• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.95-101
• /
• 2008

Modeling of stock prices forecast has been considered as one of the most difficult problem to develop accurately since stock prices are highly correlated with various environmental conditions including economics and political situation. In this paper, we propose a agent system approach to predict Korea Composite Stock Price Index (KOSPI) using neural network and statistical methods. To minimize mean of prediction error and variation of prediction error, agent system includes sub-agent modules for feature extraction, variables selection, forecast engine selection, and forecasting results analysis. As a first step to develop agent system for KOSPI forecasting, twelve economic indices are selected from twenty two basic standard economic indices using principal component analysis. From selected twelve economic indices, prediction model input variables are chosen again using best-subsets regression method. Two different types data are tested for KOSPI forecasting and the Prediction results showed 11.92 points of root mean squared error for consecutive thirty days of prediction. Also, it is shown that proposed agent system approach for KOSPI forecast is effective since required types and numbers of prediction variables are time-varying, so adaptable selection of modeling inputs and prediction engine are essential for reliable and accurate forecast model.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.412-415
• /
• 2017

In this paper, we propose a multi license plate recognition system using high resolution $360^{\circ}$ omnidirectional IP camera. The proposed system consists of a planar division part of $360^{\circ}$ circular image and a multi license plate recognition part. The planar division part of the $360^{\circ}$ circular image are divided into a planar image with enhanced image quality through processes such as circular image acquisition, circular image segmentation, conversion to plane image, pixel correction using color interpolation, color correction and edge correction in a high resolution $360^{\circ}$ omnidirectional IP Camera. Multi license plate recognition part is through the multi-plate extraction candidate region, a multi-plate candidate area normalized and restore, multiple license plate number, character recognition using a neural network in the process of recognizing a multi-planar imaging plates. In order to evaluate the multi license plate recognition system using the proposed high resolution $360^{\circ}$ omnidirectional IP camera, we experimented with a specialist in the operation of intelligent parking control system, and 97.8% of high plate recognition rate was confirmed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.89-103
• /
• 2020

As we face an aging society, the demand for personal mobility for disabled and aged people is increasing. In fact, as of 2017, the number of electric wheelchair in the country continues to increase to 90,000. However, people with disabilities and seniors are more likely to have accidents while driving, because their judgment and coordination are inferior to normal people. One of the causes of the accident is the interference of personal vehicle steering control due to unbalanced road surface conditions. In this paper, we introduce a encoder type semantic segmentation algorithm that can recognize road conditions at high speed to prevent such accidents. To this end, more than 1,500 training data and 150 test data including road surface damage were newly secured. With the data, we proposed a deep neural network composed of encoder stages, unlike the Auto-encoding type consisting of encoder and decoder stages. Compared to the conventional method, this deep neural network has a 4.45% increase in mean accuracy, a 59.2% decrease in parameters, and an 11.9% increase in computation speed. It is expected that safe personal transportation will be come soon by utilizing such high speed algorithm.

• Journal of Korea Water Resources Association
• /
• v.41 no.3
• /
• pp.341-351
• /
• 2008

Since the damage from the torrential rain increases recently due to climate change and global warming, the significance of flood forecasting and warning becomes important in medium and small streams as well as large river. Through the preprocess and main processes for estimating runoff, diverse errors occur and are accumulated, so that the outcome contains the errors in the existing flood forecasting and warning method. And estimating the parameters needed for runoff models requires a lot of data and the processes contain various uncertainty. In order to overcome the difficulties of the existing flood forecasting and warning system and the uncertainty problem, ANFIS(Adaptive Neuro-Fuzzy Inference System) technique has been presented in this study. ANFIS, a data driven model using the fuzzy inference theory with neural network, can forecast stream level only by using the precipitation and stream level data in catchment without using a lot of physical data that are necessary in existing physical model. Time series data for precipitation and stream level are used as input, and stream levels for t+1, t+2, and t+3 are forecasted with this model. The applicability and the appropriateness of the model is examined by actual rainfall and stream level data from 2003 to 2005 in the Tancheon catchment area. The results of applying ANFIS to the Tancheon catchment area for the actual data show that the stream level can be simulated without large error.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.563-568
• /
• 2007

This paper presents a methodology for predicting nonlinear time series based on the neural network with weighted fuzzy membership functions (NEWFM). The degree of classification intensity is obtained by bounded sum of weighted fuzzy membership functions extracted by NEWFM, then weighted average defuzzification is used for predicting nonlinear time series. The experimental results demonstrate that NEWFM has the classification capability of 92.22% against the target class of GDP. The time series created by NEWFM model has a relatively close approximation to the GDP which is a typical business cycle indicator, and has been proved to be a useful indicator which has the turning point forecasting capability of average 12 months in the peak point and average 6 months in the trough point during 5th to 8th cyclical period. In addition, NEWFM measures the efficiency of the economic indexes by the feature selection and enables the users to forecast with reduced numbers of 7 among 10 leading indexes while improving the classification rate from 90% to 92.22%.

