Fast Processing Time Research Articles

A Fast and Cost-Effective Electronic Nose Model for Methanol Detection Using Ensemble Learning

Methanol, commonly used to cut costs in the production of counterfeit alcohol, is extremely harmful to human health, potentially leading to severe outcomes, including death. In this study, an electronic nose system was designed using 11 inexpensive gas sensors to detect the proportion of methanol in an alcohol mixture. A total of 168 odor samples were taken and analyzed from eight types of ethanol–methanol mixtures prepared at different concentrations. Only 4 features out of 264 were selected using the feature selection method based on feature importance. These four features were extracted from the data of MQ-3, MQ-4, and MQ-137 sensors, and the classification process was carried out using the data of these sensors. A Voting Classifier, an ensemble model, was used with Linear Discriminant Analysis, Support Vector Machines, and Extra Trees algorithms. The Voting Classifier achieved 85.88% classification accuracy before and 81.85% after feature selection. With its cost effectiveness, fast processing time, and practicality, the recommended system shows great potential for detecting methanol, which threatens human health in counterfeit drink production.

AI-optimized elliptic curve with Certificate-Less Digital Signature for zero trust maritime security

The proliferation of sensory applications has led to the development of the Internet of Things (IoT), which extends connectivity beyond traditional computing platforms and connects all kinds of everyday objects. Marine Ad Hoc Networks are expected to be an essential part of this connected world, forming the Internet of Marine Things (IoMaT). However, marine IoT systems are often highly distributed, and spread across large sparse areas which makes it challenging to implement and manage centralized security measures. Despite some ongoing efforts to establish network connectivity in such environment, securing these networks remains an unreached goal. The use of Certificate-Less Digital Signatures (CLDS) with Elliptic Curve Cryptography (ECC) shows great promise in providing secure communication in these networks and achieving zero trust IoMaT security. By eliminating the need for certificates and associated key management infrastructure, CLDS simplifies the key management process. ECC also enables secure communication with smaller key sizes and faster processing times, which is crucial for resource-limited IoMaT devices. In this paper, we introduce CLDS using ECC as a means of securing IoT networks in a marine environment, creating a zero trust security framework for Internet of Marine Things (IoMaT). To increase security and robustness of the framework, we optimize the ECC parameters using two vital artificial intelligence algorithms, namely Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Evaluation results demonstrate a reduction in ECC parameter generation time by over 40% with GA optimization and 20% with PSO optimization. Additionally, the computational cost and memory usage for major ECC attacks increased significantly by up to 40% and 67% for Rho attacks, 34% and 53% for brute-force attacks, and 30% and 67% for improved hybrid attacks, respectively.

BrainQCNet: A Deep Learning attention-based model for the automated detection of artifacts in brain structural MRI scans

Abstract Analyses of structural MRI (sMRI) data depend on robust upstream data quality control (QC). It is also crucial that researchers seek to retain maximal amounts of data to ensure reproducible, generalizable models and to avoid wasted effort, including that of participants. The time-consuming and difficult task of manual QC evaluation has prompted the development of tools for the automatic assessment of brain sMRI scans. Existing tools have proved particularly valuable in this age of Big Data; as datasets continue to grow, reducing execution time for QC evaluation will be of considerable benefit. The development of Deep Learning (DL) models for artifact detection in structural MRI scans offers a promising avenue toward fast, accurate QC evaluation. In this study, we trained an interpretable Deep Learning model, ProtoPNet, to classify minimally preprocessed 2D slices of scans that had been manually annotated with a refined quality assessment (ABIDE 1; n = 980 scans). To evaluate the best model, we applied it to 2141 ABCD T1-weighted MRI scans for which gold-standard manual QC annotations were available. We obtained excellent accuracy: 82.4% for good quality scans (Pass), 91.4% for medium to low quality scans (Fail). Further validation using 799 T1w MRI scans from ABIDE 2 and 750 T1w MRI scans from ADHD-200 confirmed the reliability of our model. Accuracy was comparable to or exceeded that of existing ML models, with fast processing and prediction time (1 minute per scan, GPU machine, CUDA-compatible). Our attention model also performs better than traditional DL (i.e., convolutional neural network models) in detecting poor quality scans. To facilitate faster and more accurate QC prediction for the neuroimaging community, we have shared the model that returned the most reliable global quality scores as a BIDS-app (https://github.com/garciaml/BrainQCNet).

