Search Results (175)

A large number of architectural drawings have historically existed in paper form or as non-editable raster images, which makes them difficult to directly support information reuse and digital management, while manual CAD reconstruction is time-consuming and inefficient. This paper proposes a hybrid deep learning and rule-based method for architectural drawing vectorization and CAD reconstruction, which automatically converts scanned raster images into editable CAD vector files while preserving geometric structure and scale consistency. The proposed method consists of four modules: axis grid and dimension detection, text recognition and scale recovery, architectural line topology reconstruction, and CAD geometric rectification and reconstruction. The method utilizes object detection and OCR technologies to extract key semantic information from the drawings. By extracting semantic information, the method constructs a line topology structure and applies architectural drawing constraints to parameterize and normalize geometric results, thereby achieving the recognition and vectorization of raster drawings. Experimental results and engineering case studies demonstrate that the proposed method can effectively extract typical architectural elements, and generate directly editable CAD vector drawings. The method achieves favorable geometric accuracy and topological consistency in architectural drawing digitization and automatic CAD reconstruction tasks, providing a technical solution for the automatic vectorization of existing architectural drawings. Full article

This paper explores the feasibility of using acoustic wave propagation, particularly in the ultrasonic range, as a solution for data transmission in environments where traditional radio frequency (RF) communication is ineffective due to signal attenuation—such as in liquids or dense media like metal or stone. Leveraging GNU Radio and commercially available audio hardware, a low-cost, SDR (Software Defined Radio) system was developed to transmit data blocks (e.g., images, text, and audio) through various substances. The system employs BFSK (Binary Frequency Shift Keying) and BPSK (Binary Phase Shift Keying), operates at ultrasonic frequencies (typically 40 kHz), and has performance validated under real-world conditions, including water, viscous substances, and flammable liquids such as hydrocarbon fuels. Experimental results demonstrate reliable, continuous communication at Nyquist–Shannon sampling rates, with effective demodulation and file reconstruction. The methodology builds on concepts originally developed for Ad Hoc Sensor Networks in shipping containers, extending their applicability to submerged and RF-hostile environments. The modularity and flexibility of the GNU Radio platform allow for rapid adaptation across different media and deployment contexts. This work provides a reproducible and scalable communication solution for scenarios where RF transmission is impractical, offering potential applications in underwater sensing, industrial monitoring, railways, and enclosed infrastructure diagnostics. Across controlled laboratory experiments, the system achieved 100% successful reconstruction of transmitted image files up to 100 kB and sustained packet delivery success exceeding 98% under stable coupling conditions. Full article

In recent years, Advanced Persistent Threat (APT) malware, with its high stealth, has made it difficult for unimodal detection methods to accurately identify its disguised malicious behaviors. To address this challenge, this paper proposes an APT Malware Detection Model based on Heterogeneous Multimodal Semantic Fusion (HMSF-ADM). By integrating the API call sequence features of APT malware in the operating system and the RGB image features of PE files, the model constructs multimodal representations with stronger discriminability, thus achieving efficient and accurate identification of APT malicious behaviors. First, the model employs two encoders, namely a Transformer encoder equipped with the DPCFTE module and a CAS-ViT encoder, to encode sequence features and image features, respectively, completing local–global collaborative context modeling. Then, the sequence encoding results and image encoding results are interactively fused via two cross-attention mechanisms to generate fused representations. Finally, a TextCNN-based classifier is utilized to perform classification prediction on the fused representations. Experimental results on two APT malware datasets demonstrate that the proposed HMSF-ADM model outperforms various mainstream multimodal comparison models in core metrics such as accuracy, precision, and F1-score. Notably, the F1-score of the model exceeds 0.95 for the vast majority of APT malware families, and its accuracy and F1-score both remain above 0.986 in the task of distinguishing between ordinary malware and APT malware. Full article

