The existing long-term time-series forecasting methods based on the neural networks suffer from multiple limitations, such as accumulated errors and diminishing temporal correlation, which compromise prediction quality. To overcome these shortcomings, in this article, we build trend fuzzy granulation-based long short-term memory (LSTM) to carry out forecasting, where data points with consistent characteristics, including change, fluctuation range, persistence, are predicted unison rather...

Type-2 fuzzy sets provide an efficient vehicle for handling uncertainties of real-world problems, including noisy observations. Bringing type-2 to clustering algorithms offers more flexibility handle associated with membership concepts caused by a environment. However, the existing suffer from time-consuming type-reduction process, which not only hampers performance but also increases burden understanding results. In order alleviate problem, this article introduces set typical...

Fuzzy information granulation transfers the time series analysis from numerical platform to granular platform, which enables us study at a different granularity. In previous studies, each fuzzy granule in can reflect average, range, and linear trend characteristics of data corresponding window. order get more general granule, this paper proposes polynomial granules, both nonlinear The distance metric proposed granules is given theoretically. After studying measure its geometric...

Digital image scrambling is an effective tool in preprocessing and post-pressing of data hiding, digital watermarking encryption. In order to evaluate the performance, different methods have been proposed by authors based on assumptions. this paper, a new measure degree method Chi square good fitness hypothesis testing proposed. Using estimator its P-value, we can randomness any specific region. Scrambling degrees constructed using solid theoretical foundation are more rational than some...

Abstract Over the past few decades, sophisticated nanomaterials have been used as carries for targeted delivery of therapeutics to solid tumors. However, low efficiency intracellular internalization nanocarriers in current use restricts their biomedical application. In this work, we demonstrate that novel virus‐bionic mesoporous‐silica‐based can be successfully prepared programmed precise drug delivery. These unique viral mimic nanovesicles not only present virus bionic counterparts and...

This paper presents an efficient and practical variable universe based fuzzy controller (VUBFC) for the control problem of backing up a truck trailer. The design VUBFC essentially amounts to (1) designing typical controller, (2) choosing contraction-expansion factors on input-output universes. To backer-upper problem, we propose new factor controller's output. Being with such factor, is able vary membership functions its valuables in response varying system errors, thus achieve precise,...

Most patients diagnosed with thoracic esophageal squamous cell carcinoma (ESCC) have progressed beyond surgical resection as a therapeutic option. Difficulties in the proper assessment of tumor invasion depth before treatment complicate determination type and extent therapy. Therefore, accurate clinical staging is necessity for identifying options aiding patient prognosis. We investigated radiographic factors prognostic indicators survival ESCC. Between July 2006 - 2010, 324 ESCC who...

The traditional Ordered Weighting Average (OWA) operator is suitable for aggregating numerical attributes. However, this method fails when the attribute values are given in a linguistic form. In paper, novel named Entropy and Probability based Fuzzy Induced Weighted Averaging (EPFIOWA) proposed Gaussian-fuzzy-number-based A first designed to obtain reasonable weighting vector on probability distribution maximal entropy. Such optimal vectors can be obtained under any level of optimism,...

A novel Semi-supervised fuzzy clustering model based on mahalanobis distance is proposed in this paper, we show that the iterative formulas to solve simple and comprehensible, standard FCM may be viewed as a special case of our formulation. An experiment artificial data set verifies effectiveness new algorithm.

Clustering accuracy of fuzzy clustering is sensitive to the structure dataset be studied. Semi-supervised algorithms aim increase under supervisions a limited amount labeled data, but classification rate highly dependent on size available data. To overcome this disadvantage, we propose novel semi-supervised based label propagation. Under our propagation mechanism, an unlabeled datum propagates estimated from two aspects: (1) its adjacent data; (2) previous result. The effects these labels...

In the existing short-term forecasting methods of time series, two challenges are faced: capture associations data and avoid cumulative errors. For tackling these challenges, fuzzy information granule based model catches our attention. The rule used in this is association (FAR), which FAR constructed from a premise to consequent at consecutive periods, then it describes short-association data. However, real another association, between non-consecutive frequently exists, especially periodical...

This thesis discussed the situation of value system digital cultural resources at present. Through a variety researches about methods evaluation, are and defined briefly. And then estimate its depending on own characteristics different resources. Taking ancient books as an example, by adopting method integrated evaluation to quantify value, we elected important weight property study deeply. Finally appropriate is established. It provided with good reference views for future studies, strong...

This paper proposed a hierarchical variable universe fuzzy controller for the control problem of double-tank system. A is able to reduce computation complexity ordinary controller, while achieve an efficient, accurate control. Simulation examples and comparison with PID show that controls system much better, applicable other nonlinear systems.

The OWA operator is an important assessment method in multiple-attribute decision making.A new model based on the density function of normal distribution given to assign reasonable weights operators.Using orness level as a parameter this method, one can deduce by solving quadratic programing problem.Three propositions are proven, and numerical example about red wines analyze illustrate method.