教学课程资源库 更多>>

关键词： Breast cancer   Data mining   Principal component analysis   Random forest tree   Blood routine analysis  

摘要： Breast cancer is the most common cancer in women occurring worldwide. Some of the procedures used to diagnose breast cancer are mammogram, breast ultrasound, biopsy, breast magnetic resonance imaging, and blood tests such as complete blood count. Detecting breast cancer at an early stage plays an important role in diagnostic and curative procedures. This paper aims to develop a predictive model for detecting the breast cancer using blood samples data containing age, body mass index (BMI), glucose, insulin, homeostasis model assessment (HOMA), leptin, adiponectin, resistin, and chemokine monocyte chemoattractant protein 1 (MCP-1).The two main challenges encountered in this process are identification of biomarkers and the precision of disease prediction accuracy. The proposed methodology employs principal component analysis in a peculiar approach followed by random forest tree prediction model to discriminate between healthy and breast cancer patients. This approach extracts high communalities, a linear combination of input attributes in a systematic procedure as principal axis elements. The iteratively extracted principal axis elements combined with minimum number of input attributes are able to predict the disease with higher accuracy of classification with increased sensitivity and specificity score. The results proved that the proposed approach generates a higher predictor performance than the previous reported results by opting relevant extracted principal axis elements and attributes that commend the classifier with increased performance measures.

关键词： Bullying   Perpetration   Victimization   Cyberbullying   Latent class analysis   Psychosomatic symptoms  

摘要： The aim of the study was to investigate the pattern of traditional- and cyberbullying, and fighting involvement and identify its most important correlates in a nationally representative sample. We analyzed the data of Hungarian 11-18-year-old adolescents in the framework of the Health Behaviour in School-aged Children Study. A latent class analysis was performed first and afterwards a multinomial logistic regression analysis to examine factors explaining class membership. Four latent classes were identified: "high probability involvement in all forms of violence";"low involvement in any forms of violence";"predominantly involved in traditional bullying and fighting";"high engagement in online victimization". As no clear victim or perpetrator group was identified, a high overlap between these violence involvement statuses is reinforced.

关键词： Uncertainty   Feature extraction   Histograms   Training   Image segmentation   Histopathology   Entropy   Interpretability   Sample Selection   Self-supervised   Lung disease classification   Histopathology segmentation  

摘要： In supervised learning for medical image analysis, sample selection methodologies are fundamental to attain optimum system performance promptly and with minimal expert interactions (e.g. label querying in an active learning setup). In this article we propose a novel sample selection methodology based on deep features leveraging information contained in interpretability saliency maps. In the absence of ground truth labels for informative samples, we use a novel self supervised learning based approach for training a classifier that learns to identify the most informative sample in a given batch of images. We demonstrate the benefits of the proposed approach, termed Interpretability-Driven Sample Selection (IDEAL), in an active learning setup aimed at lung disease classification and histopathology image segmentation. We analyze three different approaches to determine sample informativeness from interpretability saliency maps: (i) an observational model stemming from findings on previous uncertainty-based sample selection approaches, (ii) a radiomics-based model, and (iii) a novel data-driven self-supervised approach. We compare IDEAL to other baselines using the publicly available NIH chest X-ray dataset for lung disease classification, and a public histopathology segmentation dataset (GLaS), demonstrating the potential of using interpretability information for sample selection in active learning systems. Results show our proposed self supervised approach outperforms other approaches in selecting informative samples leading to state of the art performance with fewer samples.

关键词： multilevel MIMIC   model misspecification   fit indices  

摘要： This study examined the impact of omitting covariates interaction effect on parameter estimates in multilevel multiple-indicator multiple-cause models as well as the sensitivity of fit indices to model misspecification when the between-level, within-level, or cross-level interaction effect was left out in the models. The parameter estimates produced in the correct and the misspecified models were compared under varying conditions of cluster number, cluster size, intraclass correlation, and the magnitude of the interaction effect in the population model. Results showed that the two main effects were overestimated by approximately half of the size of the interaction effect, and the between-level factor mean was underestimated. None of comparative fit index, Tucker-Lewis index, root mean square error of approximation, and standardized root mean square residual was sensitive to the omission of the interaction effect. The sensitivity of information criteria varied depending majorly on the magnitude of the omitted interaction, as well as the location of the interaction (i.e., at the between level, within level, or cross level). Implications and recommendations based on the findings were discussed.