An Improved Hyper Spectral Imaging for Accurate Disease Diagnosis in Sustainable Medical Environments

Hyper spectral imaging (HSI) has emerged as a powerful technique for accurate disease diagnosis in medical environments. It provides high-resolution images with detailed spectral information, making it possible to identify subtle differences between healthy and diseased tissues. However, current HSI systems face challenges in terms of accuracy and efficiency, limiting their widespread application in sustainable medical environments. To overcome these challenges, our team has developed an improved HSI system that utilizes state-of-the-art spectral imaging technology and machine learning algorithms. This system is capable of capturing and analyzing a wider range of spectral data, enabling more precise identification of disease-specific spectral signatures. Furthermore, our system has been optimized to operate with minimal power consumption, making it environmentally friendly and suitable for sustainable medical environments. The improved HSI system has been successfully tested in clinical settings and has shown promising results in accurately diagnosing various diseases such as cancer, dermatitis, and cardiovascular conditions. Its high accuracy and fast processing time make it a valuable tool for early disease detection and treatment planning. Moreover, the ability to operate with low energy consumption makes it a sustainable solution for medical facilities in resourcelimited areas. In addition to its accuracy and efficiency, our improved HSI system is also user-friendly and can be easily integrated into existing medical imaging systems.

Rapid headspace analysis of commercial spearmint and peppermint teas using volatile 'fingerprints' and an electronic nose.

Spearmint and peppermint teas are widely consumed around the world for their flavor and therapeutic properties. Dynamic headspace sampling (HS) coupled to gas chromatography/mass spectrometry (GC-MS) with principal component analysis (PCA) of 'fingerprint' volatile profiles were used to investigate 27 spearmint and peppermint teas. Additionally, comparisons between mint teas were undertaken with an electronic nose (enose). Twenty compounds, all previously known in the literature, were identified using HS-GC-MS. PCA found distinct differences between the fingerprint volatile profiles of spearmint, peppermint and spearmint/peppermint combination teas. HS-GC-MS analysis performed with an achiral column allowed faster processing time and yielded tighter clustering of PCA tea groups than the analysis which used a chiral column. Two spearmint outliers were detected. One showed a high degree of variation in volatile composition and a second wholly overlapped with the peppermint PCA grouping. Enose analysis separated all treatments with no overlaps. Characterizing the volatile fingerprints of mint teas is critical to quality control for this valuable agricultural product. The results of this study show that fingerprint volatile profiles and enose analysis of mint teas are distinctive and could be used to rapidly identify unknown samples. With specific volatile profiles identified for each tea, samples could be tested in the laboratory, or potentially on a farm or along the supply chain, to confirm the provenance and authenticity of mint food or beverage commodities. © 2024 Society of Chemical Industry. This article has been contributed to by U.S. Government employees and their work is in the public domain in the USA.

MEDANet: More Efficient Dual Attention Network for Scene Segmentation

The dual attention module is a potent semantic segmentation technique renowned for its capabilities, yet it often faces significant computational demands and GPU memory usage. To tackle these challenges, we introduce an advanced dual perception network comprising two modules: A streamlined Multi-scale Efficient Position Attention Module (MEPAM) and an optimized Efficient Channel Attention Module (MECAM). MEPAM incorporates multi-scale global average pooling into the Position Attention Module (PAM), substantially cutting computational overhead and memory consumption without compromising performance. Meanwhile, MECAM integrates compressed convolutions into the Channel Attention Module (CAM), improving segmentation accuracy and inference speed compared to conventional methods like DANet. Our approach underwent comprehensive evaluation on a semantic segmentation benchmark dataset, showcasing superior performance. For instance, on the Cityscapes dataset, our method achieves an IoU of 82.2%. In terms of efficiency gains, MEPAM operates nearly 1.97 times faster than the standard PAM module on GPU, while requiring 7.55 times less memory with a [Formula: see text] input. Similarly, MECAM achieves approximately 2.2 times faster processing than CAM, while cutting GPU memory usage by 7.53 times. This innovative dual perception network not only enhances segmentation accuracy and speed but also addresses the computational challenges associated with traditional dual attention modules.

