Extraction Approach Research Articles

Schema Extraction in NoSQL Databases: A Systematic Literature Review

Introduction: Nowadays, NoSQL databases have taken on an increasingly important role in the storage of massive data within companies. Due to a common property called schema-less, NoSQL databases offer great flexibility, particularly for the storage of data in different formats. However, despite their success in data storage, schema-less databases are a major obstacle in areas requiring precise knowledge of this schema, especially in the field of data integration. Method: This study presents a Systematic Literature Review (SLR) to explore, evaluate, and discuss relevant existing research and endeavors using novel schema extraction approaches. Furthermore, we conducted this study using a well-defined methodology to examine and study the problem of schema extraction from NoSQL databases. Results: Our research results highlight and emphasize the scheme extraction approaches and provide knowledge to researchers and practitioners by proposing schema extraction approaches and their limitations, which contributes to inventing new, more efficient approaches. Conclusion: In our future work, inspired by the recent advances in quantum computing and the emergence of post-quantum cryptography (PQC), we aim to propose a schema extraction approach that blends cutting-edge technologies with a strong focus on database security.

An approach for built-up area extraction using different indices and deep neural network (DNN) model

Mapping urbanization and built-up areas from remotely sensed data poses a formidable challenge, particularly when the spectral reflectance of built-up regions intersects with other land types. To address this, numerous spectral indices have been developed. This paper utilizes multiple indices: Normalized Difference Built-up Index (NDBI), Built-up Area Extraction Index (BAEI), Normalized Built-up Area Index (NBAI), New Built-up Index (NBI), Modified Built-up Index (MBI), Band Ratio for Built-up Area (BRBA), and Normalized Difference Vegetation Index (NDVI) to delineate built-up regions. An intersection approach between BAEI, NBAI, and NDVI refines the methodology, resulting in a final built-up map with 92.5 % accuracy and a 0.848 Kappa coefficient. Subsequently, a Deep Neural Network (DNN) model trained on this map achieves over 95 % accuracy in predicting built-up areas from Landsat 5 imagery, and the resultant built-up map achieved an overall accuracy of 92 % and a Kappa coefficient of 0.85. The proposed methodology demonstrates efficiency for time-series analysis and addresses misclassification in built-up areas. Moreover, the optimization of the DNN model proves effective when meticulous training and validation processes incorporate more precise sample datasets.

AI-Based Feature Extraction Approaches for Dual Modalities of Autism Spectrum Disorder Neuroimages

AI-Based Feature Extraction Approaches for Dual Modalities of Autism Spectrum Disorder Neuroimages

Mercury speciation in environmental samples associated with artisanal small-scale gold mines using a novel solid-phase extraction approach to sample collection and preservation

In artisanal small-scale gold mines (ASGM), mercury (Hg) is known to pollute nearby river waters and sediments where it can be methylated to the highly bioavailable methylmercury (MeHg). The assessment of Hg speciation in water samples has been challenging for many years, with recommended procedures often not adequately allowing for analysis of samples in a suitable timeframe. Using a novel solid-phase extraction (SPE) method for sampling and preservation of Hg species, representative speciation data can be safely and easily collected and retained for up to 4-weeks (MeHg = 115 ± 8% refrigerated and 109 ± 13% unrefrigerated storage; Hg2+ = 100 ± 14% refrigerated and 94 ± 12% unrefrigerated storage). Concentrations of MeHg in environmental water samples and drinking water were below detection limit across two ASGM sites in western Kenya and concentrations of Hg2+ were below drinking water guidelines; however, drinking water sources contribute 20–30% of the tolerable weekly intake of Hg, indicating a need to minimise exposure of Hg from dietary sources to prevent Hg poisoning. Sediments from receiving rivers at ASGM sites showed total Hg concentrations above guideline limits (0.08–1.84 mg kg−1 total Hg) along the length of the river; however, MeHg concentrations fluctuated dependent on the stagnation of the river due to damns and ponds (5.9 ± 14.3 µg kg−1 MeHg). The findings show that SPE can be used as a robust sample collection and preservation approach for Hg speciation, which can better inform mitigation measures, understand ecological and human health implications, and improve environmental monitoring.

