International Journal of Pattern Recognition and Artificial Intelligence

The television audience rating is an important indicator of the quality of television programs and important reference for decision-television operator. As many factors that affect the ratings and the trends are complex, the article proposes a television rating mining predictive model based on fuzzy cognitive maps (FCMs) with forward stepwise regression. The FCMs use the causal relationship among various concept nodes to simulate the fuzzy reasoning, and enhance the dynamic behavior of the simulation system with its feedback mechanism, which is suitable for system to predict the trend of television audience rating. A FCM-based model for predicting television audience rating is proposed in this paper. The forward stepwise regression algorithm is used to obtain concept nodes of coarse weight matrix for FCMs, and then a training weight algorithm is used to refine the coarse weight matrix model. The FCM model is applied to mine the television audience rating, realizing to predict the television playback volume. The experimental result shows that the modeling method is effective.

Sentiment classification is significant in everyday life of everyone, in political activities, activities of commodity production, commercial activities. In this research, we propose a new model for Big Data sentiment classification in the parallel network environment. Our new model uses STING Algorithm (SA) (in the data mining field) for English document-level sentiment classification with Hadoop Map (M)/Reduce (R) based on the 90,000 English sentences of the training data set in a Cloudera parallel network environment — a distributed system. In the world there is not any scientific study which is similar to this survey. Our new model can classify sentiment of millions of English documents with the shortest execution time in the parallel network environment. We test our new model on the 25,000 English documents of the testing data set and achieved on 61.2% accuracy. Our English training data set includes 45,000 positive English sentences and 45,000 negative English sentences.

Memristor, as the future of artificial intelligence, has been widely used in pattern recognition or signal processing from sensor arrays. Memristor-based recurrent neural network (MRNN) is an ideal model to mimic the functionalities of the human brain due to the physical properties of memristor. In this paper, the periodicity for memristor-based Cohen–Grossberg neural networks (MCGNNs) is studied. The neural network (NN) considered in this paper is based on the memristor and involves time-varying delays, distributed delays and impulsive effects. The boundedness and monotonicity of the activation function are not assumed. By some inequality technique and contraction mapping principle, we prove the existence, uniqueness and exponential stability of periodic solution for MCGNNs. Finally, some numeral examples and comparisons are provided to illustrate the validation of our results.

Multilinear principal component analysis (MPCA) has been applied for tensor decomposition and dimensionality reduction in image databases modeled through higher order tensors. Despite the well-known attractive properties of MPCA, the traditional approach does not incorporate prior information in order to steer its subspace computation. In this paper, we propose a method to explicitly incorporate such semantics in the MPCA framework to allow an automatic selective treatment of the variables that compose the patterns of interest. The method relies on spatial weights calculated, in this work, by separating hyperplanes and Fisher criterion. In this way, we can perform feature extraction and dimensionality reduction taking advantage of high level information in the form of labeled data. Besides, the corresponding tensor components are ranked in order to identify the principal weighted tensor subspaces for classification tasks. In the computational results we consider gender and facial expression experiments to illustrate the capabilities of the method for dimensionality reduction, classification and reconstruction of face images.

In this paper, a method is proposed to reduce artifact effect for images. The proposed approach first decomposes an original image into four subband images. The powers of the four sub-images are calculated and compared with a power threshold accompanying entropy measure to decide that whether the sub-images are reserved or not. The pixels of the reserved sub-images are then compared with a pixel threshold accompanying different entropy measure in order to determine that the pixel is discarded or not. The experimental results of this approach in comparison with other methods are performed both subjectively and qualitatively and shown that the proposed algorithms could reconstruct the desired recovered performance subjectively and objectively.

This paper presents a novel active contour model for image segmentation and bias correction in terms of robustness to initialization and intensity inhomogeneity. In our model, the local image intensities are described by Gaussian distributions with different means and variances. The local Gaussian distribution fitting energy with a new guided image filtering (GIF) regularization is proposed. The new guided image regularization not only considers the spatial information, but also utilizes the local image content. So compared with the traditional algorithms, the proposed model is less sensitive to initialization and converges faster. Comparative experiments show the advantage of the proposed method.

Computing performance is one of the key problems in embedded systems for high-resolution face detection applications. To improve the computing performance of embedded high-resolution face detection systems, a novel parallel implementation of embedded face detection system was established based on a low power CPU-Accelerator heterogeneous many-core architecture. First, a basic CPU version of face detection prototype was implemented based on the cascade classifier and Local Binary Patterns operator. Second, the prototype was extended to a specified embedded parallel computing platform that is called Parallella and consists of Xilinx Zynq and Adapteva Epiphany. Third, the face detection algorithm was optimized to adapt to the Parallella architecture to improve the detection speed and the utilization of computing resources. Finally, a face detection experiment was conducted to evaluate the computing performance of the proposal in this paper. The experimental results show that the proposed implementation obtained a very consistent accuracy as that of the dual-core ARM, and achieved 7.8 times speedup than that of the dual-core ARM. Experiment results prove that the proposed implementation has significant advantages on computing performance.

This paper proposes a novel approach for face recognition when only one sample per individual is available. The proposed technique, referred to as MODPL, determines a one-dimensional projection line for each individual in the dataset. Each of these lines discriminates the corresponding individual with respect to the other people in the database. The vector consisting on the projections of the individual’s raw data on the different projections lines provides an excellent characterization of the individual. Results obtained using the XM2VTS database show that the proposed technique is capable of achieving classification rates similar to the ones obtained by means of the Uniform-pursuit algorithm and at least 5% higher than other currently used techniques that deal with the one sample problem. Two additional sets of experiments were conducted on the BioID and AR databases, where the proposed algorithm showed a performance similar to the state-of-the-art algorithms. Moreover, the proposed technique allows the visualization of the most discriminative features of the individuals.

