Extract Accurate Information Research Articles

Schrödinger spectrum and slim CNN architecture-based signal quality estimation for Photoplethysmogram signals

Photoplethysmography (PPG) signal comprises physiological information related to cardiorespiratory health. However, these signals are often contaminated by motion artifacts, resulting in low-quality noise-enriched signals. Therefore, it is crucial to ensure high-quality signals to extract accurate cardiorespiratory information. Although several rule-based and Machine-Learning (ML) - based approaches exist for PPG signal quality estimation but their effectiveness is questionable during evaluation in diverse datasets. This study proposes a lightweight, slim CNN architecture that utilizes a novel Quantum Pattern Recognition (QPR) technique for signal quality assessment. The proposed algorithm is initially validated on the University of Queensland database (clinical) and a noisy PPG database (non-clinical) collected from the ‘Welltory app’. A total of 28366, 5 s signal segments are preprocessed and transformed into image files of 20 × 500 pixels. The image files and heart rate obtained from the PPG signals are treated as input to the 2D slim CNN architecture. The developed model classifies the PPG signal as ‘good’ or ‘bad’ with an accuracy of 98.5%, 99.2% sensitivity, 97.5% specificity, and 99% F1-score. The classified database is further used for cuffless Blood Pressure estimation, and estimation error is reduced ≥ 1 mmHg w.r.t. reference BP signals. Finally, the proposed scheme is validated in STM32 series board for a resource-constrained wearable implementation. The computational load of the algorithm is reduced by network pruning and quantization for edge-device implementation, and it achieves an accuracy of 94.3%. This extensive analysis concludes that a slim architecture, along with a novel spatio–temporal pattern recognition technique, improves the system’s performance.

Enhancing Job Recommendation through LLM-Based Generative Adversarial Networks

Recommending suitable jobs to users is a critical task in online recruitment platforms. While existing job recommendation methods encounter challenges such as the low quality of users' resumes, which hampers their accuracy and practical effectiveness.With the rapid development of large language models (LLMs), utilizing the rich external knowledge encapsulated within them, as well as their powerful reasoning capabilities, is a promising way to complete users' resumes for more accurate recommendations. However, directly leveraging LLMs to enhance recommendation results is not a one-size-fits-all solution, as LLMs may suffer from fabricated generation and few-shot problems, which degrade the quality of resume completion. In this paper, we propose a novel LLM-based approach for job recommendation. To alleviate the limitation of fabricated generation for LLMs, we extract accurate and valuable information beyond users' self-description, which helps the LLMs better profile users for resume completion. Specifically, we not only extract users' explicit properties (e.g., skills, interests) from their self-description but also infer users' implicit characteristics from their behaviors for more accurate and meaningful resume completion. Nevertheless, some users still suffer from few-shot problems, which arise due to scarce interaction records, leading to limited guidance for high-quality resume generation. To address this issue, we propose aligning unpaired low-quality with high-quality generated resumes by Generative Adversarial Networks (GANs), which can refine the resume representations for better recommendation results. Extensive experiments on three large real-world recruitment datasets demonstrate the effectiveness of our proposed method.

Multistage Interaction Network for Remote Sensing Change Detection

Change detection in remote sensing imagery is vital for Earth monitoring but faces challenges such as background complexity and pseudo-changes. Effective interaction between bitemporal images is crucial for accurate change information extraction. This paper presents a multistage interaction network designed for effective change detection, incorporating interaction at the image, feature, and decision levels. At the image level, change information is directly extracted from intensity changes, mitigating potential change information loss during feature extraction. Instead of separately extracting features from bitemporal images, the feature-level interaction jointly extracts features from bitemporal images. By enhancing relevance to spatial variant information and shared semantic channels, the network excels in overcoming background complexity and pseudo-changes. The decision-level interaction combines image-level and feature-level interactions, producing multiscale feature differences for precise change prediction. Extensive experiments demonstrate the superior performance of our method compared to existing approaches, establishing it as a robust solution for remote sensing image change detection.

