2014, Vol.19, No.8

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

pISSN : 1598-849X / eISSN : 2383-9945
https://journal.kci.go.kr/jksci

This paper proposes a parallel implementation of the video based 4-stage fire detectionalgorithm using a general-purpose graphics processing unit (GPGPU) to support real-timeprocessing of the high computational algorithm. In addition, this paper compares the performanceof the GPGPU based fire detection implementation with that of the CPU implementation to showthe effectiveness of the proposed method. Experimental results using five fire included videos withan SXGA (1400×1050) resolution, the proposed GPGPU implementation achieves 6.6x better performance that the CPU implementation, showing 30.53ms per frame which satisfies real-timeprocessing (30 frames per second, 30fps) of the fire detection algorithm

In This paper, we propose the unsupervised learning and fuzzy logic-based coupled dataclassification method base on ART. The unsupervised learning-based data classification helpsimprove the grouping technique, but decreases the processing efficiency. However, the dataclassification requires the decision technique to induce high success rate of data classification withoptimal threshold. Therefore it is also necessary to solve the uncertainty of the threshold decision. The proposed method deduces the optimal threshold with the designing of fuzzy parameter andrules. In order to evaluate the proposed method, we design the simulation model with the GPCR(Gprotein coupled receptor) data in cloud computing environment. Simulation results verify theefficiency of our method with the high recognition rate and low processing time.

Analysis of influential factors on water consumption in households will help predicting the waterdemand of end-use in household and give an explanation to cause on the change of trend. In thisresearch, the data are gathered by radio telemetry system which is combined electronic flow-meterand wireless communication system in 140 household in Korea. Using this data, we estimate foreach residential type to determine liter per capita day. we used real data to predict bathtub andwashbowl water-uses and compared the ordinary least square regression model and autoregressiveregression error model. The results of this study can be applied in the planning stages of water andwaste water facilities.