• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.107-116
• /
• 2009

This paper presents an approach to detect arrhythmia using heart rate variability and a fuzzy neural network. The proposed algorithm diagnoses arrhythmia using 32 RR-intervals that are 25 seconds on average. We extract six statistical values from the 32 RR-intervals, which are used to input data of the fuzzy neural network. This paper uses the neural network with weighted fuzzy membership functions(NEWFM) to diagnose arrhythmia. The NEWFM used in this algorithm classifies normal and arrhythmia. The performances by Tsipouras using the 48 records of the MIT-BIH arrhythmia database was below 80% of SE(sensitivity) and SP(specificity) in both. The detection algorithm of arrhythmia shows 88.75% of SE, 82.28% of SP, and 86.31% of accuracy.

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1561-1567
• /
• 2015

Abstract Semi-supervised learning is an area in machine learning that employs both labeled and unlabeled data in order to train a model and has the potential to improve prediction performance compared to supervised learning. Graph-based semi-supervised learning has recently come into focus with two phases: graph construction, which converts the input data into a graph, and label inference, which predicts the appropriate labels for unlabeled data using the constructed graph. The inference is based on the smoothness assumption feature of semi-supervised learning. In this study, we propose an enhanced label inference algorithm by incorporating the importance of each vertex. In addition, we prove the convergence of the suggested algorithm and verify its excellence.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.26 no.12
• /
• pp.1100-1107
• /
• 2015

In this paper, we propose an algorithm to identify Wobble PRI and Sinusoidal PRI among Radar pulses. We applied not only the DTOA(Difference Time Of Arrival) concept of radar pulse signals incoming to antennas but also a rising and falling cub characteristic of those PRIs. After making a program by such algorithm, we input each 40 data to Wobble PRI's and Sinusoidal PRI's identification programs and in result, those programs fully processed the data the according to expectations. In the future, those programs can be applied to the ESM, ELINT system.

• The KIPS Transactions:PartA
• /
• v.8A no.1
• /
• pp.48-55
• /
• 2001

Using BDD, we can represent Boolean functions uniquely and compactly, Hence, BDD have become widely used for CAD applications, such as logic synthesis, formal verification, and etc. The size of the BDD representation for a function is very sensitive to the choice of orderings on the input variables. Therefore, it is very important to find a good variable ordering which minimize the size of the BDD. Since finding an optimal ordering is NP-complete, several heuristic algorithms have been proposed to find good variable orderings. In this paper, we propose a variable ordering algorithm based on the $\mu$O(microcanonical optimization). $\mu$O consists of two distinct procedures that are alternately applied : Initialization and Sampling. The initialization phase is to executes a fast local search, the sampling phase leaves the local optimum obtained in the previous initialization while remaining close to that area of search space. The proposed algorithm has been experimented on well known benchmark circuits and shows superior performance compared to a algorithm based on simulated annealing.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.4
• /
• pp.247-254
• /
• 2004

The mechanical informations such as the rotor speed and angle are required to operate the Cylindrical Permanent Magnet Synchronous Motor(PMSM). A resolver or encoder is typically used to supply the mechanical informations. This position sensor adds length to the machine, raises system cost, increases rotor inertia and requires additional devices. As the result, there has been a significant interest in the development of sensorless strategies to eliminate the position sensor. This paper presents an implementation of the new sensorless speed comtrol scheme for a PMSM. In the proposed algorithm, the line currents are estimated by a observer and the estimated speed can be yielded from the voltage equation because the information of speed is included in back emf. But the speed estimation error between the estimated and the real speeds is occured by errors due to measuring the motor parameters and sensing the line current and the input voltage. To minimize the speed estimations error, the estimated speeds are compensated by using an instantaneous reactive power in synchronously rotating reference frame. In this paper, the proposed algorithm is not affected by mechanical motor parameters because the mechanical equation is not used. The effectiveness of algorithm is confirmed by the experiments.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.4
• /
• pp.35-44
• /
• 1989

In this paper, a precisely speed-controlled DC servo motor system utilizing direct adaptive control (DAC) algorithm which require that neither satisfaction of the perfect model following conditions (PMFC) nor explicit parameter identification is proposed. Computer simulation as well as experiments using MC-68000 are implemened with the above input trajectory fairly well in spite of load disturbances and parameter variations. Presented algorithm is simple and effective both in software and hardware applications.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.7
• /
• pp.124-133
• /
• 1999

In this paper, an event detection algorithm is proposed based on the statistics of subblock images. For an event of small size, we first divide each image into smaller subblocks and then for camera trembling, we use the statistics of three kinds of images such as the input image, reference image, and their difference image as features of the event. Simulation results show that the proposed algorithm is much more effective in event detection than the conventional cases based on only the difference image.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.111-119
• /
• 2009

This paper presents an adaptive image interpolation algorithm using local characteristics. An input image is classified into edge region and flat low frequency region. And then, the edge region is further partitioned into directive edge region and high frequency texture region. A bilinear interpolation is applied to flat low frequency region, cubic convolution is applied to texture region, and new edge directed interpolation to directive edge region, respectively. Simulation results show that the proposed algorithm outperforms the existing interpolation methods in terms of visual quality as well as PSNR.

• Earthquakes and Structures
• /
• v.17 no.3
• /
• pp.307-315
• /
• 2019

Building prediction and control theory have been drawing the attention of many scientists over the past few years because design and control efficiency consumes the most financial and energy. In the literature, many methods have been proposed to achieve this goal by trying different control theorems, but all of these methods face some problems in correctly solving the problem. The Evolutionary Bat (EB) Algorithm is one of the recently introduced optimization methods and providing researchers to solve different types of optimization problems. This paper applies EB to the optimization of building control design. The optimized parameter is the input to the fuzzy controller, which gives the status response as an output, which in turn changes the state of the associated actuator. The novel control criterion for guarantee of the stability of the system is also derived for the demonstration in the analysis. This systematic and simplified controller design approach is the contribution for solving complex dynamic engineering system subjected to external disturbances. The experimental results show that the method achieves effective results in the design of closed-loop system. Therefore, by establishing the stability of the closed-loop system, the behavior of the closed-loop building system can be precisely predicted and stabilized.