Convection rather than diffusion for fast efficient mRNA vaccine purification

In the rush to produce mRNA vaccines and ensure integrity and purity, capital-intensive purification steps were used, typically involving slow diffusion-driven, inefficient, and costly chromatographic resin processes. We present the first results that microporous affinity synthetic polymer membranes can outperform commercial monolithic and resin approaches for capture of mRNA, thereby promoting fast purification of mRNA vaccines and therapeutics. Our seminal finding is that capture of Fluc-mRNA by synthetic affinity membranes enables efficient intact mRNA recovery (∼100 % of bound mass), faster processing times and lower dispersion by leveraging convective flow with short diffusional path lengths. We also demonstrate higher ligand accessibility and device productivity. Accessible ligand per device volume was 87–94 %, ∼74 % and ∼53 % for the membranes, monoliths, and resin column, respectively. A calibrated mathematical framework predicted mRNA pulse breakthrough with dispersion that was measured in the process tubing and membrane module using a non-reactive tracer and modeled using ideal reactors.

Simultaneous frequency and phase corrections of single-shot MRS data using cross-correlation.

The objective of this study was to propose a novel preprocessing approach to simultaneously correct for the frequency and phase drifts in MRS data using cross-correlation technique. The performance of the proposed method was first investigated at different SNR levels using simulation. Random frequency and phase offsets were added to a previously acquired STEAM human data at 7 T, simulating two different noise levels with and without baseline artifacts. Alongside the proposed spectral cross-correlation (SC) method, three other simultaneous alignment approaches were evaluated. Validation was performed on human brain data at 3 T and mouse brain data at 16.4 T. The results showed that the SC technique effectively corrects for both small and large frequency and phase drifts, even at low SNR levels. Furthermore, the mean square measurement error of the SC algorithm was comparable to the other three methods used, with much faster processing time. The efficacy of the proposed technique was successfully demonstrated in both human brain MRS data and in a noisy MRS dataset acquired from a small volume-of-interest in the mouse brain. The study demonstrated the availability of a fast and robust technique that accurately corrects for both small and large frequency and phase shifts in MRS.

Deep Learning Method for Real-Time Fire Detection System for Urban Fire Monitoring and Control

During urban fire incidents, real-time videos and images are vital for emergency responders and decision-makers, facilitating efficient decision-making and resource allocation in smart city fire monitoring systems. However, real-time videos and images require simple and embeddable models in small computer systems with highly accurate fire detection ratios. YOLOv5s has a relatively small model size and fast processing time with limited accuracy. The aim of this study is to propose a method that employs a YOLOv5s network with a squeeze-and-excitation module for image filtering and classification to meet the urgent need for rapid and accurate real-time screening of irrelevant data. In this study, over 3000 internet images were used for crawling and annotating to construct a dataset. Furthermore, the YOLOv5, YOLOv5x and YOLOv5s models were developed to train and test the dataset. Comparative analysis revealed that the proposed YOLOv5s model achieved 98.2% accuracy, 92.5% recall, and 95.4% average accuracy, with a remarkable processing speed of 0.009 s per image and 0.19 s for a 35 frames-per-second video. This surpasses the performance of other models, demonstrating the efficacy of the proposed YOLOv5s for real-time screening and classification in smart city fire monitoring systems.

