Information Extraction Research Articles

Sequence labeling via reinforcement learning with aggregate labels

Sequence labeling is pervasive in natural language processing, encompassing tasks such as Named Entity Recognition, Question Answering, and Information Extraction. Traditionally, these tasks are addressed via supervised machine learning approaches. However, despite their success, these approaches are constrained by two key limitations: a common mismatch between the training and evaluation objective, and the resource-intensive acquisition of ground-truth token-level annotations. In this work, we introduce a novel reinforcement learning approach to sequence labeling that leverages aggregate annotations by counting entity mentions to generate feedback for training, thereby addressing the aforementioned limitations. We conduct experiments using various combinations of aggregate feedback and reward functions for comparison, focusing on Named Entity Recognition to validate our approach. The results suggest that sequence labeling can be learned from purely count-based labels, even at the sequence-level. Overall, this count-based method has the potential to significantly reduce annotation costs and variances, as counting entity mentions is more straightforward than determining exact boundaries.

Data-Driven Insights Into Post-Earthquake Reconnaissance Findings: 2023 Türkiye Earthquake Sequence

Post-earthquake reconnaissance stands as a vital endeavor, encompassing a systematic survey and data collection to gain insights into the aftermath of seismic events. Grappling with a multitude of multidimensional data poses inherent challenges in the proper interpretation and extraction of hidden information. This paper unfolds in two parts. Initially, we delineate the reconnaissance mission following the February 06 Türkiye earthquake sequence, elucidating the challenges, complexities, and nature of the amassed data. Subsequently, a paradigm shift toward automated machine learning (AutoML) is embraced to ascertain the optimal model, categorize observed damages, and unveil underlying patterns within the collected data. The most accurate machine learning model is then coupled with Shapley Additive Explanations (SHAP) to explicate observations, steering away from a black-box model. SHAP values discern and prioritize factors significantly contributing to various damage levels. The results reveal a test set accuracy of 0.75 and 0.95 for multi- and binary-class problems, respectively, employing both raw and composite features. Building-related features exert more control over light damage, while earthquake-related factors dominate severe damage. In critical damage scenarios, duration- and velocity-dependent intensity measures assume significance. Furthermore, findings indicate that if column and wall indices are below 0.07 and 0.08, respectively, they positively contribute to the likelihood of critical structural damage.

Attention model of EEG signals based on reinforcement learning

BackgroundApplying convolutional neural networks to a large number of EEG signal samples is computationally expensive because the computational complexity is linearly proportional to the number of dimensions of the EEG signal. We propose a new Gated Recurrent Unit (GRU) network model based on reinforcement learning, which considers the implementation of attention mechanisms in Electroencephalogram (EEG) signal processing scenarios as a reinforcement learning problem.MethodsThe model can adaptively select target regions or position sequences from inputs and effectively extract information from EEG signals of different resolutions at multiple scales. Just as convolutional neural networks benefit from translation invariance, our proposed network also has a certain degree of translation invariance, making its computational complexity independent of the EEG signal dimension, thus maintaining a lower learning cost. Although the introduction of reinforcement learning makes the model non differentiable, we use policy gradient methods to achieve end-to-end learning of the model.ResultsWe evaluated our proposed model on publicly available EEG dataset (BCI Competition IV-2a). The proposed model outperforms the current state-of-the-art techniques in the BCI Competition IV- 2a dataset with an accuracy of 86.78 and 71.54% for the subject-dependent and subject-independent modes, respectively.ConclusionIn the field of EEG signal processing, attention models that combine reinforcement learning principles can focus on key features, automatically filter out noise and redundant data, and improve the accuracy of signal decoding.

How patient-reported outcomes and experience measures (PROMs and PREMs) are implemented in healthcare professional and patient organizations? An environmental scan.

