Image Discrepancy Research Articles

Body Fat and Obesity Rates, Cardiovascular Fitness, and the Feasibility of a Low-Intensity Non-Weight-Centric Educational Intervention Among Late Adolescents: Quasi-Experimental Study.

Obesity rates among Saudi adolescents are increasing, with regional variations highlighting the need for tailored interventions. School-based health programs in Saudi Arabia are limited and often emphasize weight and body size, potentially exacerbating body image dissatisfaction. There is limited knowledge on the feasibility of non-weight-centric educational programs in Saudi Arabia and their effects on health behaviors and body image. This study aimed to (1) assess the prevalence of obesity using BMI-for-age z score (BAZ) and fat percentage among Saudi adolescents; (2) evaluate key health behaviors, cardiovascular fitness, and health literacy; and (3) assess the feasibility and impact of a low-intensity, non-weight-centric educational intervention designed to improve knowledge of macronutrients and metabolic diseases, while examining its safety on body image discrepancies. A quasi-experimental, pre-post trial with a parallel, nonequivalent control group design was conducted among 95 adolescents (58 boys and 37 girls; mean age 16.18, SD 0.53 years) from 2 public high schools in Medina City, Saudi Arabia. Participants were randomly assigned to either the weight-neutral Macronutrient + Non-Communicable Diseases Health Education group or the weight-neutral Macronutrient Health Education group. Anthropometry (BAZ and fat percentage), cardiovascular fitness, physical activity, and eating behaviors were measured at baseline. Independent t tests and χ² tests were conducted to compare group differences, and a 2-way mixed ANOVA was used to evaluate the effect of the intervention on macronutrient knowledge and body image discrepancies. A total of 69 participants completed the postintervention assessments. The prevalence of overweight and obesity based on BAZ was 37.9% (36/95), while 50.5% (48/95) of participants were classified as overfat or obese based on fat percentage. Students with normal weight status were significantly more likely to have had prior exposure to health education related to metabolic diseases than students with higher weight status (P=.02). The intervention significantly improved macronutrient-metabolic knowledge (F1,64=23.452; P<.001), with a large effect size (partial η²=0.268). There was no significant change in students' body image from pre- to postintervention (P=.70), supporting the safety of these weight-neutral programs. The intervention demonstrated strong feasibility, with a recruitment rate of 82.6% and a retention rate of 72.6%. This study reveals a high prevalence of obesity among Saudi adolescents, particularly when measured using fat percentage. The significant improvement in knowledge and the nonimpact on body image suggest that a non-weight-centric intervention can foster better health outcomes without exacerbating body image dissatisfaction. Region-specific strategies that prioritize metabolic health and macronutrient education over weight-centric messaging should be considered to address both obesity and body image concerns in adolescents.

Single-View Fluoroscopic X-Ray Pose Estimation: A Comparison of Alternative Loss Functions and Volumetric Scene Representations.

Many tasks performed in image-guided procedures can be cast as pose estimation problems, where specific projections are chosen to reach a target in 3D space. In this study, we construct a framework for fluoroscopic pose estimation and compare alternative loss functions and volumetric scene representations. We first develop a differentiable projection (DiffProj) algorithm for the efficient computation of Digitally Reconstructed Radiographs (DRRs) from either Cone-Beam Computerized Tomography (CBCT) or neural scene representations. We introduce two innovative neural scene representations, Neural Tuned Tomography (NeTT) and masked Neural Radiance Fields (mNeRF). Pose estimation is then performed within the framework by iterative gradient descent using loss functions that quantify the image discrepancy of the synthesized DRR with respect to the ground-truth, target fluoroscopic X-ray image. We compared alternative loss functions and volumetric scene representations for pose estimation using a dataset consisting of 50 cranial tomographic X-ray sequences. We find that Mutual Information significantly outperforms alternative loss functions for pose estimation, avoiding entrapment in local optima. The alternative discrete (CBCT) and neural (NeTT and mNeRF) volumetric scene representations yield comparable performance (3D angle errors, mean ≤ 3.2° and 90% quantile ≤ 3.4°); however, the neural scene representations incur a considerable computational expense to train.

