Search

Local Outlier Factor (LOF) outlier detecting algorithm has good accuracy in detecting global and local outliers. However, the algorithm needs to traverse the entire dataset when calculating the local outlier factor of each data point, which adds extra time overhead and makes the algorithm execution inefficient. In addition, if the K-distance neighborhood of an outlier point P contains some outliers that are incorrectly judged by the algorithm as normal points, then P may be misidentified as normal point. To solve the above problems, this paper proposes a Neighbor Entropy Local Outlier Factor (NELOF) outlier detecting algorithm. Firstly, we improve the Self-Organizing Feature Map (SOFM) algorithm and use the optimized SOFM clustering algorithm to cluster the dataset. Therefore, the calculation of each data point's local outlier factor only needs to be performed inside the small cluster. Secondly, this paper replaces the K-distance neighborhood with relative K-distance neighborhood and utilizes the entropy of relative K neighborhood to redefine the local outlier factor, which improves the accuracy of outlier detection. Experiments results confirm that our optimized SOFM algorithm can avoid the random selection of neurons, and improve clustering effect of traditional SOFM algorithm. In addition, the proposed NELOF algorithm outperforms LOF algorithm in both accuracy and execution time of outlier detection.

Electronic medical record (EMR) text word segmentation is the basis of natural language processing in medicine. Due to the characteristics of EMR, such as strong specialization, high cost of annotation, special writing style and sustained growth of terminology, the current Chinese word segmentation (CWS) methods cannot fully meet the requirements of the application of EMR. In order to solve this problem, an EMR word segmentation model based on Graph Neural Network (GNN), bidirectional Long Short-Term Memory network (Bi-LSTM) and conditional random field (CRF) is designed in this paper to improve the segmentation effect and reduce the dependence on data set. In the model, GNN based on the domain lexicon is used to learn the local composition features, Bi-LSTM is used to capture the long-term dependence and context sequence information, and CRF is used to obtain the optimal annotation sequence based on the sentence level label information. Through multi-feature interaction, the ambiguity resolution and new word recognition in the EMR word segmentation are effectively carried out. Compared with CWS tools such as Jieba and Pkuseg, as well as baseline models and state-of-the-art methods, the precision and recall rate of the model in this paper have been significantly improved.

Topic models, such as probabilistic latent semantic analysis (PLSA) and latent Dirichlet allocation (LDA), have shown impressive success in many fields. Recently, multi-view learning via probabilistic latent semantic analysis (MVPLSA), is also designed for multi-view topic modeling. These approaches are instances of generative model, whereas they all ignore the manifold structure of data distribution, which is generally useful for preserving the nonlinear information. In this paper, we propose a novel multiple graph regularized generative model to exploit the manifold structure in multiple views. Specifically, we construct a nearest neighbor graph for each view to encode its corresponding manifold information. A multiple graph ensemble regularization framework is proposed to learn the optimal intrinsic manifold. Then, the manifold regularization term is incorporated into a multi-view topic model, resulting in a unified objective function. The solutions are derived based on the Expectation Maximization optimization framework. Experimental results on real-world multi-view data sets demonstrate the effectiveness of our approach.

With the development of the city, the problem of wastewater is becoming more and more serious. In wastewater treatment, membrane treatment technology is becoming more and more mature. In membrane treatment technology, the SDI value of filtered water is a key indicator to show the treatment capacity, which has a great relationship with the turbidity of sewage. In this paper, the relationship between turbidity and SDI of effluent was studied in the same membrane treatment.

The oncogenic STAT3 signaling pathway is emerging as a promising target for the treatment of multiple myeloma (MM). In the present study, we identified a novel STAT3 inhibitor SC99 in a target-based high throughput screen. SC99 inhibited JAK2-STAT3 activation but had no effects on other transcription factors such as NF-κB, and kinases such as AKT, ERK, and c-Src that are in association with STAT3 signaling pathway. Furthermore, SC99 downregulated the expression of STAT3-modulated genes, including Bcl-2, Bcl-xL, VEGF, cyclin D2, and E2F-1. By inhibiting the STAT3 signaling, SC99 induced MM cell apoptosis which could be partly abolished by the ectopic expression of STAT3. Furthermore, SC99 displayed potent anti-MM activity in two independent MM xenograft models in nude mice. Oral administration of SC99 led to marked decrease of tumor growth within 10 days at a daily dosage of 30 mg/kg, but did not raise toxic effects. Taken together, this study identified a novel oral JAK2/STAT3 inhibitor that could be developed as an anti-myeloma agent.

An increasing number of reviews from the customers have been available online. Thus, sentiment classification for such reviews has attracted more and more attention from the natural language processing (NLP) community. Related literature has shown that sentiment analysis can benefit from Deep Belief Networks (DBN). However, determining the structure of the deep network and improving its performance still remains an open question. In this paper, we propose a sophisticated algorithm based on fuzzy mathematics and genetic algorithm, called evolutionary fuzzy deep belief networks with incremental rules (EFDBNI). We evaluate our proposal using empirical data sets that are dedicated for sentiment classification. The results show that EFDBNI brings out significant improvement over existing methods.