An algorithm has been implemented and it is provided in this article as an executable program to extract the five solar cell parameters within the one-diode solar cell model. Boole’s integration rule has been put into practice to integrate the current minus the short-circuit current, yielding a more accurate Co-Content function. Afterwards, the Co-Content function is fitted to a second-degree polynomial in two variables, namely, the voltage and the current minus the short-circuit current, providing six fitting constants. The five solar cells are deduced from these six fitting constants. This algorithm has been implemented in an automatic program that performs the calculations. The program also obtains the standard deviations of the fitting errors, which are used to obtain the standard deviations of the five solar cell parameters. The program reports to the user the results in three text files, from which the user can easily copy-paste the results into softwares like Origin, Word, or Excel. A program to smooth the current voltage curves is also provided. Two videos are also available, one explaining how to profit from this executable program, and the other one how to use the smoothing program. Full article

Background: The Metabolomics Workbench (MW) is a public scientific data repository consisting of experimental data and metadata from metabolomics studies collected with mass spectroscopy (MS) and nuclear magnetic resonance (NMR) analyses. Although not as rapidly as in the past, MW has steadily evolved, updating its mwTab and JSON deposition text file formats and its web-based infrastructure. However, the growth of MW has been exponential since its inception in 2013 and continues to be exponential, with the number of datasets hosted on the repository increasing by 50% since April 2024. As part of regular maintenance to keep up with changes to the mwTab file format and an earnest effort to use MW datasets in meta-analyses, the mwtab Python package has been updated. Methods: Updates include better error handling for batch processing, better parsing to read more files without error, and extensive improvements to the validation capabilities of the package. These updates also required our mwFileStatusWebsite to be updated and improved. Results: We used the enhanced validation features of the mwtab package to evaluate all available datasets in MW to facilitate improved curation, FAIRness of the repository, and reuse for meta-analyses. Conclusions: Version 2.0.0 of the mwtab Python package is now officially released and freely available on GitHub and the Python Package Index (PyPI) under a Clear Berkeley Software Distribution (BSD) license, with documentation available on GitHub. The updated mwFileStatusWebsite is also officially in its 2.0.0 version. Full article

Background/Objectives: Periodontal disease is a condition marked by the destruction of tooth-supporting tissues, driven by an exaggerated immune response to an unbalanced dental biofilm. Conventional treatments struggle due to antimicrobial resistance and the biofilm’s protective extracellular matrix. This study evaluates the potential of bacteriophages as an innovative strategy for managing periodontal disease. Methods: This research employed a qualitative approach using Discursive Textual Analysis, with IRAMUTEQ version 0.8 alpha 7 (Interface de R pour les Analyses Multidimensionnelles de Textes et de Questionnaires) software. The search was conducted in the Orbit Intelligence and PubMed databases, for patents and scholarly articles, respectively. The textual data underwent Descending Hierarchical Classification, Correspondence Factor Analysis, and Similarity Analysis to identify core themes and relationships between words. Results: The analysis revealed an increase in research and patent filings concerning phage therapy for periodontal disease since 2017, emphasizing its market potential. The primary centers for intellectual property activity were identified as China and the United States. The study identified five focus areas: Genomic/Structural Characterization, Patent Formulations, Etiology, Therapeutic Efficacy, and Ecology/Phage Interactions. Lytic phages were shown to be effective against prominent pathogens such as Fusobacterium nucleatum and Enterococcus faecalis. Conversely, the lysogenic phages poses a potential risk, as they may transfer resistance and virulence factors, enhancing pathogenicity. Conclusions: Phage therapy is a promising approach to address antimicrobial resistance and biofilm challenges in periodontitis management. Key challenges include the need for the clinical validation of formulations and stable delivery systems for the subgingival area. Future strategies, such as phage genetic engineering and data-driven cocktail design, are crucial for enhancing efficacy and overcoming regulatory hurdles. Full article