Scalable and rapid building damage detection after hurricane Ian using causal Bayesian networks and InSAR imagery

Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response and recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid building damage assessment. Compared to optical satellite imageries, the Synthetic Aperture Radar can penetrate cloud cover and provide more complete spatial coverage of damaged zone in various weather conditions. However, these InSAR imageries often contain highly noisy and mixed signals induced by co-occurring or co-located building damage, flood, flood/wind-induced vegetation changes, as well as anthropogenic activities, making it challenging to extract accurate building damage information. In this paper, we introduced a causality-informed Bayesian network inference approach for rapid post-hurricane building damage detection from InSAR imagery. This approach encoded complex causal dependencies among wind, flood, building damage, and InSAR imagery using a holistic causal Bayesian network. Based on the causal Bayesian network, we further jointly inferred the large-scale unobserved building damage by fusing the information from InSAR imagery with prior physical models of flood and wind, without the need for ground truth labels. Furthermore, we validated our estimation results in a real-world devastating hurricane—the 2022 Hurricane Ian. We gathered and annotated building damage ground truth data in Lee County, Florida, and compared the introduced method’s estimation results with the ground truth and also benchmarked it against state-of-the-art models to assess the effectiveness of our proposed method. The results show that our method advances building damage assessment after hurricanes by accurately reflecting the complex dynamics between wind and flood impacts. Notably, it achieves this without the need for a ground truth label, which is a substantial step forward from traditional methods. Our model registers a 22.6% increase in the Area Under the Curve (AUC) and a 46.29% enhancement in the True Positive Rate (TPR). Moreover, it expedites the detection of building damage, cutting down processing times by up to 83.8%. These improvements mark a considerable leap in efficiency, demonstrating our method’s ability to streamline the assessment process markedly over conventional methods.

A High-Precision Position Estimation Method for Low Saliency Ratio Machine Based on Convolutional Neural Networks

Sensorless control of surface permanent magnet synchronous motor (SPMSM) faces great challenges in achieving high precision of rotor position estimation at low speed because the saliency of an SPMSM is only a minor secondary effect. In order to extract accurate position information for SPMSM with low and ultra-low saliency ratios, this paper presents a method that implements image recognition techniques with high-frequency (HF) rotating voltage vector injection. For building an image of the induced current vector, the information of the negative-sequence and the second harmonic of positive-sequence HF current signals in the stationary reference frame is extracted. Then, convolutional neural networks (CNN) are applied to the current vector images to establish the relationship between the vector image and the rotor position. Subsequently, the rotor position can be obtained from the result of image recognition from the neural network. Benefiting from CNN’s excellent performance in image classification, the proposed method is able to recognize subtle position signatures even under low saliency. This confirms the opportunity to increase position estimation accuracy for sensorless control of SPMSM. Finally, the experimental results have provided proof that the proposed method has significantly enhanced estimation accuracy.

Comparison of Random Forest and XGBoost Classifiers Using Integrated Optical and SAR Features for Mapping Urban Impervious Surface

The integration of optical and SAR datasets through ensemble machine learning models shows promising results in urban remote sensing applications. The integration of multi-sensor datasets enhances the accuracy of information extraction. This research presents a comparison of two ensemble machine learning classifiers (random forest and extreme gradient boost (XGBoost)) classifiers using an integration of optical and SAR features and simple layer stacking (SLS) techniques. Therefore, Sentinel-1 (SAR) and Landsat 8 (optical) datasets were used with SAR textures and enhanced modified indices to extract features for the year 2023. The classification process utilized two machine learning algorithms, random forest and XGBoost, for urban impervious surface extraction. The study focused on three significant East Asian cities with diverse urban dynamics: Jakarta, Manila, and Seoul. This research proposed a novel index called the Normalized Blue Water Index (NBWI), which distinguishes water from other features and was utilized as an optical feature. Results showed an overall accuracy of 81% for UIS classification using XGBoost and 77% with RF while classifying land use land cover into four major classes (water, vegetation, bare soil, and urban impervious). However, the proposed framework with the XGBoost classifier outperformed the RF algorithm and Dynamic World (DW) data product and comparatively showed higher classification accuracy. Still, all three results show poor separability with bare soil class compared to ground truth data. XGBoost outperformed random forest and Dynamic World in classification accuracy, highlighting its potential use in urban remote sensing applications.