Phenolic Content, Antioxidant and Antimicrobial Properties of Hawthorn (Crataegus orientalis) Fruit Extracts Obtained via Carbohydrase-Assisted Extraction

The enzyme-assisted approaches for plant phenolics extraction are more eco-friendly methods compared to acid or alkaline hydrolysis. Carbohydrase enzymes can release free phenolics from plant materials by cleaving the glycosidic bonds between phenolic compounds and cell wall polymers. In this study, the efficiency of carbohydrase-assisted treatment approaches was evaluated to extract bioactive phenolics from hawthorn (Crataegus orientalis) fruit residues. Enzymatic treatment of the fruits was operated by using a crude cellulolytic enzyme cocktail from Rhizomucor miehei NRRL 5282 and a pectinase preparate from Aspergillus niger. Both cellulase and combined cellulase–pectinase treatments improved the total phenolic content (TPC) and antioxidant activity of extracts. The TPC increased to 1899 ± 27 mg gallic acid equivalents/100 g dry matter during the combined enzyme treatment, showing a strong correlation with the average antioxidant capacity determined by ferric-reducing antioxidant power (1.7-fold increment) and 2,2-diphenyl-1-picrylhydrazyl (1.15-fold increment) reagents. The major phenolics in enzyme-treated extracts were vanillic and ferulic acids, the concentrations of which increased 115.6-fold and 93.9-fold, respectively, during carbohydrase treatment. The planktonic growth of Escherichia coli, Bacillus subtilis, Pseudomonas aeruginosa, and Chromobacterium violaceum was slightly inhibited by the extracts with minimum inhibitory concentration values between 15.0 and 77.9 mg/mL, while the yeasts tested were quite resistant to the samples. B. subtilis and yeast biofilms were sensitive to the enzyme-treated extracts, which also showed quorum-sensing inhibitory effects against C. violaceum. The obtained bioactive hawthorn extracts hold potential as a natural source of antioxidants and antimicrobials.

Isolation and Characterization of Novel Cellulose Micro/Nanofibers from Lygeum spartum Through a Chemo-Mechanical Process

Recent studies have focused on the development of bio-based products from sustainable resources using green extraction approaches, especially nanocellulose, an emerging nanoparticle with impressive properties and multiple applications. Despite the various sources of cellulose nanofibers, the search for alternative resources that replace wood, such as Lygeum spartum, a fast-growing Mediterranean plant, is crucial. It has not been previously investigated as a potential source of nanocellulose. This study investigates the extraction of novel cellulose micro/nanofibers from Lygeum spartum using a two-step method, including both alkali and mechanical treatment as post-treatment with ultrasound, as well as homogenization using water and dilute alkali solution as a solvent. To determine the structural properties of CNFs, a series of characterization techniques was applied. A significant correlation was observed between the Fourier transform infrared (FTIR) spectroscopy and X-ray diffraction (XRD) results. The FTIR results revealed the elimination of amorphous regions and an increase in the energy of the H-bonding modes, while the XRD results showed that the crystal structure of micro/nanofibers was preserved during the process. In addition, they indicated an increase in the crystallinity index obtained with both methods (deconvolution and Segal). Thermal analysis based on thermogravimetric analysis (TGA) and differential scanning calorimetry (DSC) confirmed improvement in the thermal properties of the isolated micro/nanofibers. The temperatures of maximum degradation were 335 °C and 347 °C. Morphological analysis using a scanning electron microscope (SEM) and atomic force microscope (AFM) showed the formation of fibers along the axis, with rough and porous surfaces. The findings indicate the potential of Lygeum spartum as a source for producing high-quality micro/nanofibers. A future direction of study is to use the cellulose micro/nanofibers as additives in recycled paper and to evaluate the mechanical properties of the paper sheets, as well as investigate their use in smart paper.