Cross-sectional Assessment of Body Image Perception, Image Satisfaction, Body Image Discrepancy and Dietary Habits in Medical Students of Ujjain

Background: Being judgmental about self-body image and satisfaction or dissatisfaction with one’s own body is a natural phenomenon. If perceived incorrectly can lead to dissatisfaction and negative social, emotional, psychological and physical consequences. Methods: A cross-sectional study was planned and the data was collected with the help of a semi-structured proforma. Body image perception, image satisfaction, and associated dietary modification were inquired about, and Body Mass Index (BMI) and Body Image Discrepancy Score (BIDS) were calculated. The body image perception of participants was collected with the help of the Figure Rating Scale (FRS). Results: χ2 test, kappa statistics, Mann–Whitney test, multinominal regression, and Z-standardization were applied. Few 10% of participants perceived themselves as underweight, 48% as normal weight and 42% as overweight or obese. About 48%, 19%, and 33% of participants were satisfied, neutral and dissatisfied respectively by their perceived body image, and 43% of the participants had modified their diet. A statistically significant association was found between body image perception, image satisfaction, body image discrepancy and gender. Conclusion: There was a huge disagreement between perceived and actual body image. Overestimation and underestimation of body image were common in males and females respectively. Misperception of body image might lead to unnecessary dietary modifications resulting in malnutrition and somatoform disorders.

Metric learning guided sinogram denoising for cone beam CT enhancement.

Cone beam computed tomography (CBCT) is a widely available modality, but its clinical utility has been limited by low detail conspicuity and quantitative accuracy. Convenient post-reconstruction denoising is subject to back projected patterned residual, but joint denoise-reconstruction is typically computationally expensive and complex. In this study, we develop and evaluate a novel Metric-learning guided wavelet transform reconstruction (MEGATRON) approach to enhance image domain quality with projection-domain processing. Projection domain based processing has the benefit of being simple, efficient, and compatible with various reconstruction toolkit and vendor platforms. However, they also typically show inferior performance in the final reconstructed image, because the denoising goals in projection and image domains do not necessarily align. Motivated by these observations, this work aims to translate the demand for quality enhancement from the quantitative image domain to the more easily operable projection domain. Specifically, the proposed paradigm consists of a metric learning module and a denoising network module. Via metric learning, enhancement objectives on the wavelet encoded sinogram domain data are defined to reflect post-reconstruction image discrepancy. The denoising network maps measured cone-beam projection to its enhanced version, driven by the learnt objective. In doing so, the denoiser operates in the convenient sinogram to sinogram fashion but reflects improvement in reconstructed image as the final goal. Implementation-wise, metric learning was formalized as optimizing the weighted fitting of wavelet subbands, and a res-Unet, which is a Unet structure with residual blocks, was used for denoising. To access quantitative reference, cone-beam projections were simulated using the X-ray based Cancer Imaging Simulation Toolkit (XCIST). In both learning modules, a data set of 123 human thoraxes, which was from Open-Source Imaging Consortium (OSIC) Pulmonary Fibrosis Progression challenge, was used. Reconstructed CBCT thoracic images were compared against ground truth FB and performance was assessed in root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM). MEGATRON achieved RMSE in HU value, PSNR, and SSIM were 30.97±4.25, 37.45±1.78, and 93.23±1.62, respectively. These values are on par with reported results from sophisticated physics-driven CBCT enhancement, demonstrating promise and utility of the proposed MEGATRON method. We have demonstrated that incorporating the proposed metric learning into sinogram denoising introduces awareness of reconstruction goal and improves final quantitative performance. The proposed approach is compatible with a wide range of denoiser network structures and reconstruction modules, to suit customized need or further improve performance.

Body mass index, body satisfaction, and body image discrepancy among Latinx men: Implications for Latinx-centered cancer and diabetes risk reduction interventions.

