Segmentation Analysis Research Articles

Association between insulin resistance and vascular damage in an adult population in China: a cross-sectional study

There is a relative scarcity of large-scale population studies investigating the relationship between the insulin resistance index of homeostasis model assessment (HOMA-IR) and vascular damage. Therefore, we assessed the association between HOMA-IR and vascular damage in adults aged 18 years and older in China. A total of 17,985 research subjects were included. Vascular damage markers and relevant laboratory tests were measured. HOMA-IR was calculated as (fasting insulin * fasting blood glucose)/22.5. Vascular damage included arteriosclerosis (ba-PWV > 1800 cm/s), peripheral artery disease (ABI < 0.9), and microalbuminuria (UACR > 30 mg/g). The relationship between HOMA-IR and vascular damage was analyzed using the RCS. The restricted cubic spline (RCS) analysis suggested that HOMA-IR was nonlinearly associated with arteriosclerosis (P for no-liner < 0.01), peripheral artery disease (P for no-liner < 0.01), and microalbuminuria (P for no-liner < 0.01). Further segmented regression analyses revealed that in study subjects with HOMA-IR < 5, we found that HOMA-IR was associated with an increased OR for arteriosclerosis (OR: 1.36, 95% CI (1.28, 1.45), P < 0.01), peripheral artery disease (OR: 1.33, 95% CI (1.10, 1.60), P < 0.01) and microalbuminuria (OR: 1.59, 95% CI (1.49, 1.70), P < 0.01). HOMA-IR is an independent risk factor for vascular damage, both macrovascular and microvascular. The phenomenon of saturation of HOMA-IR with vascular damage needs further investigation.

Incorporation of suvorexant and lemborexant into hair and their distributions after a single intake.

This study examined the applicability of hair analysis as an approach to identify suvorexant (SUV) and lemborexant (LEM) intake by analyzing black hair specimens collected from study participants after a single oral administration. Hair specimens were collected form participants who took a single dose of 10 mg SUV or 5 mg LEM. Identification of the dual orexin receptor antagonists (DORAs) and their metabolites was performed by liquid chromatography-tandem mass spectrometry. Reference standards of S-M9 and L-M4, the metabolites of SUV and LEM, respectively, were synthesized in our laboratory. Sectional analysis of 1-mm segments of the single-hair strands was also performed to investigate the incorporation behavior of the drugs into hair. Unchanged SUV and LEM, and their metabolites S-M9 and L-M4 were detected even in the single-hair specimens. Results of the segmental hair analysis showed predominant incorporation of the drugs into hair through the hair bulb region rather than through the upper dermis zone of the hair root. The drug concentrations in the hair specimens, collected about 1month after intake, were 0.033-0.037pg/hair strand (0.17-0.19pg/mg) for SUV and 0.054-0.28pg/hair strand (0.28-1.5pg/mg) for LEM. The calculated distribution ratios of the DORAs into hair to the oral doses were much lower than those of benzodiazepines and zolpidem reported in a previous study. This is the first report of the detection of the DORAs in hair. The incorporation behavior of the DORAs into hair revealed herein are crucial for proper interpretation of hair test results.

Association of Opioid Disposal Practices with Parental Education and a Home Opioid Disposal Kit Following Pediatric Ambulatory Surgery.

The majority of opioid analgesics prescribed for pain after ambulatory pediatric surgery remain unused. Most parents do not dispose of these leftover opioids or dispose of them in an unsafe manner. We aimed to evaluate the association of optimal opioid disposal with a multidisciplinary quality improvement (QI) initiative that proactively educated parents about the importance of optimal opioid disposal practices and provided a home opioid disposal kit before discharge after pediatric ambulatory surgery. Opioid disposal behaviors were assessed during a brief telephone interview pre- (Phase I) and post-implementation (Phase II) after surgery. For each phase, we aimed to contact the parents of 300 pediatric patients ages 0 to 17 years who were prescribed an opioid after an ambulatory surgery. The QI initiative included enhanced education and a home opioid disposal kit including DisposeRX®, a medication disposal packet that renders medications inert within a polymeric gel when mixed with water. Weighted segmented regression models evaluated the association between the QI initiative and outcomes. We considered the association between the QI initiative and outcome significant if the beta coefficient for the change in intercept between the end of Phase I and the beginning of Phase II was significant. Safe opioid disposal and any opioid disposal were evaluated as secondary outcomes. The analyzed sample contained 161 pediatric patients in Phase I and 190 pediatric patients in Phase II. Phase II (post-QI initiative) cohort compared to Phase I cohort reported higher rates of optimal (58%, n = 111/190 vs 11%, n = 18/161) and safe (66%, n = 125/190 vs 34%, n = 55/161) opioid disposal. Weighted segmented regression analyses demonstrated significant increases in the odds of optimal (odds ratio [OR], 26.5, 95% confidence interval [CI], 4.0-177.0) and safe (OR, 4.4, 95% CI, 1.1-18.4) opioid disposal at the beginning of Phase II compared to the end of Phase I. The trends over time (slopes) within phases were nonsignificant and close to 0. The numbers needed to be exposed to achieve one new disposal event were 2.2 (95% CI, 1.4-3.7]), 3.1 (95% CI, 1.6-7.4), and 4.3 (95% CI, 1.7-13.6) for optimal, safe, and any disposal, respectively. A multidisciplinary approach to educating parents on the importance of safe disposal of leftover opioids paired with dispensing a convenient opioid disposal kit was associated with increased odds of optimal opioid disposal.