Studies have discovered that face recognition will benefit from age information. However, since the age estimation is unstable in practice, it is still an open question how to improve face recognition with help of automatic age estimation techniques. This paper presents to improve the performance of face recognition by automatic age estimation. The main contribution is a new age-variational face recognition algorithm based on Bayesian framework (FRAB). By introducing the age estimation result as a prior, the recognition problem is divided into several age-specific sub-problems. As a result, the proposed algorithm leads to two algorithms according to how the age is given. The first one is FRAB-AE, which introduces age estimation result as the age prior. The second one is FRAB-GT, which considers that the ground truth of age information is given. Experimental results are conducted on FG-NET and Morph datasets to evaluate the performance of the proposed framework. It shows that the proposed algorithms is able to make use of age priors to improve the face recognition.

Supercomputing Cloud Platform (SCP) provides a simple online Web way for computer aided engineering (CAE) simulation on supercomputer “Tianhe No.1.” We develop SCP prototype by using service-oriented architecture (SOA). Fuzzy colored Petri nets (FCPN) is selected as the automatic combination technology for the Ontology Web Language for Services (OWL-S) in our SCP. To build the dependency relation graphs among Web services in our SCP, we put forward some definitions of semantic threshold similarity for Web services. Based on these definitions, we propose a generation algorithm to build the FCPN dependency relation graph based on semantic similarity of Web services, and analyze an example about this algorithm. Also, we design an algorithm to simplify the FCPN dependency relation graph for fast responding the user’s requirements. The research works of this paper (SCP prototype) have been applied in real world, and we show the engineering design and application at the end. We will further research the service verification, transaction model and exception recovery mechanism in the future.

Objective: With data drawn from Beijing’s New Rural Cooperative Medical System (NRCMS), the rule characteristics of disease risks are mined in terms of risk factors and risk measurements aiming to discover valuable knowledge within the vast amounts of Beijing’s NRCMS data and provide administrators with a more scientific basis for decision making. Methodology:The association rule algorithm is utilized to recover both potentially valuable knowledge and decision-making information from Beijing’s NRCMS data. Results: The main objects of healthcare in Beijing from 2012 to 2014 include: circulatory diseases in patients 41 years of age or older, pediatric respiratory disease prevention, reproductive healthcare for women of childbearing age, and the prevention and treatment of diabetes in female patients; in county-level hospitals with a relatively low average level of consumption, injuries still resulted in high expenses; the primary post-NRCMS reimbursement level-3 and level-4 high-risk groups were patients of 41–65 years of age. Conclusion: According to the ranking of rule supports, the highest support rule in Beijing is the circulatory diseases of middle-aged patients, especially patients that are hospitalized in county-level medical institutions; the second highest support comes from the utilization of fertility services for women of childbearing age. Suggestions: It is recommended that the rule support rankings should be combined to actively and implement with emphasis major prevention and healthcare services, lower disease risk factors, control NRCMS reimbursement costs, promote the sustainable development of NRCMS, adopt a classified management of mined rules, and establish a decision-making knowledge base.

As a traffic language, sharp turn sign is a kind of important road infrastructure that indicates a sharp turning will show up at the coming road, warning drivers to slow down to ensure the driving safety. In this paper, real vehicle test was carried out on mountain road with an eye tracker equipment. At different driving speeds, parameters of eye movement characteristics in the visual cognition process of sharp turn signs were collected, including distribution of gaze points, fixation and saccade. Simultaneously, driver’s scan paths of recognizing sharp turn signs with different supporting forms were gathered. The results of the analysis of testing data showed that the dispersion of distribution of gaze points would increase with driving velocity. Saccade was the main method for driver to capture information of sharp turn signs. While driving speed was lower than 60km/h, fixation was also one of the methods. For the visual cognition process of sharp turn sign with cantilever, compared to post, the searching scope was wider both in horizontal and vertical directions. This study is beneficial to evaluate the rationality of sharp turn signs, promoting the using efficiency of signs and improving the driving safety on mountain road.

Heterogeneous small cell networks (HSCN), as a promising paradigm to increase end-user data rates and improve the overall capacity, is expected to be a key cellular architecture in 5G wireless networks. However, energy consumed in HSCN is considerable due to the massive use of small cells. In this paper, we investigate the energy consumption issue which stems from the enormous number of running small cell base stations (SBSs) deploying in the HSCN. We first propose power consumption models so as to characterize the active state and the idle state of SBSs, respectively. Then two sleep modes for SBSs tier, i.e. random sleep mode and load-awareness dynamic sleep mode, are proposed. The random sleep is designed based on a binomial distribution of the SBS operation probability. Through the analysis on activeness of SBSs, we define the operation probability for the SBS applying the proposed dynamic sleep mode is associated to its traffic load level. The closed-form expressions of success probability for coverage, which is used to decide whether an active user can connect to a SBS successfully, are derived for the proposed sleep modes. Energy consumption minimizations are presented for the two proposed sleep modes under the success probability constraint. Simulation results prove the effectiveness of the proposed two sleep modes. Different energy saving gains can be achieved via using of the energy saving strategy. The superior of the dynamic sleep mode by comparing the random sleep is also verified in terms of energy consumption, success probability and power efficiency.