Patient-reported outcome measures (PROMs) and patient-reported experience measures (PREMs) are becoming essential parts of a learning health system, and using these measures is a promising approach for value-based healthcare. However, evidence regarding healthcare professional and patient organizations' knowledge, use and perception of PROMs and PREMs is lacking. The objectives of the study were to: 1- Describe the current knowledge and use of PROMs and PREMs by healthcare professional and patient organizations, 2- Describe the determinants of PROMs and PREMs implementation according to healthcare professional and patient organizations. We conducted an environmental scan using semi-structured interviews with representatives from healthcare professional and patient organizations. Interviews were recorded and live coded based on the Franklin framework. We used inductive and deductive thematic analysis to extract information about the main themes addressed during the interview (awareness of PROMs and PREMs, examples of implementation and use of PROMs and PREMs, tools used, vision for future implementation, barriers and facilitators to implementation and the best way to collect PROMs and PREMs data). 63% of healthcare professional organizations (n = 19) and 41% of patient organizations (n = 9) that were contacted agreed to have a representative interviewed. The representatives from both the healthcare professional and patient organizations acknowledged the importance of assessing patients' experience and outcomes. However, they considered the implementation of PROMs and PREMs tools to be scarce within their organizations, in clinical practice and in the education system. Patient organizations were worried that overuse of PROMs and PREMs could lead to depersonalization of practice. Barriers to implementing PROMs and PREMs included lack of awareness of tools, resistance to change and lack of motivation to complete or explain the questionnaire. Barriers also included factors such as lack of financial, technological and human resources and issues with integration of data and inconsistency of digital platforms. This environmental scan revealed a lack of awareness of tools by healthcare professional and patient organizations' representatives and limited implementation. Adequate training, technological integration, and demonstration of PROMs and PREMs benefits to foster broader adoption in clinical and organizational settings is dearly needed. Addressing these challenges is essential for enhancing value-based care.

Development of Four Component Scattering Power Decomposition Technique for Dual Polarization SAR Data

AbstractThe increasing availability of dual-polarimetric synthetic aperture radar (PolSAR) data has led to a significant rise in its applications over the past few decades. Model-based decompositions combined with polarimetric information extraction from PolSAR data play a crucial role in target identification and classification. In this context, the covariance matrix [C], composed of four independent parameters, was used as the input for dual-pol four-component scattering power decomposition (DP-4SD). A novel 4SD model was tested using dual polarimetric SAR data from the spaceborne ALOS-2/PALSAR-2, and its performance was evaluated against existing scattering power decomposition methods. The performance of the proposed 4SD model was assessed using dual-polarization data from the Haldwani Forest and San Francisco to evaluate its classification capabilities within a single class (forest) and across various land use and land cover classes in San Francisco. The overall classification accuracy achieved was 85.69% for the Haldwani forest and 93.66% for San Francisco, with fewer unclassified samples compared with the existing model. The 4SD model demonstrates superior classification accuracy and enhances the interpretation of polarimetric information, indicating its potential to significantly improve land-use and land-cover mapping using dual PolSAR data.

Oncoming Revolution in the Next Generation of Cohort Studies

The world is changing rapidly, mainly due to the impact of megatrends that have an impact on the entire human life, particularly in medical sciences. Medical research methodologies such as cohort studies provide very critical information, but it is not clear what would be its destination in the future. In this short article, we have tried to offer a somewhat different perspective on the future of cohort studies by analyzing the texts and their conclusions from the author's viewpoint. According to our assessment, cohorts will play a key role in medical research, but their methodology will significantly change in terms of designing, implementing, analysing, and applying the findings. The new generation of cohort study extracts most of their information from electronic health records, and it is not just restricted to a particular geographic area. With the changes in the levels of occupational exposure, risk factors, and the introduction of Omics, likely, occupational and birth cohorts as well as human diseases will likely undergo fundamental changes in the future. Big data will provide researchers with new opportunities, but information extraction and analysis require a team of specialists from several scientific fields. Furthermore, participants are likely to play a more active role in setting priorities and implementing research findings.