Multivariate analysis of nanoparticle translocation through a nanopore to improve the accuracy of resistive pulse sensing.

The advent of nanopore-based sensors based on resistive pulse sensing gave rise to a remarkable breakthrough in the detection and characterization of nanoscale species. Some strong correlations have been reported between the resistive pulse characteristics and the particle's geometrical and physical properties. These correlations are commonly used to obtain information about the particles in commercial devices and research setups. The correlations, however, do not consider the simultaneous effect of influential factors such as particle shape and off-axis translocation, which complicates the extraction of accurate information from the resistive pulses. In this paper, we numerically studied the impact of the shape and position of particles on pulse characteristics in order to estimate the errors that arise from neglecting the influence of multiple factors on resistive pulses. We considered the sphere, oblate, and prolate particles to investigate the nanoparticle shape effect. Moreover, the trajectory dependency was examined by considering the translocation of nanoparticles away from the nanopore axis. Meanwhile, the shape effect was studied for different trajectories. We observed that the simultaneous effects of influential parameters could lead to significant errors in estimating particle properties if the coupled effects are neglected. Based on the results, we introduce the "pulse waveshape" as a novel characteristic of the resistive pulse that can be utilized as a decoupling parameter in the analysis of resistive pulses.

Channel-Specific and Spatial Residual Attention Network for Medical Image Denoising.

Medical image quality is crucial for physicians to ensure accurate diagnosis and therapeutic strategies. However, due to the interference of noise, there are often various types of noise and artifacts in medical images. This not only damages the visual clarity of images, but also reduces the accuracy of information extraction. Considering that the edges of medical images are rich in high-frequency information, to enhance the quality of medical images, a dual attention mechanism, the channel-specific and spatial residual attention network (CSRAN) in the U-Net framework is proposed. The CSRAN seamlessly integrates the U-Net architecture with channel-wise and spatial feature attention (CSAR) modules, as well as low-frequency channel attention modules. Combined with the two modules, the ability of medical image processing to extract high-frequency features is improved, thereby significantly improving the edge effects and clarity of reconstructed images. This model can present better performance in capturing high-frequency information and spatial structures in medical image denoising and super-resolution reconstruction tasks. It cannot only enhance the ability to extract high-frequency features and strengthen its nonlinear representation capability, but also endow strong edge detection capabilities of the model. The experimental results further prove the superiority of CSRAN in medical image denoising and super-resolution reconstruction tasks.

Size-refocusing fitting of small-angle X-ray scattering from polydisperse nanoparticles for shape determination

Small-angle X-ray scattering (SAXS) which records reciprocal-space signals with characteristic Bessel-type oscillations is a powerful technique for studying nanoparticles. However, the size polydispersity (or size distribution) of nanoparticles in an ensemble sample smears the oscillational peaks and valleys in the SAXS profile, making it difficult to extract accurate real-space information (e.g. three-dimensional geometry) on the nanoparticles. In this work, a method capable of eliminating the size-distribution-induced smearing effect from SAXS profiles by taking the known size-distribution function into consideration has been developed. The method employs a penalized iterative regression to fit the pair distance distribution function (PDDF) derived from a SAXS profile, recovering the representative PDDF of the nanoparticles. The method has been evaluated with a series of nanoparticle systems of various shapes and size distributions, showing their PDDF profiles to have high fidelity to the reference ideal PDDF profiles. Inverse Fourier transformation of the recovered PDDF profiles gives SAXS profiles presenting the characteristic Bessel-type oscillations, enabling reconstruction of the representative three-dimensional geometry of the nanoparticles. This method will help in the use of SAXS to image synthesized colloidal nanoparticles where size polydispersity is inevitable.

