Hybrid k -Nearest Neighbor Classifier Zhiwen Yu; Hantao Chen; Jiming Liu ...
IEEE transactions on cybernetics,
2016-June, 2016-06-00, 2016-6-00, 20160601, Volume:
46, Issue:
6
Journal Article
Peer reviewed
Conventional k-nearest neighbor (KNN) classification approaches have several limitations when dealing with some problems caused by the special datasets, such as the sparse problem, the imbalance ...problem, and the noise problem. In this paper, we first perform a brief survey on the recent progress of the KNN classification approaches. Then, the hybrid KNN (HBKNN) classification approach, which takes into account the local and global information of the query sample, is designed to address the problems raised from the special datasets. In the following, the random subspace ensemble framework based on HBKNN (RS-HBKNN) classifier is proposed to perform classification on the datasets with noisy attributes in the high-dimensional space. Finally, the nonparametric tests are proposed to be adopted to compare the proposed method with other classification approaches over multiple datasets. The experiments on the real-world datasets from the Knowledge Extraction based on Evolutionary Learning dataset repository demonstrate that RS-HBKNN works well on real datasets, and outperforms most of the state-of-the-art classification approaches.
There is a strong demand for novel native peptide motifs for post-synthetic modifications of peptides without pre-installation and subsequent removal of directing groups. Herein, we report an ...efficient method for peptide late-stage C(sp
3
)-H arylations assisted by the unmodified side chain of asparagine (Asn) without any exogenous directing group. Thereby, site-selective arylations of C(sp
3
)-H bonds at the N-terminus of di-, tri-, and tetrapeptides have been achieved. Likewise, we have constructed a key building block for accessing agouti-related protein (AGRP) active loop analogues in a concise manner.
An efficient method for peptide late-stage C(sp
3
)-H arylations assisted by unmodified side chain of asparagine (Asn) without any exogenous directing group has been reported.
The low-temperature fatigue crack propagation rate of 925A steel, as a rudder steel for polar special ships, has a crucial impact on the evaluation of the fatigue strength of polar ships. The purpose ...of this article is to study the fatigue crack propagation rate of 925A steel under different low-temperature conditions from room temperature (RT) to -60 °C. The material was subjected to fatigue crack propagation tests and stress intensity factor tests. The experimental tests were conducted according to the Chinese Standard of GB/T6398-2017. The results show that as the temperature decreases, the lifespan of 925A increases. Within a certain stress intensity factor, as the temperature decreases, the fatigue crack propagation rate decreases. At -60 °C, it exhibits ductile fracture; within normal polar temperatures, it can be determined that 925A meets the requirements for low-temperature fatigue crack propagation rates in polar regions. However, in some extreme polar temperatures below -60 °C, preventing brittle failure becomes a key focus of fatigue design. Finally, the fatigue crack propagation behavior at the microscale of 925A steel at low temperatures was described using fracture morphology. The experimental data can provide reference for the design of polar ships to further resist low-temperature fatigue and cold brittle fracture.
Introduction: As a new discipline, network pharmacology has been widely used to disclose the material basis and mechanism of Traditional Chinese Medicine in recent years. However, numerous researches ...indicated that the material basis of TCMs identified based on network pharmacology was the mixtures of beneficial and harmful substances rather than the real material basis. In this work, taking the anti-NAFLD (non-alcoholic fatty liver disease) effect of Bai Shao (BS) as a case, we attempted to propose a novel bioinformatics strategy to uncover the material basis and mechanism of TCMs in a precise manner. Methods: In our previous studies, we have done a lot work to explore TCM-induced hepatoprotection. Here, by integrating our previous studies, we developed a novel computational pharmacology method to identify hepatoprotective ingredients from TCMs. Then the developed method was used to discover the material basis and mechanism of Bai Shao against Non-alcoholic fatty liver disease by combining with the techniques of molecular network, microarray data analysis, molecular docking, and molecular dynamics simulation. Finally, literature verification method was utilized to validate the findings. Results: A total of 12 ingredients were found to be associated with the anti-NAFLD effect of BS, including monoterpene glucosides, flavonoids, triterpenes, and phenolic acids. Further analysis found that IL1-β, IL6, and JUN would be the key targets. Interestingly, molecular docking and molecular dynamics simulation analysis showed that there indeed existed strong and stable binding affinity between the active ingredients and the key targets. In addition, a total of 23 NAFLD-related KEGG pathways were enriched. The major biological processes involved by these pathways including inflammation, apoptosis, lipid metabolism, and glucose metabolism. Of note, there was a great deal of evidence available in the literature to support the findings mentioned above, indicating that our method was reliable. Discussion: In summary, the contributions of this work can be summarized as two aspects as follows. Firstly, we systematically elucidated the material basis and mechanism of BS against NAFLD from multiple perspectives. These findings further enhanced the theoretical foundation of BS on NAFLD. Secondly, a novel computational pharmacology research strategy was proposed, which would assist network pharmacology to uncover the scientific connotation TCMs in a more precise manner.