An Investigation into the Utilisation of CNN with LSTM for Video Deepfake Detection

Video deepfake detection has emerged as a critical field within the broader domain of digital technologies driven by the rapid proliferation of AI-generated media and the increasing threat of its misuse for deception and misinformation. The integration of Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) has proven to be a promising approach for improving video deepfake detection, achieving near-perfect accuracy. CNNs enable the effective extraction of spatial features from video frames, such as facial textures and lighting, while LSTM analyses temporal patterns, detecting inconsistencies over time. This hybrid model enhances the ability to detect deepfakes by combining spatial and temporal analysis. However, the existing research lacks systematic evaluations that comprehensively assess their effectiveness and optimal configurations. Therefore, this paper provides a comprehensive review of video deepfake detection techniques utilising hybrid CNN-LSTM models. It systematically investigates state-of-the-art techniques, highlighting common feature extraction approaches and widely used datasets for training and testing. This paper also evaluates model performance across different datasets, identifies key factors influencing detection accuracy, and explores how CNN-LSTM models can be optimised. It also compares CNN-LSTM models with non-LSTM approaches, addresses implementation challenges, and proposes solutions for them. Lastly, open issues and future research directions of video deepfake detection using CNN-LSTM will be discussed. This paper provides valuable insights for researchers and cyber security professionals by reviewing CNN-LSTM models for video deepfake detection contributing to the advancement of robust and effective deepfake detection systems.

A hybrid of RSM, ANFIS, and machine learning algorithm approach for ultrasound-assisted extraction of bioactive compounds from Semecarpus anacardium Linn

ABSTRACT Ultrasound-assisted solvent extraction (UASE) was appslied to extract phytoconstituents from Semecarpus anacardium L. The effective extraction parameters were optimized using the Response Surface Methodology (RSM) with Central Composite Face Centered design (CCFC), and the optimization parameters were validated through Adaptive Neuro-Fuzzy Inference System (ANFIS) and Machine Learning (ML) algorithm models. The four independent parameters, i.e. ethanol concentration (X 1: 62–72% v/v), temperature (X 2: 38–48°C), ultrasonic-exposure time (X 3: 12–24 min), and particle size (X 4: 2–5 mm) were optimized. The maximum yield of phytocompounds was achieved at X 1 = 67%, X 2 = 43°C, X 3 = 18 min, and X 4 = 3.5 mm. The optimized yield of total phenolic, flavonoid, and antioxidant activity was considered when selecting process parameters. In this scenario, the optimized yields of total polyphenolic content (y1 = 619.25 mg gallic acid equivalent (GAE)/g), total flavonoid content (y2 = 151.24 mg Quercetin equivalents (QE)/g), free radical scavenging abilities (%DPPH*sc (y3 = 66.41%), and %ABTS*sc (y4 = 56.94%). The LC-MS peaks identify the presence of semecarpetin, butein, and amentoflavone, whereas GS-MS peaks represent seventeen gaseous components. Furthermore, the bioactive-rich optimized extract was nontoxic and supported the growth of macrophage- and epithelial cells in vitro. Conclusively, optimizing the UASE parameters enhanced the yield of bioactive compounds of S. anacardium L.

A Review on Bacteriocin Extraction Techniques from Lactic Acid Bacteria.

Lactic acid bacteria (LAB) are widely known for the production of secondary metabolites such as organic acids and other bioactive compounds such as bacteriocins. Finding a broad application in food and healthcare, bacteriocins have received increased attention due to their inherent antimicrobial properties. However, the extraction of bacteriocins is often plagued with low yields due to the complexity of the extraction processes and the diversity of bacteriocins themselves. Here, we review the current knowledge related to bacteriocin extraction on the different extraction techniques for isolating bacteriocins from LAB. The advantages and disadvantages of each technique will also be critically appraised, taking into account factors such as extraction efficiency, scalability and cost-effectiveness. This review aims to guide researchers and professionals in selecting the most suitable approach for bacteriocin extraction from LAB by illuminating the respective advantages and limitations of various extraction techniques.

Implementation of a semi-automatic approach for detection and extraction of oil slicks using Sentinel-1: Case study of the Moroccan exclusive economic zone

Due to its strategic geographic location, Morocco experiences heavy ship traffic, which inevitably has consequences. Ship accidents and illegal discharges, commonly referred to as oil spills, are frequent and pose significant harm to the marine ecosystem. Therefore, employing new technologies, such as satellite monitoring, is crucial and will greatly enhance the ability to monitor and assess these oil spills. The present work is based on Sentinel-1 SAR images and aims to take into evidence the extent of the hydrocarbon marine pollution in all of the Moroccan EEZ. More than 220 possible cases were detected and mapped during the last decade (2014–2024). A batch process was developed to automate the detection of oil spills by identifying areas with reduced Normalized Radar Cross Section (NRCS) values. This process incorporates corrections, masks, wind field estimation, and oil clustering. The method successfully detected approximately 80% of the cases between Kenitra and Casablanca. The closest detected spill is located 1 km from the coast, the largest spill covers an area of 90 km2, and the most extended spill measures about 145 km. This study can help raise awareness among governmental authorities about potential environmental damage and can be used to train artificial intelligence models, which could simulate oil slick propagation.