CDMnet: Cloud Detection in Remote Sensing Images Based on CNN

The main objective of cloud detection is to accurately distinguish between clouds and areas that are not clouds to extract accurate surface information. To achieve an accurate distinction between cloud and non-cloud regions, we propose a novel method called Cloud Detection Method Net (CDMnet). The method employs a lightweight network backbone, compared to traditional classical algorithms like SVM, to effectively reduce computational costs while maintaining accuracy. Additionally, we utilize hole convolutions with varying dilation rates to extract cloud features in parallel. We also employ SAM spatial attention multiple times to fine-tune cloud position positioning and obtain more accurate cloud masks. From the experimental results, it can be concluded that our method is more efficient than other traditional methods.

An Accurate Detection and Location of Weld Surface Defect Based on Laser Vision

In order to effectively improve the efficiency of automatic detection and subsequent processing of welding defects in the construction field, this paper proposes a method for detecting and locating weld surface defects based on machine vision and laser vision. YOLOv5 is used for the initial detection and identification of weld hole defects to obtain the approximate location of the defect. Subsequently, the detailed features of the defect sites are extracted by scanning the approximate range of defect locations with a line laser 3D sensor based on the identification of weld defect holes. Finally, the defect location and depth are accurately located based on the extracted features. Experimental results show that the proposed method is capable of identifying weld surface hole defects with an accuracy rate of over 94%. Furthermore, the combination of the system with the line laser 3D sensor detection can significantly improve the accuracy compared to pure 2D visual inspection, while the manual measurement is neither convenient nor accurate. This indicates that the proposed system can be used for rapid and accurate feature information extraction of weld hole defects, making subsequent remedial welding in actual engineering more automatic and efficient.

Remote sensing traffic scene retrieval based on learning control algorithm for robot multimodal sensing information fusion and human-machine interaction and collaboration.

In light of advancing socio-economic development and urban infrastructure, urban traffic congestion and accidents have become pressing issues. High-resolution remote sensing images are crucial for supporting urban geographic information systems (GIS), road planning, and vehicle navigation. Additionally, the emergence of robotics presents new possibilities for traffic management and road safety. This study introduces an innovative approach that combines attention mechanisms and robotic multimodal information fusion for retrieving traffic scenes from remote sensing images. Attention mechanisms focus on specific road and traffic features, reducing computation and enhancing detail capture. Graph neural algorithms improve scene retrieval accuracy. To achieve efficient traffic scene retrieval, a robot equipped with advanced sensing technology autonomously navigates urban environments, capturing high-accuracy, wide-coverage images. This facilitates comprehensive traffic databases and real-time traffic information retrieval for precise traffic management. Extensive experiments on large-scale remote sensing datasets demonstrate the feasibility and effectiveness of this approach. The integration of attention mechanisms, graph neural algorithms, and robotic multimodal information fusion enhances traffic scene retrieval, promising improved information extraction accuracy for more effective traffic management, road safety, and intelligent transportation systems. In conclusion, this interdisciplinary approach, combining attention mechanisms, graph neural algorithms, and robotic technology, represents significant progress in traffic scene retrieval from remote sensing images, with potential applications in traffic management, road safety, and urban planning.

Sanitizing data for analysis: Designing systems for data understanding

As organizations accumulate vast amounts of data for analysis, a significant challenge remains in fully understanding these datasets to extract accurate information and generate real-world impact. Particularly, the high dimensionality of datasets and the lack of sufficient documentation, specifically the provision of metadata, often limit the potential to exploit the full value of data via analytical methods. To address these issues, this study proposes a hybrid approach to metadata generation, that leverages both the in-depth knowledge of domain experts and the scalability of automated processes. The approach centers on two key design principles—semanticization and contextualization—to facilitate the understanding of high-dimensional datasets. A real-world case study conducted at a leading pharmaceutical company validates the effectiveness of this approach, demonstrating improved collaboration and knowledge sharing among users. By addressing the challenges in metadata generation, this research contributes significantly toward empowering organizations to make more effective, data-driven decisions.