Performing clustering analysis is one of the important research topics in cancer discovery using gene expression profiles, which is crucial in facilitating the successful diagnosis and treatment of ...cancer. While there are quite a number of research works which perform tumor clustering, few of them considers how to incorporate fuzzy theory together with an optimization process into a consensus clustering framework to improve the performance of clustering analysis. In this paper, we first propose a random double clustering based cluster ensemble framework (RDCCE) to perform tumor clustering based on gene expression data. Specifically, RDCCE generates a set of representative features using a randomly selected clustering algorithm in the ensemble, and then assigns samples to their corresponding clusters based on the grouping results. In addition, we also introduce the random double clustering based fuzzy cluster ensemble framework (RDCFCE), which is designed to improve the performance of RDCCE by integrating the newly proposed fuzzy extension model into the ensemble framework. RDCFCE adopts the normalized cut algorithm as the consensus function to summarize the fuzzy matrices generated by the fuzzy extension models, partition the consensus matrix, and obtain the final result. Finally, adaptive RDCFCE (A-RDCFCE) is proposed to optimize RDCFCE and improve the performance of RDCFCE further by adopting a self-evolutionary process (SEPP) for the parameter set. Experiments on real cancer gene expression profiles indicate that RDCFCE and A-RDCFCE works well on these data sets, and outperform most of the state-of-the-art tumor clustering algorithms.
In order to investigate the effect of Si content on the microstructures and properties of directionally solidified (DS) Fe-B alloy, a scanning electron microscope (SEM) with an energy dispersive ...spectrum (EDS), and X-ray diffraction have been employed to investigate the as-cast microstructures of DS Fe-B alloy. The results show that Si can strongly refine the columnar microstructures of the DS Fe-B alloy, and the columnar grain thickness of the oriented Fe2B is reduced with the increase of Si addition. In addition, Si is mainly distributed in the ferrite matrix, almost does not dissolve in boride, and seems to segregate in the center of the columnar ferrite to cause a strong solid solution strengthening and refinement effect on the matrix, thus raising the microhardness of the matrix and bulk hardness of the DS Fe-B alloy.
