Loading...

Table of Content

    28 February 2015, Volume 20 Issue 1 Previous Issue    Next Issue

    For Selected: Toggle Thumbnails
    Sentiment Analysis for Chinese Text Based on Emotion Degree Lexicon and Cognitive Theories
    WU Xing* (武 星), Lü Hai-tao (吕海涛), ZHUO Shao-jian (卓少剑)
    2015, 20 (1):  1-6.  doi: 10.1007/s12204-015-1579-x
    Abstract ( 745 )  

    The mass data of social media and social networks generated by users play an important role in tracking users'sentiments and opinions online. A good polarity lexicon which can effectively improve the classification results of sentiment analysis is indispensable to analyze the user’s sentiments. Inspired by social cognitive theories, we combine basic emotion value lexicon and social evidence lexicon to improve traditional polarity lexicon. The proposed method obtains significant improvement in Chinese text sentiment analysis by using the proposed lexicon and new syntactic analysis method.

    References | Related Articles | Metrics
    Research on High Power Inter-Channel Crosstalk Attack in Optical Networks
    ZHANG Yin-fa1 (张引发), REN Shuai1* (任 帅), LI Juan1 (李 娟), LIAO Xiao-min1 (廖晓闽),LI Ming1 (李 明), FANG Yuan-yuan2 (方园园)
    2015, 20 (1):  7-13.  doi: 10.1007/s12204-015-1580-4
    Abstract ( 586 )  

    While all-optical networks become more and more popular as the basis of the next generation Internet (NGI) infrastructure, such networks raise many critical security issues. High power inter-channel crosstalk attack is one of the security issues which have negative effect on information security in optical networks. Optical fiber in optical networks has some nonlinear characteristics, such as self phase modulation (SPM), cross phase modulation (XPM), four-wave mixing (FWM) and stimulated Raman scattering (SRS). They can be used to implement high power inter-channel crosstalk attack by malicious attackers. The mechanism of high power inter-channel crosstalk attack is analyzed. When an attack occurs, attack signal power and fiber nonlinear refractive index are the main factors which affect quality of legitimate signals. The effect of high power inter-channel crosstalk attack on quality of legitimate signals is investigated by building simulation system in VPI software. The results show that interchannel crosstalk caused by high power attack signal leads to quality deterioration of legitimate signals propagated in the same fiber. The higher the power of attack signal is, the greater the fiber nonlinear refractive index is. The closer the channel spacing away from the attack signal is, the more seriously the legitimate signals are affected by attack. We also find that when attack position and power of attack signal are constant, attack signal cannot infinitely spread, while its attack ability shows a fading trend with the extension of propagation distance.

    References | Related Articles | Metrics
    Exploiting Local and Global Characteristics for Contrast Based Visual Saliency Detection
    XU Xin1,2* (徐 新), WANG Ying-lin3 (王英林), ZHANG Xiao-long1,2 (张晓龙)
    2015, 20 (1):  14-20.  doi: 10.1007/s12204-015-1581-3
    Abstract ( 580 )  

    Visual saliency is an important cue in human visual system to identify salient region in the image; it can be useful in many applications including image retrieval, object recognition, image segmentation, etc. Image contrast has been used as an effective feature to detect visual salient region. However, the conventional contrast measures either in spectral domain or in spatial domain fail to give sufficient consideration towards the local and global characteristics of the image. This paper presents a visual saliency detection algorithm based on a novel contrast measurement. This measurement extracts the spectral information of image block using the 2D discrete Fourier transform (DFT), and combines with the total variation (TV) of image block in spatial domain. The proposed algorithm is used to perform salient region detection in the image, and compared with state-of-the-art algorithms. The experimental results from the MSRA dataset validate the effectiveness of the proposed algorithm.