Surface Tuning of Transparent Electrodes with Atmospheric Pressure Plasma for Third Generation Photovoltaics

Transparent semiconductor thin films such as indium tin oxide (ITO) and fluorine-doped tin oxide (FTO) are commonly used in optoelectronic devices due to their favorable properties such as high conductivity and transparency and suitable work function [1]. Their use ranges from light-emitting diodes through flat panel displays up to solar cells. In this context, surface stoichiometry plays a crucial role in influencing the final properties of the final device. Therefore, efficient surface treatment has been a topic in research for years, covering a wide range of approaches from wet and dry treatments. Among these possibilities, plasma treatment remains today the most effective. In several studies [2, 3], atmospheric pressure plasma shown an increase of surface energy, decrease the contamination while enhancing the work function of both ITO and FTO. Low temperature, fast processing times, and no special requirements for working gas are the main advantages of this approach.In this study, the authors compare the effects of cold (<100°C) atmospheric pressure plasma on ITO and FTO after air and nitrogen treatment to provide deeper insight into the interaction of discharge with semiconductive materials during treatment. A coplanar dielectric barrier discharge has been used for the surface modification (more information available in [4]). For this configuration both electrodes lay in one plane, and the discharge occurs on the top of the barrier. Chemical changes in the surface were also evaluated as a function of plasma parameters without any pre-treatment of the substrates. For both studied materials, similar trends were observed at fast treatment times (<60s of plasma exposure). The plasma treatment resulted in a decrease of water contact angle from the initial 90° for ITO to 10° after 30 seconds of exposure. For FTO, the initial angle 60° was lowered to 10° after just 5 seconds of exposure, and complete hydrophilicity was obtained after 30 seconds of plasma treatment. An interesting trend in oxygen concentration measured by XPS was observed for ITO but not FTO samples. From a physical point of view, the interaction with the conductive sample affects the orientation of filaments during the surface modification. Additionally, the results suggest that for small working distances, the physical regime can vary from coplanar to volume discharge as shown in Figure 1. All changes were observed with ICCD imaging (Pi-Max 4, Princeton Instruments). Regarding the physical changes over the surface, the plasma treatment resulted in decreased roughness with no significant effect on conductivity.In conclusion, the results obtained in this study can be utilized in the manufacturing process of microelectronic devices and provide a deeper insight into how the treatment process influences discharge parameters.[1] Armstrong et al. https://doi.org/10.1016/j.tsf.2003.08.067[2] Šimor et al. https://doi.org/10.1063/1.1513185[3] Donley et al. https://doi.org/10.1021/la011101t[3] Chaney et al. https://doi.org/10.1016/S0169-4332(03)00617-2 Figure 1

A transfer learning approach to identify Plasmodium in microscopic images.

Plasmodium parasites cause Malaria disease, which remains a significant threat to global health, affecting 200 million people and causing 400,000 deaths yearly. Plasmodium falciparum and Plasmodium vivax remain the two main malaria species affecting humans. Identifying the malaria disease in blood smears requires years of expertise, even for highly trained specialists. Literature studies have been coping with the automatic identification and classification of malaria. However, several points must be addressed and investigated so these automatic methods can be used clinically in a Computer-aided Diagnosis (CAD) scenario. In this work, we assess the transfer learning approach by using well-known pre-trained deep learning architectures. We considered a database with 6222 Region of Interest (ROI), of which 6002 are from the Broad Bioimage Benchmark Collection (BBBC), and 220 were acquired locally by us at Fundação Oswaldo Cruz (FIOCRUZ) in Porto Velho Velho, Rondônia-Brazil, which is part of the legal Amazon. We exhaustively cross-validated the dataset using 100 distinct partitions with 80% train and 20% test for each considering circular ROIs (rough segmentation). Our experimental results show that DenseNet201 has a potential to identify Plasmodium parasites in ROIs (infected or uninfected) of microscopic images, achieving 99.41% AUC with a fast processing time. We further validated our results, showing that DenseNet201 was significantly better (99% confidence interval) than the other networks considered in the experiment. Our results support claiming that transfer learning with texture features potentially differentiates subjects with malaria, spotting those with Plasmodium even in Leukocytes images, which is a challenge. In Future work, we intend scale our approach by adding more data and developing a friendly user interface for CAD use. We aim at aiding the worldwide population and our local natives living nearby the legal Amazon's rivers.

