Extraction Method Research Articles

Extraction of high‐quality Antarctic krill (Euphausia Superba) oil using low‐temperature continuous phase‐transition extraction equipment

AbstractThe aim of this study was to explore a processing method for efficient extraction of high‐quality krill oil (KO) using a low‐temperature continuous phase‐transition extraction equipment (LCPE). The efficiency of lipid extraction and quality of KO and defatted krill meal (DKM) by LCPE were compared with those of supercritical CO2 and n‐hexane extraction. Results showed that compared to other methods, extraction using LCPE had the highest lipid yield (21.72 ± 0.34%), bioactive substances, and dimethyl sulfide (3.12 ± 0.09 mg/kg), the lowest oxidative deterioration. Moreover, compared to other methods, DKM extracted by LCPE had the lowest fat (<2%), the highest protein (>60%), and the best oxidative stability. These benefits would ensure easier transportation and better long‐term storage, allowing for its application on distant‐ocean fishing vessels. Therefore, LCPE is a method that allows for efficient extraction of high‐quality KO.

Phytosterols in Plant-Derived Foods: Recent Updates in Extraction and Analysis Methods

Phytosterols in Plant-Derived Foods: Recent Updates in Extraction and Analysis Methods

A Modified Control Strategy for Three-Phase Four-Switch Active Power Filters Based on Fundamental Positive Sequence Extraction

Three-phase four-switch active power filters (APFs) have attracted attention due to their low amount of semiconductors and low cost. The traditional control strategy of three-phase four-switch APFs usually includes phase-locked loops (PLLs) and rotating coordinate transformation for harmonic detection, resulting in complicated calculations and increased computation. In this paper, a modified control strategy for three-phase four-switch APFs based on fundamental positive sequence extraction is proposed, eliminating PLLs and rotating coordinate transformation with trigonometric calculations. Harmonic extraction is based on the fundamental positive sequence extraction method, while non-locked phase loop coordinate transformation is proposed to eliminate trigonometric calculations. Quasi-PR control is adopted for current tracking, and DC voltage control is designed to suppress voltage imbalance between the two split capacitors on the DC side. The space vector pulse width modulation (SVPWM) method is modified for a reduced-switch APF topology. The proposed control strategy guarantees excellent harmonic compensation: harmonic currents are significantly suppressed when the APFs are working, the THD of the source current decreases to 3.86%, the bus voltage fluctuation on the DC side is small, the voltage remains stable, and the computational complexity is reduced. Finally, a simulation and an experimental hardware platform are established to validate the feasibility and performance of the proposed control strategy. The experimental results show that it has good performance in suppressing harmonics and improving power quality.

A Spectral–Spatial Approach for the Classification of Tree Cover Density in Mediterranean Biomes Using Sentinel-2 Imagery

Tree canopy cover is an important forest inventory parameter and a critical component for the in-depth mapping of forest fuels. This research examines the potential of employing single-date Sentinel-2 multispectral imagery, combined with contextual spatial information, to classify areas based on their tree cover density using Random Forest classifiers. Three spatial information extraction methods are investigated for their capacity to acutely detect canopy cover: two based on Gray-Level Co-Occurrence Matrix (GLCM) features and one based on segment statistics. The research was carried out in three different biomes in Greece, in a total study area of 23,644 km2. Three tree cover classes were considered, namely, non-forest (cover < 15%), open forest (cover = 15%–70%), and closed forest (cover ≥ 70%), based on the requirements set for fuel mapping in Europe. Results indicate that the best approach identified delivers F1-scores ranging 70%–75% for all study areas, significantly improving results over the other alternatives. Overall, the synergistic use of spectral and spatial features derived from Sentinel-2 images highlights a promising approach for the generation of tree cover density information layers in Mediterranean regions, enabling the creation of additional information in support of the detailed mapping of forest fuels.

