POTEE (POTE ankyrin domain family, member E) is a newly identified cancer-testis antigen that has been found to be expressed in a wide variety of human cancers including cancers of the colon, ...prostate, lung, breast, ovary, and pancreas.
To measure the serum levels of POTEE in patients with non-small-cell lung cancer (NSCLC) and to explore the clinical significance of POTEE in NSCLC.
104 NSCLC patients, 66 benign lung disease patients and 80 healthy volunteers were enrolled in this study from May 2013 to February 2014. Serum POTEE levels were measured using enzyme-linked immunosorbent assay (ELISA). Numerical variables were recorded as means ± standard deviation (SD) and analyzed by independent t tests. Categorical variables were calculated as rates and were analyzed using a χ2 test or Fisher's exact test. Survival curves were estimated and compared using the Kaplan-Meier method and log-rank tests.
Serum POTEE levels were significantly higher in NSCLC patients than in benign lung disease patients and healthy controls (mean ± SD pg/ml, 324.38± 13.84 vs. 156.93 ± 17.38 and 139.09 ± 15.80, P<0.001) and were significantly correlated with TNM stage. Survival analysis revealed that patients with low serum POTEE had longer progression-free survival (PFS) than those with high serum POTEE (P=0.021). Cox multivariate analysis indicated that POTEE was an independent prognostic factor of progression-free survival (P =0.009, hazard ratio, 2.440).
Serum POTEE level in NSCLC patients is associated with TNM stage and is a potential prognostic factor.
Abstract Whether Cell block (CB) samples are applicable to detect anaplastic lymphoma kinase (ALK), c-ros oncogene 1 (ROS1) and ret proto-oncogene (RET) fusion genes in lung adenocarcinoma is still ...unknown. In this study, 108 cytological samples that contained lung adenocarcinoma cells were collected, and made into CB. The CB samples all contained at least 30% lung adenocarcinoma cells. In these patients, 48 harbored EGFR mutation. Among the 50 EGFR wild type patients who detected fusion genes, 14 carried EML4-ALK fusion (28%), 2 had TPM3-ROS1 fusion (4%), and 3 harbored KIF5B-RET fusion (6%). No double fusions were found in one sample. Patients with fusion genes were younger than those without fusion genes (p = 0.032), but no significant difference was found in sex and smoking status (p > 0.05). In the thirty-five patients who received first-line chemotherapy, patients with fusion gene positive had disease control rate (DCR) (72.7% VS 50%, p > 0.05) and objective response rate (ORR) (9.1% VS 4.2%, p > 0.05) compared with those having fusion gene negative. The median progression free survival (mPFS) were 4.0 and 2.7 months in patients harbored fusion mutations and wild type, respectively (p > 0.05). We conclude that CB samples could be used to detect ALK, ROS1 and RET fusions in NSCLC. The frequency distribution of three fusion genes is higher in lung adenocarcinoma with wild-type EGFR, compared with unselected NSCLC patient population. Patients with fusion genes positive are younger than those with fusion gene negative, but they had no significantly different PFS in first-line chemotherapy.
•Extant information theoretic feature selection methods are reformulated and analyzed.•Higher-order feature inner correlations are approximated by parametric pairwise analysis.•Effective lower bounds ...for higher-order feature inner correlations are proposed.•Salient and interpretable features can be obtained by the proposed method.
Feature selection is an important preprocessing and interpretable method in the fields where big data plays an essential role. In this paper, we first reformulate and analyze some representative information theoretic feature selection methods from the perspective of approximations of feature inner correlations, and indicate that many of these methods cannot guarantee any theoretical bounds of feature inner correlations. We thus introduce two lower bounds that have very simple forms for feature redundancy and complementarity, and verify that they are closer to the optima than the existing lower bounds applied by some state-of-the-art information theoretic methods. A simple and effective feature selection method based on the proposed lower bounds is then proposed and empirically verified with a wide scope of real-world datasets. The experimental results show that the proposed method achieves promising improvement on feature selection, indicating the effectiveness of the feature criterion consisting of the proposed lower bounds of redundancy and complementarity.