POST-IVUS: A perceptual organisation-aware selective transformer framework for intravascular ultrasound segmentation.

Intravascular ultrasound (IVUS) is recommended in guiding coronary intervention. The segmentation of coronary lumen and external elastic membrane (EEM) borders in IVUS images is a key step, but the manual process is time-consuming and error-prone, and suffers from inter-observer variability. In this paper, we propose a novel perceptual organisation-aware selective transformer framework that can achieve accurate and robust segmentation of the vessel walls in IVUS images. In this framework, temporal context-based feature encoders extract efficient motion features of vessels. Then, a perceptual organisation-aware selective transformer module is proposed to extract accurate boundary information, supervised by a dedicated boundary loss. The obtained EEM and lumen segmentation results will be fused in a temporal constraining and fusion module, to determine the most likely correct boundaries with robustness to morphology. Our proposed methods are extensively evaluated in non-selected IVUS sequences, including normal, bifurcated, and calcified vessels with shadow artifacts. The results show that the proposed methods outperform the state-of-the-art, with a Jaccard measure of 0.92 for lumen and 0.94 for EEM on the IVUS 2011 open challenge dataset. This work has been integrated into a software QCU-CMS2 to automatically segment IVUS images in a user-friendly environment.

Structuring Information from Plant Morphological Descriptions using Open Information Extraction

Structuring Information from Plant Morphological Descriptions using Open Information Extraction

How ambiguity codes specify molecular descriptors and information flow in Code Biology

The article presents IUPAC ambiguity codes for incomplete nucleic acid specification, and their use in Code Biology. It is shown how to use this nomenclature in order to extract accurate information on different properties of the biological systems. We investigated the use of ambiguity codes, as mathematical and logical operators and truth table elements, for the encoding of amino acids by means of the Standard Genetic Code. It is explained how to use ambiguity codes and truth functions in order to obtain accurate information on different properties of the biological systems. Nucleotide ambiguity codes could be applied to: 1. encoding descriptive information of nucleotides, amino acids and proteins (e.g., of polarity, relative solvent accessibility, atom depth, etc.), and 2. system modelling ranging from standard bioinformatics tools to classic evolutionary models (i.e. from Miyazawa−Jernigan statistical potential to Kimura three-substitution-type model, respectively). It is shown that the algorithms based on IUPAC ambiguity codes, Boolean functions and truth table, Probabilistic Square of Opposition/Semiotic Square and Klein 4-groups—could be used for the bioinformatics analyses and Relational data modelling in natural science. Underlying mathematical, logical and semiotic concepts of interest are presented and addressed.

A screen-shooting resilient data-hiding algorithm based on two-level singular value decomposition

This paper presents a screen-shooting resilient data-hiding scheme for JPEG images based on a two-level Singular Value Decomposition (SVD). The mid-to-high frequency coefficients are chosen to balance the data-embedding robustness and the image's visual quality. At the same time, the two-level singular value decomposition (SVD) is additionally utilized to construct the feature matrices, thereby enhancing the robustness of the embedded message. The combination of DCT and two-level SVD enables achieving a high-performance screen-shooting resilient data-hiding algorithm. Moreover, the affine transformation is employed to rectify the distortion that caused by screen-shooting, thus further improving the data extraction accuracy. Experimental results demonstrate a minimum 3 % improvement in confidential information extraction accuracy, with the data extraction rate exceeding 92 % across screen-shooting angles ranging from −40 to 40°. The performance of the proposed algorithm outperforms other state-of-the-art schemes apparently.