    References | Related Articles | Metrics
    Key Technology of 3D Geosciences Modeling in Coal Mine Engineering
    CHE De-fu* (车德福), JIA Guo-bing (贾国兵), JIA Qing-ren (贾庆仁)
    2015, 20 (1):  21-25.  doi: 10.1007/s12204-015-1582-2
    Abstract ( 444 )  

    A new method for simulation technology of laneway engineering seamless excavation based on 3D geoscience modeling (3DGM) was proposed to overcome the deficiency in current research. The generalized triprism (GTP) data model was used as the basic modeling element in this method. The models of geological body were created by the method of rock pillar body partition (RPBP) modeling. The laneway engineering models were built with component method, while the corresponding triangles in sections were connected and transformed into tunnel GTP models. All the GTP models were converted into tetrahedron models based on the smallest vertex identifier (SVID). The simulation and spatial analysis of laneway engineering seamless excavation could be realized through the local hierarchical intersection (LHI) algorithm. The application case showed that the method was fast and effective, and it could meet the needs of design and spatial analysis for mine laneway engineering.

    References | Related Articles | Metrics
    Single Image Super-Resolution Method via Refined Local Learning
    TANG Song-ze*(唐松泽), XIAO Liang (肖亮), LIU Peng-fei (刘鹏飞)
    2015, 20 (1):  26-31.  doi: 10.1007/s12204-015-1583-1
    Abstract ( 546 )  

    In this paper, we propose a refined local learning scheme to reconstruct a high resolution (HR) face image from a low resolution (LR) observation. The contribution of this work is twofold. Firstly, multi-direction gradient features are extracted to search the nearest neighbors for each image patch, then the non-negative matrix factorization (NMF) is used to reduce the complexity in weight calculation, and the initial HR embedding is estimated from the training pairs by preserving local geometry. Secondly, a global reconstruction constraint and post-processing by non-local filtering is incorporated into super-resolution (SR) reconstruction process to reduce the image artifacts and further improve the image visual quality. Experimental results show that the proposed algorithm improves the SR performance both in subjective and objective assessments compared with several existing methods.

    References | Related Articles | Metrics
    Generating Domain-Specific Affective Ontology from Chinese Reviews for Sentiment Analysis
    LIU Li-zhen (刘丽珍), LIU Hao (刘昊), WANG Han-shi* (王函石),SONG Wei (宋巍), ZHAO Xin-lei (赵新蕾)
    2015, 20 (1):  32-37.  doi: 10.1007/s12204-015-1584-0
    Abstract ( 586 )  
    Considering the diversities and ambiguities of opinion expressions in Chinese online product reviews, normal sentiment analysis technologies have exposed their inadequateness in both classification accuracy and identifying effectiveness. We propose a novel approach which can easily identify product features and corresponding opinions by building a domain-specific affective ontology and thus mapping comment sentences to the objects defined in the affective ontology. Ontology is created automatically by processing the online reviews; both product features and affective words are presented as nodes which are connected to each other by their semantic relationship. Furthermore, in order to increase the accuracy, we introduce a dynamic polarity detection technique for affective words whose sentimental tendencies are dependent on particular contexts. The experimental results clearly demonstrate the performance improvement of our approach compared with others in real world online product reviews for classification tests.
    References | Related Articles | Metrics
    Simplified Group Search Optimizer Algorithm for Large Scale Global Optimization
    ZHANG Wen-fen (张雯雰)
    2015, 20 (1):  38-43.  doi: 10.1007/s12204-015-1585-z
    Abstract ( 643 )  
    A simplified group search optimizer algorithm denoted as “SGSO” for large scale global optimization is presented in this paper to obtain a simple algorithm with superior performance on high-dimensional problems. The SGSO adopts an improved sharing strategy which shares information of not only the best member but also the other good members, and uses a simpler search method instead of searching by the head angle. Furthermore, the SGSO increases the percentage of scroungers to accelerate convergence speed. Compared with genetic algorithm (GA), particle swarm optimizer (PSO) and group search optimizer (GSO), SGSO is tested on seven benchmark functions with dimensions 30, 100, 500 and 1 000. It can be concluded that the SGSO has a remarkably superior performance to GA, PSO and GSO for large scale global optimization.
    References | Related Articles | Metrics
    A Two-Stage Feature Selection Method for Text Categorization by Using Category Correlation Degree and Latent Semantic Indexing
    WANG Fei (王飞), LI Cai-hong* (李彩虹), WANG Jing-shan (王景山),XU Jiao (徐娇), LI Lian (李廉)
    2015, 20 (1):  44-50.  doi: 10.1007/s12204-015-1586-y
    Abstract ( 591 )  
    With the purpose of improving the accuracy of text categorization and reducing the dimension of the feature space, this paper proposes a two-stage feature selection method based on a novel category correlation degree (CCD) method and latent semantic indexing (LSI). In the first stage, a novel CCD method is proposed to select the most effective features for text classification, which is more effective than the traditional feature selection method. In the second stage, document representation requires a high dimensionality of the feature space and does not take into account the semantic relation between features, which leads to a poor categorization accuracy. So LSI method is proposed to solve these problems by using statistically derived conceptual indices to replace the individual terms which can discover the important correlative relationship between features and reduce the feature space dimension. Firstly, each feature in our algorithm is ranked depending on their importance of classification using CCD method. Secondly, we construct a new semantic space based on LSI method among features. The experimental results have proved that our method can reduce effectively the dimension of text vector and improve the performance of text categorization.
    References | Related Articles | Metrics
    Research of Improved Fuzzy c-means Algorithm Based on a New Metric Norm
    MAO Li1 (毛力), SONG Yi-chun1* (宋益春), LI Yin1 (李引),YANG Hong2 (杨弘), XIAO Wei2 (肖炜)
    2015, 20 (1):  51-55.  doi: 10.1007/s12204-015-1587-x
    Abstract ( 563 )  