Actors (e.g., people, organizations and nations) of online social networks often express different opinions toward opinion targets (e.g., products, events and political figures). Extracting and visualizing the distributions of different opinions among actors facilitate policy-makers (e.g., business managers and government officials) to develop informed decisions promptly. In this paper, by extending the notion of signed networks, we first provide a formal definition of opinion networks which are networks of actors who hold potentially different opinions against specific targets. Another main contribution of our research is the development of a visualization method called OpinionRings to infer and visualize the actual and the potential opinions of different groups of actors. In particular, the proposed OpinionRings method leverages three concentric rings with various colors and widths to highlight different groups of actors and their opinions. One unique feature of the OpinionRings method is that the inclination of an actor, who originally holds a neutral opinion polarity, to adopt a positive or negative opinion polarity can be estimated according to the color of the actor and the distance to other actors with known opinion polarities. A series of objective quantitative experiments and subjective user-based evaluation show that the proposed OpinionRings method significantly outperforms the traditional visualization methods in terms of cohesiveness of displays, informativeness of visualized contents, and inference power of the visualization scheme. The practical implication of our research is that business managers or government officials can apply our proposed computational method to extract and visualize valuable social intelligence from online social networks to facilitate their decision-making processes.

Heterogeneous data sources and multi-label are two important characteristics of protein function prediction. They describe protein data from two different aspects. However, it is of considerable challenge to integrate multiple data sources and multi-label simultaneously for predicting protein functions, especially when there are only a limited number of labeled proteins. In this paper, we propose a generative model with hypergraph regularizers algorithm, called GMHR, for predicting proteins with multiple functions. The GMHR algorithm integrates all data sources that are available, including protein attribute features, interaction networks, label correlations, and unlabeled data. Experimental results on the real-world datasets predicting the functions of proteins demonstrate the superiority of our proposed method compared with the state-of-the-art baselines.

A representative sample of a social network is essential for many internet services that rely on accurate analysis. A good sampling method for social network should be able to generate small sample network with similar structures and distributions as its original network. In this paper, a sampling algorithm based on graph partition, sampling based on graph partition (SGP), is proposed to sample social networks. SGP firstly partitions the original network into several sub-networks, and then samples in each sub-network evenly. This procedure enables SGP to effectively maintain the topological similarity and community structure similarity between the sampled network and its original network. Finally, we evaluate SGP on several well-known datasets. The experimental results show that SGP method outperforms seven state-of-the-art methods.

Purpose: To investigate the safety and potential pharmacokinetic (PK) interaction between retagliptin, a selective inhibitor of dipeptidyl peptidase-4, and metformin in healthy subjects. Methods: In open-label, randomized, three-period, three-treatment crossover studies, 15 subjects received 100 mg retagliptin, 1500 mg metformin or the combination. The area under the curve from the time of dosing to infinity (AUC inf ) and the maximum observed plasma concentration (C max ) of each drug were measured. Results: The combination of retagliptin and metformin did not result in clinically significant alterations in the pharmacokinetics of SP2086 or metformin. The AUC inf and C max of retagliptin co-administered with metformin were 16.49 and 25.88 % higher than for retagliptin alone, respectively, while the AUC inf of metformin co-administered with retagliptin was 22.06 % higher than for metformin alone. The 90 % confidence interval of both glucose-lowering drugs’ AUC inf and C max of the geometric mean ratios of SP2086 + metformin fell within the pre-specified interval of 80 - 125 %. No laboratory adverse conditions occurred during the study. Retagliptin appeared generally safe and well-tolerated when administered alone or in combination with metformin. Conclusion: The results may be an indication that no dose adjustments are likely to be required when retagliptin is given in combination with metformin.

Deriving a representative sample from a big social network is essential for many Internet services that rely on accurate analysis of big social data. A good sampling method for social network should be able to generate small sample networks with similar structures as original big network. In this paper, we propose SGP, a new big social network sampling algorithm based on graph partition. In SGP, original network is firstly partitioned into several sub-networks that will be sampled evenly. This procedure enables SGP to effectively maintain the topological similarity and community structure similarity between the sampled network and its original network. We have evaluated SGP on several well-known data sets. The experimental results show that SGP outperforms six state-of-the-art methods.

In agricultural colleges, teaching method of multivariate statistical analysis can't copy the traditional teaching mode in science and engineering colleges. The author combined with years of teaching experience and the characteristics of agricultural science, discusses the teaching reform of multivariate statistical course in agricultural colleges, included optimize the course structure, reform the teaching content, reform teaching method, strengthen the experiment teaching, and reform assessment method. KEYWORD: Multivariate statistical analysis; agricultural science; teaching method; experiment teaching

With the recent explosive growth of e-commerce and online communication, a new genre of text, short text, has been extensively applied in many areas. So many researches focus on short text mining. It is a challenge to classify the short text owing to its natural characters, such as sparseness, large-scale, immediacy, non-standardization. It is difficult for traditional methods to deal with short text classification mainly because too limited words in short text cannot represent the feature space and the relationship between words and documents. Several researches and reviews on text classification are shown in recent times. However, only a few of researches focus on short text classification. This paper discusses the characters of short text and the difficulty of short text classification. Then we introduce the existing popular works on short text classifiers and models, including short text classification using sematic analysis, semi-supervised short text classification, ensemble short text classification, and real-time classification. The evaluations of short text classification are analyzed in our paper. Finally we summarize the existing classification technology and prospect for development trend of short text classification.