Prevalence of paucibacillary cases of leprosy in Brazil: a 20-year systematic review and meta-analysis

IntroductionLeprosy is a chronic infectious disease caused by the agent Mycobacterium leprae, characterized by its high disabling power. Data points to Brazil being the second country with the highest number of cases in the world, behind only India, representing a major challenge for public health. This work aims to determine the prevalence of paucibacillary (PB) cases in relation to leprosy cases in Brazil, using data published in the literature.MethodsThis is a systematic review and meta-analysis carried out with studies from the last 20 years, being developed based on the Preferred Reporting Items for Systematic Review and Meta-analyzes (PRISMA).The search was carried out in the databases: PUBMED, SciELO, LILACS (via VHL)and Science Direct in October 2023, using the following descriptors (((“Brazil” [Mesh]) AND (“Leprosy, paucibacillary” [Mesh])) AND “Epidemiology” [Mesh]), in English, Portuguese and Spanish. Original studies of the analytical case–control, cohort, cross-sectional, epidemiological types were selected, as well as articles with satisfactory information for numerical extraction with separate data on the paucibacillary and multibacillary clinical forms. The methodological quality assessment followed the JBI critical appraisal checklist. Statistical analysis was performed using the Comprehensive Meta-Analyses-CMA software, version 3.0 (Biostat, Engewood, NJ, United States).ResultsThe meta-analysis of the 48 studies obtained a paucibacillary prevalence rate in Brazil of 50.5% or 0.505 (95% CI = 0.502–0.509).The differences in the analyzes were statistically significant (Q-value 4302.681;df 47; I 98.905), with a high heterogeneity value evidenced by I2 (98.905). This analysis demonstrated that the frequency in the Midwest region was the highest and the South region was the lowest (21.4%). Begg’s (Kendall Tau p = 0.35) and Egger’s tests (p = 0.20) were performed, in which no high publication bias was noted. Subgroup analysis indicated that paucibacillary cases varied from region to region, with the Midwest region having the highest prevalence and the South region having the lowest.ConclusionThe results stand out significantly for the research gaps that investigate PB cases, requiring more research aimed at investigating the paucibacillary clinical form that can contribute to the early diagnosis of leprosy.Systematic review registrationPROSPERO code: CRD42024514106.

TIA-UNet: transformer-enhanced deep learning for adolescent idiopathic scoliosis spinal x-ray image segmentation

Abstract Adolescent Idiopathic Scoliosis (AIS) is a common spinal deformity where precise diagnosis is crucial for developing effective treatment strategies. Traditional manual x-ray image analysis is time-consuming and highly dependent on the operator’s expertise, thus constraining diagnostic efficiency and accuracy. This study aimed to develop an automated thoracolumbar spine segmentation method utilizing deep learning to enhance the efficiency and accuracy of AIS diagnosis. We introduced TIA-UNet, an innovative network architecture that combines Convolutional Neural Networks (CNN) with Transformer models. By integrating the IR Block and DA Block, TIA-UNet was optimized for feature extraction and multi-scale information fusion. The model underwent training and validation using our established Adolescent Scoliosis Medical Dataset (ASMD). TIA-UNet attained a Dice similarity coefficient of 90. 02%, a Mean Intersection over Union (MIoU) of 81. 96%, and a Hausdorff Distance (HD) of 4. 09, significantly surpassing current state-of-the-art methods such as UNet and TransUNet. Moreover, TIA-UNet exhibited superior computational efficiency regarding parameter count, inference time, and floating-point operations (FLOPs). As an automated medical image segmentation algorithm, TIA-UNet enhanced segmentation accuracy while maintaining high computational efficiency, demonstrating significant potential for clinical diagnostic applications. This study provides compelling evidence supporting the utilization of deep learning techniques in medical image analysis.

Enhancing the performance of a resonance-based sensor network for soft robots using binary excitation

Embedded, flexible, multi-sensor sensing networks have shown the potential to provide soft robots with reliable feedback while navigating unstructured environments. Time delay associated with extracting information from these sensing networks and the complexity of constructing them are significant obstacles to their development. This paper presents a novel enhancement to an existing class of embedded sensor network with the potential to overcome these challenges. In its original version, this sensor network extracts information from multiple reactive sensors on a two-wire electrical circuit simultaneously. This paper proposes to change the excitation signal applied to this sensor network to a binary signal. This change offers two key advantages: it provides the ability to employ small, inexpensive microcontrollers and results in a faster data extraction process. The potential of this enhanced system is demonstrated here with a proof of concept implementation. The self-inductance of all inductance-based sensors within this proof of concept sensor network can be measured at a rate of over 5000 times per second with an average measurement error of less than 2%.

