• The KIPS Transactions:PartD
• /
• v.10D no.2
• /
• pp.317-326
• /
• 2003

The possession rate of residential telephones tend to decrease as mobile phones are widely spread. There is also a decrease in the access rate of the qualified respondents due to the low rate of phone book registration and that of house owner's presence at home. Such a change in telephone survey environment calls for another survey-channel which makes good use of new telecommunication services. In this paper, a mobile survey system was designed and performed by the use of SMS (Short Message Service) which is a kind of mobile data communication service. The system draws the sample by using random digit sampling based on 'quota allocation', and sends the SMS to the sample according to the arranged scheduler. Then, the survey-panel which received the SMS connects to the responding server by pressing the 'send' button (which is connected by the callback number), responding to the question. As a result, the responding value is stored in the database and is analyzed in real-time. This system is distinguished from other research methodologies for its simplicity in data collection, its inexpensive research price, and the innovatively low research time.

• The Journal of the Convergence on Culture Technology
• /
• v.3 no.4
• /
• pp.165-169
• /
• 2017

CNN(Convolutional Nerual Network) is one of the algorithms that show superior performance in image recognition and classification among machine learning algorithms. CNN is simple, but it has a large amount of computation and it takes a lot of time. Consequently, in this paper we performed an parallel processing unit for the convolution layer, pooling layer and the fully connected layer, which consumes a lot of handling time in the process of CNN, through the SIMT(Single Instruction Multiple Thread)'s structure of GPGPU(General-Purpose computing on Graphics Processing Units).And we also expect to improve performance by reducing the number of memory accesses and directly using the output of convolution layer not storing it in pooling layer. In this paper, we use MNIST dataset to verify this experiment and confirm that the proposed CNN structure is 12.38% better than existing structure.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.1
• /
• pp.59-67
• /
• 2008

In this paper we propose an algorithm to extract the license plate regions from Korean car images. The idea of this paper is that we first find the four digits in the input car image and then segment the plate region using the digit information. Out method has advantage of segmenting simultaneously the plate regions and four digits regions. The first step finds and groups the connected components with proper sizes as candidate digits. The second step applies an serial alignment condition to find out probable 4-digits. In the third step, we recognize the candidate digits and assign the confidence values to each of them. The final step extracts the license plate region which has the highest confidence value. We used the Perfect Metrics classification algorithm to estimate the confidence. In our experiment, we got 97.23% and 95.45% correct detection rates, 0.09% and 0.11% false detection rates for 4,600 daytime and 264 nighttime images, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.35-41
• /
• 2003

Feature vectors for conventional speech recognition are usually extracted in full frequency band. Therefore, each sub-band contributes equally to final speech recognition results. In this paper, feature Teeters are extracted indepedently in each sub-band. The cepstral resolution of each sub-band feature is controlled for the optimal speech recognition. For this purpose, different dimension of each sub-band ceptral vectors are extracted based on the multi-band approach, which extracts feature vector independently for each sub-band. Speech recognition rates and clustering quality are suggested as the criteria for finding the optimal combination of sub-band Teeter dimension. In the connected digit recognition experiments using TIDIGITS database, the proposed method gave string accuracy of 99.125%, 99.775% percent correct, and 99.705% percent accuracy, which is 38%, 32% and 37% error rate reduction relative to baseline full-band feature vector, respectively.