Body mass index, body satisfaction, and body image discrepancy among Latinx men: Implications for Latinx-centered cancer and diabetes risk reduction interventions.

Image Discrepancies: Motivators for Sustainable Practices in the Hairdressing Industry

Image Discrepancies: Motivators for Sustainable Practices in the Hairdressing Industry

Beyond the prototype: Unpacking the intersectional identity and image work of female minority founders in a startup context.

It is well documented that female minority founders (FMFs) face disadvantages in starting and scaling their ventures. However, the causes of these disadvantages-as well as how FMFs navigate these challenges-are less understood. Our article adopts an intersectionality lens, which allows us to focus on and examine the multiple intersecting dimensions of FMFs (such as gender, ethnicity, migrant status, and social class) and how they influence their entrepreneurial experiences. Drawing upon an inductive study of FMFs operating in Berlin, we build a theory on intersectional identity and image work in startup contexts. We found key structural barriers that serve to sustain inequality and continue to favor more prototypical founders. However, we also identified sources of penalties and privileges that exacerbate (or mitigate) inequality and result in founder image discrepancy. Our analysis demonstrates how founder image discrepancy can prompt FMFs to engage in a progression of intersectional identity and image work that shapes their founder identity. These findings advance entrepreneurship and identity research by extending our understanding of how intersectional identity challenges and opportunities manifest and can be managed within startup contexts. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Body Size Perceptions Associated with Body Mass Index and Weight Loss Intentions Among Two Immigrant Populations.

The rates of obesity among immigrant populations within the USA rise with increasing duration of residency. The aims of this study were to examine weight self-perception and body image discrepancy within a large community sample of Hispanic and Somali predominantly immigrant adults. Utilizing a community-based participatory research (CBPR) approach to collect survey data from a sample of adults who self-identified as Hispanic, Latino, or Somali in Southeast Minnesota. Correlations among actual body mass index (BMI), perceived weight category, and perceived body size were assessed with Spearman rank correlation coefficients. Associations of weight loss intentions with actual BMI, perceived weight category, perceived body size, and body image discrepancy were assessed using Kruskal-Wallis nonparametric tests. A total of 1256 adults completed the survey and biometric measurements (610 Hispanic, 646 Somali); 81% (457) and 50% (328) had a BMI in the overweight or obese category in the Hispanic and Somali cohorts, respectively. Among participants with a BMI of > 25, more participants reported a perceived body size that was overweight or obese than a perceived weight category that was in the overweight or obese category (79% vs. 48%, p = < 0.0001). Body image discrepancy, but not actual BMI, was associated with weight loss intentions for both groups. Perceived body size and perceived weight category were associated with weight loss intentions for Hispanic participants only. Perceived body size is a more accurate self-report proxy of BMI-defined weight status compared with the perceived weight category among Hispanic and Somali immigrant groups. Body image discrepancy may be more predictive of weight loss intentions than actual BMI.

Entropy-Based re-sampling method on SAR class imbalance target detection

Detection tasks based on Synthetic aperture radar (SAR) images have been studied widely but severely constrained by the quality of datasets. Meanwhile, both the unperceived category imbalance problem and SAR image discrepancy of multi-class SAR datasets are not fully considered. Researchers usually care about the foreground-background imbalance more than the class imbalance for SAR images. To solve these problems, an entropy-based re-sampling method is proposed in which category imbalance and quality discrepancies of SAR images are both considered. Initially, the relationship is established between variance-weighted image entropy and factors affecting SAR image quality, such as noise, resolution, and density, thereby validating entropy as a robust metric for image quality assessment. Subsequently, quantity penalty scores of categories and difficulty penalty scores of each image are calculated separately to capture the inter-class and intra-class disparities. Next, logarithmic smoothing is employed to avoid overestimation of image difficulty due to the margin effect. Finally, all these scores are combined to generate normalized scores representing the final distribution of the dataset to guide the training process. The proposed approach serves as a plug-and-play strategy for general SAR detection tasks, and experimental results indicate a significant performance improvement. Specifically, detection accuracy in terms of AP for airplanes and bridges (minority classes) in the MSAR dataset is improved by 16.6 % and 13.0 %, respectively, compared to the YOLOv5 baseline, with only a minimal 1.6 % sacrifice in ship detection (majority class). The datasets and the codes can be found at https://www.radars.ac.cn/web/data/getData?dataType=MSAR, https://github.com/Phoenix0qi/Yolov5-entropy-balance/tree/master.