DEUFormer: High‐precision semantic segmentation for urban remote sensing images

AbstractUrban remote sensing image semantic segmentation has a wide range of applications, such as urban planning, resource exploration, intelligent transportation, and other scenarios. Although UNetFormer performs well by introducing the self‐attention mechanism of Transformer, it still faces challenges arising from relatively low segmentation accuracy and significant edge segmentation errors. To this end, this paper proposes DEUFormer by employing a special weighted sum method to fuse the features of the encoder and the decoder, thus capturing both local details and global context information. Moreover, an Enhanced Feature Refinement Head is designed to finely re‐weight features on the channel dimension and narrow the semantic gap between shallow and deep features, thereby enhancing multi‐scale feature extraction. Additionally, an Edge‐Guided Context Module is introduced to enhance edge areas through effective edge detection, which can improve edge information extraction. Experimental results show that DEUFormer achieves an average Mean Intersection over Union (mIoU) of 53.8% on the LoveDA dataset and 69.1% on the UAVid dataset. Notably, the mIoU of buildings in the LoveDA dataset is 5.0% higher than that of UNetFormer. The proposed model outperforms methods such as UNetFormer on multiple datasets, which demonstrates its effectiveness.

Bifurcation Enhances Temporal Information Encoding in the Olfactory Periphery

Living systems continually respond to signals from the surrounding environment. Survival requires that their responses adapt quickly and robustly to the changes in the environment. One particularly challenging example is olfactory navigation in turbulent plumes, where animals experience highly intermittent odor signals while odor concentration varies over many length- and timescales. Here, we show theoretically that olfactory receptor neurons (ORNs) can exploit proximity to a bifurcation point of their firing dynamics to reliably extract information about the timing and intensity of fluctuations in the odor signal, which have been shown to be critical for odor-guided navigation. Close to the bifurcation, the system is intrinsically invariant to signal variance, and information about the timing, duration, and intensity of odor fluctuations is transferred efficiently. Importantly, we find that proximity to the bifurcation is maintained by mean adaptation alone and therefore does not require any additional feedback mechanism or fine-tuning. Using a biophysical model with calcium-based feedback, we demonstrate that this mechanism can explain the measured adaptation characteristics of ORNs. Published by the American Physical Society 2024

Revolutionizing Cytology and Cytopathology with Natural Language Processing and Chatbot Technologies: A Narrative Review on Current Trends and Future Directions

The application of chatbots and Natural Language Processing (NLP) in cytology and cytopathology is an emerging field, which is currently characterized by a limited but growing body of research. Here, a narrative review has been proposed utilizing a standardized checklist and quality control procedure for including scientific papers. This narrative review explores the early developments and potential future impact of these technologies in medical diagnostics. The current literature, comprising 11 studies (after excluding comments, letters, and editorials) suggests that chatbots and NLP offer significant opportunities to enhance diagnostic accuracy, streamline clinical workflows, and improve patient engagement. By automating the extraction and classification of medical information, these technologies can reduce human error and increase precision. They also promise to make patient information more accessible and facilitate complex decision-making processes, thereby fostering greater patient involvement in healthcare. Despite these promising prospects, several challenges need to be addressed for the full potential of these technologies to be realized. These include the need for data standardization, mitigation of biases in Artificial Intelligence (AI) systems, and comprehensive clinical validation. Furthermore, ethical, privacy, and legal considerations must be navigated carefully to ensure responsible AI deployment. Compared to the more established fields of histology, histopathology, and especially radiology, the integration of digital tools in cytology and cytopathology is still in its infancy. Building on the advancements in related fields, especially radiology’s experience with digital integration, where these technologies already offer promising solutions in mentoring, second opinions, and education, we can leverage this knowledge to further develop chatbots and natural language processing in cytology and cytopathology. Overall, this review underscores the transformative potential of these technologies while outlining the critical areas for future research and development.