The key idea of active learning is that it can perform better with less data or costs if a machine learner is allowed to choose the data actively. However, the relation between labeling cost and model performance is seldom studied in the literature. In this paper, we thoroughly study this problem and give a criterion called as cost-performance to balance this relation. Based on the criterion, a cost-driven active SSC algorithm is proposed, which can stop the active process automatically. Empirical results show that our method outperforms active SVM and co-EMT.

A popular solution to dealing with large-scale social networks is to derive a representative sample from a social network. This sample is expected to represent the original social network well such that the sampled network can be used for simulations and analysis. In this paper, we propose a new social network sampling algorithm based on the Temperature Conduction model. Our sampling approach is able to effectively maintain the topological similarity between the sampled network and its original network. We have evaluated our algorithm on several well-known data sets. The experimental results show that our algorithm outperforms the state-of-the-art methods.

Our previous study indicated that the antidepressant amitriptyline showed potent activity in inducing multiple myeloma (MM) cell apoptosis in vitro. In the present study, we further showed that amitriptyline was active against MM in vivo. Oral administration of amitriptyline significantly decreased tumor growth in two MM xenograft models derived from murine and human MM cells, respectively. Molecular pathological analysis showed that amitriptyline induced p53, activated caspase-3, and decreased antiapoptotic Bcl-2 and Mcl-1 in tumor tissues. Amitriptyline also significantly extended the survival period of MM-tumor-bearing mice. In the in-vitro study, we also found that amitriptyline synergistically induced MM cell apoptosis in combination with bortezomib, the most potent anti-MM agent. Because amitriptyline has been proposed to control cancer-associated pain, depression, and anxiety, proper application of amitriptyline will benefit MM patients.

We describe an area-adaptive multi-level layout for visualising social networks. This area-adaptive layout can visualise social networks according to the display area and community structure, which could reasonably utilise the display area and enhance the community features. The whole process consists of two parts: graph multi-layered compression and top-down multi-level layout. The multi-layered compression process groups vertices to form clusters and then abstracts the clusters as new vertices to define a new graph and is repeated until the graph size falls below some threshold. Based on the compressed graph, we optimise the display area to top-down positions all vertices. We have evaluated our layout on several well-known data sets. The experimental results show that our layout outperforms the state-of-the-art methods.

LTE is the newly emerging telecommunication mode. Owing to its multiple antennas and high frequency radiation characteristics, its electromagnetic radiation and SAR value are different with terminals operating with other modes. Simulation model of LTE terminal with MIMO antenna is constructed in this paper. Radiation and SAR value of different telecommunication modes are compared with simulation and test. During the simulation, the input power for different mode is set the same to obtain meaningful comparison. On the other hand, terminals are operating with their maximum emission power in the SAR test according to the specification. It can be seen that LTE terminals has the highest SAR although it has low emission power. It gives some insight into analysis of telecommunication terminals operated in different modes.

Based on the motion characteristics of double half-revolution mechanism, a new-style wheel-legged lunar rover was proposed. In order to evaluate its maneuvering performance, the performance experiment of single wheel-legged mechanism is needed. To simulate the loading conditions of single wheel-legged mechanism when the lunar rover is walking in flat ground, climbing up a slope or walking sideways in a slope, this paper analyzed their statics under the above three conditions, and set up their force models respectively. Using MATLAB software, the pressure loads which applied on each wheel-legged mechanism under the above three conditions are simulated, and their curves are given. The results provide a loading reference for the performance experiment of single wheel-legged mechanism.

Toll-like receptors (TLRs) are pattern-recognition receptors and have a critical role in both innate and adaptive responses to tissue injury. Our previous study showed that wound healing was impaired in TLR3-deficient mice. In this study, we investigated the capacity of the TLR3 agonist polyriboinosinic-polyribocytidylic acid (poly(I:C)) to promote the healing of skin wounds in humans and mice. We found that topical application with poly(I:C) accelerated the closure of wounds in patients with laser plastic surgery. In a mouse model, topical application of poly(I:C) markedly enhanced re-epithelialization, granulation, and neovascularization required for wound closure. Further studies revealed that poly(I:C) treatment resulted in enhanced recruitment of neutrophils and macrophages in association with upregulation of a chemokine, macrophage inflammatory protein-2 (MIP-2/CXCL2), in the wounds. The effect of poly(I:C) was abolished in TLR3-deficient mice or by treatment with MIP-2/CXCL2-neutralizing antibodies. These results suggest a potential therapeutic value of the TLR3 activator poly(I:C) for wound healing.