Synchronized low-frequency spontaneous fluctuations of the functional MRI (fMRI) signal have recently been applied to investigate large-scale neuronal networks brain in absence specific task instructions. However, underlying neural mechanisms these remain largely unknown. To this end, electrophysiological recordings and resting-state fMRI measurements were conducted α-chloralose-anesthetized rats. Using a seed-voxel analysis strategy, region-specific, anesthetic dose-dependent connectivity...

Different from general face recognition, age-invariant recognition (AIFR) aims at matching faces with a big age gap. Previous discriminative methods usually focus on decomposing facial feature into age-related and components, which suffer the loss of identity information. In this article, we propose novel Multi-feature Fusion Decomposition (MFD) framework for learns more robust features reduces intra-class variants. Specifically, first sample multiple images different ages same as time...

In traffic accident, an accurate and timely severity prediction method is necessary for the successful deployment of intelligent transportation system to provide corresponding levels medical aid in a manner. The existing accident's methods mainly use shallow models statistical models. To promote accuracy, novel prediction-convolutional neural network (TASP-CNN) model proposed that considers combination relationships among features. Based on weights features, feature matrix gray image (FM2GI)...

In multi-label learning, each training example is associated with multiple class labels and the task to learn a mapping from feature space power set of label space. It generally demanding time-consuming obtain for examples, especially learning where number need be annotated instance. To circumvent this difficulty, semi-supervised aims exploit readily-available unlabeled data help build predictive model. Nonetheless, most solutions work under transductive setting, which only focus on making...

Affordances are fundamental attributes of objects. reveal the functionalities objects and possible actions that can be performed on them. Understanding affordances is crucial for recognizing human activities in visual data robots to interact with world. In this paper we introduce new problem mining knowledge semantic affordance: given an object, determining whether action it. This equivalent connecting verb nodes noun WordNet, or filling affordance matrix encoding plausibility each...

Preparing conjugated polymer films via interfacial Suzuki polymerization is a promising method for obtaining desirable electrochromic materials with desired structures. Here, series of aryl boronic esters and triphenylamine-based bromides were applied as precursors, several finally obtained the liquid/liquid reaction under mild conditions. FT-IR, UV, Raman well electrochemistry, SEM, EDS results all provide strong evidence formation Among them, TPA-Wu (containing triphenylamine...

Abstract Objective Rule-based data quality assessment in health care facilities was explored through compilation, implementation, and evaluation of 63,397 rules a single-center case study to assess the ability rules-based identify errors importance physicians system owners. Methods We applied design science framework design, demonstrate, test, evaluate scalable with which can be managed used for monitoring. Results identified partitioned into 28 logic templates. A total 819,683 discrepancies...

Abstract Chinese media companies are facing opportunities and challenges brought about by digital transformation. Media economics takes the evaluation of business results as main research topic. However, overcoming internal differences in industry comprehensively predicting transformation from multiple dimensions has become an important issue to be understood. Based on “TOE-I” theoretical framework, this study innovatively uses machine learning methods predict analyze specific modes driving...

As alternative herbal medicine gains soar in popularity around the world, it is necessary to apply a fast and convenient means for classifying evaluating medicines. In this work, an electronic nose system with seven classification algorithms used discriminate between 12 categories of The results show that these medicines can be successfully classified, support vector machine (SVM) linear discriminant analysis (LDA) outperforming other terms accuracy. When principal component (PCA) lower...

Abstract Quantitative structure-activity relationship methods are used to study the quantitative structure triboability (QSTR), which refers tribology capability of a compound from calculation descriptors. Here, we Bayesian regularization neural network (BRNN) establish QSTR prediction model. Two-dimensional (2D) BRNN–QSTR models can flexibly and easily estimate lubricant-additive antiwear properties. Our results show that electron transfer heteroatoms (such as S, P, O, N) in molecule...

In this paper, a fuzzy PID controller based on yaw angle prediction is applied to design an attitude for spherical rolling robot. The robot consists of 2-DOF pendulum located inside shell with freedom rotate about the transversal and longitudinal axis. proposed allows autonomously change its parameters adapt different environments current state. past researches motion robots mostly focused simulation or ideal experimental environment. But in physical system built experiments are carried out...

This study aimed to develop a dual-energy spectral computed tomography (DESCT) nomogram that incorporated both clinical factors and DESCT parameters for individual preoperative prediction of lymph node metastasis (LNM) in patients with colorectal cancer (CRC).We retrospectively reviewed 167 pathologically confirmed CRC who underwent enhanced preoperatively, these were categorized into training (n = 117) validation cohorts 50). The monochromatic CT value, iodine concentration value (IC),...

In this paper the effectiveness of three neural networks, competitive, backpropagation (BP) and radial basis function (RBF), in text classification is examined. The competitive network a kind unsupervised learning which used data clustering. BP one most widely models among artificial patterns RBF has also showed its vitality recent years. All are fit for pattern approximation. networks independently automatic classification. Experimental results show that outperform because application...

Multi-label learning deals with objects rich semantics where each example is associated multiple class labels simultaneously. Intuitively, label supposed to possess specific characteristics of its own. Therefore, exploiting label-specific features serves as one the promising techniques learn from multi-label examples. Specifically, LIFT approach generates by clustering training examples in a label-wise style, which ignores utilization correlations improve generalization performance. In this...

An estimate on the reliability of prediction in applications electronic nose is essential, which has not been paid enough attention. algorithm framework called conformal introduced this work for discriminating different kinds ginsengs with a home-made instrument. Nonconformity measure based k-nearest neighbors (KNN) implemented separately as underlying prediction. In offline mode, predictor achieves classification rate 84.44% 1NN and 80.63% 3NN, better than that simple KNN. addition, it...