    For the question that fuzzy c-means (FCM) clustering algorithm has the disadvantages of being too sensitive to the initial cluster centers and easily trapped in local optima, this paper introduces a new metric norm in FCM and particle swarm optimization (PSO) clustering algorithm, and proposes a parallel optimization algorithm using an improved fuzzy c-means method combined with particle swarm optimization (AF-APSO). The experiment shows that the AF-APSO can avoid local optima, and get the best fitness and clustering performance significantly.

    References | Related Articles | Metrics
    Feature Extraction of Bearing Vibration Signals Using Second Generation Wavelet and Spline-Based Local Mean Decomposition
    WEN Cheng-yu* (文成玉), DONG Liang (董良), JIN Xin (金欣)
    2015, 20 (1):  56-60.  doi: 10.1007/s12204-015-1588-9
    Abstract ( 688 )  
    In order to extract the fault feature frequency of weak bearing signals, we put forward a local mean decomposition (LMD) method combining with the second generation wavelet transform. After performing the second generation wavelet denoising, the spline-based LMD is used to decompose the high-frequency detail signals of the second generation wavelet signals into a number of production functions (PFs). Power spectrum analysis is applied to the PFs to detect bearing fault information and identify the fault patterns. Application in inner and outer race fault diagnosis of rolling bearing shows that the method can extract the vibration features of rolling bearing fault. This method is suitable for extracting the fault characteristics of the weak fault signals in strong noise.
    References | Related Articles | Metrics
    Mutual Information Optimization Based Dynamic Log-Polar Image Registration
    ZHANG Kui* (张葵), ZHANG Xiao-long (张晓龙), XU Xin (徐新), FU Xiao-wei (付晓薇)
    2015, 20 (1):  61-67.  doi: 10.1007/s12204-015-1589-8
    Abstract ( 838 )  
    Log-polar transformation (LPT) is widely used in image registration due to its scale and rotation invariant properties. Through LPT, rotation and scale transformation can be made into translation displacement in log-polar coordinates, and phase correlation technique can be used to get the displacement. In LPT based image registration, constant samples in digitalization processing produce less precise and effective results. Thus, dynamic log-polar transformation (DLPT) is used in this paper. DLPT is a method that generates several sample sets in axes to produce several results and only the effective results are used to get the final results by using statistical approach. Therefore, DLPT can get more precise and effective transformation results than the conventional LPT. Mutual information (MI) is a similarity measure to align two images and has been used in image registration for a long time. An optimal transform for image registration can be obtained by maximizing MI between the two images. Image registration based on MI is robust in noisy, occlusion and illumination changing circumstance. In this paper, we study image registration using MI and DLPT. Experiments with digitalizing images and with real image datasets are performed, and the experimental results show that the combination of MI with DLPT is an effective and precise method for image registration.
    References | Related Articles | Metrics
    Comparison of Color and Grayscale Simulated TV-Graphics in Rendezvous and Docking
    ZHAO Zai-qian (赵再骞), CHAO Jian-gang (晁建刚), ZHANG Yan (张炎),WANG Jin-kun (王金坤), HU Hong* (胡弘)
    2015, 20 (1):  68-75.  doi: 10.1007/s12204-015-1590-2
    Abstract ( 593 )  