Cancer class discovery using biomolecular data is one of the most important tasks for cancer diagnosis and treatment. Tumor clustering from gene expression data provides a new way to perform cancer ...class discovery. Most of the existing research works adopt single-clustering algorithms to perform tumor clustering is from biomolecular data that lack robustness, stability, and accuracy. To further improve the performance of tumor clustering from biomolecular data, we introduce the fuzzy theory into the cluster ensemble framework for tumor clustering from biomolecular data, and propose four kinds of hybrid fuzzy cluster ensemble frameworks (HFCEF), named as HFCEF-I, HFCEF-II, HFCEF-III, and HFCEF-IV, respectively, to identify samples that belong to different types of cancers. The difference between HFCEF-I and HFCEF-II is that they adopt different ensemble generator approaches to generate a set of fuzzy matrices in the ensemble. Specifically, HFCEF-I applies the affinity propagation algorithm (AP) to perform clustering on the sample dimension and generates a set of fuzzy matrices in the ensemble based on the fuzzy membership function and base samples selected by AP. HFCEF-II adopts AP to perform clustering on the attribute dimension, generates a set of subspaces, and obtains a set of fuzzy matrices in the ensemble by performing fuzzy c-means on subspaces. Compared with HFCEF-I and HFCEF-II, HFCEF-III and HFCEF-IV consider the characteristics of HFCEF-I and HFCEF-II. HFCEF-III combines HFCEF-I and HFCEF-II in a serial way, while HFCEF-IV integrates HFCEF-I and HFCEF-II in a concurrent way. HFCEFs adopt suitable consensus functions, such as the fuzzy c-means algorithm or the normalized cut algorithm (Ncut), to summarize generated fuzzy matrices, and obtain the final results. The experiments on real data sets from UCI machine learning repository and cancer gene expression profiles illustrate that 1) the proposed hybrid fuzzy cluster ensemble frameworks work well on real data sets, especially biomolecular data, and 2) the proposed approaches are able to provide more robust, stable, and accurate results when compared with the state-of-the-art single clustering algorithms and traditional cluster ensemble approaches.
For underwater vehicles navigating in Arctic Sea ice-covered waters, fatigue damage is a crucial issue. Many scholars have conducted low-temperature fatigue analysis on low-temperature materials and ...substrate platforms for ships, and the results show that low temperature is beneficial for improving the mechanical properties of materials. However, they have mainly focused on low-temperature performance experiments and simulation analysis of standard components of materials, and there are very few fatigue life experimental studies on underwater vehicle mechanical structures. This paper conducts experimental investigations on a scaled model of an underwater vehicle rudder mechanism in a polar environment laboratory. Using a comparative analysis method involving simulations and experiments, the low-temperature fatigue test data of the scaled underwater vehicle rudder mechanism are analyzed, and the quantified analysis between fatigue and different low-temperature loading cycles, as well as the influence of icing on the fatigue life, is explored. It is indicated that the Arctic environment can decrease the fatigue life of the underwater vehicle rudder mechanism by deteriorating its material properties. The paper builds the foundation for the fatigue life of an underwater vehicle rudder mechanism in Arctic low-temperature environments.
Under the action of Arctic low temperatures and long-term alternating loads, the fatigue life of the submarine rudder stock mechanism is severely tested. In this paper, the research method of the ...static strength analysis and fatigue life analysis of the submarine rudder stock mechanism is proposed by combining multibody dynamics, the finite element method, and tests. Based on the three-dimensional model and the motion law of the rudder stock mechanism, a multibody dynamic model is established, and the time history loads of each node of the mechanism are obtained. According to the working temperature range of the submarine rudder stock mechanism in the Arctic, low-temperature tensile tests are carried out. Based on the experimental data, the finite element model is built, and static analysis is carried out. Using the S–N static fatigue design method, fatigue simulation analysis is performed by using nCode DesignLife. The analysis results show that the fatigue life of the submarine rudder stock mechanism decreases significantly when the temperature is reduced from 0 °C to −60 °C. This method can provide a reference for submarine design and life model establishment in the Arctic environment.
As the aromatic tryptophan (Trp) side chain plays a pivotal role in influencing the structure and function of peptides and proteins, it has become an attractive target for the late‐stage modification ...of these important biomolecules. Herein, we report an electrochemical approach for late‐stage functionalization of peptides containing a Trp side chain through manganese‐catalyzed tandem radical azidation/heterocyclization. This electrochemical oxidative strategy provides access to azide‐substituted tetrazolo1,5‐aindole‐containing peptides with broad functional group tolerance, high site selectivity, and good yields of products (up to 87 %) under mild buffer conditions. Moreover, the modified Trp‐containing peptides bearing an azide functionality are promising building blocks, paving the way for the construction of various derivatives, such as “click” chemistry products.
Manganese‐catalyzed late‐stage derivatization was used to construct azide‐substituted tetrazolo1,5‐aindole‐containing peptides through a radical azidation/heterocyclization cascade. This electrochemical oxidative strategy could be conducted under mild, efficient, and environmentally friendly conditions in buffer solution.