Attention Induced Dual Convolutional-Capsule Network (AIDC-CN): A deep learning framework for motor imagery classification

In recent times, Electroencephalography (EEG)-based motor imagery (MI) decoding has garnered significant attention due to its extensive applicability in healthcare, including areas such as assistive robotics and rehabilitation engineering. Nevertheless, the decoding of EEG signals presents considerable challenges owing to their inherent complexity, non-stationary characteristics, and low signal-to-noise ratio. Notably, deep learning-based classifiers have emerged as a prominent focus for addressing the EEG signal decoding process. This study introduces a novel deep learning classifier named the Attention Induced Dual Convolutional-Capsule Network (AIDC-CN) with the specific aim of accurately categorizing various motor imagination class labels. To enhance the classifier’s performance, a dual feature extraction approach leveraging spectrogram and brain connectivity networks has been employed, diversifying the feature set in the classification task. The main highlights of the proposed AIDC-CN classifier includes the introduction of a dual convolution layer to handle the brain connectivity and spectrogram features, addition of a novel self-attention module (SAM) to accentuate the relevant parts of the convolved spectrogram features, introduction of a new cross-attention module (CAM) to refine the outputs obtained from the dual convolution layers and incorporation of a Gaussian Error Linear Unit (GELU) based dynamic routing algorithm to strengthen the coupling among the primary and secondary capsule layers. Performance analysis undertaken on four public data sets depict the superior performance of the proposed model with respect to the state-of-the-art techniques. The code for this model is available at https://github.com/RiteshSurChowdhury/AIDC-CN.

Water-aerosol-assisted roasting for selective lithium extraction from spent lithium-ion batteries

Selective extraction of lithium from spent lithium-ion batteries (LIBs) represents a promising solution for efficient lithium recovery. Herein, a water-aerosol-assisted roasting technology is proposed to selectively extract lithium from spent lithium transition metal oxides (LTMOs) cathodes. In an exemplary recycling of spent LiCoO2, the cathode material undergoes a low-temperature (350°C) chlorinating roast process to convert it into metal chlorides, followed by a higher-temperature (500°C) roasting to facilitate the selective pyrolysis of CoCl2. The presence of water-aerosol significantly enhances the selective pyrolysis process of CoCl2, reducing roasting time eightfold compared to conventional air roasting. Subsequent water-leaching effectively extracts 99.1 % of lithium as LiCl, while only 0.2 % of cobalt is extracted, ensuring selective lithium recovery. The resulting high-purity LiCl solution and Co3O4 residue are directly utilizable for producing battery-grade Li2CO3 and LiCoO2, respectively. Regenerated LiCoO2 demonstrates excellent cycling stability, retaining 90.5 % of its capacity after 300 cycles at 1C rate. Moreover, this method is applicable to ternary cathodes (NCM) black mass, offering a sustainable, robust, and cost-effective approach for lithium extraction from spent LIBs.

MFCA-MICNN: a convolutional neural network with multiscale fast channel attention and multibranch irregular convolution for noise removal in dMRI

Diffusion magnetic resonance imaging (dMRI) currently stands as the foremost noninvasive method for quantifying brain tissue microstructure and reconstructing white matter fiber pathways. However, the inherent free diffusion motion of water molecules in dMRI results in signal decay, diminishing the signal-to-noise ratio (SNR) and adversely affecting the accuracy and precision of microstructural data. In response to this challenge, we propose a novel method known as the Multiscale Fast Attention-Multibranch Irregular Convolutional Neural Network for dMRI image denoising. In this work, we introduce Multiscale Fast Channel Attention, a novel approach for efficient multiscale feature extraction with attention weight computation across feature channels. This enhances the model's capability to capture complex features and improves overall performance. Furthermore, we propose a multi-branch irregular convolutional architecture that effectively disrupts spatial noise correlation and captures noise features, thereby further enhancing the denoising performance of the model. Lastly, we design a novel loss function, which ensures excellent performance in both edge and flat regions. Experimental results demonstrate that the proposed method outperforms other state-of-the-art deep learning denoising methods in both quantitative and qualitative aspects for dMRI image denoising with fewer parameters and faster operational speed.

