Hopanes and steranes are detectable in both free and calcite-occluded hydrocarbons within these concretions, with concentrations of individual compounds ranging from 0.001 to 0.800 μg/g TOC, whereas kerogen-bound hydrocarbons lack detectable biomarkers. The results indicate that the two Cambrian carbonate concretions were formed mainly within the iron reduction and bacterial sulfate reduction zones, extending to depths of 10 to 38 m below the sediment-water interface. The OM within these concretions mainly inherited the initial unaltered signature of OM from the Qiongzhusi host shale. The carbonate concretions protected the internal OM from further thermal and secondary (e.g., biodegradation) alteration processes and might also prevent the formation of the conventional macromolecular skeletal kerogen manifested by the absence of bound biomarkers. The biomarkers, in both free and occluded forms, in the Cambrian carbonate concretions still retained their original source information, providing valuable insights into ancient biogeochemical processes during sediment burial and ancient seawater chemistry during the early Cambrian.

Multi-spectroscopic characterization system for cultural heritage materials analysis (SYSPECTRAL): Conception and example

A comprehensive understanding of chemical composition of cultural heritage materials usually requires several complementary analytical techniques. Given the fragility and value of artworks, minimizing or avoiding sampling and performing in situ analysis under ambient light is an important goal. This article outlines a novel prototype designed to merge LIBS, laser-induced fluorescence spectroscopy (LIF), Raman spectroscopy using a single pulsed laser, and reflectance spectroscopy in a multi-spectroscopic characterization system for cultural heritage analysis (SYSPECTRAL). The aim is to analyze cultural heritage materials in their original place, obtaining both elemental and molecular information at such same point that is not always insured with several separated experimental settings. The SYSPECTRAL system focuses on compactness, mobility, and ease of operation. Software designed for the prototype controls multi-spectroscopic measurements, allows for image capture, precise localization, and data acquisition. Reflectance spectra examined the material and colors at the surface, and the LIBS-LIF-Raman package examines the stratigraphic structure of a multi-layered painted sample.