Validation of a focus reduction neutralization test (FRNT) to rapidly titrate human SARS-CoV-2 neutralizing antibodies by using the CTL Immunospot S6 universal analyzer

In this paper we describe the validation of a focus reduction neutralization test (FRNT) to quantitate human SARS-CoV-2 neutralizing antibodies by using the CTL Immunospot S6 Universal Analyzer. We employed a previously published protocol and compared its performances to a well-established and traditional serum-neutralization assay (SN). To assess diagnostic sensitivity, a total number of 201 human sera positive by SN for SARS-CoV-2 NAbs were processed: 196/201 tested positive by FRNT50 (97.51 %). A diagnostic specificity of 100 % was obtained by evaluating 206 negative serum samples. Repeatability of the test was evaluated by determining the intra and inter-assay coefficient of variation (CV). A standard deviation of 0.83 and a CV of 13 % were evidenced demonstrating an acceptable reproducibility of the assay. Moreover, a Cohen's Kappa of 0.975 was obtained proving an extremely high level of agreement between the FRNT protocol and the SN. Despite an acceptable correlation between methods (p < 0.05), FRNT demonstrated a statistically significant increase in NAbs titres compared to SN as well as higher data variability and asymmetry. These discrepancies could be attributed to FRNT sensitivity or most probably to the subjective interpretation of SN, although this aspect needs to be further investigated with a more representative number of samples.Basing on our results, it is reasonable to replace the SN with the FRNT assay as, with this, fast processing time (less than 2 days) and operator bias-free results registrations are guaranteed.

AttGAN: attention gated generative adversarial network for spatio-temporal super-resolution of ocean phenomena

ABSTRACT This study proposes an innovative deep learning-aided approach based on generative adversarial networks named AttGAN, which is specialized for solving the spatio-temporal super-resolution problem of ocean datasets with complex waveforms and turbulent features. The proposed method can efficiently restore the desired fine high-frequency details while maintaining high efficiency. The key idea of the proposed approach is to incorporate an attention gate in the generator, which allows for emphasizing salient features for super-resolution tasks. In addition, residual convolutional blocks are used in the generator and discriminator to extract features. By establishing regression loss, physical constraints, and adversarial loss into a comprehensive loss function, a generator that exhibits high fidelity and strong generalization capabilities is trained. The proposed AttGAN is evaluated by experiments conducted on two datasets, and the experimental results validate its superiority over state-of-the-art physical constraint models in both qualitative and quantitative metrics. Moreover, the AttGAN has faster processing times than the corresponding ocean numerical models and better quality of results. Impact statement

Enhancing Cloud Data Deduplication with Dynamic Chunking and Public Blockchain

The majority of cloud service providers (CSPs) store and remove customer data according to certain principles. The majority of them have designed their cloud platform to have very high levels of consistency, speed, availability, and durability. Their systems are built with these performance characteristics in mind, and the requirement to ensure precise and rapid data deletion must be carefully balanced. In the public blockchain, this paper suggests employing the rapid content-defined Chunking algorithm for data duplication. Acute data is frequently outsourced by individuals and organizations to distant cloud servers since doing so greatly reduces the headache of maintaining infrastructure and software. However, because user data is transmitted to cloud storage providers and stored on a remote cloud, ownership and control rights are nonetheless separated. Users thus have significant challenges when attempting to confirm the integrity of private information. According to the experiment results, the suggested dynamic chunking has a fast processing time that is on par with fixed-length chunking and significantly improves deduplication processing capability.

A degranulation assay using Vγ9Vδ2 T cells for the rapid diagnosis of familial hemophagocytic syndromes.