Cardiac alterations induced by Heloderma horridum horridum venom in rats: An experimental study with ECG analysis using a linear regression algorithm

Envenomation by reptile venom, particularly from lizards, poses significant health risks and can lead to physiological and cardiovascular changes. The venom of Heloderma horridum horridum, endemic to Colima, Mexico, was tested on Wistar rats. Electrocardiographic (ECG) data were collected pre-treatment and at 5-min intervals for 1 h post-envenomation. A specially designed computational linear regression algorithm (LRA) was used for the segmentation analysis of the ECG data to improve the detection of fiducial points (P, Q, R, S, and T) in ECG waves. Additionally, heart tissue was analyzed for macroscopic and microscopic changes. The results revealed significant electrocardiographic alterations, including pacemaker migration, junctional extrasystoles, and intraventricular conduction aberrations. By applying a linear regression algorithm, the study compensated for noise and anomalies in the isoelectric line in an ECG signal, improving the detection of P and T waves and the QRS complex with an efficiency of 97.5%. Cardiac enzyme evaluation indicated no statistically significant differences between the control and experimental groups. Macroscopic and microscopic examination revealed no apparent signs of damage or inflammatory responses in heart tissues. This study enhances our understanding of the cardiovascular impact of Heloderma venom, suggesting a greater influence on changes in conduction and arrhythmias than on direct cardiac damage to the myocardium.

Deep learning and multiscale analysis for epithelial-mesenchyme segmentation and classification in breast cancer histological images

Deep learning and multiscale analysis for epithelial-mesenchyme segmentation and classification in breast cancer histological images

The influence of breed, dietary energy and lysine on laying persistency and body composition of laying hens

The effect of dietary energy and lysine levels on laying persistency and body composition in brown and white hens was studied. Dietary treatments with 2 Metabolizable Energy levels (ME lay; constant or reduction over time) and 2 apparent fecal digestible Lys levels (AFD Lys; constant or reduction over time), were fed to Lohmann white or brown hens, from 17 to 75 wk of age, in a 2 × 2 × 2 factorial design. Data were subjected to mixed model analyses. The egg production curve was modeled using a non-linear regression function. White hens showed an improved laying persistency and a higher number of total eggs per hen compared to brown hens, indicated by a shorter peak production phase but a significant lower slope of decline after peak (P < 0.05). Similarly, hensfed a reduced instead of a constant ME Lay diet had a better laying persistency, indicated by a shorter peak production phase and a significant smaller slope of decline after peak (P < 0.05). This improved laying persistency was probably related to a higher ADFI and nutrient intake of hens fed the reduced ME Lay diets (P < 0.05). A segmented regression analysis showed reasonable correlation between egg mass production and ME Lay intake, with an R2 adjusted of 0.78 for the overall model. The egg mass production was not increased for intakes above 330 kcal of ME Lay intake for white hens and 324 kcal for brown hens. Limited effects of dietary treatments on body crude fat and crude protein were found. Both energy and protein requirement seemed to increase over time, indicated by higher voluntary nutrient intake and a reducing body crude fat after wk 43 in all treatments. The egg mass production correlated poorly with the AFD Lys intake, with an R2 of 0.22. In conclusion, laying persistency was mostly influenced by breed and dietary ME Lay level, but not dietary AFD Lys level.