关键词： Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry   a shareable link is not currently available for this article.Copy to clipboard Provided by the Springer Nature SharedIt content-sharing initiative  

关键词： Saturation   Quantum dots   Lipids   Peptides and proteins   Nuclear magnetic resonance spectroscopy  

摘要： We probed the "dark"state involved in the protein-quantum dot (QD) interaction using a relaxation-based solution nuclear magnetic resonance (NMR) approach. We examined the dynamics and exchange kinetics of the ubiquitin-CdTe model system, which undergoes a fast exchange in the transverse relaxation time scale. We applied the recently developed dark-state exchange saturation transfer (DEST), lifetime line broadening (Delta R-2), and exchange-induced chemical shift (delta(ex)) solution NMR techniques to obtain a residue-specific binding behavior of the protein on the QD surface. The variation in the estimated N-15-R-2(bound) values clearly shows the dynamic nature of bound Ub. Upon mapping the amino acid residues showing a faster relaxation rate on the electrostatic potential surface of the protein, we have determined that the interaction is preferably electrostatic, and the amino acid residues involved in binding lie on the positively charged surface of the protein. We believe that our experimental approach should provide more in-depth knowledge to engineer new hybrid protein-QD systems in the future.

关键词： PLS-DA   LDA   SIMCA   Authentication   Food control   Breed purity   Feeding regime  

摘要： The potential of Near Infrared Spectroscopy combining different spectral treatments and classification models was assessed for the classification of individual pre-sliced Iberian dry-cured loin packaged under modified atmosphere packaging (MAP) into three official commercial categories (which involve the breed purity and production system) according to the current Iberian Quality Standard (Black, Red and White) and for the assignment to the shelf-life time (0, 4, 8 and 12 months). External validation results provided acceptable results, with up to 100% of samples correctly assigned to Black and White official commercial category and into all storage times. Actually the 100% assignments were obtained using more than one approach (SIMCA and LDA for commercial categories and PLS-DA, SIMCA and LDA for storage times). These results might contribute to support the on-line control of authenticity of official commercial category and to facilitate the monitoring of the quality of pre-package dry-cured products throughout the shelf-life prediction.

关键词： 生产检测检验   矿山   安全生产  

摘要： 随着现代社会的不断发展,国家生产水平要求也越来越高,矿山的安全生产也成了越来越多的人关注的话题,为了保障矿山生产生活工作的顺利实施,我国也为矿山的生产建设投入了非常大的精力,为了保证工程的建设进程,以及工程的监管力度,国家投入了技术上的支持和鼓励。目前为止,我国的对于矿山的生产检测制度得到了非常广泛的应用,生产检测技术的普及标志着我国矿山安全方面有了非常大的保障,本文就生产检测检验在矿山安全生产的过程中的作用进行了分析和研究。

关键词： 血常规检验   巨幼细胞贫血   缺铁性贫血   健康体检  

摘要： 探讨血常规检验在贫血患者临床诊断中的作用。方法:选择我院2020年1~12月收治的巨幼细胞贫血和缺铁性贫血患者各50例作为研究对象,选择同期的50例健康体检者作为对照组,对比三组观察对象的血常规检查情况。结果:缺铁性贫血患者的血红蛋白、平均红细胞体积、红细胞、平均红细胞血红蛋白含量水平均明显低于健康对照组,巨幼细胞贫血患者的血红蛋白、红细胞水平均明显低于健康对照组,而平均红细胞体积、平均红细胞血红蛋白含量水平却高于健康对照组。两种贫血患者的红细胞体积分布宽度则明显高于健康对照组(P<0.05)。结论:贫血患者的血常规检查结果存在明显的异常表现,因而可以将血常规检查结果作为贫血诊断和治疗的依据,推广应用价值较高。

关键词： 产品质量检测   市场监管   作用  

摘要： 产品质量直接关系到我国的社会稳定发展和经济的可持续发展,是国家重要的民生问题。在我国经济发展的新形势下,产品的质量检验是我国市场监督管理部门开展质量监督工作的重要内容,也是最为基础的内容,控制产品质量不仅能维持市场平衡,实现市场的稳定发展,也是当前经济发展建设的必然要求。