We are not who they think we are! Examining responses of qualified Tunisian immigrants in France to country-of-origin based image discrepancies

In this paper, we examine the dimensions of country-of-origin based image discrepancies that qualified immigrants perceive at the workplace and their responses to such discrepancies. By country-of-origin based image discrepancies, we mean misalignments between immigrants’ own notions and their perceptions of how host country employees (HCEs) think about their countries-of-origin and themselves based on their countries-of-origin. Our findings reveal that immigrants perceive discrepancies pertaining to four domains: national distinctiveness, dietary sophistication, governance and development, and religious practice. Further, they respond to them through two broad sets of tactics. The first set of responses involve engagement with HCEs via discussing, misleading, and individualizing. The second set involves evading HCEs and includes striving, immigrant socializing, avoiding, and rationalizing. This study contributes to the literature on image discrepancies by highlighting the importance of country-of-origin, specifically for qualified immigrants, who respond to them through various tactics. Our results would be helpful to both qualified immigrants and their organizations in managing image discrepancies and eventually adjustment at the workplace.

Duplex ultrasound and cross-sectional imaging in carotid artery occlusion diagnosis

ObjectiveInvestigations into imaging modalities in the diagnosis of extracranial carotid artery occlusion (CAO) have raised questions about the inter-modality comparability of duplex ultrasound (DUS) and cross-sectional imaging (CSI). This study examines the relationship between DUS and CSI diagnoses of extracranial CAO. MethodsThis single-institution retrospective analysis studied patients with CAO diagnosed by DUS from 2010 to 2021. Patients were identified in our office-based accredited vascular laboratory database. Imaging and clinical data was obtained via our institutional electronic medical record. Primary outcome was discrepancy between DUS and CSI modalities. Secondary outcomes included incidence of stroke and intervention subsequent to CAO diagnosis. ResultsOf our 140-patient cohort, 95 patients (67.9%) had DUS follow-up (mean, 42.7 ± 31.3 months). At index duplex, 68.0% of individuals (n = 51) were asymptomatic. Seventy-five patients (53.6%) had CSI of the carotids after DUS CAO diagnosis; 18 (24%) underwent magnetic resonance imaging and 57 (76%) underwent computed tomography. Indications for CSI included follow-up of DUS findings of carotid stenosis/occlusion (44%), stroke/transient ischemic attack (16%), other symptoms (12%), preoperative evaluation (2.7%), unrelated pathology follow-up (9.3%), and outside institution imaging with unavailable indications (16%). When comparing patients with CSI and those without, there were no differences with regard to symptoms at diagnosis, prior neck interventions, or hypertension. There was a significant difference between cross-sectionally imaged and non-imaged patients in anti-hypertensive medications (72% vs 53.8%; P = .04). Despite initial DUS diagnoses of carotid occlusion, 10 patients (13.3%) ultimately had CSI indicating patent carotids. Four of these 10 patients had stenoses of ∼99% (with 1 string sign), four of 70% to 99%, one of 50% to 69%, and one of less than 50% on CSI. The majority of patients (70%) had CSI within 1 month of the index ultrasound. There were no significant relationships between imaging discrepancies and body mass index, heart failure, upper body edema, carotid artery calcification, and neck hardware. Eight individuals (10.7%) underwent ipsilateral revascularization; 62.5% (n = 5) were carotid endarterectomy procedures, and the remaining three procedures were a transcervical carotid revascularization, subclavian to internal carotid artery bypass, and transfemoral carotid artery stenting. Eight patients (10.7%) underwent contralateral revascularization, with the same distribution of procedures as those ipsilateral to occlusions. Two of the 10 patients with discrepancies underwent carotid endarterectomy, and one underwent carotid stenting. ConclusionsIn our experience, duplex diagnosis of CAO is associated with a greater than 10% discordance when compared with CSI. These patients may benefit from closer surveillance as well as confirmatory computed tomography or magnetic resonance angiography. Further work is needed to determine the optimal diagnostic modality for CAO.