Development of a GC-MS Method for the Analysis of Selected Opioids in Human Hair Samples

Background: Hair samples are recognized as alternative biological specimens in forensic and clinical toxicology for detecting drug abuse and poisoning. Forensic testing for opioids in hair has become a useful diagnostic measure for assessing chronic drug usage through segmental analysis. However, accurate, sensitive and specific analytical methods are needed. The aim of this study was to introduce a simple, sensitive and specific GC-MS method for the identification and quantitation of selected and commonly abused opioids (tramadol, methadone, morphine, and codeine) in hair samples. Methods: After external decontamination, a 50 mg portion of powdered hair sample was combined with hydrochloric acid (0.1 M) and incubated on a magnetic stirrer at 56°C for 16 hours. Then, 1 mL of sodium hydroxide (0.1 M) and 2 mL of phosphate buffer (1 M, pH=8.4) were added. Chloroform-isopropanol (ratio: 80:20 V/V) was utilized as the extracting solvent and the sample was homogenized and centrifuged for 5 minutes (at 3500 rpm). After centrifugation, the organic phase was dried using dry nitrogen gas. The sample was derivatized with N-methyl-N-(trimethylsilyl) trifluoroacetamide (MSTFA). The blank, standards, and real samples were subsequently analyzed by GC-MS.Results: The limits of detection in the linearity experiments ranged from 0.12 to 0.21 ng/mg. According to the validation results, the method exhibited linearity in the concentration range of 0.1-2.5 ng/mg for all analytes, with calibration curve slopes ranging from R2=0.98 to 0.99. Good inter and intra-day precision relative standard deviations (RSDs) were observed to be &lt;3.5% for all compounds. Extraction efficiency varied from 91.8 to 102.4%. Conclusion: The validation and analysis of actual samples indicate that this method is straightforward, sensitive, and specific for the analysis of opioids in routine hair analysis.

Seasonal and vertical tidal variability in the Southeastern Mediterranean Sea

Currents and pressure records from the DeepLev mooring station and drifter data in the eastern Levantine Basin were analyzed to identify the dominant tidal constituents and their seasonal and depth variability. Harmonic and spectral analysis of seasonal segments of currents and pressure reveal key attributes of the tidal regime: (1) dominant semidiurnal sea level variability; (2) seasonal variation of semidiurnal and diurnal tides in both currents and pressure datasets; and (3) significant diurnal currents with weak semidiurnal currents across all seasons. The most dominant tidal constituent from the pressure dataset is the M2 (12.4 h). Results from pressure datasets align with previous models and observations of semidiurnal tides. In contrast, the diurnal tides are larger than previously reported by 8—9 cm in the winter and 1—2 cm in the summer. The surface current tidal regime differs from prior reports in the eastern Levantine Basin, with M2 magnitudes weaker by 1 cm s-1, while the diurnal tides (K1, O1) are 1—2 cm s-1 larger. Seasonal segments showed seasonal differences in the local tidal regime’s amplitudes. The most pronounced seasonal differences were with the K1 and S2 tides, with differences between winter and fall of 7 cm for the K1 and 4 cm between summer and fall for the S2. We utilized the DeepLev datasets to compare a moored device with surface drifters near DeepLev by analyzing the M2 and S2 tides. Additionally, we examined data at different dataset lengths, considering the time constraints needed to resolve the tides adequately. Longer datasets improved the resolution of the tidal analysis and reduced amplitude leakages from nearby frequencies, resulting in a more realistic and accurate analysis of the tidal currents. Conversely, longer datasets resulted in fewer drifters remaining our study region for the allotted dataset length. From 32 available segments in 15 day dataset to 7 with a 30 day dataset, reducing the effectiveness of drifters as a local tidal research tool.

A wavelet-based denoising method for pipeline dent assessments

Strain-based assessments of dents in buried steel oil and gas pipelines are commonly carried out in practice. Dent signals obtained from the caliper inspection tool contain noises that can have a large impact on the accuracy of the estimated strain. This paper proposes a novel wavelet-based denoising method for dent signals based on the overcomplete expansion with the corresponding dictionary constructed using the stationary and hyperbolic wavelet transforms. The proposed method is validated based on noise-free and noisy dent signals generated from elasto-plastic finite element analyses of a pipe segment subjected to an indenter and shown to be more effective than the commonly used wavelet transform-based hard- and soft-thresholding methods in terms of the root mean square error and the accuracy of the effective dent strain estimated from the denoised signal. The proposed method is further employed to denoise 42 real dent signals from in-service pipelines to illustrate its effectiveness and potential practical application to facilitate strain-based dent assessments.