Rapid technological innovation has made navigating millions of new patent filings a critical challenge for corporations and research institutions. Existing patent recommendation systems, largely constrained by their static designs, struggle to capture the dynamic pulse of an ever-evolving technological ecosystem. At the same time, their “black-box” decision-making processes severely limit their trustworthiness and practical value in high-stakes, real-world scenarios. To address this impasse, we introduce TEAHG-EPR, a novel, end-to-end framework for explainable patent recommendation. The core of our approach is to reframe the recommendation task as a dynamic learning and reasoning process on a temporal-aware attributed heterogeneous graph. Specifically, we first construct a sequence of patent knowledge graphs that evolve on a yearly basis. A dual-encoder architecture, comprising a Relational Graph Convolutional Network (R-GCN) and a Bidirectional Long Short-Term Memory network (Bi-LSTM), is then employed to simultaneously capture the spatial structural information within each time snapshot and the evolutionary patterns across time. Building on this foundation, we innovatively introduce uncertainty modeling, learning a dual “deterministic core + probabilistic potential” representation for each entity and balancing recommendation precision with exploration through a hybrid similarity metric. Finally, to achieve true explainability, we design a feature-guided controllable text generation module that can attach a well-reasoned, faithful textual explanation to every single recommendation. We conducted comprehensive experiments on two large-scale datasets: a real-world industrial patent dataset (USPTO) and a classic academic dataset (AMiner). The results are compelling: TEAHG-EPR not only significantly outperforms all state-of-the-art baselines in recommendation accuracy but also demonstrates a decisive advantage across multiple “beyond-accuracy” dimensions, including explanation quality, diversity, and novelty. Full article

Law Enforcement Agencies (LEAs) typically analyse vast collections of media files, extracting visual information that helps them to advance investigations. While recent advancements in deep learning-based computer vision algorithms have revolutionised the ability to detect multi-class objects and text instances (characters, words, numbers) from in-the-wild scenes, their association remains relatively unexplored. Previous studies focus on clustering text given its semantic relationship or layout, rather than its relationship with objects. In this paper, we present an efficient, modular pipeline for contextual scene text grouping with three complementary strategies: 2D planar segmentation, multi-class instance segmentation and promptable segmentation. The strategies address common scenes where related text instances frequently share the same 2D planar surface and object (vehicle, banner, etc.). Evaluated on a custom dataset of 1100 images, the overall grouping performance remained consistently high across all three strategies (B-Cubed F1 92–95%; Pairwise F1 80–82%), with adjusted Rand indices between 0.08 and 0.23. Our results demonstrate clear trade-offs between computational efficiency and contextual generalisation, where geometric methods offer reliability, semantic approaches provide scalability and class-agnostic strategies offer the most robust generalisation. The dataset used for testing will be made available upon request. Full article

By searching for and summarizing the relevant information of the enterprise, we can build relevant knowledge maps, supplement and enrich the existing knowledge base, and support existing experiments and subsequent algorithm improvements. The extracted input text of enterprise archives is described via relation extraction and semantic analysis to improve the efficiency of archive retrieval and reduce the cost of communication. On the basis of the analysis of previous research, an enterprise archive semantic retrieval algorithm based on deep learning technology is constructed, that is, the BERT + BiGRU + CRF + HHO_improved model, to extract the relevant information of the enterprise. In the model, the Bidirectional Encoder Representations from Transformers (BERT) model is used to preprocess the Chinese word embedding, and the question-and-answer data are generated from the actual enterprise file database. Next, a Bidirectional Gated Recursive Unit (BiGRU) is used with the attention mechanism to capture the contextual features of the sequence. The Conditional Random Field (CRF) classifier is subsequently used to classify the text related to the enterprise archives, and the obtained data are labeled in sequence. Moreover, the swarm intelligence algorithm is introduced to dynamically optimize the model parameters and data processing strategies further to improve the generalization ability and adaptability of the model. The Harris Hawks Optimizer Improved (HHO_improved) algorithm is used to optimize the parameters of the CRF module to increase the performance and efficiency of named entity recognition. On the independently constructed dataset, the advantages of our algorithm are verified via comparative experiments with a variety of semantic matching algorithms and ablation experiments on the CRF and HHO_improved. The CRF and HHO_improved play essential roles in improving model performance. The obtained knowledge extraction results are expected to supplement and enhance the existing knowledge base, simplify the workflow, assist the enterprise’s dynamic production task management, and improve the efficiency of enterprise operations. The proposed algorithm achieves an accuracy improvement of 36.33%, 43.88%, 15.24%, and 12.41% over the BERT, BiGRU, BERT + BiGRU, and BERT + BiGRU + CRF models, respectively. Full article