Feature selection is one of the core issues in designing pattern recognition and machine learning systems, and has attracted considerable attention in the literature. In this paper, a new feature ...subset selection algorithm with conditional mutual information is proposed, which firstly guarantees to find a subset of which the mutual information with the class is the same as that of the original set of features, and then eliminates potential redundant features from the view of minimal information loss based on the cumulate conditional mutual information minimization criterion. From the reliability point of view, this criterion can also abate the disturbance caused by sample insufficiency in conditional mutual information estimation. In addition, a fast implementation of conditional mutual information estimation is proposed and used to tackle the computationally intractable problem. Empirical results verify that our algorithm is efficient and achieves better accuracy than several representative feature selection algorithms for three typical classifiers on various datasets.
Probabilistic hesitant fuzzy sets (PHFSs) add the probability value corresponding to each degree of membership on the basis of hesitant fuzzy sets, so as to express the initial decision information ...given by experts more accurately and comprehensively. In this article, we mainly study how to integrate large-scare probabilistic hesitant fuzzy information more efficiently. We first discuss some basic operation laws of probabilistic hesitant fuzzy numbers, based on which the concepts of continuous PHFSs and continuous probabilistic hesitant fuzzy functions (c-PHFFs) are defined. They are the main objects of our research. We further explore definite integrals of the c-PHFFs and their related properties. They have direct and powerful applications in continuous probabilistic hesitant fuzzy environments, and lay the foundation for subsequent theoretical analysis. Based on the weight density function, we finally get the weighted-integral operator of continuous probabilistic hesitant fuzzy information. Then, some important properties of this integration operator are studied, including normalization, monotonicity, boundedness, etc. We are also devoted to revealing the inner connection between the continuous probabilistic hesitant fuzzy weighted-integral operator and the probabilistic hesitant fuzzy weighted averaging operator, the latter is usually used when dealing with discrete information. At last, we state why it is necessary to introduce a novel aggregation method based on continuous probabilistic hesitant fuzzy definite integrals, and in turn provide an application of the proposed method to prove its validity and rationality.
•A deep learning method is proposed for autonomous ship-oriented small ship detection.•A modified Generative Adversarial Network is applied for training data augmentation.•An improved YOLO v2 ...algorithm is used for small ship detection.•Extensive experiments are conducted to show the effectiveness of the proposed method.
Small ship detection is an important topic in autonomous ship technology and plays an essential role in shipping safety. Since traditional object detection techniques based on the shipborne radar are not qualified for the task of near and small ship detection, deep learning-based image recognition methods based on video surveillance systems can be naturally utilized on autonomous vessels to effectively detect near and small ships. However, a limited number of real-world samples of small ships may fail to train a learning method that can accurately detect small ships in most cases. To address this, a novel hybrid deep learning method that combines a modified Generative Adversarial Network (GAN) and a Convolutional Neural Network (CNN)-based detection approach is proposed for small ship detection. Specifically, a Gaussian Mixture Wasserstein GAN with Gradient Penalty is utilized to first directly generate sufficient informative artificial samples of small ships based on the zero-sum game between a generator and a discriminator, and then an improved CNN-based real-time detection method is trained on both the original and the generated data for accurate small ship detection. Experimental results show that the proposed deep learning method (a) is competent to generate sufficient informative small ship samples and (b) can obtain significantly improved and robust results of small ship detection. The results also indicate that the proposed method can be effectively applied to ensuring autonomous ship safety.
In order to rank all decision making units (DMUs) on the same basis, this paper proposes a multiobjective programming (MOP) model based on a compensatory data envelopment analysis (DEA) model to ...derive a common set of weights that can be used for the full ranking of all DMUs. We first revisit a compensatory DEA model for ranking all units, point out the existing problem for solving the model, and present an improved algorithm for which an approximate global optimal solution of the model can be obtained by solving a sequence of linear programming. Then, we applied the key idea of the compensatory DEA model to develop the MOP model in which the objectives are to simultaneously maximize all common weights under constraints that the sum of efficiency values of all DMUs is equal to unity and the sum of all common weights is also equal to unity. In order to solve the MOP model, we transform it into a single objective programming (SOP) model using a fuzzy programming method and solve the SOP model using the proposed approximation algorithm. To illustrate the ranking method using the proposed method, two numerical examples are solved.
