Search results for: Fulian Yin
chapter
To overcome the unsatisfying trend prediction results of network public opinion in the present research, this paper put forward a method of Levenberg-Marquardt-based Back-Propagation (LM-BP) neural network algorithm to predict the network public opinion trend. Taking the microblog as the research object, the effectiveness and reliability of the method are proved with some real data in this article...
chapter
Along with the changing interest of Cable Television users, it is difficult to make personalized recommendation and put advertisement intelligently for users. This research is aimed at the viewing behaving of Cable Television users based on long-term interest. The users' interest attenuation model and the interest enhancement model are constructed to precisely describe the users' viewing behaviors...
chapter
Aiming at reducing the overload of cable television information and the difficulty to pinpoint users, this research employs the directed preview method of CATV's live programs which is grounded in labels. Long-term and short-term models of users' viewing behaviors and models of period preference are constructed accurately and can multi-dimensionally describe users' viewing behaviors. Based on labels,...
chapter
In this paper, we present a tag-based recommendation system which generates personalized recommendations for TV users. The proposed approach, based on collaborative filtering recommendation algorithm, uses similarity calculation and vector production to process the users' data. In order to test the applicability of this method, we operated several experiments on random users' data, and the overall...
chapter
The public comments on the social hot events on Weibo has attracted lots of attentions in recent years. To remedy the shortage of sentiment analysis about typical events on Weibo, the classification method based on sentiment dictionary is put forward in this paper, and the accuracy rate is close to 50%. This paper also proposed a sentiment classification method based on Naive Bayesian in order to...
chapter
In this paper, the characteristics of five main subjective weighting methods for multi-attribute decision making problems are analyzed by means of horizontal and longitudinal comparison. And the five weighting methods are applied to the field of broadcasting and television program evaluation respectively to obtain the evaluation results calculated by five methods and analyze the relationship between...
chapter
Aiming to meet the demand of intellectual delivery business, this paper puts forward Broadcast Television user dividing groups technology based on concept data clustering ensemble. Firstly, by Glass data, Blance data and Zoo data in UCI, the paper verify that concept data clustering ensemble technique based on K-MODES method can get more stable and more accurate results than K-MEANS method. Secondly,...
chapter
This paper studied the information overload brought by abundant digital television (TV) program resources and media image which need to adapt to the changing market environment by crowd mining based on audience behavior analysis. When the audience crowd is classified to several levels, personalized audience behavior analysis method and group audience behavior analysis method are proposed separately...
article
Chinese Journal of Electronics > 2015 > 24 > 1 > 212 - 217
Dual polarization technology is gradually promoted in our country after Doppler weather radar network. It extends the capabilities of conventional Doppler radar, and can directly detect the differential reflectivity factor and the zero-lag correlation coefficient and so on which are related with the micro-physics characteristics of precipitation. Considering that small error may lead to erroneous...
chapter
This paper proposes a study of Delay ring Tagging of Television Programs to overcome the disadvantages of treelike and singly structured classification systems of television programs. For those structured classification systems, it is incapable to meet the increasing need of in-depth research, analysis of personalized recommendation and advertising targeted delivery. This paper proposes three methods...
chapter
A data mining mode of decision support system (DSS) fills up the blank of broadcasting and television area. It consists of four bases which are data base, model base, method base and knowledge base. This paper builds the architecture of model base and gives the model for typical use case according to effective demand analysis. The result of typical model for broadcasting and television DSS proves...
chapter
In this paper, a projection approximation subspace tracking with deflation (PASTd) algorithm based on subspace technique for narrowband interference (NBI) suppression of code division multiple access (CDMA) is proposed to improve the performance of recursive least square (RLS) algorithm based on direct matrix inverse (DMI) code-aided technique firstly. Specifically, this technique is against the type...
chapter
A broadcasting and television decision support system based on use case is proposed. This method fills up the blank of demand analysis for broadcasting and television chain and provides an effective measure. Under the practical analysis of demand, this paper designs the model of use case which applied to broadcasting and television system. The result of typical use case for decision support system...
chapter
In this paper, an adaptive recursive least square prediction and least mean square code-aided (RLS-LMS) technique for narrow-band interference (NBI) rejection of code division multiple access (CDMA) system is proposed. This technique is to solve the problem that adaptive LMS code-aided technique has poor convergence and adaptive RLS code-aided technique has high complexity. Specifically, the proposed...
chapter
A blind adaptive subspace code-aided technique for suppression of narrowband interference (NBI) and multiple access interference (MAI) in code division multiple access (CDMA) networks is proposed. This technique is based on projection approximation subspace tracking with deflation (PASTd) algorithm to improve the performance of recursive least square (RLS) algorithm based on direct matrix inverse...
chapter
A blind subspace code-aided technique for suppression of narrowband interference (NBI) and multiple access interference (MAI) in code division multiple access (CDMA) networks is proposed. This technique is based on the minimum mean output energy (MMOE) algorithm to improve the performance of direct matrix inverse (DMI) code-aided technique. Specifically, the performance of this technique against the...
chapter
To fill up the blank of decision support for business operation support system (BOSS) of broadcasting and television, a data acquisition and data mining scheme is proposed. The data acquisition brings out the desiging about data classification, data transformation and data warehouse. And data mining provides object demands of broadcasting and television chain. Under the background of "integration...
chapter
A decision support system for broadcasting and television is proposed. This broadcasting and television decision support system (BT-DSS) filled the blank of broadcasting and television area under the background of "integration of three networks". This paper designs the model of BT-DSS which based on data acquisition and data mining for solving techniques. This system exhibits the excellent...
chapter
This paper analyzes zero-forcing (ZF) code-aided narrow-band interference (NBI) rejection in synchronous direct-sequence code-division multiple access (DS-CDMA) systems of complex channel circumstance. The performance of decoding is badly affected based on general ZF code-aided techniques because of the phase of complex gain accounting for channel effects. The system based on modified ZF code-aided...