Hemophagocytic lymphohistiocytosis (HLH) is a life-threatening immune disorder characterized by uncontrolled lymphocyte and macrophage activation and a subsequent cytokine storm. The timely initiation of immunosuppressive treatment is crucial for survival. Here, we harnessed Vγ9Vδ2 T cell degranulation to develop a novel functional assay for the diagnosis of HLH. We compared the novel assay with the conventional natural killer (NK) cell stimulation method in terms of efficiency, specificity, and reliability. Our analysis involved 213 samples from 182 individuals, including 23 samples from 12 patients with degranulation deficiency (10 individuals with UNC13D deficiency, 1 with STXBP2 deficiency, and 1 with RAB27A deficiency). While both tests exhibited 100% sensitivity, the Vγ9Vδ2 T cell degranulation assay showed a superior specificity of 86.2% (n=70) compared to the NK cell degranulation assay, which achieved 78.9% specificity (n=213). The Vγ9Vδ2 T cell degranulation assay offered simpler technical requirements and reduced labor intensity, leading to decreased susceptibility to errors with faster processing times. This efficiency stemmed from the sole requirement of dissolving (E)-4-hydroxy-3-methyl-but-2-enyl pyrophosphate (HMBPP) powder, contrasting with the intricate maintenance of K562 cells necessary for the NK cell degranulation assay. With its diminished susceptibility to errors, we anticipate that the assay will require fewer repetitions of analysis, rendering it particularly well-suited for testing infants. The Vγ9Vδ2 T cell degranulation assay is a user-friendly, efficient diagnostic tool for HLH. It offers greater specificity, reliability, and practicality than established methods. We believe that our present findings will facilitate the prompt, accurate diagnosis of HLH and thus enable rapid treatment and better patient outcomes.

Optimizing HAR Systems: Comparative Analysis of Enhanced SVM and k-NN Classifiers

This research addresses the accuracy issues in IoT-based human activity recognition (HAR) applications, essential for health monitoring, elderly care, gait analysis, security, and Industry 5.0. This study uses 12 machine learning approaches, split equally between support vector machine (SVM) and k-nearest neighbor (k-NN) models. Data from 102 individuals, aged 18–43, were used to train and test these models. The researchers aimed to detect twelve daily activities, such as sitting, walking, and cycling. Results showed k-NN models achieved slightly higher accuracy (97.08%) compared to SVM models (95.88%), though SVM had faster processing times. The improved machine learning approaches proved effective in accurately classifying daily activities, with k-NN models outperforming SVM models marginally. The paper provides significant contributions to the field of HAR by enhancing the performance of SVM and k-NN classifiers, optimizing them for higher accuracy and faster processing. Through robust testing with samples of real-world data, the study provides a detailed comparative analysis that highlights strengths and weaknesses of each classifier model, specifically within IoT-based systems. This work not only advances the theoretical understanding and practical applications of HAR systems in areas, such as healthcare and industrial automation, but also sets the stage for future research that could explore hybrid models or further enhancements, consequently improving the efficiency and functionality of IoT devices based on activity recognition.

VSNP: a SNP pipeline for the generation of transparent SNP matrices and phylogenetic trees from whole genome sequencing data sets

BackgroundSeveral single nucleotide polymorphism (SNP) pipelines exist, each offering its own advantages. Among them and described here is vSNP that has been developed over the past decade and is specifically tailored to meet the needs of diagnostic laboratories. Laboratories that aim to provide rapid whole genome sequencing results during outbreak investigations face unique challenges. vSNP addresses these challenges by enabling users to verify and validate sequence accuracy with ease- having utility across various pathogens, being fully auditable, and presenting results that are easy to interpret and can be comprehended by individuals with diverse backgrounds.ResultsvSNP has proven effective for real-time phylogenetic analysis of disease outbreaks and eradication efforts, including bovine tuberculosis, brucellosis, virulent Newcastle disease, SARS-CoV-2, African swine fever, and highly pathogenic avian influenza. The pipeline produces easy-to-read SNP matrices, sorted for convenience, as well as corresponding phylogenetic trees, making the output easily understandable. Essential data for verifying SNPs is included in the output, and the process has been divided into two steps for ease of use and faster processing times. vSNP requires minimal computational resources to run and can be run in a wide range of environments. Several utilities have been developed to make analysis more accessible for subject matter experts who may not have computational expertise.ConclusionThe vSNP pipeline integrates seamlessly into a diagnostic workflow and meets the criteria for quality control accreditation programs, such as 17025 by the International Organization for Standardization. Its versatility and robustness make it suitable for use with a diverse range of organisms, providing detailed, reproducible, and transparent results, making it a valuable tool in various applications, including phylogenetic analysis performed in real time.