Being Able to Describe How One Thinks and Feels May (Partly) Attenuate the Association Between Perceived body Image Discrepancy and Body Dissatisfaction: Preliminary Evidence in Young Women

Being Able to Describe How One Thinks and Feels May (Partly) Attenuate the Association Between Perceived body Image Discrepancy and Body Dissatisfaction: Preliminary Evidence in Young Women

Image discrepancy around professional work matters: a moderated mediation study

Image discrepancy around professional work matters: a moderated mediation study

Fundus autofluorescence abnormalities can predict fluorescein angiography abnormalities in patients with chronic central serous chorioretinopathy.

This study is to assess the possible correlation between findings on fundus autofluorescence (FAF) and fluorescein angiography (FA) in patients with chronic central serous chorioretinopathy (cCSC). This multicentre retrospective cohort study included 71 cCSC patients (92 eyes) with at least 6months of follow-up, who had a FAF-FA imaging discrepancy larger than 0.5 optic disc diameters in size in the corresponding areas of hyperfluorescent abnormalities. A comparison was performed between progression in size of areas of hyperautofluorescent retinal pigment epithelium (RPE) abnormalities on FAF (HF-FAF) and the hyperfluorescent areas on FA (HF-FA) at first visit and last visit. The possible correlations were estimated between FAF-FA discrepancy and disease characteristics. The median area of HF-FAF at first visit was 7.48mm2 (1.41-27.9). The median area of HF-FA at first visit and last visit was 2.40mm2 (0.02-17.27) and 5.22mm2 (0.53-25.62), respectively. FAF-FA discrepancy was associated with follow-up duration and the area of HF-FAF at first visit. A mathematical algorithm for grading FAF-FA discrepancy in time was suggested, which predicted the enlargement of hyperfluorescent RPE abnormalities on FA in 82.6% of cases. There is a statistically significant relationship between the areas of HF-FAF and HF-FA in cCSC patients with FAF-FA imaging discrepancy at first presentation. Long-term changes in RPE alterations in cCSC on FA can be predicted based on baseline HF-FAF and follow-up duration.

Misdiagnosis of Cerebellar Infarcts and Its Outcome.

Cerebellar infarction, a rare category of stroke, is often misdiagnosed but not given much importance in the available literature. Its presentation overlaps with symptoms of other neurologic, cardiovascular, gastrointestinal, and systemic conditions and therefore is nonspecific. Early diagnosis and management of cerebellar strokes are of utmost importance as the lack of a proper diagnosis may increase overall morbidity and mortality. Lack of awareness of the warning signs and symptoms, non-specificity of symptoms, absence of neurological deficits, and imaging discrepancies are some of the factors contributing to misdiagnosis and delayed treatment. If symptomatology is considered, it is found that symptoms of posterior circulation stroke were more frequently misdiagnosed compared to anterior circulation. Nausea and vomiting increased the chance further. Some other rare presentations include gastrointestinal symptoms, isolated vertigo, and symptoms of inner ear disease. Overdependence on radiological investigations often masks the significance of clinical examination. Ischemic stroke may appear normal in the initial 48 hours in the computed tomography scan of the brain or bony artefacts may hide the lesion. Permanent disabling deficits can follow a cerebellar stroke and the complications, which include hydrocephalus, brain stem compression, and gait abnormalities, necessitate prompt identification and management. In this review article, we aim at analysing various case reports of cerebellar infarction, the most common presentations that were under-evaluated, and their outcomes, thereby highlighting the importance of proper diagnosis and reporting of cerebellar infarction in the future. A thorough knowledge of the association between various clinical presentations of cerebellar stroke and its misdiagnosis helps clinicians to be more vigilant about the disease.