Fault Diagnosis of Aircraft Hydraulic Pipeline Clamps Based on Improved KPCA and WOA–KELM

Due to the complexity and diversity of aviation hydraulic pipeline systems, there has been a lack of qualitative formulas or characteristic indicators to describe clamp failures within these systems. In this paper, based on the data-driven idea, an improved KPCA-based feature extraction method is proposed and combined with the optimized KELM for fault diagnosis and condition monitoring of aviation hydraulic line clamps. Firstly, the kernel parameters of KPCA are combined using polynomial and Gaussian kernels based on their proportional weights. Secondly, a GA–PSO (Genetic Algorithm–Particle Swarm Optimization) hybrid algorithm is employed to optimize the kernel parameters, selecting 13 time-domain and 4 frequency-domain feature indicators to form the initial feature dataset, which is then subjected to dimensionality reduction using the improved KPCA. Finally, diagnosis is conducted using a KELM optimized by the whale optimization algorithm. The results indicate that, across multiple diagnostic trials, the average diagnostic accuracy can reach 99.99%, providing a feasible approach for the precise diagnosis of clamp faults in aviation hydraulic pipeline systems.

Investigation on β-D-glucan extraction methods from Pleurotus ostreatus mycelium and its capability to adsorb aflatoxin M1 in milk

Investigation on β-D-glucan extraction methods from Pleurotus ostreatus mycelium and its capability to adsorb aflatoxin M1 in milk

Rotor angle stability of a microgrid generator through polynomial approximation based on RFID data collection and deep learning.

The article proposes a novel approach to assess rotor angle stability in microgrids by enhancing the Modified Galerkin Method (MGM), which is based on the Polynomial Approximation, using real-time RFID data acquisition. Due to their reliance on assumptions, traditional rotor angle stability methodologies frequently fail in online transient stability testing. MGM successfully captures the dynamic behavior of microgrids by approximating state variables using a sequence of polynomials and coefficients. Redundant data, like as vibrations or noise signals, can cause delays in defect diagnosis and decrease diagnostic accuracy. This problem is addressed by integrating RFID technology. RFID technology could potentially be used with a hybrid CNN-LSTM model to develop a sophisticated fault diagnostic system. This entails identifying fault characteristics through the use of signal processing techniques and feature extraction methods, such as the Fourier transform and time-domain statistical features. In addition, we use Total Harmonic Distortion (THD) to reduce superfluous data. The suggested techniques significantly increase fault detection efficiency and precision, outperforming existing techniques with a 0.94 classification accuracy. An extensive case study on an IEEE 3-machine 9-bus system is used to illustrate its efficacy, showing observable improvements in fault detection speed and accuracy that make microgrid operations safer and more dependable.

Antioxidant activities of aqueous and 70% ethanol extracts of akar kuning (Arcangelisia flava (L.) Merr) stem using the DPPH method

Background: Numerous herbs can be used as natural exogenous antioxidants and clinically proven effective as antioxidants. Objective: The primary objective of this study is to assess the antioxidant activity of the stems of akar kuning (Arcangelisia flava (L.) Merr). Method: This plant was extracted with aqueous solution using the decoction method and 70 % ethanol using the maceration method. Antioxidant activity was evaluated using the TLC-Bioautography sprayed with DPPH reagent for the qualitative method and microplate assay with DPPH for the quantitative method. This research also identified the total phenol from each extract which was measured using the Folin-Ciocalteu method. Result: Based on phytochemical screening, each extract contained flavonoids, polyphenols, anthraquinones, terpenoids, and saponins. TLC-bioautography showed flavonoids, polyphenols, and anthraquinones were responsible for antioxidant activity. Quantification of antioxidant activity results of aqueous and 70% ethanol extracts of akar kuning (Arcangelisia flava (L.) Merr) showed IC50 value at 78.8 ± 1.2 µg/mL and 142.8± 2.9 µg/mL respectively. The content of total phenolic compounds was 80.544 ± 2.6 mg GAE/ g and 52.522 ± 1.9 mg GAE/g. Conclusion: As observed in the study, Arcangelisia flava (L.) Merr extracts from both extraction methods possess an antioxidant.

DEVELOPMENT AND OPTIMIZATION OF HPLC METHODS FOR THE CHIRAL SEPARATION OF ARYLPYRAZOLE, CHLOROACETANILIDE AND ORGANOCHLORINE PESTICIDES: CASE STUDIES OF BENZOBICYCLON, ACETOCHLOR AND CHLORDANE.