Upscaling relative permeability and capillary pressure from digital core analysis in Otway formation: Considering the order and size effects of facies

Digital Core Analysis (DCA) has emerged as a crucial instrument in reservoir characterization in recent times. With the advent of high-resolution micro-CT imaging, it is now possible to visualize the three-dimensional microstructures of in-situ pores and flow patterns within rocks. DCA offers several notable benefits over traditional techniques, such as a higher density of measurements, faster processing times, and the preservation of rock samples. It also demonstrates considerable flexibility with challenging core conditions and can derive numerous parameters from each individual sample. The objective of this work is to utilise DCA data from Otway formation to enhance reservoir characterisation and CO2 plume forecast. However, a critical challenge is that these data are obtained at a micro-scale, necessitating an upscaling of DCA properties from the micro-scale to core scale, and subsequently to the site and field scale, for compatibility with reservoir simulation and field studies. This study proposes an implicit and iterative method to upscale DCA properties and explore the impact of facies order and size on the upscaling process of relative permeability and capillary pressure. This method is implemented in an open-source simulator known as the Matlab Reservoir Simulation Toolbox (MRST). The findings indicate that relative permeability and capillary pressure outcomes from upscaling are influenced by order and portion of facies. This highlights the importance of considering both the size and arrangement of facies during the upscaling process, given their potential impact on fluid dynamics and the accuracy of reservoir simulation results.

Enhancing Subsurface Phytoplankton Layer Detection in LiDAR Data through Supervised Machine Learning Techniques

Phytoplankton are the foundation of marine ecosystems and play a crucial role in determining the optical properties of seawater, which are critical for remote sensing applications. However, passive remote sensing techniques are limited to obtaining data from the near surface, and cannot provide information on the vertical distribution of the subsurface phytoplankton. In contrast, active LiDAR technology can provide detailed profiles of the subsurface phytoplankton layer (SPL). Nevertheless, the large amount of data generated by LiDAR brought a challenge, as traditional methods for SPL detection often require manual inspection. In this study, we investigated the application of supervised machine learning algorithms for the automatic recognition of SPL, with the aim of reducing the workload of manual detection. We evaluated five machine learning models—support vector machine (SVM), linear discriminant analysis (LDA), a neural network, decision trees, and RUSBoost—and measured their performance using metrics such as precision, recall, and F3 score. The study results suggest that RUSBoost outperforms the other algorithms, consistently achieving the highest F3 score in most of the test cases, with the neural network coming in second. To improve accuracy, RUSBoost is preferred, while the neural network is more advantageous due to its faster processing time. Additionally, we explored the spatial patterns and diurnal fluctuations of SPL captured by LiDAR. This study revealed a more pronounced presence of SPL at night during this experiment, thereby demonstrating the efficacy of LiDAR technology in the monitoring of the daily dynamics of subsurface phytoplankton layers.

BSEO-Semiautomatic Method for Determination of Oil Recovery with Nanofluids in Microfluidic Devices.

Microfluidic models have become essential instruments for studying enhanced oil recovery techniques through fluid and chemical injection into micromodels to observe interactions with pore structures and resident fluids. The widespread use of cost-effective lab-on-a-chip devices, known for efficient data extraction and minimal reagent usage, has driven demand for efficient data management methods crucial for high-performance data and image analyses. This article introduces a semiautomatic method for calculating oil recovery in polymeric nanofluid flooding experiments based on the background subtraction (BSEO). It employs the background subtraction technique, generating a foreground binary mask to detect injected fluids represented as pixel areas. The pixel difference is then compared to a threshold value to determine whether the given pixel is foreground or background. Moreover, the proposed method compares its performance with two other representative methods: the ground truth (manual segmentation) and Fiji-ImageJ software. The experiments yielded promising results. Low values of mean-squared error (MSE), mean absolute error (MAE), and root-mean-squared error (RMSE) indicate minimal prediction errors, while a substantial coefficient of determination (R2) of 98% highlights the strong correlation between the method's predictions and the observed outcomes. In conclusion, the presented method emphasizes the viability of BSEO as a robust alternative, offering the advantages of reduced computational resource usage and faster processing times.