samad noorizad
@iums.ac.ir
Iran university of medical sciences
EDUCATION
Anesthesia
RESEARCH INTERESTS
Anesthesia
Scopus Publications
Scopus Publications
Zhizhou Kong and Zixing Cai
IEEE
Semi-supervised classification algorithms attempt to overcome this major limitation by also using unlabelled examples. In this framework, This paper proposes a method working under a multi-view setting. we motivate BIC to optimize classifiers selection and use DCCA (Detrended Canonical Correspondence Analysis) to complete unlabeled examples selection by eliminating the arch effect. We empirically show that classification performance increases by improving the semi-supervised algorithm's ability to correctly assign labels to previously-unlabelled data. Experiments validate the effectiveness of the proposed method.
Zhizhou Kong and Zixing Cai
IEEE
Information Fusion is a valid way which can decrease the uncertainty of making decision, and is also a hotspot. The paper makes some work on a important problem about Fuzzy Integral, that is how to get the Fuzzy Density, and compares two typical means. Based on 11 UCI data set, this paper conducts the compared experiment of several Information Fusion methods. It is compared with references 4 and 5. The result shows that the Fuzzy Integral method based on probability is better than the Fuzzy Integral method based on beliefs, is also better than the best results of single classifiers in references 4. The result also shows that the Fuzzy Integral method based on beliefs is nearly equal to the best results of fusion classifiers in references 5 in general, better than the average fusion method, and is also better the best results of single classifiers in references 4.
Zhizhou Kong, Zixing Cai, and Yulin Chen
IEEE
As the common queue management strategy of Router, queue trail dropping has serious limitations such as full queue, whole synchronization and dead lock which leads to passive congestion management after the queue is full. Therefore the strategy easily leads to network congestion even crash. There are some good research fruits of active queue management (AQM) in keeping short queue length and keeping reasonable balance between high throughput and low time delay. Whereas in many of its arithmetic, there are still certain shortages, for example, the improper queue management arithmetic might lead to the problems of whole synchronization linked by TCP, the queue being full for a long time and the problem of equity in managing the outburst operation. Based on C-R fuzzy reasoning strategy model, this paper designed an aptitude pocket dropping strategy to further optimize the property of Router. The emulational experiments indicate that the property of the strategy, which can better resist the outburst interference, is better than that of classical RED arithmetic.
Dong Guan, Zixing Cai, and Zhizhou Kong
IEEE
In the paper, a micro-genetic algorithm (MGA) based approach to the optimization of reactive power and voltage profiles improvement and real power loss minimization is present. The proposed strategy aims to prevent voltage fluctuations and unconvergence cases by coordinating the operation of reactive power and voltage control equipments. The problem is formulated as a combinatorial nonlinear optimization problem. Genetic algorithms (GA) are well-known global search technique anchored on the mechanisms of natural selection and genetics. Because of the time intensive nature of the conventional GA, the MGA is proposed as a more time efficient alternative. The feasibility and effectiveness of the developed algorithm is tested and verified on the Hunan grid power system.
Zhizhou Kong, Shenggang Yang, Zixing Cai, and Dong Guan
IEEE
Since clustering ensemble was firstly presented in 2002, it is more and more becoming a new hotspot to improve clustering performance. Through using the mechanism of information rolling and selecting component clusters with the help of mutual information weight, this paper proposes a new clustering ensemble algorithm. Experiments show that this algorithm could effectively improve the clustering results.
Zhizhou Kong, Lai Wei, Shenggang Yang, Dong Guan, and Zixing Cai
IEEE
Clustering Ensemble is more and more becoming a new hotspot to improve clustering performance since it was firstly presented in 2002. Through using the mechanism of the integrate mechanism of testing and information rolling method to decrease the error probability of matching cluster members, and using a method of category weight to ensemble clustering members, this paper proposes a novel Clustering Ensemble algorithm. Experiments show that this algorithm could effectively improve the clustering results.
Zhizhou Kong, Lai Wei, Shenggang Yang, Dong Guan, and Zixing Cai
IEEE
Fuzzy Integral is a valid method which can decrease the uncertainty of making decision. During this researching field how to get the fuzzy density is a difficult problem ,and is also a hotspot. This paper brings forward a new algorithm to determine fuzzy density compared with the existing algorithms this method the emulational result testifies its validity.