WGAN-based multi-structure segmentation of vertebral cross-section MRI using ResU-Net and clustered transformer

The vertebral foramen, lamina, and vertebral body are three critical components of the spine structure, essential for maintaining spinal connectivity and stability. Accurately segmenting lumbar structures such as the vertebral body, vertebral foramen, and lamina in MRI cross-sections helps doctors better understand and diagnose the pathological causes of spine-related diseases. This study presents a multi-structure semantic segmentation method for vertebral transverse section MRI slices using WGAN with a residual U-Net and clustered Transformer. The generator network was replaced with a combination of a residual U-Net and a clustered Transformer-based segmentation network. The enhanced U-Net encoder, utilizing dilated convolutions and residual structures, improved multi-scale feature extraction capabilities. Meanwhile, the clustered Transformer structure, with reduced progressive linear complexity, ensured the extraction of global positional information. The results of multiple experiments show that the Dice coefficient for vertebral body segmentation increased by 3.1%, the Hausdorff distance decreased by 0.6 mm, mIOU improved by 4.1–96.2%, and PPV increased by 2.0–98.8% compared to mainstream segmentation models. These improvements are statistically significant (p < 0.05).Ablation experiments further validated the effectiveness of the proposed enhanced modules in improving segmentation accuracy for the three target structures.

Art Pattern Design Based on Visual Semantic Segmentation and Evolutionary Algorithm Optimization

This paper aims to address the issue of traditional art patterns not fully leveraging contextual information in image semantic segmentation. It proposes a multi-level feature aggregation method for image semantic segmentation based on visual Transformer and coordinate attention adjustment (CA Adjustment). Initially, the input image is segmented into slices for linear projection, incorporating learnable positional embeddings to derive an encoded input sequence. Subsequently, employing a visual Transformer-based encoder, the image is transformed into patches to capture global context across the network. CA Adjustment is then introduced to adaptively merge fusion features and visual backbone features using weighted adjustments. Lastly, a multi-objective grasshopper optimization algorithm is designed based on a clustering evolution mechanism to further enhance algorithm performance. Extensive experimental results demonstrate that our proposed algorithm effectively models global contextual information for image feature extraction. Compared to existing advanced algorithms, our method achieves high segmentation accuracy in semantic segmentation tasks, consistently exceeding 95%. Ablation experiments further validate the efficacy of our approach, underscoring its broad applicability in high-precision image semantic segmentation.

Exploration of an intrinsically explainable self-attention based model for prototype generation on single-channel EEG sleep stage classification.

Prototype-based methods in deep learning offer interpretable explanations for decisions by comparing inputs to typical representatives in the data. This study explores the adaptation of SESM, a self-attention-based prototype method successful in electrocardiogram (ECG) tasks, for electroencephalogram (EEG) signals. The architecture is evaluated on sleep stage classification, exploring its efficacy in predicting stages with single-channel EEG. The model achieves comparable test accuracy compared to EEGNet, a state-of-the-art black-box architecture for EEG classification. The generated prototypical components are exaimed qualitatively and using the area over the perterbation curve (AOPC) indicate some alignment with expected bio-markers for different sleep stages such as alpha spindles and slow waves in non-REM sleep, but the results are severely limited by the model's ability to only extract and present information in the time-domain. Ablation studies are used to explore the impact of kernel size, number of heads, and diversity threshold on model performance and explainability. This study represents the first application of a self-attention based prototype method to EEG data and provides a step forward in explainable AI for EEG data analysis.