A Net Shape Profile Extraction Approach for Exploring the Forming Appearance of Inclined Thick-Walled Structures by Wire Arc Additive Manufacturing

Wire arc additive manufacturing (WAAM) offers a viable solution for fabricating large-scale metallic parts, which contain various forms of inclined thick-walled structure. Due to the variety of heat dissipation conditions at different positions, the inclined thick-walled structure is a major challenge in fabrication that may produce collapses and defects. However, there is a lack of effective sensing method for acquiring the forming appearance of individual beads in the structure. This paper proposes a novel approach for extracting individual bead profiles during the WAAM process. The approach utilizes a structured-laser sensor to capture the morphology of the surface before and after deposition, thereby enabling an accurate acquisition of the bead profile by integrating the laser stripes. Utilizing the proposed approach, the research investigated the forming mechanism of beads in inclined thick-walled components that were fabricated by various deposition parameters. The width of the overlapping area at the overhanging feature decreased as the layer number increased, while the height of the same area increased. The height of the overlapping area in each layer increased with an increase in deposition current and decreased when the deposition speed was increased. These phenomena suggest that the heat input is a major factor that influences the formation of the overhanging feature. Both the deposition current and deposition velocity influence heat input, and thereby have an effect in enhancing the geometrical accuracy of an overhanging feature. The experimental results indicate that the proposed approach facilitates morphology change investigation, providing a sufficient reference for optimizing deposition parameters.

Evaluation of a combined chemical, electrochemical, and mechanochemical approach for metal extraction from contaminated dredged sediments: preliminary studies

Evaluation of a combined chemical, electrochemical, and mechanochemical approach for metal extraction from contaminated dredged sediments: preliminary studies

Comparative analysis of features extraction protocols for LC-HRMS untargeted metabolomics in mountain cheese ‘identitation’

This study presents a comprehensive metabolomic analysis of Parmigiano Reggiano samples to differentiate between those designated as Mountain Quality Certification (QC) and conventional Protected Designation of Origin (PDO). Despite following the same production protocol, these cheese varieties differ in the cows’ feeding regimes and milk stable locations, with mountain-certified samples adhering to specific requirements regarding milk origin and feed composition. An untargeted approach with Liquid Chromatography-High Resolution Mass Spectrometry (LC-HRMS) was proposed to characterize the cheese metabolome. High-resolution LC-MS data can generate gigabyte-sized files, making data compression essential for manageable multivariate analysis and noise reduction. This study employs the Region of Interest-Multivariate Curve Resolution (ROI-MCR) protocol to achieve effective data compression and chromatographic resolution, thereby extracting the most informative features. This method was compared with a classical approach for feature extraction from chromatographic data, namely Compound Discoverer (CD) software. The features extracted by both methods were analysed through Principal Component Analysis (PCA) and ASCA (ANOVA Simultaneous Component Analysis). The comparison of ROI-MCR and CD approaches demonstrated that while both methods yielded similar overall conclusions, ROI-MCR provided a more streamlined and manageable dataset, facilitating easier interpretation of the metabolic differences. Both approaches indicated that amino acids, fatty acids, and bacterial activity-related compounds played significant roles in distinguishing between the two sample types.

Covalent organic framework composite hydrogel sorbent beads for vortex-assisted dispersive miniaturized solid phase extraction of parabens and synthetic phenolic antioxidants in foodstuffs

A covalent organic framework composite hydrogel sorbent beads was fabricated for the vortex-assisted dispersive miniaturized-solid phase extraction and determination of parabens and synthetic phenolic antioxidants from food matrices. The covalent organic framework was entrapped into alginate hydrogel beads. This composite sorbent effectively adsorbs analytes through hydrophobic, π-π and hydrogen bonding interactions. Under optimal extraction conditions, the developed method demonstrated good linearity from 1.00 to 100 µg kg−1 for methyl paraben and 2.00 to 100 µg kg−1 for tertiary butylhydroquinone, propyl paraben, butyl paraben and butylated hydroxyanisole. Limits of detection ranged from 0.25 to 0.50 µg kg−1. The developed sorbent was applied to the extraction of parabens and synthetic phenolic antioxidants from tomato paste, mayonnaise, infant milk powder and coffee creamer samples. The analytes were separated and quantified by high-performance liquid chromatography, achieving recoveries ranging from 89 to 98 % with RSDs lower than 7 %. The vortex-assisted extraction approach was efficient, and the fabricated sorbent could be reused for up to eight cycles. The greenness of the methodology was also evaluated.

