Browse Articles
Discover research articles across all indexed journals
<i>Ortho</i> – <i>Meta</i> and <i>Para</i> – <i>Meta</i> Isomerization of Phenols
SPARTAN: automated table detection and extraction from documents using advanced OpenCV heuristics and OCR techniques
Abstract The rapid growth of born-digital PDF documents has amplified the demand for fast, precise tabular data extraction on an industrial scale. State-of-the-art deep-learning approaches have high accuracy, but at the resource expense of substantial computational complexity, data-hungry training process and black-box incomprehensibility, confining deployment in the real world. In this paper, we introduce SPARTAN (Structured Parsing and Relevant Table Analysis), an entirely open-source, heuristic-based pipeline, with high-fidelity table detection and extraction and no model training or GPU requirements. SPARTAN mixes lightweight OpenCV image-processing modules: column whitespace analysis, boundary and text-based region segmentation and line segment cell parsing, with a modular OCR layer and optional post-processing hooks for LLM-driven schema mapping. We evaluated SPARTAN on more than 20 K pages of PCN-480 (Product Change Notification and Product Discontinuance Notification), scientific papers, certificates and datasheets and reported 0.94 precision, 0.91 recall and 0.93 F1-score, with 96.7% OCR character accuracy, processing a page in 2.8 s CPU time on an average, and requiring 1.2 GB peak RAM on the most demanding PDFs. Our model outperformed Tabula, Deepdoctection, TabbyPDF and EMbTTBF in accuracy and speed. It must be noted that this comparison was conducted against standard inference configurations for the learning-based baselines; a performance evaluation against highly-optimized, edge-device deployments is a consideration for future work. Its rule transparency effortlessly copes with borderless, nested and merged-cell layouts that easily outsmart classical heuristics, without incurring the resource cost of end-to-end neural pipelines. SPARTAN’s CLI-governed, swap-in-swap-out architecture encourages domain tuning, edge deployment and cloud-scalable REST service wrapping, making it a practical bridge between brittle rule systems and heavyweight AI for document-understanding pipelines. The work proves that well-crafted modernized heuristics, combined with high-quality OCR, can match or even outperform state-of-the-art deep learning while remaining within reach of small and medium enterprises, thus re-opening a critical gate to cost-efficient, explainable PDF table extraction.
Multiplexed Photo-Cross-Linking Reveals Comprehensive Midnolin Interactome: Insights into Ubiquitin-Independent Degradation and Functional Diversity
Impact of genotype and soil fertility on wheat rhizosphere microbiota under the trans-gangetic plain
Mapping the Coordination Number and Coordination Geometry of Lanthanide Ions in Aqueous and Nonaqueous Solution Phases
Tailored personas for anticipatory grief management among primary family caregivers of patients with advanced lung cancer in China: a qualitative study
Au-Coordinated Motifs with Optimization of Electronic Structure and Hydrogen Bond Network in Zr-Based Metal–Organic Frameworks for Enhanced Photocatalytic Hydrogen Evolution
In situ assembled MIL-101(Cr) composite functionalized with chitosan and tannic acid as an efficient adsorbent for Pb2+ removal from aqueous solutions
Reaction-Class-Dependent Intrinsic Barriers Unify Deviant and Multimodal Bell–Evans–Polanyi Behavior in Polar Group Transfer Reactions
c-MYC enhances transcription of the type 1 diabetes mellitus associated gene BATF3 via promoter binding
Correction to “A Tandem Bioorthogonal Retro-Cope and Cope Elimination for the Activation of Covalent Inhibitors with an Acrylamide or Vinylsulfonamide Warhead in Live Cells”
Clinical evaluation of plasma neopterin as a biomarker of immune activation in allergic rhinitis using a fluorescence-based o-phthaldehyde derivatization method
A Dinuclear Iron(II) Persulfide Complex Reacts with O <sub>2</sub> to Give Sulfite: Relevance to Persulfide Dioxygenases
Symptoms, risk factors, and health outcomes of long COVID in the United Arab Emirates
Catalyzing Li-Salt Dissociation and Decomposition for a Conformal Low-Impedance Solid Electrolyte Interphase in Solid-State Li Metal Batteries
Effect of app-based mindfulness on extinction recall – a 7T-fMRI study
Abstract Fear-based disorders affect millions worldwide, yet current treatments show limited effectiveness for many patients. While mindfulness is increasingly used clinically for anxiety and trauma disorders, the neural mechanisms underlying its effects on fear processing remain unclear. We conducted a randomized controlled trial using 7T fMRI to test whether mindfulness training enhances fear extinction recall—a process critical for recovery from these disorders. Healthy participants received four weeks of app-based mindfulness meditation ( n = 27) or served as waitlist controls ( n = 28), then underwent fear conditioning and extinction recall testing. Mindfulness training specifically enhanced extinction recall, reducing threat responses to extinguished cues by both physiological (skin conductance, p =.028) and neural measures. Critically, our findings reveal a candidate mechanism: mindfulness reduced activation in subcortical threat-processing regions (amygdala, striatum, supplementary motor area) without enhancing cognitive control areas, a pattern consistent with direct modulation of fear circuits rather than top-down inhibition, though top-down contributions cannot be excluded. This pattern is consistent with mindfulness enhancing safety memory retrieval through implicit rather than explicit emotion regulation, providing preliminary neurobiological evidence relevant to optimizing mindfulness-based treatments. Our findings suggest that mindfulness training, whether administered before or alongside exposure therapy, could potentially enhance therapeutic outcomes by improving the consolidation and retrieval of safety memories, although replication in larger clinical samples is needed.