Short-term traffic flow prediction is a core branch of intelligent traffic systems (ITS) and plays an important role in traffic management. The graph convolution network (GCN) is widely used in ...traffic prediction models to efficiently handle the graphical structural data of road networks. However, the influence weights among different road sections are usually distinct in real life and are difficult to analyze manually. The traditional GCN mechanism, which relies on a manually set adjacency matrix, is unable to dynamically learn such spatial patterns during training. To address this drawback, this study proposes a novel location graph convolutional network (location-GCN). The location-GCN solves this problem by adding a new learnable matrix to the GCN mechanism, using the absolute value of this matrix to represent the distinct influence levels among different nodes. Subsequently, long short-term memory (LSTM) is employed in the proposed traffic prediction model. Moreover, trigonometric function encoding was used in this study to enable the short-term input sequence to convey long-term periodic information. Finally, the proposed model was compared with the baseline models and evaluated on two real-world traffic flow datasets. The results show that our model is more accurate and robust than the other representative traffic prediction models.
•Predicting users’ openness from text using a topic-emotion-openness mixture model.•Predicting openness in a data-driven manner via Maximum-A-Posteriori estimation.•Topic and emotional intensity are ...identified from text for openness prediction.
Openness to experience, one of the essential individual characteristics, is of great theoretical and practical value in psychological and behavioral domains. Although typical machine learning methods can be utilized to extract individuals’ openness to experience from the large-scale textual data like the unprecedented massive user generated contents (UGCs), they are often regarded as “black boxes” because they are unable to provide knowledge about the influential factors of openness to experience. This is of no help for us to investigate why a particular level of openness to experience is predicted for an individual. In addition, high dimensionality and sparseness of textual data impairs the performance of the typical machine learning method in extracting individuals’ characteristics. In this study, we propose an interpretable data-driven mixture method for qualified modeling and predicting individuals’ openness to experience. The proposed method extends the latent Dirichlet allocation (LDA) to overcome the problem of high dimensionality and sparseness in modeling the textual data, and can effectively extract two influential variables, namely, the topic preference and the expressed emotional intensity, to make an accurate prediction and to help us fully understand individuals’ openness to experience lurking in the textual data. Experimental results indicate the effectiveness of the proposed method in drawing individuals’ openness to experience, and also validate the predictive ability of topic preference and expressed emotional intensity which are indicated in psychological literature to be influential factors of openness to experience.
With the increasing information transparency of business operations' environmental influences, public opinion plays an important role in the green technology adoption of enterprises. Identifying the ...diffusion path of public opinion involving the process of enterprise green technology adoption is a significant task to verify the triggering mechanisms among the external factors and internal ones. An appropriate framework may help to clarify how the sustainability elements of public opinion are introduced to green technology adoption. Therefore, an interpretive structural-modeling (ISM)-based approach was applied to explore the basic transmission process and path of public opinion involving green technology adoption in enterprise practices. From the pressure of public opinion to the stakeholders involved, as well as the corresponding operational environmental activities, this study explored the psychological behavior of internal and external stakeholders and tried to clarify what the driving elements of green technology adoption are and how they relate to each other. Based on the field data collected from practitioners with Chinese contextual experience, the driving elements of the enablers of green technology adoption by enterprises were identified, and the fundamental triggering mechanisms of the public opinion pressure among them were analyzed. Thereafter, the influence of internal and external stakeholders involving green technology adoption and their corresponding behaviors under the pressure of public opinion were determined and expounded comprehensively, which illustrates the diffusion path of how public opinion influences the operational green technology adoption. This may narrow the gap between public environmental expectation and business operations. Finally, the managerial implications and the limitations of this study were concluded. The explanatory corresponding ISM model established in this study enriches the literature on the theoretical research of the mechanisms of green technology adoption.