关键词： Benign ovarian mass   IOTA simple rules   Level 2 ultrasound   Level 3 ultrasound   Ovarian malignancy   Pattern recognition  

摘要： Objective To compare the efficacy of the International Ovarian Tumor Analysis (IOTA) simple rules versus pattern recognition to differentiate between benign and malignant ovarian masses. Methods A prospective cross-sectional study conducted at Kasr El Aini Hospital, Cairo, between April 2016 and October 2018 of 396 women with ovarian masses measuring more than 5 cm who were candidates for surgery. All patients underwent two-dimensional transvaginal sonography: level 2 with IOTA simple rules followed by level 3 with pattern recognition. Patients subsequently underwent ovarian cystectomy or oophorectomy and the specimens were examined histopathologically. Accuracy was measured by comparing sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Results IOTA simple rules specified 44/50 cases as malignant and 220/242 as benign (sensitivity and specificity of 88.0% and 90.9%, respectively). Pattern recognition identified 83/94 cases as malignant and 281/302 as benign (sensitivity and specificity of 88.3% and 92.7%, respectively). No statistically significant difference in accuracy was found between the two methods. Conclusion IOTA simple rules are an effective tool for detecting ovarian malignancy when performed by nonexpert sonographers. When results are inconclusive, pattern recognition should be performed additionally by an expert sonographer. Clinical trials registration NCT02800031

关键词： Artificial neural network   Clustering   Electrofacies   Pattern recognition   Palaeozoic shale gas formation  

摘要： Unconventional oil and gas reservoirs from the lower Palaeozoic basin at the western slope of the East European Craton were taken into account in this study. The aim was to supply and improve standard well logs interpretation based on machine learning methods, especially ANNs. ANNs were used on standard well logging data, e.g. P-wave velocity, density, resistivity, neutron porosity, radioactivity and photoelectric factor. During the calculations, information about lithology or stratigraphy was not taken into account. We apply different methods of classification: cluster analysis, support vector machine and artificial neural network-Kohonen algorithm. We compare the results and analyse obtained electrofacies. Machine learning method-support vector machine SVM was used for classification. For the same data set, SVM algorithm application results were compared to the results of the Kohonen algorithm. The results were very similar. We obtained very good agreement of results. Kohonen algorithm (ANN) was used for pattern recognition and identification of electrofacies. Kohonen algorithm was also used for geological interpretation of well logs data. As a result of Kohonen algorithm application, groups corresponding to the gas-bearing intervals were found. Analysis showed diversification between gas-bearing formations and surrounding beds. It is also shown that internal diversification in gas-saturated beds is present. It is concluded that ANN appeared to be a useful and quick tool for preliminary classification of members and gas-saturated identification.

关键词： Comparative study on pattern recognition algorithms   Laboratory measurements   Predicting inpatient mortality risk  

摘要： Laboratory tests are a common and relatively cheap way to assess the general health status of patients. Various publications showed the potential of laboratory measurements for predicting inpatient mortality using statistical methodologies. However, these efforts are basically limited to the use of logistic regression models. In the present paper we use anonymized data from about 40,000 inpatient admissions to the Inselspital in Bern (Switzerland) to evaluate the potential of powerful pattern recognition algorithms employed for this particular risk prediction. In addition to the age and sex of the inpatients, a set of 33 laboratory measurements, frequently available at the Inselspital, are used as basic variables. In a large empirical evaluation we demonstrate that recent pattern recognition algorithms (such as random forests, gradient boosted trees or neural networks) outperform the more traditional approaches based on logistic regression. Moreover, we show how the predictions of the pattern recognition algorithms, which cannot be directly interpreted in general, can be calibrated to output a meaningful probabilistic risk score.

关键词： Geriatrics   Risk factors  

摘要： Objectives The aims of the present study were: (i) to analyze the associations of the time spent in daily activities (i.e., lie, recline, passive sit, active sit, stand, walk at slow pace, walk at average pace, walk at brisk pace, and other activities) with body mass index (BMI) and waist circumference (WC);and (ii) to examine how theoretically reallocating time between these daily activities is associated with BMI and WC. Methods The sample included 437 older adults (288 women), aged 65 to 92 years, participating in the IMPACT65+ study. The time in daily activities was assessed by the Intelligent Device for Energy Expenditure and Activity (IDEEA). BMI and WC were measured following standardized procedures. Associations of daily activities with BMI and WC were examined using linear regression models adjusting for potential confounders. Isotemporal substitution models were performed to estimate the theoretical effect of replacing one activity with another activity while holding total time constant. Results The time spent lying and reclining was associated with increased BMI and WC, while the time spent standing, walking at average pace, and walking at brisk pace was associated with decreased BMI and WC. Isotemporal substitution analyses revealed significant hypothetical reductions in BMI and WC when reallocating 15 min from lying or reclining to standing or walking at average pace. Moreover, replacing 15 min from any sedentary activity or light physical activity (except for walking at average pace) with an equal amount of time in walking at brisk pace was associated with lower BMI and WC. Conclusions This is the first study examining the activity specific and isotemporal associations of daily behaviors (considering body postures and movements) with overall and abdominal obesity in older people. The results could be used in the development of specific recommendations encouraging an active lifestyle in older people.