This work is centered on the development and optimization of High-Performance Liquid Chromatographic methods for the separation of chiral pesticides, particularly benzobicyclon, chlordane and acetochlor employing Agilent Technologies Infinity II chiral HPLC system equipped with a UV – 2000 detector. The stereoisomers were successively separated using a standard analytical column of dimensions 250 mm X 4.6 mm. The Cis– stereoisomers of chlordane exhibited partial baseline separation while the Trans – enantiomers were fully separated. Benzobicyclon and acetochlor enantiomers attained full baseline separation under optimized conditions. Chlordane and benzobicyclon were analyzed using normal phase chromatography [NP]c with a mobile phase of 90% Normal hexane and 10% Isopropanol, while acetochlor was analyzed by reverse phase chromatography [RP] c using 70% methanol and 30% water. Benzobicyclon was later spiked into soil sample and subsequently extracted using Environmental Protection Agency (EPA) methods and the extracts were further analyzed with a shorter analytical column of dimensions 75 mm X 4.6 mm. The HPLC separation revealed that the longer column provided more efficient separation for the benzobicyclon stereoisomers than the shorter column as reflected by high separation factors (?). The high recovery rate of the stereoisomers of benzobicyclon and the internal standard from the soil extracts confirmed the effectiveness of the method of extraction and the HPLC system employed.

A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning

Epilepsy is a chronic neurological disorder that poses significant challenges to patients and their families. Effective detection and prediction of epilepsy can facilitate patient recovery, reduce family burden, and streamline healthcare processes. Therefore, it is essential to propose a deep learning method for efficient detection and prediction of epileptic electroencephalography (EEG) signals. This paper reviews several key aspects of epileptic EEG signal processing, focusing on epilepsy detection and prediction. It covers publicly available epileptic EEG datasets, preprocessing techniques, feature extraction methods, and deep learning-based networks used in these tasks. The literature is categorized based on patient independence, distinguishing between patient-independent and non-patient-independent studies. Additionally, the evaluation methods are classified into general classification indicators and specific epilepsy prediction criteria, with findings organized according to the prediction cycles reported in various studies. The review reveals several important insights. Despite the availability of public datasets, they often lack diversity in epilepsy types and are collected under controlled conditions that may not reflect real-world scenarios. As a result, signal preprocessing methods tend to be limited and may not fully represent practical conditions. Feature extraction and network designs frequently emphasize fusion mechanisms, with recent advances in Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) showing promising results, suggesting that new network models warrant further exploration. Studies using patient-independent data generally produce better results than those relying on non-patient-independent data. Metrics based on general classification methods typically perform better than those using specific epilepsy prediction criteria, though future research should focus on the latter for more accurate evaluation. Epilepsy prediction cycles are typically kept under 1 h, with most studies concentrating on intervals of 30 min or less.

Analysis and Characterization of Pericopsis mooniana Seed Oil for Potential Applications in Cosmetics and Nutritional Supplements

Pericopsis mooniana is renowned for wood applications, while its bark and leaves find uses in ayurvedic medicine. The shifting of global cosmetic and nutritional supplement industries towards plant-based oils has led to explore novel sources. No prior studies were done on P. mooniana seed oil. Therefore this study aims to characterize the seed oil of P. mooniana by determining Fatty Acids (FA) composition as their methyl esters, nonpolar constituents in unsaponifiable matter, and other physio-chemcial properties. The oil was extracted using the soxhlet extraction method. Ash and moisture contents of seeds, Acid Value (AV), Iodine Value (IV), smoke point and thermal stability of oil were also determined. Prepared fatty acid methyl esters and chemical constituents in unsaponifiable matter were identified and quantified using Gas Chromatography-Mass Spectrometry method. Results indicated a substantial oil yield of 36.71± 0.01% with moisture content of 5.60 ± 0.19%, ash content of 3.65 ± 0.38%, AV of 2.97 ± 0.40 mg KOH/g, IV of 16.02 ± 0.14 g I2/100g, smoke point of 233.6 ± 8.57°C, decomposition temperature of 409.95 ± 1.74°C and yield of unsaponifiable matter of 1.35 ± 0.01%. The dominant FAs are oleic (41.02%) and linoleic (38.12%) acids. Major unsaponifiable matter constituents are squalene (4.01 mg/g), beta.-sitosterol (2.63 mg/g), stigmasterol (1.23 mg/g), phytol (1.45 mg/g), geranylgeraniol (1.03 mg/g) and amyrin (0.95 mg/g). Based on the finding of this study, it can be concluded that P. mooniana seed oil has the potential to be utilized in both cosmetic and nutritional supplement industries.

