Search

Kernel clustering has the ability to get the inherent nonlinear structure of the data. But the high computational complexity and the unknown representation of the kernel space make it unavailable for the data clustering in distributed peer-to-peer (P2P) networks. To solve this issue, we propose a new series of random feature-based collaborative kernel clustering algorithms in this article. In the most basic algorithm, each node in a distributed P2P network first maps its data into a low-dimensional random feature space with the approximation of the given kernel by using the random Fourier feature mapping method. Then, each node independently searches the clusters with its local data and the collaborative knowledge from its neighbor nodes, and the distributed clustering is performed among all network nodes until reaching the global consensus result, i.e., all nodes have the same cluster centers. In addition, an improved version is designed with assignment of feature weights, which is optimized by the maximum-entropy technique to extract important features for the cluster identification. What’s more, to relief the impact of different kernel functions and related parameters on clustering results, the combination of multiple kernels rather than a single kernel is adopted for the low-dimensional approximation, and the optimized weights are assigned to provide the guidance on the choice of the kernels and their parameters and discover significant features at the same time. Experiments on synthetic and real-world datasets show that the proposed methods achieve similar and even better results than the traditional kernel clustering methods on various performance metrics, including the average classification rate, the average normalized mutual information, and the average adjusted rand index. More importantly, the low-dimensional random features approximated to kernels and the distributed clustering mechanism adopted in these methods bring the greatly lower temporal complexity.

It is hard to construct an optimal classifier for high-dimensional imbalanced data, on which the performance of classifiers is seriously affected and becomes poor. Although many approaches, such as resampling, cost-sensitive, and ensemble learning methods, have been proposed to deal with the skewed data, they are constrained by high-dimensional data with noise and redundancy. In this study, we propose an adaptive subspace optimization ensemble method (ASOEM) for high-dimensional imbalanced data classification to overcome the above limitations. To construct accurate and diverse base classifiers, a novel adaptive subspace optimization (ASO) method based on adaptive subspace generation (ASG) process and rotated subspace optimization (RSO) process is designed to generate multiple robust and discriminative subspaces. Then a resampling scheme is applied on the optimized subspace to build a class-balanced data for each base classifier. To verify the effectiveness, our ASOEM is implemented based on different resampling strategies on 24 real-world high-dimensional imbalanced datasets. Experimental results demonstrate that our proposed methods outperform other mainstream imbalance learning approaches and classifier ensemble methods.

The thioamide group represents a highly attractive isostere of the amide bond. We report a combined structural and computational study on cis-thioamide conformation of N-thioacyl-N-methylanilines. Amide to thioamide replacement in a class of anilides that are highly valuable as conformational locks results in a higher preference for cisconformation in a unique compacted template intrinsic to the thioamide structure. The study strongly supports the use of N-methylthioanilides as cis-conformational locks in various facets of chemistry.

After a very fast and efficient discriminative broad learning system (BLS) that takes advantage of flatted structure and incremental learning has been developed, here, a mathematical proof of the universal approximation property of BLS is provided. In addition, the framework of several BLS variants with their mathematical modeling is given. The variations include cascade, recurrent, and broad–deep combination structures. From the experimental results, the BLS and its variations outperform several exist learning algorithms on regression performance over function approximation, time series prediction, and face recognition databases. In addition, experiments on the extremely challenging data set, such as MS-Celeb-1M, are given. Compared with other convolutional networks, the effectiveness and efficiency of the variants of BLS are demonstrated.

A 5,6-difluorobenzothiazole-based dibromo monomer was successfully synthesized, from which new fluorinated conjugated polymers PF-ffBTz and PFN-ffBTz were prepared via copolymerizations with two fluorene-based diboronic ester monomers. Twisted fluorene-ffBTz backbones enable PF-ffBTz and PFN-ffBTz with large band gaps up to 3.10 eV and deep-lying highest occupied molecular orbital levels down to −6.2 eV. The chemical structures of PF-ffBTz and PFN-ffBTz impart some new functionalities of fluorinated conjugated polymers. PF-ffBTz can show deep blue electroluminescent emission, with high external quantum efficiency of 3.71%. PFN-ffBTz, with amino-functionalized side chains on the fluorene unit, can serve as an efficient cathode interlayer in inverted polymer solar cells (PSCs), showing better photovoltaic performances if compared with a ZnO interlayer. In addition, it is found that using an optical filter to cut off the short wavelength section (≤380 nm) of incident light can significantly elevate photostability of PSCs under continuous illumination.

Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as “mapped features” in feature nodes and the structure is expanded in wide sense in the “enhancement nodes.” The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.

How to energy-efficiently maintain the topology of wireless sensor networks (WSNs) is still a difficult problem because of their numerous nodes, highly dynamic nature, varied application scenarios and limited resources. An energy-efficient multi-mode clusters maintenance (M2CM) method is proposed based on localized and event-driven mechanism in this work, which is different from the conventional clusters maintenance model with always periodically re-clustered among the whole network style based on time-trigger for hierarchical WSNs. M2CM can meet such demands of clusters maintenance as adaptive local maintenance for the damaged clusters according to its changes in time and space field., the triggers of M2CM include such events as nodes' residual energy being under the threshold, the load imbalance of cluster head, joining in or exiting from any cluster for new node or disable one, etc. Based on neighboring relationship of the damaged clusters, one can start a single cluster (inner-cluster) maintenance or clusters (inter-cluster) maintenance program to meet diverse demands in the topology management of hierarchical WSNs. The experiment results based on NS2 simulation show that the proposed method can significantly save energy used in maintaining a damaged network, effectively narrow down the influenced area of clusters maintenance, and increase transmitted data and prolong lifetime of network compared to the traditional schemes.