Emotional eating, family functioning, and anxiety: Body image discrepancy during the pandemic

La pandemia por la Covid-19 implicó la incorporación de múltiples medidas para preservar la vida de la población, entre las cuales están el confinamiento y la reducción de actividades educativas, laborales y económicas. A mediano y largo plazo dichas medidas influyeron en la salud de las personas especialmente en relación con la obesidad como resultado de la modificación del estilo de vida y de la alimentación. Esta investigación tuvo por objetivo describir las diferencias de la alimentación emocional, el funcionamiento familiar y la ansiedad entre los diferentes niveles de discrepancia corporal en el contexto de la pandemia, derivado de la preocupación por el incremento de peso y el empeoramiento de la calidad de vida debido al impacto que han tenido los cambios en el bienestar emocional y las relaciones sociales. Se empleó un estudio transversal descriptivo de campo con una muestra no probabilística de 814 personas, 506 mujeres y 308 hombres entre 18 a 76 años con un promedio de 28.76. Se empleó la Escala de Alimentación Emocional, el instrumento para evaluar Funcionamiento Familiar y las Siluetas de Stunkard para evaluar la satisfacción corporal. Se encontró que la población con mayor grado de discrepancia con la imagen corporal reportó mayores niveles de obesidad, menor cohesión familiar, mayor indiferencia y tendencia a comer por emociones. La alimentación emocional tuvo un notable aumento como uno de los efectos negativos de la pandemia y como estrategia para afrontar situaciones adversas, con ello también el grado de insatisfacción o corporal y problemas de salud como la obesidad. Se requiere informar a la población sobre el manejo y gestión adecuada de las emociones, alimentación saludable y la importancia de las redes de apoyo como la familia y amigos frente a situaciones adversas.

Obesity and Overweight among in-School Students in Private and Public Schools in Ibadan North Local Government Area, Oyo State: A Comparative Study

The growing alarming rate of obesity worldwide is a great concern to individuals and the general public. This has been the trend among secondary schools in many parts of the world in the past three decades. This study, therefore, was aimed at assessing the obesity and overweight among in-school students in public and private schools in Ibadan North Local Government, Oyo State Nigeria. A comparative cross sectional study was carried out among in-school students in Ibadan North Local Government area Oyo State Nigeria. Four hundred (400) respondents were selected using multi-stage sampling technique. Information from respondents was obtained using pre-tested semi-structured questionnaires. Data analysis was done with Statistical Package for Social Sciences (SPSS) version 21. The results showed that when Body Mass Index was used as a measure of obesity, the number of overweight and obesity was significantly more in private schools than in public schools with a p-value less than 0.001. Using Waist and Hip Ratio private school have significantly higher number of obese compared to the public. Body Image Discrepancy private school was higher than that of the public school, but the difference was not statistically high. The nutritional rating of the respondents showed that few of the private students on first day, about one third on the second day and the same on the third day had a healthy eating index. Majority of the respondents scored below six percet which is an indication that many of them are not eating well, that is they are not abiding by the food pyramid rules of daily recommended dietary allowances (RDAs). The nutritional status was significantly associated with the gender, types of school, age groups and class categories of the respondents. The study concludes that WHR detects more of central obesity while BMI accounts for generalised obesity. There was a significant difference in the feeding patterns and activity patterns of the students attending public and private schools. Factors associated with the nutritional status of the respondents were their age, gender, the type of schools and their class categories.