MaskDGNets: Masked-attention guided dynamic graph aggregation network for event extraction.

Considering that the traditional deep learning event extraction method ignores the correlation between word features and sequence information, it cannot fully explore the hidden associations between events and events and between events and primary attributes. To solve these problems, we developed a new framework for event extraction called the masked attention-guided dynamic graph aggregation network. On the one hand, to obtain effective word representation and sequence representation, an interaction and complementary relationship are established between word vectors and character vectors. At the same time, a squeeze layer is introduced in the bidirectional independent recurrent unit to model the sentence sequence from both positive and negative directions while retaining the local spatial details to the maximum extent and establishing practical long-term dependencies and rich global context representations. On the other hand, the designed masked attention mechanism can effectively balance the word vector features and sequence semantics and refine these features. The designed dynamic graph aggregation module establishes effective connections between events and events, and between events and essential attributes, strengthens the interactivity and association between them, and realizes feature transfer and aggregation on graph nodes in the neighborhood through dynamic strategies to improve the performance of event extraction. We designed a reconstructed weighted loss function to supervise and adjust each module individually to ensure the optimal feature representation. Finally, the proposed MaskDGNets framework is evaluated on two baseline datasets, DuEE and CCKS2020. It demonstrates its robustness and event extraction performance, with F1 of 81.443% and 87.382%, respectively.

Multi-class cyanobacterial toxin analysis using hydrophilic interaction liquid chromatography-mass spectrometry.

Cyanobacteria produce diverse classes of toxins including microcystins, nodularins, anatoxins, cylindrospermopsins and saxitoxins, encompassing a range of chemical properties and mechanisms of toxicity. Comprehensive analysis of these toxins in cyanobacterial, environmental and biological samples generally requires multiple methods of extraction and analysis. In this work, a method was developed for the major classes of cyanotoxins, which comprised of a three-step liquid-solid extraction method using 75 % CH3CN with 0.1 % HCOOH and a hydrophilic interaction liquid chromatography (HILIC) elution gradient that provided retention of the less polar microcystins through to the highly polar saxitoxins. Detection was performed by tandem mass spectrometry in selected reaction monitoring mode with positive and negative polarity switching. Identification criteria included matching retention times and product ion ratios with available standards. In-house validation demonstrated good performance of the method including precision ranging from 1.5 (microcystin-LA) to 5.8 (gonyautoxin-2) % RSDs, and detection limits ranging from 0.01 (cylindrospermopsin) to 0.99 (gonyautoxin-3) µg/g in freeze dried material cyanobacteria. Recovery was assessed using spiked non-toxic cyanobacterial samples (Aphanizomenon sp.) and ranged from 83 (neosaxitoxin) to 107 % ([Dha7]microcystin-LR). As a demonstration of application, toxin profiles in cyanobacterial cultures, benthic and planktonic cyanobacteria field samples, and shellfish reference materials were successfully evaluated. The procedure is also amenable for extension to other polar toxin classes including domoic acid and guanitoxin. With increasing reports of cyanobacterial blooms globally, the method represents a powerful quantitative screening tool for measuring cyanotoxins across a broad range of samples.

Do you love traveling to the beach or mountain? Predicting personality traits and choice behaviour

ABSTRACT Several personality-predicting tools are being used by managers in their strategic decision-making process. The most common are the Big Five model and the Myers – Myers-Briggs Type Indicator model, respectively. This study deviates and tests a novel personality prediction model. Specifically, it utilizes the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm as a feature extraction method to map personality traits based on consumers’ textual data from the Kaggle MBTI Personality Type dataset. This study uses realistic data gathered from traveller reviews and comments on hotel stays from TripAdvisor’s widely recognised platform to predict different personality traits and their travel destination preferences, i.e. beach or mountain. The contribution of this study lies in the identification of multiple dimensions of peoples’ personality traits and their relationship with their preferences for travel locations. This proposed trait classification mechanism can assist marketing managers in effectively carrying out customer segmentation, setting realistic goals, and optimizing marketing strategies.

An improved DNA extraction method in okra for rapid PCR detection of Okra enation leaf curl virus from diverse Indian regions.