Vessel Traffic Service systems play a critical role in maritime safety by providing timely advisories to vessels in congested waterways. However, the optimal timing for VTS operator interventions has remained largely unstudied, relying primarily on subjective operator experience rather than empirical evidence. This study presents the first large-scale empirical analysis of VTS operator intervention timing using automated speech recognition technology applied to actual maritime communication data. VHF radio communications were collected from five major VTS centers in Korea over nine months, comprising 171,175 communication files with a total duration of 334.2 h. The recorded communications were transcribed using the Whisper speech-to-text model and processed through natural language processing techniques to extract encounter situations and advisory distances. A tokenization and keyword framework was developed to handle Maritime English and local-language communications, normalize textual numerical expressions, and facilitate cross-site analysis. Results reveal that VTS operator intervention timing varies by encounter type. In head-on and crossing encounters, advisories are provided at distances, with mean values of 3.1 nm and 2.8 nm, respectively. These quantitative benchmarks provide an empirical foundation for developing standardized VTS operational guidelines and decision support systems, ultimately enhancing maritime safety and operational consistency across jurisdictions. Full article

To address information isolation and incomplete parameter extraction among multi-modal data (e.g., drawings, text, and tables) in the operation and maintenance stage of buildings, this paper proposes a multi-modal data parsing, automatic parameter extraction, and standardized integration method oriented toward 3D modeling. First, by employing vector element parsing and layer semantic analysis, the method enables structured extraction of key component geometry from architectural drawings and improves modeling accuracy via spatial topological relationship analysis. Second, by combining regular expressions, a domain-specific terminology dictionary, and a BiLSTM-CRF deep learning model, the extraction accuracy of unstructured parameters from architectural texts is significantly improved. Third, a multi-scale sliding window and geometric feature analysis are used to achieve automatic detection and parameter extraction from complex nested tables. Regarding the experimental setup: the drawings consist of a large-scale collection of DXF files stratified and randomly split into train/val/test with an approximate 8:1:1 ratio; the text set includes 1550 PDF-derived specification fragments (8:1:1 split); and the tables cover typical door/window, structural, and electrical schedules (also split ~8:1:1). F1 scores use micro-F1 (instance-level aggregation), and 95% confidence intervals and their computation are described in the main text. Experimental results show that the F1 scores for wall line, wall, and column recognition reach 98.1%, 84.9%, and 92.2%, respectively, while the F1 scores for door and window recognition are 74.3% and 76.2%. For text parameter extraction, the proposed PENet model achieves a precision of 83.56% and a recall of 86.91%. For the table task, the parameter extraction recalls for doors/windows and structure are 95.0% and 96.7%, respectively. The proposed method enables efficient parameter extraction and standardization from multi-modal architectural data, demonstrates significant advantages in handling heterogeneous data and improving modeling efficiency, and provides practical technical support for the digital reconstruction and intelligent management of existing buildings. Full article

Electroencephalography (EEG) provides insights into the neural mechanisms underlying attention, response inhibition, and distraction in cognitive tasks. This dataset was collected to examine neural activity in young drivers and non-drivers performing Go/No-Go tasks under visual and auditory distraction conditions. A total of 40 university students (20 drivers, 20 non-drivers; balanced by sex) completed eight experimental blocks combining visual or auditory stimuli with realistic distractions, such as text message notifications and phone call simulations. EEG was recorded using a 16-channel BrainAccess MIDI system at 250 Hz. Experiments 1, 3, 5, and 7 served as transitional blocks without participant responses and were excluded from behavioral and event-related potential analyses; however, their EEG recordings and event markers are included for baseline or exploratory analyses. The dataset comprises raw EEG files, event markers for Go/No-Go stimuli and distractions, and metadata on participant demographics and mobile phone usage. This resource enables studies of attentional control, inhibitory processes, and distraction-related neural dynamics, supporting research in cognitive neuroscience, brain–computer interfaces, and transportation safety. Full article