关键词： Cynoglossus semilaevis   Collectin-11 (CL-11)   Gene clone   Gene expression analysis   Bacterial infection   Recombinant protein   Antibacterial activity  

摘要： Collectin 11 (CL-11, also known as collectin kidney-1, CL-K1), a new member of the vertebrate C-type lectin superfamily, plays an important role in innate immunity as a pattern recognition molecule of the lectin complement pathway. However, little is known about CL-11 in teleosts. In the present study, a CL-11 homolog was identified and characterized from half-smooth tongue sole (Cynoglossus semilaevis) (designated as CsCL-11). The full-length cDNA of CsCL-11 is 1220 bp long and includes a 5'untranslated region (5'-UTR) of 180 bp, a 3'-UTR of 218 bp and an open reading frame (ORF) of 819 bp encoding 273 amino acids. Multiple sequence alignment revealed that the deduced CsCL-11 protein has the typical modular architecture (EPN and WTD) conserved throughout vertebrates, suggesting a conserved function of CsCL-11. Tissue expression profile analysis by quantitative real-time PCR (qRT-PCR) showed CsCL-il to be ubiquitously distributed in tissues and highly expressed in the ovary and liver. A pattern of significant upregulation of CsCL-11 expression was observed in the blood, spleen, head kidney and gill at 6 h, 12 h and 24 h after infection with Vibrio anguillarum, and western blotting showed that natural CsCL-11 protein levels in the blood were significantly increased after V. anguillarum infection. Moreover, by binding to various bacteria, recombinant CsCL-11 (rCsCL-11) expressed in HEK-293 T cells displayed strong antibacterial activity. Taken together, these results suggest that CsCL-11 is a unique C-type lectin that is likely involved in host defense against bacterial infection. To our knowledge, this is the first study on CL-11 in marine fish.

关键词： 算法语言  

ISBN: (数字)9787121358661 ISBN: (纸本)9787121358661

摘要： 本书分为14章，内容包括：模式识别概述、特征的选择与优化、模式相似性测度、基于概率统计的贝叶斯分类器设计、判别函数分类器设计、神经网络分类器设计、决策树分类器设计、粗糙集分类器设计、聚类分析等。

关键词： HDLSS asymptotics   kernel discriminant function   naive Bayes  

摘要： Kernel discriminant analysis translates the original classification problem into feature space and solves the problem with dimension and sample size interchanged. In high-dimension low sample size (HDLSS) settings, this reduces the 'dimension' to that of the sample size. For HDLSS two-class problems we modify Mika's kernel Fisher discriminant function which - in general - remains ill-posed even in a kernel setting;see Mika et al. (1999). We propose a kernel naive Bayes discriminant function and its smoothed version, using first- and second-degree polynomial kernels. For fixed sample size and increasing dimension, we present asymptotic expressions for the kernel discriminant functions, discriminant directions and for the error probability of our kernel discriminant functions. The theoretical calculations are complemented by simulations which show the convergence of the estimators to the population quantities as the dimension grows. We illustrate the performance of the new discriminant rules, which are easy to implement, on real HDLSS data. For such data, our results clearly demonstrate the superior performance of the new discriminant rules, and especially their smoothed versions, over Mika's kernel Fisher version, and typically also over the commonly used naive Bayes discriminant rule.

关键词： congou black tea   electronic tongue   type   grade   pattern recognition  

摘要： It is very difficult for humans to distinguish between two kinds of black tea obtained with similar processing technology. In this paper, an electronic tongue was used to discriminate samples of seven different grades of two types of Chinese Congou black tea. The type of black tea was identified by principal component analysis and discriminant analysis. The latter showed better results. The samples of the two types of black tea distributed on the two sides of the region graph were obtained from discriminant analysis, according to tea type. For grade discrimination, we determined grade prediction models for each tea type by partial least-squares analysis;the coefficients of determination of the prediction models were both above 0.95. Discriminant analysis separated each sample in region graph depending on its grade and displayed a classification accuracy of 98.20% by cross-validation. The back-propagation neural network showed that the grade prediction accuracy for all samples was 95.00%. Discriminant analysis could successfully distinguish tea types and grades. As a complement, the models of the biochemical components of tea and electronic tongue by support vector machine showed good prediction results. Therefore, the electronic tongue is a useful tool for Congou black tea classification.

关键词： 模式识别  

ISBN: (纸本)9787030639363

摘要： 本书从计算机科学的角度研究金融数据中的规则，力图发现和挖掘出海量金融数据中的隐藏信息。书中从计算机科学的模式识别理论和相关技术出发，利用深度信念网络进行金融异常检测，去发现隐藏在金融交易后面的那些欺诈行为；利用非负矩阵分解去研究股指的波动，进而预判证券市场的震荡；把卷积神经网络改造为一个信用评分模型，为信贷提供决策支持；通过决策树得到股市预测模型的前提，然后引入情感数据来修正预测结果；建立以股票技术指标为基础，股民情绪分析为辅助的方法较为准确地对股市走势进行预测。