The extraction of DNA from okra (Abelmoschus esculentus) is challenging due to its high mucilage and polysaccharide content, which can hinder both the yield and quality of DNA.In this study, an improved DNA isolation method is described incorporating a key modification being the use of solution I (1 M NaCl and 2% Sarcosyl) as a pre-treatment before applying the CTAB buffer, resulting in high-purity genomic DNA in just 1h and 45min., making it suitable for handling large sample sizes due to its rapid processing capabilities. This enhanced DNA extraction method was crucial for the accurate and rapid molecular detection of Okra enation leaf curl virus (OELCuV), a monopartitebegomovirus that has spread across various regions of India. Transmitted by the whitefly (Bemisia tabaci), OELCuV causes leaf curling, enations, and stunted growth in okra, leading to significant yield losses. The surveys conducted during the 2020-21 and 2021-22 sowing seasons revealed disease incidence ranging from 14.03 to 67.57%. The extracted DNA via the improved DNA extraction method enhanced the speed of PCR based molecular identification of OELCuV, using virus-specific coat protein primers. The amplified CP genes were cloned and sequenced to study the CP gene based diversity among OELCuV isolates from different states of India. The CP gene nucleotide identity among the studied OELCuV isolates ranged from 95.57 to 99.27%, while comparison with previously reported Indian OELCuV CP sequences, the nucleotide identity ranged from 89.35 to 98.83%.The successful application of this optimized DNA extraction method sped up the detection process but also holds promise for broader use in the molecular study of okra and other mucilaginous crops, particularly in the rapid and reliable identification ofbegomoviruses. The optimized DNA extraction method significantly accelerated the detection of OELCuV, demonstrating its efficiency and reliability. This method shows strong potential for broader applications in the molecular study of okra and other mucilaginous crops, making it a valuable tool for future research and disease management.

Analyzing the Impacts of Inter-Provincial Trade on the Quantitative and Spatial Characteristics of Six Embodied Air Pollutants in China Through Multi-Scenario Simulation

Inter-provincial trade is accompanied by the transfer of embodied pollution emissions, leading to emissions leakage, thereby hindering the sustainable development of society. Therefore, it is imperative to analyze the characteristics of embodied pollutant emission and spatial transfer driven by inter-provincial trade. In this study, the quantitative and spatial characteristics of the six main embodied pollutants (i.e., SO2, NOX, CO, VOC, PM2.5, and PM10) were analyzed by a hypothetical extraction method (HEM) and complex network analysis (CNA) under an input–output analysis (IOA) framework. Then, the row arrange series (RAS) method was employed to simulate the impacts of varying levels of trade intensity, economic growth rate, and technological progress on embodied pollutants and spatial-transfer characteristics. The major findings are as follows: (i) the increase in inter-provincial trade led to a corresponding rise in embodied pollutant emissions due to the relocation of production activities towards provinces with higher emission intensity. Excessive responsibility was assumed by provinces such as Shanxi and Hebei, engaging in production outsourcing for reducing pollutants. (ii) The macro direction of pollutant transfer paths was from the resource-rich northern and central provinces towards the trade-developed southern provinces. Sectors in the transfer path, such as the industry sectors of Shanxi, Guangdong, Henan, and the transport sector of Henan, exhibited high centrality and dominated pollutant transfer activities in the network. (iii) The industry sector, characterized by substantial energy consumption, was the predominant emitter of all pollutant production-based emissions, accounting for more than 40% of total emissions. This study is conducive to analyzing the impacts of inter-provincial trade on embodied pollutant emissions and developing emissions reduction policies considering equitable allocation of emissions responsibilities from both production and consumption perspectives.

Hydrogen-as-a-probe applied to investigate the influence of extraction and preparation methods on TDS spectra of 13CrMo4-5 samples

AbstractThermal desorption spectroscopy (TDS) provides rich information on the desorbed hydrogen flow rate activated at different heat energy levels, supporting high-resolution assessment of small-scale features that are preferential trapping sites. TDS spectra are also highly sensitive to hydrogen uptake from the sample’s extraction and preparation methods, whose influence requires further evaluation. In this research, hydrogen-as-a-probe is applied to evaluate the influence of extraction, surface grinding, dwelling time, plate thickness, and sample thickness on TDS spectra of 13CrMo4-5 steel. Validation of TDS results confirms that all hydrogen present in the sample before the TDS measurement, including metallurgical hydrogen and hydrogen uptake from the studied methods, is desorbed during the first heating cycle. Results indicate that peaks 1 and 3 are negligibly influenced by the studied methods. Peak 2 and total hydrogen concentration are significantly influenced by sample extraction and surface grinding methods, which provide the main outcomes of this work. Methods based on severe solid-state distortion, like machine cutting and grit P320, present an increased total hydrogen content of 99% and 142%, respectively. Dwelling time and plate thickness have small influence on hydrogen content. Reducing the sample thickness results in less total hydrogen concentration at a rate of 5.7 at.ppm/mm.