    Subjective evaluation is one of the most important methods of assessing the fidelity of a virtual dynamic scene, whose results could be seen as a reference to improve a rendering method. In the present study, we apply a rendering method to the color rendezvous and docking (RVD) scene, where one shadow algorithm and three tone mapping operator algorithms are used to process the scene based on the distance between two spacecrafts. The grayscale RVD scene is transformed from the color RVD scene, and each RVD scene is desired to make comparisons with the real RVD-video recorded in SZ-10 mission. In addition, we perform an evaluation on 36 subjects to compare the results. The results show that shadow effects have important roles in RVD virtual scenes, where they enhance the sense of realism and immersion. Shadows, high brightness, contrast and luminance are highly correlated with the overall preference, and the grayscale scene receives better evaluations than the color scene. The analysis of these conclusions is vital for improving the algorithms used to render color virtual space scenes when virtual scenes for astronaut training in Chinese space station mission are prepared.
    References | Related Articles | Metrics
    AR-Dedupe: An Efficient Deduplication Approach for Cluster Deduplication System
    XING Yu-xuan1* (邢玉轩), XIAO Nong1 (肖侬), LIU Fang1 (刘芳), SUN Zhen1 (孙振), HE Wan-hui2 (何晚辉)
    2015, 20 (1):  76-81.  doi: 10.1007/s12204-015-1591-1
    Abstract ( 709 )  
    As data are growing rapidly in data centers, inline cluster deduplication technique has been widely used to improve storage efficiency and data reliability. However, there are some challenges faced by the cluster deduplication system: the decreasing data deduplication rate with the increasing deduplication server nodes, high communication overhead for data routing, and load balance to improve the throughput of the system. In this paper, we propose a well-performed cluster deduplication system called AR-Dedupe. The experimental results of two real datasets demonstrate that AR-Dedupe can achieve a high data deduplication rate with a low communication overhead and keep the system load balancing well at the same time through a new data routing algorithm. In addition, we utilize application-aware mechanism to speed up the index of handprints in the routing server which has a 30% performance improvement.
    References | Related Articles | Metrics
    A Strategy for Middleman Attack Prevention in Remote Desktop Protocol
    HE Jing-sha1,2 (何泾沙), XU Chen1* (徐琛), ZHANG Yi-xuan1 (张伊璇), ZHOU Shi-yi2 (周世义)
    2015, 20 (1):  82-85.  doi: 10.1007/s12204-015-1592-0
    Abstract ( 681 )  
    This paper introduces the middleman attack methods which are against the remote desktop protocol (RDP), discusses advantages and disadvantages of several current mainstream prevention strategies, and puts forward a new prevention strategy. The strategy, taking advantage of the original key agreement process of the RDP, designs a piecewise authentication scheme of the key agreement. Using the strategy can achieve the purpose of prevention and detection of middleman attacks. Finally, the security of the strategy is analyzed.
    References | Related Articles | Metrics
    Research of Consistency Maintenance Mechanism in Real-Time Collaborative Multi-View Business Modeling
    CAI Hong-ming* (蔡鸿明), JI Xiao-feng (计晓峰), BU Feng-lin (步丰林)
    2015, 20 (1):  86-92.  doi: 10.1007/s12204-015-1593-z
    Abstract ( 486 )  
    Real-time collaborative editing (RTCE) can support a group of people collaboratively work from distributed locations at the same time. However, consistency maintenance is one key challenge when different types of conflicts happen. Therefore a common synchronous mechanism is proposed to support consistency maintenance in the process of multi-view business modeling. Based on operation analysis on different views of models in the real-time collaborative editing system, detection of potential conflicts is realized by means of a decision-making tree. Then consistency maintenance provides a comprehensive and applicable conflicts detection and resolution for collaborative business modeling. Finally, a prototype of collaborative multi-view business modeling system is introduced to verify the approach. The point is that the mechanism proposes a comprehensive solution for collaborative multi-view business modeling.
    References | Related Articles | Metrics
    A Thermometer Based on Diverse Types Thermocouples and Resistance Temperature Detectors
    ZHU Min-ling (朱敏玲)