Seasonal amplitude of principal tidal constituents in shallow shelf regions

Understanding the seasonal variation (annual cycle) of tides is crucial for coastal management and the planning of coastal infrastructure, as well as pivotal for navigation safety, prediction of extreme sea levels and so on. Specifically, seasonal variations of M2 amplitudes, larger in summer and smaller in winter, have attracted widespread attention. Nevertheless, investigations into other tidal constituents, such as S2, K1, O1, remain comparatively sparse. Here, seasonal variations of the four principal tidal constituents are studied in the shallow shelf regions of the China Seas and the North Sea, both acknowledged for exhibiting the most pronounced seasonal modulations of M2 amplitude, attributable to vertical stratification. We perform a segmented Harmonic Analysis with moving average filter, to remove semi-annual cycle, at 25 tide gauge data and find a synchronized seasonal modulation of M2 and O1 in China, which can be explained by stratification. Whereas S2 manifest an inverse seasonal modulation, larger in winter and smaller in summer, attributed to the sun's varying proximity to the earth. The K1 tide displays two very different seasonal cycle, also influenced by astronomical modulation. This observed pattern basically persists in the North Sea, while O1 shows a negative seasonal amplitude but still exists high correlation coefficient with M2. Consequently, this study provides a deep insight into 4 principal tidal constituents' seasonal modulation and underlying mechanisms, thereby enhancing our ability to comprehend and predict water level extremes and flooding with greater precision.

Comparative analysis of semantic segmentation and multi-boosted faster R-CNN for robotic tool detection in diabetes patient care

Diabetes, a common chronic illness, need meticulous patient care and treatment, which frequently necessitates advanced robotic help. The identification of robotic tools is critical in guaranteeing precise and safe medical procedures. With the growing use of robots in healthcare, reliable identification of instruments inside a patient care setting is critical for allowing smooth and efficient medical procedures. We used a Multi-Boosted Faster-Region-based Convolutional Neural Network (MBF-RCNN) to estimate Robotic Tool Detection in Diabetes Patient Care in the present research. Semantic Segmentation is a machine learning methodology centered on classifying pictures pixel-by-pixel, whereas Multi-Boosted Faster R-CNN recognizes objects using a variety of boosting strategies. Decimal Scaling Normalization is used during the preprocessing step to optimize the input data for both procedures. The effectiveness of both approaches is improved by doing extraction of features using Linear Discriminant Analysis (LDA) to find key trends in the information that is provided.The Multi-Boosted Faster-Region-based Convolutional Neural Network (MBF-RCNN) is an improved variation of the Faster R-CNN design that uses the boosting approach to improve object identification performance.Accuracy, Precision, Recall, F1-score, and the Receiver Operating Characteristic (ROC) curve among the assessment metrics used. The findings show that the suggested approaches are effective in identifying and localizing robotic equipment, which is critical for effective treatments in controlling diabetes.This research promotes computer vision applications in healthcare, particularly in the care of diabetic patients. It assesses the efficiency and dependability of Semantic Segmentation and MBF-RCNN for robotic tool identification, opening the way for more efficient and dependable automation for healthcare contexts.

Automatic reorientation to generate short-axis myocardial PET images

BackgroundAccurately redirecting reconstructed Positron emission tomography (PET) images into short-axis (SA) images shows great significance for subsequent clinical diagnosis. We developed a system for automatic redirection and quantitative analysis of myocardial PET images.MethodsA total of 128 patients were enrolled for 18 F-FDG PET/CT myocardial metabolic images (MMIs), including 3 image classifications: without defects, with defects, and excess uptake. The automatic reorientation system includes five modules: regional division, myocardial segmentation, ellipsoid fitting, image rotation and quantitative analysis. First, the left ventricular geometry-based canny edge detection (LVG-CED) was developed and compared with the other 5 common region segmentation algorithms, the optimized partitioning was determined based on partition success rate. Then, 9 myocardial segmentation methods and 4 ellipsoid fitting methods were combined to derive 36 cross combinations for diagnostic performance in terms of Pearson correlation coefficient (PCC), Kendall correlation coefficient (KCC), Spearman correlation coefficient (SCC), and determination coefficient. Finally, the deflection angles were computed by ellipsoid fitting and the SA images were derived by affine transformation. Furthermore, the polar maps were used for quantitative analysis of SA images, and the redirection effects of 3 different image classifications were analyzed using correlation coefficients.ResultsOn the dataset, LVG-CED outperformed other methods in the regional division module with a 100% success rate. In 36 cross combinations, PSO-FCM and LLS-SVD performed the best in terms of correlation coefficient. The linear results indicate that our algorithm (LVG-CED, PSO-FCM, and LLS-SVD) has good consistency with the reference manual method. In quantitative analysis, the similarities between our method and the reference manual method were higher than 96% at 17 segments. Moreover, our method demonstrated excellent performance in all 3 image classifications.ConclusionOur algorithm system could realize accurate automatic reorientation and quantitative analysis of PET MMIs, which is also effective for images suffering from interference.