Aircraft Detection from Low SCNR SAR Imagery Using Coherent Scattering Enhancement and Fused Attention Pyramid

Recently, methods based on deep learning have been applied to target detection using synthetic aperture radar (SAR) images. However, due to the SAR imaging mechanism and low signal-clutter-noise-ratio (SCNR), it is still a challenging task to perform aircraft detection using SAR imagery. To address this issue, a novel aircraft detection method is proposed for low SCNR SAR images that is based on coherent scattering enhancement and a fusion attention mechanism. Considering the scattering characteristics discrepancy between human-made targets and natural background, a coherent scattering enhancement technique is introduced to heighten the aircraft scatter information and suppress the clutter and speckle noise. This is beneficial for the later ability of the deep neural network to extract accurate and discriminative semantic information about the aircraft. Further, an improved Faster R-CNN is developed with a novel pyramid network constructed by fusing local and contextual attention. The local attention adaptively highlights the significant objects by enhancing their distinguishable features, and the contextual attention facilitates the network to extract distinct contextual information of the image. Fusing the local and contextual attention can guarantee that the aircraft is detected as completely as possible. Extensive experiments are performed on TerraSAR-X SAR datasets for benchmark comparison. The experimental results demonstrate that the proposed aircraft detection approach could achieve up to 91.7% of average precision in low SCNR, showing effectiveness and superiority over a number of benchmarks.

Secret-to-Image Reversible Transformation for Generative Steganography

Recently, generative steganography that transforms secret information to a generated image has been a promising technique to resist steganalysis detection. However, due to the inefficiency and irreversibility of the secret-to-image transformation, it is hard to find a good trade-off between the information hiding capacity and extraction accuracy. To address this issue, we propose a secret-to-image reversible transformation (S2IRT) scheme for generative steganography. The proposed S2IRT scheme is based on a generative model, i.e., Glow model, which enables a bijective-mapping between latent space with multivariate Gaussian distribution and image space with a complex distribution. In the process of S2I transformation, guided by a given secret message, we construct a latent vector and then map it to a generated image by the Glow model, so that the secret message is finally transformed to the generated image. Owing to good efficiency and reversibility of S2IRT scheme, the proposed steganographic approach achieves both high hiding capacity and accurate extraction of secret message from generated image. Furthermore, a separate encoding-based S2IRT (SE-S2IRT) scheme is also proposed to improve the robustness to common image attacks. The experiments demonstrate the proposed steganographic approaches can achieve high hiding capacity (up to 4 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">bpp</i> ) and accurate information extraction (almost 100% accuracy rate) simultaneously, while maintaining desirable anti-detectability and imperceptibility.

Motion and geometry-related information fusion through a framework for object identification from a moving camera in urban driving scenarios

Accurate and robust semantic scene understanding for urban driving is challenging due to the complex object types, object motion, and as well as ego-motion. Typical approaches to this problem use the fusion of multiple sensors such as camera, IMU, LiDAR, and radar to identify the state of the surrounding objects, including distance, direction, position, and velocity. However, such sensor modalities are very much complex and costly. This paper proposes a new framework for object identification (FOI) from a moving camera in a complex driving environment utilizing only camera sensor data. The framework is capable of detecting objects, extracting their behavioral features in terms of motion, position, velocity, and distance. All of this information (referred to as object-wise semantic information) are fused in order to acquire a better understanding of the driving scenario. The work addresses ego-motion compensation and extraction of accurate motion information of moving objects from a moving camera using image registration and optical flow estimation. A moving object detection model is designed within the framework by integrating an encoder–decoder network with a semantic segmentation network. The approach involves two mutual tasks: semantic segmentation of objects into specific classes and binary pixel classification to predict whether the detected object is moving or static based on temporal information. The work also contributes a novel dataset for moving object detection that covers all types of dynamic objects. The evaluation of FOI has been performed on different sequences of KITTI, EU-life long, and the proposed datasets. The experimental results show that the proposed framework provides accurate object-wise semantic information.