• Journal of Biosystems Engineering
• /
• v.29 no.4
• /
• pp.341-346
• /
• 2004

Recent livestock people concern not only increase of production, but also superior quality of animal-breeding environment. So far, the optimization of the breeding and air environment has been focused on the production increase. In the very near future, the optimization will be emphasized on the environment for the animal welfare and health. Especially, cattle farming demands the precision livestock farming and special attention has to be given to the management of feeding, animal health and fertility. The management of individual animal is the first step for precision livestock farming and animal welfare, and recognizing each individual is important for that. Though electronic identification of a cattle such as RFID(Radio Frequency Identification) has many advantages, RFID implementations practically involve several problems such as the reading speed and distance. In that sense, computer vision might be more effective than RFID for the identification of an individual animal. The researches on the identification of cattle via image processing were mostly performed with the cows having black-white patterns of the Holstein. But, the native Korean and Japanese cattle do not have any definite pattern on the body. The purpose of this research is to identify the Japanese black cattle that does not have a body pattern using computer vision technology and neural network algorithm. Twelve heads of Japanese black cattle have been tested to verify the proposed scheme. The values of input parameters were specified and then computed using the face images of cattle. The images of cattle faces were trained using associate neural network algorithm, and the algorithm was verified by the face images that were transformed using brightness, distortion, and noise factors. As a result, there was difference due to transform ratio of the brightness, distortion, and noise. And, the proposed algorithm could identify 100% in the range from -3 to +3 degrees of the brightness, from -2 to +4 degrees of the distortion, and from 0% to 60% of the noise transformed images. It is concluded that our system can not be applied in real time recognition of the moving cows, but can be used for the cattle being at a standstill.

• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.246-252
• /
• 2018

Hand gestures are attracting attention as a NUI (Natural User Interface) of wearable devices such as smart glasses. Recently, to support efficient media consumption in IoT (Internet of Things) and wearable environments, the standardization of IoMT (Internet of Media Things) is in the progress in MPEG. In IoMT, it is assumed that hand gesture detection and recognition are performed on a separate device, and thus provides an interoperable interface between these modules. Meanwhile, deep learning based hand gesture recognition techniques have been recently actively studied to improve the recognition performance. In this paper, we propose a method of hand gesture recognition based on CNN (Convolutional Neural Network) for various applications such as media consumption in wearable devices which is one of the use cases of IoMT. The proposed method detects hand contour from stereo images acquisitioned by smart glasses using depth information and color information, constructs data sets to learn CNN, and then recognizes gestures from input hand contour images. Experimental results show that the proposed method achieves the average 95% hand gesture recognition rate.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.983-991
• /
• 2019

This study aims to analyze movies which contain various stories according to the size of their shots. To achieve this, it is needed to classify dataset according to the shot size, such as extreme close-up shots, close-up shots, medium shots, full shots, and long shots. However, a typical video storytelling is mainly composed of close-up shots, medium shots, full shots, and long shots, it is not an easy task to construct an appropriate dataset for extreme close-up shots. To solve this, we propose an image cropping method based on the region of interest (ROI) detection. In this paper, we use the face detection and saliency detection to estimate the ROI. By cropping the ROI of close-up images, we generate extreme close-up images. The dataset which is enriched by proposed method is utilized to construct a model for classifying shots based on its size. The study can help to analyze the emotional changes of characters in video stories and to predict how the composition of the story changes over time. If AI is used more actively in the future in entertainment fields, it is expected to affect the automatic adjustment and creation of characters, dialogue, and image editing.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1076-1084
• /
• 2019

In this paper, we introduced a system that extracts metadata by recognizing characters and objects in media using deep learning technology. In the field of broadcasting, multimedia contents such as video, audio, image, and text have been converted to digital contents for a long time, but the unconverted resources still remain vast. Building media archives requires a lot of manual work, which is time consuming and costly. Therefore, by implementing a deep learning-based metadata generation system, it is possible to save time and cost in constructing media archives. The whole system consists of four elements: training data generation module, object recognition module, character recognition module, and API server. The deep learning network module and the face recognition module are implemented to recognize characters and objects from the media and describe them as metadata. The training data generation module was designed separately to facilitate the construction of data for training neural network, and the functions of face recognition and object recognition were configured as an API server. We trained the two neural-networks using 1500 persons and 80 kinds of object data and confirmed that the accuracy is 98% in the character test data and 42% in the object data.