Ensuring the security and privacy of confidential data during transmission is a critical challenge, necessitating advanced techniques to protect against unwarranted disclosures. Steganography, a concealment technique, enables secret information to be embedded in seemingly harmless carriers such as images, audio, and video. This work proposes two secure audio steganography models based on the least significant bit (LSB) and discrete wavelet transform (DWT) techniques for concealing different types of multimedia data (i.e., text, image, and audio) in audio files, representing an enhancement of current research that tends to focus on embedding a single type of multimedia data. The first model (secured model (1)) focuses on high embedding capacity, while the second model (secured model (2)) focuses on improved security. The performance of the two proposed secure models was tested under various conditions. The models’ robustness was greatly enhanced using convolutional encoding with binary phase shift keying (BPSK). Experimental results indicated that the correlation coefficient (Cr) of the extracted secret audio in secured model (1) increased by 18.88% and by 16.18% in secured model (2) compared to existing methods. In addition, the Cr of the extracted secret image in secured model (1) was improved by 0.1% compared to existing methods. The peak signal-to-noise ratio (PSNR) of the steganography audio of secured model (1) was improved by 49.95% and 14.44% compared to secured model (2) and previous work, respectively. Furthermore, both models were evaluated in an orthogonal frequency division multiplexing (OFDM) system over various wireless channels, i.e., Additive White Gaussian Noise (AWGN), fading, and SUI-6 channels. In order to enhance the system performance, OFDM was combined with differential phase shift keying (DPSK) modulation and convolutional coding. The results demonstrate that secured model (1) is highly immune to noise generated by wireless channels and is the optimum technique for secure audio steganography on noisy communication channels. Full article

Background: Emergency airway management is a crucial and complex procedure frequently performed in the emergency department (ED). Airway contamination usually caused by blood, secretions, and emesis impairs ventilation, reduces successful intubation, and increases the complication rates, leading to difficult laryngoscopy, delayed intubation, and increased mortality rates. One technique employed to decontaminate these airways when standard approaches fail is Suction-Assisted Laryngoscopy and Airway Decontamination (SALAD). Methods: A comprehensive literature search was conducted across PubMed, Cochrane, and Science direct databases following a specific search strategy. All search results were screened in a two-stage process (title–abstract and full-text screening) in accordance with Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) 2020 guidelines. Data from finalized articles were extracted using a standardized excel file developed a priori. Lastly, quality and risk of bias were assessed using appropriate tools according to respective study designs, and data were narratively synthesized. Results: A total of 224 records were identified. Upon screening, seven studies were included consisting of five simulation-based studies and two clinical case reports. Simulation studies reported that SALAD training significantly improved first-pass intubation success (53.7–90.2%), reduced time to intubation (up to 30 s), and enhanced airway visualization. Clinical cases further reported successful first-pass intubation in patients with massive airway contamination without complications. Overall, across both study types, the SALAD technique improved airway management performance, provider confidence, and airway contamination control compared to standard suction techniques. Conclusions: This systematic review highlights the benefits of the SALAD technique by enhancing airway visualization, reinforcing it as a significant tool for contaminated airway management. Trainees who underwent SALAD training demonstrated improved first-pass intubation success, reduced intubation time, and increased operator confidence. While data from the included studies seems promising, most studies are small simulation-based studies with limited clinical outcome data. Given its clinical relevance and educational value, future studies must prioritize high-quality research in clinical environments to establish SALAD’s efficacy and to define its role in integration into prehospital protocols. Full article

Background: Next-generation sequencing (NGS) analysis of viral samples generates results dispersed across multiple files—genome assembly, variant calling, and functional annotations—making integrated interpretation challenging. Variants often yield numerous low-frequency or non-significant variants, yet only a small fraction are biologically relevant. Virologists must manually sift through extensive data to identify meaningful mutations, a time-consuming and error-prone process. To address these practical challenges, we developed vvv2_display, a dedicated summarization and visualization tool, integrated within comprehensive Galaxy workflows. Results: vvv2_display streamlines variant interpretation by consolidating key results into two concise and interoperable outputs. The first output is a PNG image showing alignment coverage depth and genomic annotations, with significant variants displayed along the genome as symbols whose height reflects frequency and shape indicates the affected protein. At a glance, this enables virologists to identify all deviations from a reference viral genome. Each significant variant is assigned a unique identifier that directly links to the second output: a tab-separated (TSV) text file listing only high-confidence variants, with frequencies, flanking nucleotides, and impacted genes and proteins. This cross-referenced design supports rapid, accurate, and intuitive data exploration. Availability: vvv2_display is open source, available on Github and installable via Mamba. Full article