Multimodal quantitative segmental analysis of seismicity of the Zhangjiakou-Bohai tectonic belt (North China)

Multimodal quantitative segmental analysis of seismicity of the Zhangjiakou-Bohai tectonic belt (North China)

Generation of input spectrum for electrolysis stack degradation test applied to wind power PEM hydrogen production

Hydrogen production by proton exchange membrane electrolysis has good fluctuation adaptability, making it suitable for hydrogen production by electrolysis in fluctuating power sources such as wind power. However, current research on the durability of proton exchange membrane electrolyzers is insufficient. Studying the typical operating conditions of wind power electrolysis for hydrogen production can provide boundary conditions for performance and degradation tests of electrolysis stacks. In this study, the operating condition spectrum of an electrolysis stack degradation test cycle was proposed. Based on the rate of change of the wind farm output power and the time-averaged peak-valley difference, a fluctuation output power sample set was formed. The characteristic quantities that played an important role in the degradation of the electrolysis stack were selected. Dimensionality reduction of the operating data was performed using principal component analysis. Clustering analysis of the data segments was completed using an improved Gaussian mixture clustering algorithm. Taking the annual output power data of wind farms in Northwest China with a sampling rate of 1 min as an example, the cyclic operating condition spectrum of the proton-exchange membrane electrolysis stack degradation test was constructed. After preliminary simulation analysis, the typical operating condition proposed in this paper effectively reflects the impact of the original curve on the performance degradation of the electrolysis stack. This study provides a method for evaluating the degradation characteristics and system efficiency of an electrolysis stack due to fluctuations in renewable energy.

Segmental Analysis of Racial and Ethnic Diversity in the Pipeline to Anesthesiology Fellowship from 2012-2022

Segmental Analysis of Racial and Ethnic Diversity in the Pipeline to Anesthesiology Fellowship from 2012-2022

A bibliometric analysis of semantic segmentation in remote sensing images from 1981 to 2024

Semantic segmentation of remote sensing images plays a crucial role in various fields, such as disaster assessment, forestry measurement, and environmental monitoring. This study conducts a bibliometric analysis to investigate the research trends and development of semantic segmentation in remote sensing from 1981 to 2024. Utilizing the Web of Science Core Collection database, we retrieved representative literature data and analyzed the publication trends, main source journals, institutional cooperation, and keyword co-occurrence networks. The results show that the number of publications in this field has increased significantly since 2000, with an exponential growth pattern. Remote sensing is the most active research topic, followed by imaging science, photographic technology, and electrical and electronic engineering. The analysis of institutional cooperation reveals that Chinese research institutions, such as the Chinese Academy of Sciences and Wuhan University, play a leading role in this field and maintain close collaboration with research institutions worldwide. The keyword co-occurrence network analysis demonstrates the evolution of research focus from basic remote sensing and image processing techniques in the early stage to advanced image processing algorithms in the middle stage and deep learning and neural network technologies in the recent stage. The findings provide valuable insights into the current status and future trends of semantic segmentation in remote sensing, highlighting the importance of international cooperation and interdisciplinary exchange in driving technological innovation.

Review on the Use of Data Analysis for Customer Segmentation and Personalization in Marketing Strategies

This paper studies the application of data analysis in the field of customer segmentation and personalization. With the advent of the era of big data, enterprises and organizations have rich data resources that contain important information about customer behavior, preferences, and purchasing habits. Through data analytics, companies can better understand customer needs and provide personalized products and services, thereby improving customer satisfaction and loyalty. This study aims to explore the application of data analytics in the field of customer segmentation and personalization, and provides some common data analysis methods. Data analysis methods include probabilistic methods and Bayesian methods, among others. Through case studies, the application of data analysis in the field of e-commerce is explained. The research results show that data analytics has important value and potential applications in customer segmentation and personalized marketing. However, data analysis still faces some challenges and limitations in practice, including data security and quality issues. Future research can continue to explore methods and techniques for data analysis, solve problems such as data privacy and security, and apply data analysis in more fields.