    2015, 20 (1):  93-100.  doi: 10.1007/s12204-015-1594-y
    Abstract ( 473 )  
    A universal and low-cost temperature thermometer is realized via a special circuit, integrated circuit chip with microprocessor and analog to digital converter, and digital bus interface. Various thermocouples and resistance temperature detectors used for temperature sensing may be connected to same thermometer. A special signal condition circuitry is designed and a matching algorithm is proposed. A novel calibration method named disassembled calibration is proposed in order to enhance efficiency and flexibility for the whole system. Additionally, it presents a combination method of low order polynomial fitting and piecewise linearity for the nonlinearity calibration of the thermocouple and the resistance temperature detector. A cold junction compensation based on digital way is described. And the matching algorithm and calibration method may eliminate errors stemming from excitation voltage source and reference voltage source, and can weaken quantization error of analog to digital converter and drift of components, too. Furthermore, the 400 times oversampling is completed by sequential and equal interval sampling to upgrade accuracy of analog to digital converter from original 12 to 15 bits and to raise signal-to-noise ratio. Finally, during a long time monitoring, experiment results show that errors at each static point are less than ±0.2?C for the thermocouple system and less than ±0.1?C for the resistance temperaturedetector system.
    References | Related Articles | Metrics
    Online Mind-Map as Interface of Electronic Resource Integration and Sharing
    LIU Xiao-qiang1*(刘晓强), ZHANG Tian-xin1 (章田鑫), TAO Li2 (陶莉),REN Jian-jun1 (任建军), LI Bai-yan1 (李柏岩), DU Ming1 (杜明)
    2015, 20 (1):  101-105.  doi: 10.1007/s12204-015-1595-x
    Abstract ( 460 )  
    The paper aims to research on online mind map as interface of learning resource integration and sharing. We developed a web application that provides a interface to allow users to create a knowledge mind map. With the online mind mapping tool, the electronic learning resource will be discovered and shared in the form of subject-oriented package, it is more flexibly than the other E-Learning systems, and the interaction and cooperation of the users are strengthened to some extent.
    References | Related Articles | Metrics
    Semantic-Based Knowledge Categorization and Organization for Product Design Enterprises
    LIU Xi-juan1* (刘溪涓), WANG Ying-lin2 (王英林)
    2015, 20 (1):  106-112.  doi: 10.1007/s12204-015-1596-9
    Abstract ( 510 )  
    Former knowledge engineering research aimed at boosting automatic reasoning. However recent knowledge management research focused on promoting the knowledge sharing and reusing among the people. Because of the different aims between the two directions, former knowledge representation schemata, such as rule based representation, frame from knowledge engineering research does not fit to the current knowledge management scenarios. In this paper, for the purpose of building knowledge management systems for product design enterprises, knowledge items are classified into seven types based on the semantics of their usage. Then their representations are discussed respectively. Based on the above classification, a knowledge representation meta-model and a basic domain ontology reference model for cooperative knowledge management systems are put forward. The reference model is an abstraction that can be reused and extended in knowledge management systems of different enterprises. Finally, the patterns of knowledge acquisition processes in cooperative knowledge management scenarios of product design processes are studied.
    References | Related Articles | Metrics
    A Context-Aware Medical Instant Message Middleware
    CHENG Hai-xia (成海霞), MIN Ling-tong (闵令通), Lü Xu-dong (吕旭东), DUAN Hui-long (段会龙)
    2015, 20 (1):  113-117.  doi: 10.1007/s12204-015-1597-8
    Abstract ( 506 )  