Vision-guided crack identification and size quantification framework for dam underwater concrete structures

Remotely operated vehicles with cameras provide a non-contact inspection solution for dam underwater structural defect detection. However, manual information extraction methods suffer from problems like labor costs and high misjudgment. This study proposes an integrated dam underwater crack identification and size quantification framework using machine vision and deep learning. First, a real-time automatic detection framework for dam underwater cracks is built via You Only Look Once v5 (YOLOv5), and four different backbone detectors are introduced to balance detection accuracy and speed. Then, the Swin-Transformer module is inserted into the YOLOv5 model to enhance its feature extraction capability and small object detection capability. Next, a method for measuring the true size of cracks was constructed based on deep learning and infrared laser rangefinders. In this study, physical model experiments and actual engineering projects are combined to validate the generalization capability of the proposed crack identification and size quantification method. Experimental results show that the Swin-Transformer-based YOLOv5 model effectively balances detection accuracy and speed with a precision of 0.986, a recall of 0.979, a mean average precision of 0.985, and a frame rate of 68 frames per second in detecting underwater crack images with 768 × 576 pixels. In addition, the proposed method can accurately identify and detect cracks in complex underwater scenes, including obstacle interference, tilt shooting angle, uneven illumination, and turbid water scenarios. Moreover, the method proposed in this paper can quantify the overall size and geometric parameters of underwater cracks with relatively small errors.

Network Embedding Technology Based on Breadth Learning for Information Extraction and Review in Social Media

Network Embedding Technology Based on Breadth Learning for Information Extraction and Review in Social Media

Large language models for generative information extraction: a survey

AbstractInformation Extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a result, numerous works have been proposed to integrate LLMs for IE tasks based on a generative paradigm. To conduct a comprehensive systematic review and exploration of LLM efforts for IE tasks, in this study, we survey the most recent advancements in this field. We first present an extensive overview by categorizing these works in terms of various IE subtasks and techniques, and then we empirically analyze the most advanced methods and discover the emerging trend of IE tasks with LLMs. Based on a thorough review conducted, we identify several insights in technique and promising research directions that deserve further exploration in future studies. We maintain a public repository and consistently update related works and resources on GitHub (LLM4IE repository).

SentinelGuard Pro: Deploying Cutting‐Edge FusionNet for Unerring Detection and Enforcement of Wrong Parking Incidents

ABSTRACTWrong parking incidents pose a pervasive challenge in urban environments, disrupting the smooth flow of traffic, compromising safety and contributing to various logistical issues. Unauthorized parking occurs when vehicles are parked in locations not designated for such purposes, leading to a myriad of problems for both authorities and the general public. This research introduces a pioneering approach to confront the persistent challenge of unauthorized parking incidents in urban environments. The study focuses on harnessing the advanced capabilities of the FusionNet model to enhance the accuracy of license plate detection. This paper introduces the YOLO v8 Model, a deep learning architecture designed to enhance urban parking management by accurately detecting vehicles parked in unauthorized slots. The objective is to enhance parking management efficiency by accurately detecting vehicles and their occupancy status in designated parking areas. The methodology begins with data collection and preprocessing of images of parking spaces, followed by the training of YOLO v8 to identify vehicles and parking spaces in real time. Leveraging a diverse dataset encompassing various parking scenarios, including instances of unauthorized parking, the model achieves an accuracy of 98.50% in identifying vehicles outside designated areas. This model segments characters from detected license plates, enabling the accurate extraction of alphanumeric information associated with each vehicle. The integrated system provides timely identification of parking violations and facilitates effective enforcement actions through captured license plate data. Results demonstrate the model's effectiveness in real‐world scenarios, showcasing its potential for improving urban safety and efficiency. The implementation of FusionNet in the Python programming language, the proposed solution aims to streamline parking management, improve compliance with parking regulations and enhance overall urban mobility., with robust precision 96.17%, specificity 97.42% and sensitivity 96.19%, surpassing other MobileNet, CNN, ANN, DNN and EfficientNet models.

DocNER: Document Chat Assistance with NER

The increasing amounts of high volume unstructured medical data, such as research and clinical articles, impede efficient information extraction. Since the medical texts have a complex structure, many times these approaches do not work, leading to significant losses. The current approaches are not robust to a wide spectrum of medical content as they are too specific to the given domain.This study proposes a recent innovative approach that involves the combination of Named Entity Recognition (NER) and Retrieval-Augmented Generation (RAG) to enhance entity extraction and give useful bibliographic information from medical data respectively. The objectives of our method are to improve accuracy, accommodate different kinds of documents, and assist in clinical research and patient care.