Self-interest or ethic: Consumer segmentation for purchasing agricultural products online based on attitude in China

This paper aims to segment online consumers based on their attitude toward self-interest and ethical attitudes and explore the impact of these attitudes on the purchasing behavior of agricultural products online in China. The study was conducted using 633 online survey responses from consumers who have purchased agricultural products online in China. First, to validate the relationship between attitude and behavior by structural equation modeling. Next, the number of segments was determined using K-means. Finally, Pearson Chi-square difference tests were performed to analyze demographic and behavioral variables and identify each segment’s characteristics. The results of this study provide a segmentation analysis of the online market for agricultural products in China. The four segments identified are pure ethical consumers, information communicators, brand-quality pursuers, and well-heeled shoppers. Additionally, this study reveals the characteristics of each segment based on demographic and behavioral variables. This study provides a novel approach to segmenting Chinese consumers who purchase agricultural products online based on their attitudes toward self-interest and ethical attitudes, aiming to understand the impact of these attitudes on their purchasing behavior. Moreover, from an ethical consumerism perspective, it explores the effect of ethical information on purchasing agricultural products online, highlighting its significant implications for online marketing strategies.

Quantitative Analysis of Right Atrial Functions by 2D-Speckle Tracking Echocardiography During Healthy Pregnancy.

The role of speckle tracking in the assessment of right atrial (RA) deformation parameters has not been investigated yet. The purpose of this article is to establish the effects of normal pregnancy on RA mechanical changes obtained by 2-dimensional speckle-tracking echocardiography. A total of 49 healthy pregnant women were included in the study. All participants were followed for each trimester and postpartum period, encompassing standard assessments of both RA and ventricular functions, as well as measurements of RA global peak atrial longitudinal strain (RA-Global-PALS) and RA global peak atrial contraction strain (RA-Global-PACS). Additionally, the RA segments were individually evaluated with respect to strain parameters. During pregnancy, the increased volume load resulted in elevated RA reservoir function, as indicated by RA-Global-PALS, and increased contraction parameter, as indicated by RA-Global-PACS. These changes were within physiological limits and reversible. Segmental analysis of the right atrium showed similar findings for regional PACS and PALS parameters. In this study, we established normal RA deformation parameters for healthy pregnancies. These data will aid in discerning various measures of RA phasic function in cardiovascular and systemic conditions among normal pregnant women. Moreover, they may offer insights into potential cardiac pathologies that may arise during the pregnancy.

European consumers' intention to buy sustainable aquaculture products: An exploratory study

Given the increasing global importance of low trophic level aquaculture (LTA) products (e.g. seaweed and mussels) for sustainable and healthy seafood supply, this study examined consumer intentions towards LTA products among European consumers. This study performed an extended theory of planned behaviour to focus on the influence of health consciousness, subjective knowledge, food neophobia, and sociodemographic and lifestyle factors on consumers' intentions to buy LTA products. We conducted an online questionnaire survey in Denmark, the United Kingdom and France (~500 respondents per country). Consumer segmentation analysis, based on food-related lifestyles, employing K-means clustering techniques, revealed five distinct segments, namely ‘Adventurous’, ‘Uninvolved’, ‘Foodies’, ‘Rational’, and ‘Conservative’, each reflecting unique consumer behavioural patterns. Furthermore, partial least squares structural equation modelling analysis revealed that subjective norms are the main predictor of LTA product buying intention, followed by attitude, food neophobia, subjective knowledge, and health consciousness. Furthermore, food neophobia seems to moderate the influence of subjective norms and subjective knowledge on LTA product buying intention. This dual approach explains the predictive power of the model while identifying targeted segments for sustainable aquaculture product marketing, ensuring that the distinction between the model's test and the subsequent segmentation analysis is clearly articulated. To enhance the adoption of LTA products, marketers should primarily target the ‘Foodies’ segment, characterised by high involvement and innovation, by emphasizing attitudes, health consciousness, subjective knowledge, and food quality attributes, while mitigating food neophobia and leveraging subjective norms.