    Communication or the lack of it has been complained to be a major contributor to medical errors in healthcare. To enhance communication in hospital, diverse communication mechanisms are proposed. However, human directed communication in a complex clinical setting in which many people play diverse roles and need to collaborate in many parallel tasks is always in chaos and inefficient. Context-aware communication which can help target who should be communicated and what information should be provided for different scenarios has the potential to improve the communication in hospital. This paper proposes a flexible, automated and asynchronous context-aware medical instant message (IM) middleware which support dispatch, forward and routing different message to the right person in the right time based on the context information. A prototype of this IM communication middleware was implemented in real clinical setting for evaluation. The preliminary results demonstrate its novel features and clinical feasibility.
    References | Related Articles | Metrics
    Identifying the Core Competitive Intelligence Based on Enterprise Strategic Factors
    SUN Lin1,2* (孙琳), WANG Yan-zhang1 (王延章)
    2015, 20 (1):  118-123.  doi: 10.1007/s12204-015-1598-7
    Abstract ( 541 )  
    Competitive intelligence (CI) is a key factor in helping business leaders gain and maintain competitive advantages. The emergence of big data and Web 2.0 has created new opportunities and more challenges for enterprises to effectively obtain CI. This paper attempts to explore a CI identification method based on strategic factors (SF). By filtering process before CI collection, the core CI, closely related to critical success factors and crisis inducement factors, are identified reliably and efficiently. Based on knowledge element model and multiattribute fusion method, emphasis is placed on the construction of a criterion function by which the SF thesaurus in achieving CI objectives is established. The advantages of this method lie not only in the capability of mining the core CI from massive data, but also in the foundation of efficient CI storage and analysis. This paper is of significance to make a thorough inquiry on CI obtaining and fusing methods of CI system in era of big data. Experiment results verified the feasibility and validity of this study.
    References | Related Articles | Metrics
    Critical Conditions for Left-Turn Lane’s Stop Line Backwards Setting Under Exclusive Left-Turn Phase
    WEI Fu-lu1,2 (魏福禄), QU Zhao-wei1* (曲昭伟), CHEN Yong-heng1* (陈永恒), WEI Ming-li1 (尉明丽), LI Ying-shuai3 (李英帅)
    2015, 20 (1):  124-128.  doi: 10.1007/s12204-015-1599-6
    Abstract ( 612 )  
    Aiming at the problem that the vehicles always turn left in advance which causes heavy conflicts in the intersection and effected traffic efficiency, the solution of the left-turn lane’s stop line backwards setting was proposed, and the critical conditions on the stop line’s setting were studied. Firstly, we studied the characteristics of trajectories distribution in the release process of turning left in advance vehicles. Based on that, we proposed to move the stop line backwards to solve the problem of turning left in advance. Considering the intersection’s geometric features and the vehicle operation features, the geometric critical condition was given for setting the position of left-turn lane’s stop line. And then the model of left-turn vehicles’ queuing length was established based on queuing theory and traffic wave theory. By using queuing length model, the flow restrictions of stop line backwards could be found. Assuming left-turn vehicles’ arrival rate is stable in a certain period of time, the minimum green time and the maximum red time of left-turn phase were given after the stop line was set up. According to the changes of the vehicles’ turning paths, the shortest yellow setting recommendation was given. Finally, the application of the critical limits used in stop line backwards setting was demonstrated. The research result could provide a theoretical basis for traffic signs and markings’ setting and perfect the relevant laws and regulations.
    References | Related Articles | Metrics