Development and Application of Mucilage and Bioactive Compounds from Cactaceae to Formulate Novel and Sustainable Edible Films and Coatings to Preserve Fruits and Vegetables—A Review

The accelerated ripening and senescence of fruits and vegetables is characterized by various biochemical changes that hinder the maintenance of their postharvest quality. In this context, developing edible films and coatings formulated with natural and biodegradable materials emerges as a sustainable strategy for preserving the quality parameters of these products in replacement of conventional petroleum-based packaging. Recently, plant-based polymers, including mucilage from different cactus species and/or their bioactive compounds, have been investigated to develop edible films and coatings. As the available literature indicates, the Opuntia genus stands out as the most used for mucilage extraction, with the cladode being the most exploited part of the plant. Conventional extraction methods are widely employed to obtain mucilages, which are applied to fruits and vegetables after being combined with plasticizing and cross-linking agents. In general, these films and coatings have proven effective in prolonging the shelf life and maintaining the nutritional, physical, and sensory quality of fruits and vegetables. Given their preservation potential, combining cactus mucilages with bioactive compounds, probiotics, and prebiotics represents an emerging trend in developing functional films and coatings. However, some limitations have been identified, such as the underutilization of different species and parts of the plant, the lack of standardization in extraction methods, and the absence of studies on the effects of the physicochemical properties of mucilages in the formulation and characteristics of films and coatings. Therefore, overcoming these limitations is essential for developing edible films and coatings with enhanced techno-functional properties and greater commercial viability.

Energy Consumption and Fume Analysis: A Comparative Analysis of the Blasting Technique and Mechanical Excavation in a Polish Gypsum Open-Pit Mine

This article presents a comparative assessment of energy consumption and fume emissions such as NOx, CO2, and CO associated with the excavation of a specified gypsum volume using two mining methods (blasting and mechanical extraction). The analysis was carried out based on a case study gypsum open-pit mine in Poland where both extraction methods are applied. The findings indicate that, for the same output volume, blasting operations require significantly less energy (ranging from 1298.12 MJ to 1462.22 MJ) compared to mechanical excavation (86,654.15 MJ). Furthermore, a substantial portion of the energy in blasting operations is attributed to explosive loading and drilling (970.95 MJ). Conversely, mechanical mining results in higher fume emissions compared to blasting. However, during mechanical extraction, the fumes are dispersed over a prolonged period of 275 h, whereas blasting achieves the same gypsum volume extraction in approximately 7.5 h. The prediction model suggests that, based on the obtained data, overall gypsum extraction will decline unless new operational levels are developed or the mine is expanded. This reduction in gypsum extraction will be accompanied by a corresponding decrease in energy consumption and emission of fumes.

Clustering-based topic modeling for biomedical documents extractive text summarization

AbstractThe increasing volume of electronic text, especially in the biomedical domain, requires automatic text summarization (ATS) to help researchers navigate and find relevant information. This study proposes an unsupervised extractive ATS method to improve the quality of biomedical document summaries by focusing on subtopic diversity. The method integrates topic modeling and clustering with bidirectional encoder representation from transformers (BERT). To evaluate the effectiveness of the proposed study, it tested on a new corpus of 200 biomedical research papers from Biomed Central. The results were evaluated using the ROUGE metric and qualitative evaluation by medical experts. The ROUGE metric yielded scores of 0.4838 (Rouge-1), 0.2174 (Rouge-2), and 0.2206 (Rouge-L), while the qualitative evaluation achieved an average score of 4.10, 4.06, 3.55, 4.0, and 4.0 for completeness, relevance, conciseness, informativity, and readability, respectively. The results demonstrate the effectiveness of the proposed method in summarizing long medical documents.