Identification of asynchronous motor and transformer situations in thermal images by utilizing transfer learning-based deep learning architectures

Asynchronous motors are thoroughly preferred in industrial applications regarding their advantages in comparison with other motor types, and transformers constitute another oft-used category for the adjustment of voltage to be fed to an electrical system. Concerning the inevitable usage of these equipment, the fault diagnostics are generally fulfilled by in-depth determinations of stator current signals, magnetic flux distributions, etc. which require conventional electrical measurements. Herein, thermal image analyses arise as an easy way to identify the situations of electrical equipment in which there is no need for direct intervention to the structure. In this paper, we handle the thermal image-based analyses to distinguish the situations of asynchronous motors and transformers. For this purpose, without a pre-processing step, efficient deep learning architectures (DenseNet201, MobileNetV2, ResNet50, ShuffleNet, Xception) are examined to discriminate twenty situations formed by combining the conditions of both types of equipment. These conditions are defined as the cooling fan failure, rotor fault, short-circuit faults in different phases and in various rates inside the motor, short-circuit faults in different rates inside the transformer, no-load motor, and no-load transformer. In experiments, the hyperparameters of models are examined in a comprehensive manner to observe the highest scores of architectures that can be achieved. Herein, four phenomena (mini-batch size, learning rate, learning rate drop factor, optimizer type) are evaluated to perform the transfer learning task, not to spoil the main part of the models, and to reveal the appropriate model for thermal image classification. In trials, an 80–20% training-test split is allowed to compare the models without data augmentation. As a result, the highest performance is observed with all deep learning architectures by attaining 100% accuracy for condition discrepancy of thermal images belonging to the three phase-motor and one phase-transformer. In addition to the accuracy-based analyses, an in-depth evaluation is presented to reveal the most appropriate architecture in thermal image classification.

Plant and Animal Species Recognition Based on Dynamic Vision Transformer Architecture

Automatic prediction of the plant and animal species most likely to be observed at a given geo-location is useful for many scenarios related to biodiversity management and conservation. However, the sparseness of aerial images results in small discrepancies in the image appearance of different species categories. In this paper, we propose a novel Dynamic Vision Transformer (DViT) architecture to reduce the effect of small image discrepancies for plant and animal species recognition by aerial image and geo-location environment information. We extract the latent representation by sampling a subset of patches with low attention weights in the transformer encoder model with a learnable mask token for multimodal aerial images. At the same time, the geo-location environment information is added to the process of extracting the latent representation from aerial images and fused with the token with high attention weights to improve the distinguishability of representation by the dynamic attention fusion model. The proposed DViT method is evaluated on the GeoLifeCLEF 2021 and 2022 datasets, achieving state-of-the-art performance. The experimental results show that fusing the aerial image and multimodal geo-location environment information contributes to plant and animal species recognition.

CONNECTIONS BETWEEN BODY IMAGE AND ADOLESCENTS’ HEALTH, PSYCHOLOGICAL AND SOCIAL VARIABLES

The aim was to expand the existing knowledge on adolescents’ body image and its connections with health (Body Mass Index, sleep activity), psychological (well-being, physical self-concept), and social (socio-economic status, diet) variables.&#x0D; 246 students (130 boys, 116 girls), age range 13-15 years, enrolled in 10 schools participated. Seven days/24 hours, they wore accelerometers to monitor their activity, including sleep. Participants’ Body Mass Index was obtained and they completed several questionnaires. The results indicated that most participants had an adequate BMI, optimal Mediterranean diet and medium socioeconomic status. Sleep efficiency was above 92%. One quarter showed signs of psychological disorders. The majority (52,1%) chose an ideal body image thinner than the perceived one, 32,1% a similar one, and 15% a larger one. Most participants wanted a different figure, especially among females, but it did not vary depending on socioeconomic status or Mediterranean diet. Perceived body image and body image discrepancy were positively correlated with BMI. Negative relationships were observed between sleep efficiency and perceived body image and body image discrepancy. Sleep efficiency predicted both perceived body image and body image discrepancy, while sex predicted ideal body image. Participants with greater body image discrepancy showed lower levels of physical self-concept and psychological well-being.&#x0D; In conclusion, body image dissatisfaction had high prevalence among adolescents with negative implications on their psychological well-being and physical self-concept. BMI is a factor closely linked to adolescents’ body dissatisfaction. No connection was found between body image discrepancy and SES or Mediterranean diet. Finally, sleep efficiency predicted both perceived body image and body image discrepancy.