Efficient Impurity Removal from Model FCC Fuel in Millireactors Using Deep Eutectic Solvents

The goal of strict fuel quality regulations is to decrease the levels of sulfur, nitrogen, and aromatic chemicals in gasoline, thereby enhancing environmental safety. Due to the high costs of hydrodenitrification and hydrodesulfurization, many studies are looking for alternative fuel-purifying processes. The straightforward extraction approach using deep eutectic solvents (DESs) has proven to result in the removal of impurities and the enhancement of gasoline quality. Seven DESs were employed in a batch extraction process to purify the model fuel. The TbabFa-0 solvent was chosen for extraction in millireactors with different lengths, volume flows, and solvent ratios. In the millireactor, a slug regime and a laminar flow pattern were established for every process condition. For the chosen process conditions, the diffusion coefficient, volumetric mass transfer coefficient, and distribution ratio were determined. Better separation of all three key components was achieved during extraction in a millireactor using TbabFa-0. The efficiency of extraction with regenerated solvent was lowered by a maximum of 8%, showing the possibility of performing extraction in a millireactor with solvent recirculation.

Research on fiber OTDR signal recognition and classification based on the ViT model

In the field of event recognition for phase-sensitive optical time-domain reflectometry (-OTDR), convolutional neural networks (CNNs) have been the mainstream tool. However, Transformer models, with their self-attention mechanism, have provided a new perspective for image recognition tasks. This paper proposes a -OTDR event recognition method based on the Transformer model and experimentally demonstrates its significant advantages over CNNs. The method utilizes an attention-based feature extraction approach to recognize distributed fiber optic sensing signals in a phase-sensitive optical time-domain reflectometer (-OTDR). In perimeter defense applications, various interferences and noise severely affect the recognition of -OTDR sensing signals, leading to false alarms, making accurate signal recognition both challenging and necessary. Extracting signal features and using machine learning classification models to recognize signals has been a research hotspot in recent years. The effectiveness of feature extraction is crucial to classification performance. This project introduces a temporal-spatial dual attention mechanism into the feature extraction of fiber optic sensing signals to improve the accuracy and robustness of signal recognition.

Green and efficient extraction of an anticaner agent N-methylsansalvamide using ultrasound-assisted deep eutectic solvents from mycelia of strain Frusarium sp. R1

N-methylsansalvamide (SA), one of cyclic pentadepsipeptides produced by several Fusarium strains, is a promising therapeutic agent for the treatment of cancer disease. In order to make sufficient amount of SA for drug development, a green and efficient extraction process of SA from the mycelia of strain Fusarium sp. R1 using deep eutectic solvent-assisted ultrasound extraction (DES-UAE) was firstly achieved in this work. Solvent screening results indicated that choline chloride-acetic acid (ChCl-Aa) was shown to be the best DES for SA extraction. Through single-factor trials, Plackett-Burman design (PBD) and BoxBehnken design (BBD) experiments, the optimal conditions for DES-UAE with the highest SA yield of 58.2 ± 1.1 mg/g were obtained as follows: ChCl-Aa ratio of 1:2.0 (M/M), water content of 16.4 %, liquid-solid ratio of 37:1 (mL/g), ultrasonic power of 175 W for 47.4 min at 46.3 °C. Compared to conventional extraction approaches, DES-UAE exhibited better SA yield since it caused more serious damage to the surface of mycelia powder on basis of scanning electron microscopy (SEM) analysis. Furthermore, molecular interaction studies suggested that SA has a variety of interactions with ChCl-Aa, including hydrogen and electrovalent bonds as well as van der Waals forces. Finally, the recovery rate of SA reached up to 99.5 % when the ratio of distilled water and DES extracts was 15:1 (V/V). These findings provide the way for large-scale production of SA.