RESUMEN
A method for spectral reflectance factor reconstruction based on wideband multi-illuminant imaging was proposed, using a programmable LED lighting system and modified Bare Bones Particle Swarm Optimization algorithms. From a set of 16 LEDs with different spectral power distributions, nine light sources with correlated color temperatures in the range of 1924 K - 15746 K, most of them daylight simulators, were generated. Samples from three color charts (X-Rite ColorChecker Digital SG, SCOCIE ScoColor paint chart, and SCOCIE ScoColor textile chart), were captured by a color industrial camera under the nine light sources, and used in sequence as training and/or testing colors. The spectral reconstruction models achieved under multi-illuminant imaging were trained and tested using the canonical Bare Bones Particle Swarm Optimization and its proposed modifications, along with six additional and commonly used algorithms. The impacts of different illuminants, illuminant combinations, algorithms, and training colors on reconstruction accuracy were studied comprehensively. The results indicated that training colors covering larger regions of color space give more accurate reconstructions of spectral reflectance factors, and combinations of two illuminants with a large difference of correlated color temperature achieve more than twice the accuracy of that under a single illuminant. Specifically, the average reconstruction error by the method proposed in this paper for patches from two color charts under A + D90 light sources was 0.94 and 1.08 CIEDE2000 color difference units. The results of the experiment also confirmed that some reconstruction algorithms are unsuitable for predicting spectral reflectance factors from multi-illuminant images due to the complexity of optimization problems and insufficient accuracy. The proposed reconstruction method has many advantages, such as being simple in operation, with no requirement of prior knowledge, and easy to implement in non-contact color measurement and color reproduction devices.
RESUMEN
Quantitative analysis of the process of urban expansion and evolution is of great practical significance for the future planning and development potential of valley cities. Based on GEE cloud platform and Landsat satellite data, this paper analyzed the spatio-temporal change characteristics and transfer rules of land cover in Xining City and its surrounding areas in the past 33 years by using random forest algorithm, spatio-temporal consistency test, land use dynamic attitude, transfer matrix and transfer hot spot analysis methods. The results show that the accuracy range of the preliminary classification of construction land is improved by 1.57%-3.53 % by using the spatio-temporal consistency test algorithm. The characteristics of land cover change in the study area are mainly the increase of construction land and forest area, the decrease of cultivated land and grassland area, the small change of water body and unused land, and the change of land cover type from cultivated land to urban construction land is prominent. The hot areas of construction land have gradually shifted from the central and eastern districts of the city in 1987 to the hot areas dominated by the Haihu New District of the West of the city, the Biological Park and the higher education base of the North District of the city, the South New District of the city, Duoba Town and the Ganhe Industrial Park in 2019.
RESUMEN
Background: Surgical nursing is a high-risk, high-pressure, and complex field. Nurses need extensive knowledge, skills, and abilities. Problem-Based Learning (PBL) and Simulation-Based Learning (SBL) are effective student-centered methods. Which method is better for surgical nurse training? More research is needed to determine the best approach for undergraduate surgical nurse education. Purpose: To compare the impact of PBL and SBL on undergraduate nursing students' performance and improve learning outcomes in surgical nursing education. Methods: We used a pretest/post-test design with 318 nursing undergraduates randomly assigned to two groups. Participants completed three progressive scenarios focused on surgical nursing cases. Experts blindly reviewed video recordings using the 70-item Korean Nurses' Core Competence Scale (KNCCS) to assess performance. The 13-item Satisfaction and Self-confidence in learning Scale (SSS) measured learning confidence and satisfaction. SBL participants also completed the 16-item Educational Practices in Simulation Scale (EPSS) and 20-item Simulation Design Scale (SDS). Results: The study found significant positive effects on both groups, with noticeable improvements in post-test, retention, and follow-up test results (P < 0.001). The SBL group showed higher competency levels in nurses (P < 0.001). The Cohen's d and effect size (r) for various skills were as follows: clinical performance (0.84767 and 6.39023), critical thinking (0.31017 and 0.15325), professional attitude (0.85868 and 0.39452), and communication skills (1.55149 and 0.61294). The satisfaction and self-confidence of nurses were higher in the SBL group (4.53±0.596; 4.47±0.611) compared to the PBL group (4.32±0.689; 4.25±0.632) in all dimensions of SSS (all P < 0.05). The SBL group also scored high in simulation design and EPSS. However, improvements are needed in fidelity, objectives, information, and students' expectations. Conclusion: SBL and PBL improve nurses' core competence, satisfaction, and self-confidence. SBL is superior. This study promotes student-centered education, enhancing surgical nursing professionals' quality and ensuring future patient safety.
RESUMEN
The implementation of AI assisted cancer detection systems in clinical environments has faced numerous hurdles, mainly because of the restricted explainability of their elemental mechanisms, even though such detection systems have proven to be highly effective. Medical practitioners are skeptical about adopting AI assisted diagnoses as due to the latter's inability to be transparent about decision making processes. In this respect, explainable artificial intelligence (XAI) has emerged to provide explanations for model predictions, thereby overcoming the computational black box problem associated with AI systems. In this particular research, the focal point has been the exploration of the Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) approaches which enable model prediction explanations. This study used an ensemble model consisting of three convolutional neural networks(CNN): InceptionV3, InceptionResNetV2 and VGG16, which was based on averaging techniques and by combining their respective predictions. These models were trained on the Kvasir dataset, which consists of pathological findings related to gastrointestinal cancer. An accuracy of 96.89% and F1-scores of 96.877% were attained by our ensemble model. Following the training of the ensemble model, we employed SHAP and LIME to analyze images from the three classes, aiming to provide explanations regarding the deterministic features influencing the model's predictions. The results obtained from this analysis demonstrated a positive and encouraging advancement in the exploration of XAI approaches, specifically in the context of gastrointestinal cancer detection within the healthcare domain.