An Inception Convolutional Autoencoder Model for Chinese Healthcare Question Clustering.

Each clustering algorithm usually optimizes a qualification metric during its learning process. The qualification metric in traditional clustering algorithms considers all the features of under-consideration dataset equally; it means each feature participates in the clustering process equivalently. Considering that some features have more information than the others in a dataset (due to their lower information or their higher variances, etc.), we proposes a fuzzy weighted clustering algorithm. We name this new clustering algorithm, Fuzzy Weighted Locally Adaptive Clustering (FWLAC) algorithm. The proposed FWLAC algorithm is capable of handling imbalanced clustering. However, FWLAC algorithm suffers from its sensitivity to the two parameters that should be tuned manually. The performance of FWLAC algorithm is affected by well-tuning of its parameters. So the paper proposes two solutions to well-tuning of its two parameters. In the first solution, we propose a simple clustering ensemble framework to show the sensitivity of the WLAC algorithm to its manual well-tuning. Although it is not a try-and-error procedure, it is like a grid search, where we use different pairs of values for both parameters h 1 and h 2. Per each pair of values for parameters h 1 and h 2, the algorithm produces a partitioning. So after the grid search, we obtain a large number of partitionings. We break any of the partitionings into its clusters, and then they form an ensemble of clusters. Finally the consensus partitioning is extracted from them by a consensus function. The algorithm is not data dependent at all. For all datasets, we use a similar grid search and a similar set of values for the parameters h 1 and h 2. In this way we have proposed an alternative solution to parameter selection. We use a selection phase to select/remove some clusters from our ensemble of clusters to obtain an elite ensemble of clusters. To do this, a stability measure, normalized mutual information (NMI), was used to validate a cluster. The paper shows the effectiveness of the proposed clustering frameworks both theoretically and experimentally.

Evolutionary algorithm has been widely employed for data clustering, resulting various evolutionary clustering methods. For a given clustering task, these methods generally deliver different clustering solutions and there is no clear indication which one is the best. Clustering ensemble, which tries to encompass all information contained in different clustering solutions given by different methods, is considered to be an effective approach of improving the robust of solution. However, existing clustering ensemble method generally requires a cluster number as parameter to be specified in advance. Further, they could have the difficulty to preserve the diversity of candidate clustering solutions, which plays an important role in the success of these methods. Considering these two aspects, we propose a multi-objective clustering ensemble algorithm with automatic k-determination. In the proposed method, a modified version of Dual-Similarity Clustering Ensemble (MDSCE), which does not require the cluster number in advance, is developed and employed as crossover operator to generate new clustering partitions during optimizing process. Further, a k-means based process employing the cluster number from MDSCE is employed to generate diverse and high-quality individuals. For evaluation purpose, we have tested our algorithm on a series of real datasets. The results show that the proposed algorithm is able to deliver high-quality clustering solutions and outperforms related clustering algorithms.

Identification of crops is an important topic in the agricultural domain. Hyperspectral remote sensing data are very useful for crop feature extraction and classification. Remote sensing data is an unstructured data and Convolutional Neural Network (CNN) can work on unstructured data efficiently. This paper presents an evaluation of CNN for crop classification using the Indian Pines standard dataset obtained from the AVIRIS sensor and the study area dataset obtained from the EO-1hyperion sensor. Optimized CNN has been tuned by training the model on different parameters. It has been compared with two classification algorithms: Deep Neural Network (DNN) and Convolutional Autoencoder. According to the test results, the proposed optimized CNN model provided better results as compared to the other two methods. CNN has given 97 ± 0.58% overall accuracy for the Indian Pines standard dataset and 78 ± 2.43% for our study area dataset.

Annotation-free defect detection for glasses based on convolutional auto-encoder with skip connections

A vast amount of time-series data is generated from multiple fields. Mining these data can uncover hidden patterns and behavior characteristics. The analysis of such data is complex because they are voluminous and have high dimensions. Clustering can provide a preprocessing step to extract insights. However, clustering such data poses challenges, as many existing algorithms are not efficient enough to handle them. In addition, many traditional and modern clustering algorithms need help with parameter-tuning problems. Ensemble clustering, an amalgamation of clustering algorithms, has emerged as a promising method for improving the accuracy, stability, and robustness of clustering solutions. This study presents Ensemble clustering using Affinity Propagation (ECAP). AP is efficient because it does not require the number of clusters to be specified a priori, allowing the data to reveal its structure. When used in an ensemble framework, the inherent strengths of AP are amplified by integrating multiple clustering results. This aggregation mitigates the influence of any single, potentially suboptimal clustering outcome, leading to more stable and reliable clusters. Extensive experiments were performed on four real-world datasets for rand index, homogeneity, completeness, and V-measure to determine the efficacy of the proposed approach. The results show that the proposed method outperforms AP, Kmeans, and spectral clustering.

Clustering ensemble is an open proposition that aims to solve the limitation of a single cluster algorithm on the diversity of data structures in data partitions. It obtains a consensus model by integrating multiple clustering algorithms. Compared with a single clustering algorithm, it can process the data more accurately and stably, and has a better tolerance for the structure and diversity of the data. This paper proposes to integrate particle swarm optimization for clustering ensemble model. Particularly, the idea is to first use multiple classic clustering algorithms to cluster the original data set to obtain a preliminary clustering result set, and then search for a clustering result that is most consistent with the preliminary results by a particle swarm optimization procedure. In the experiments, we make use of public data sets and micro-precision to evaluate the effectiveness of the proposed clustering ensemble model, and compare it with both base clustering algorithms and other common clustering ensemble algorithms. The evaluation results show that this model can significantly improve the base clustering algorithms and outperforms common clustering ensemble algorithms in most cases.