Advanced Etch‐Stop s tructure In‐Ga‐Zn‐Oxide thin film transistor (A‐ES TFT) using SD and IGZO layer self‐aligned process is lower production cost, less parasitic capacitance than etch‐stopped layer (ESL) Oxide TFTs. We also found excellent electrical properties and bias stability and fabricated a 12.5‐inch liquid crystal panel using A‐ES TFTs by only two photomask.

The broad learning system (BLS) based on the minimum mean square error (MMSE) criterion can achieve outstanding performance without spending too much time in various machine learning tasks. However, when data are polluted by non-Gaussian noise, the stability of BLS may be destroyed because the MMSE criterion is sensitive to outliers. Different from the MMSE criterion, the minimum error entropy (MEE) criterion utilizes the kernel function to capture high-dimensional information and decrease the negative influence of outliers, which will make BLS more discriminative and robust. Nevertheless, the computational complexity of MEE is high due to a double summation of the data size. To solve these issues, this paper proposes a new robust BLS variant based on the quantized minimum error entropy (QMEE) criterion, in which a quantization operation is used to reduce the computational complexity of MEE. The proposed model BLS-QMEE is optimized by the fixed-point iterative method, and a sufficient condition for its convergence is provided. Compared with the standard BLS and other existing robust variants of BLS, BLS-QMEE performs more satisfactorily without consuming too much time. The desirable performance of BLS-QMEE is verified by various experiments on function approximation, several public datasets, and a practical application.

Two new conjugated copolymers, PBDT-T6-TTF and PBDT-T12-TTF, were derived from a novel 4-fluorobenzoyl thienothiophene (TTF). In addition, two types of benzodithiophene (BDT) units with 2,3-dihexylthienyl (T6) and 2,3-didodecylthienyl (T12) substituents, respectively, were successfully synthesized. The effect of the dual two-dimensional (2D) substitutions of the building blocks upon the optoelectronic properties of the polymers was investigated. Generally, the two polymers exhibited good solubility and broad absorption, showing similar optical band gaps of ∼1.53 eV. However, PBDT-T6-TTF with its shorter alkyl chain length possessed a larger extinction coefficient in thin solid film. The highest occupied molecular orbital (HOMO) level of PBDT-T6-TTF was located at −5.38 eV while that of PBDT-T12-TTF was at −5.51 eV. In space charge-limited-current (SCLC) measurement, PBDT-T6-TTF and PBDT-T12-TTF displayed respective hole mobilities of 3.0×10−4and 1.6×10−5cm2V−1s−1. In polymer solar cells, PBDT-T6-TTF and PBDT-T12-TTF showed respective power conversion efficiencies (PCEs) of 2.86% and 1.67%. When 1,8-diiodooctane (DIO) was used as the solvent additive, the PCE of PBDT-T6-TTF was remarkably elevated to 4.85%, but the use of DIO for the PBDT-T12-TTF-blend film resulted in a lower PCE of 0.91%. Atomic force microscopy (AFM) indicated that the superior efficiency of PBDT-T6-TTF with 3% DIO (v/v) should be related to the better continuous phase separation of the blend film. Nevertheless, the morphology of the PBDT-T12-TTF deteriorated when the 3% DIO (v/v) was added. Our results suggest that the alkyl-chain length on the 2D BDT units play an important role in determining the optoelectronic properties of dual 2D BDT-TT-based polymers.

Broad learning system (BLS) has been proposed as an alternative method of deep learning. The architecture of BLS is that the input is randomly mapped into series of feature spaces which form the feature nodes, and the output of the feature nodes are expanded broadly to form the enhancement nodes, and then the output weights of the network can be determined analytically. The most advantage of BLS is that it can be learned incrementally without a retraining process when there comes new input data or neural nodes. It has been proven that BLS can overcome the inadequacies caused by training a large number of parameters in gradient-based deep learning algorithms. In this paper, a novel variant graph regularized broad learning system (GBLS) is proposed. Taking account of the locally invariant property of data, which means the similar images may share similar properties, the manifold learning is incorporated into the objective function of the standard BLS. In GBLS, the output weights are constrained to learn more discriminative information, and the classification ability can be further enhanced. Several experiments are carried out to verify that our proposed GBLS model can outperform the standard BLS. What is more, the GBLS also performs better compared with other state-of-the-art image recognition methods in several image databases.

Bioactive mesoporous diopside (m-DP) and poly(l-lactide) (PLLA) composite scaffolds with mesoporous/macroporous structure were prepared by the solution-casting and particulate-leaching method. The results demonstrated that the degradability and bioactivity of the mesoporous/macroporous scaffolds were significantly improved by incorporating m-DP into PLLA, and that the improvement was m-DP content-dependent. In addition, the scaffolds containing m-DP showed the ability to neutralize acidic degradation products and prevent the pH from dropping in the solution during the soaking period. Moreover, the scaffolds containing m-DP enhanced attachment, proliferation and alkaline phosphatase activity of MC3T3-E1 cells, which were also m-DP content-dependent. Furthermore, the histological and immunohistochemical analysis results showed that the scaffolds with m-DP significantly promoted new bone formation and improved the materials degraded in vivo, indicating good biocompatibility. The results suggested that the mesoporous/macroporous scaffolds of the m-DP/PLLA composite with osteogenesis had a potential for bone regeneration.