Data clustering is an important task and has found applications in numerous real-world problems. Since no single clustering algorithm is able to identify all different types of cluster shapes and structures, ensemble clustering was proposed to combine different partitions of the same data generated by multiple clustering algorithms. The key idea of most ensemble clustering algorithms is to find a partition that is consistent with most of the available partitions of the input data. One problem with these algorithms is their inability to handle uncertain data pairs, i.e. data pairs for which about half of the partitions put them into the same cluster and the other half do the opposite. When the number of uncertain data pairs is large, they can mislead the ensemble clustering algorithm in generating the final partition. To overcome this limitation, we propose an ensemble clustering approach based on the technique of matrix completion. The proposed algorithm constructs a partially observed similarity matrix based on the data pairs whose cluster memberships are agreed upon by most of the clustering algorithms in the ensemble. It then deploys the matrix completion algorithm to complete the similarity matrix. The final data partition is computed by applying an efficient spectral clustering algorithm to the completed matrix. Our empirical studies with multiple real-world datasets show that the proposed algorithm performs significantly better than the state-of-the-art algorithms for ensemble clustering.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

In the construction industry, it is desirable to develop a system to easily judge skills of workers in order to effectively pass on the skills of skilled workers to unskilled workers. This report proposes a skill analysis method in hydraulic excavator operators using a convolutional autoencoder (CAE) that is capable of nonlinear mapping to low dimensionally space. CAE is trained with the operation data of a skilled operator to acquire characteristics of the skilled operator. Then, the operation data of an unskilled operator is input to the trained CAE to analyze the unskilled operator's skill. CAE detects operations of the unskilled operator containing features that differ from the operation of the skilled operator out of many operations. First, it is confirmed that CAE can save information of the operation data in a low dimensional space than principal component analysis that is a linear mapping for dimensionality reduction. Next, the result of the proposed method for the unskilled operator is shown. Effectiveness of the result is validated by comparing a few operation data of both operators detected by the proposed method.

Lightweight single image super-resolution with attentive residual refinement network

In this paper, a novel reduced order model based on a convolutional auto-encoder with self-attention (SACAE ROM) is proposed. The proposed model is a non-intrusive reduced order model, which uses a convolutional neural network and a long short-term memory network to extract temporal feature relationships from high-fidelity numerical solutions. The self-attention is introduced into the convolutional neural network to enhance the non-local information perception ability of the convolutional neural network and improve the feature extraction ability of the network. The model adopts a joint construction method, which overcomes the problem of propagating error in each process of the model. The model proposed in this paper has been verified on the problem of the flow around a cylinder. The experimental results indicate that the SACAE ROM has higher robustness and accuracy. Compared with the ROM based on a convolutional auto-encoder, the prediction error of the SACAE ROM is reduced by 42.9%. As with other ROMs based on deep neural networks, the SACAE ROM takes a long time to train. To solve this problem, the transfer and generalization ability of the model is studied in this paper. In the experiment, the flow velocity and spoiler of the flow around the cylinder were changed, and the training time of the transfer model was reduced by about 50% to 60%. This result demonstrates that the problem of too long training time can be solved by transfer learning.

Question analysis is an important part in question and answer system. The article expounds the difference of Chinese question analysis technology between open domain and restricted domain. It also includes discussion of train of thought of Chinese question analysis in book information domain. Nowadays Chinese syntax analysis technology can't reach the practical application level, we propose Chinese question shallow semantic analysis technology based on semantic chunk. Supported by Science and Technology Department of Shanxi Province international cooperation and exchange project "China-Japan Cooperation Research on Chinese Intelligent Interactive Question and Answer System Based on Web "(Grant No.2009g18), Chinese question shallow semantic analysis technology is systematically and thoroughly studied, including definition of semantic chunk, derivation rules and generation technology of question vector. Experiments prove that this method is feasible within a sparse corpus scale.

Different from traditional text, short texts are characterized by high dimensionality, sparseness, and large text size. At the same time, some existing clustering ensemble algorithms treat each clusters equally, which will lead to the problem that the clustering results are not good enough. To solve this problem, this paper proposed a short text clustering ensemble algorithm based on convolution neural network (CNN). Firstly, the word2vec model is used to preserve the semantic relationship between words and obtain the multi-dimensional word vector representation; secondly, the feature is extracted from the original vector combining with the CNN; thirdly, clustering methods are used to cluster vectors; and then finally, Gini coefficient is used to measure the reliability of clustering, and the final clustering ensemble is carried out.

This project is aimed at providing a secure way of sending confidential images between users. Application is built to provide protection of the sensitive image being transmitted. Modern advancements have made it incredibly convenient to both send and store digital images online. Images often contain sensitive personal information, such as photographs, identifica- tion documents, medical records etc. Unauthorized access to these images can lead to identity theft, privacy invasion, and personal harm. Image security is crucial for several reasons, spanning personal privacy, corporate confidentiality, intellectual property protection and national secu rity. In order to solve the above described problems, this project provide a novel encryption method for color pictures that utilizes convolutional autoen- coder, DNA and steganography. Convolutional autoencoders can compress image data into a lower dimensional latent space before encryption. Image encryption scheme using DNA along with multiple chaotic sequences and substitution boxes provide security of the image. Hiding images within other images involves a technique known as steganography. In this process a secret image is embedded within a cover image making it imperceptible to the human eye. The security of the proposed method has been evaluated using several parameters, such as histogram of the cipher image, entropy, NPCR, UACI etc. The result shows that it a compelling approach to secure images against various attacks. Keywords− Convolutional neural network, autoencoder, chaos, DNA coding, deep learning, colour image encryption, steganography

Moderate diversity for better cluster ensembles