• Asian-Australasian Journal of Animal Sciences
• /
• v.15 no.10
• /
• pp.1489-1495
• /
• 2002

Five regions and 258 pigs were selected for this study: North (Beijing), Central (Wuhan), South (Guangzhou), Southwest (Chongqing), Northeast (Harbin). Five typical genetics of growing-finishing pig were selected: Landrace${\times}$Large White${\times}$Beijing Black, Duroc${\times}$Landrace${\times}$Large White, Duroc${\times}$Large White${\times}$Landrace, Landrace${\times}$Rongchang, Landrace${\times}$Harbin White, respectively at each sites. The basal diet was a corn-soybean meal containing sufficient nutrients to meet requirements. Carcass fat-free lean gain was determined by dissecting and analyzing chemical composition of the carcass. Cubic function fitted lean moistures to live weights better than other functions. Exponential function fitted lean lipids to live weights equally to allometric function. Carcass fat-free lean gain of Duroc${\times}$Large White${\times}$Landrace, Landrace${\times}$Large White${\times}$Beijing Black, Duroc${\times}$Landrace${\times}$Large White, Landrace${\times}$Harbin White, Landrace${\times}$Rongchang from 20 to 100 kg of average body weight was 259 g/d, 261 g/d, 311 g/d, 220 g/d, 200 g/d, respectively. All are lower than intermediate fat-free lean gain in NRC (1998).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.11
• /
• pp.1201-1209
• /
• 1991

Generally, the conventional tracking algorithms are very limited in the practical applications because of its exponential increase in the required computation time for the number of targets being tracked. Therefore, in this paper, a new real-time moving target tracking system is proposed, which is based on the neural networks with massive parallel processing capabilities. Through the theoretical and experimental results, the target tracking system based on neural network algorithm is analyzed to be computationally independent of the number of objects being tracked and performs the optimized tracking through its massive parallel computation and learning capabilities. And this system also has massive matched filtering effects because the moving target data can be compactly stored in the interconnection weights by learning. Accordingly, a possibility of the proposed neural network target tracking system can be suggested to the fields of real-time application.

• International Journal of Quality Innovation
• /
• v.7 no.2
• /
• pp.141-156
• /
• 2006

This study describes a novel algorithm for optimizing the quality yield of silicon wafer slicing. 12 inch wafer slicing is the most difficult in terms of semiconductor manufacturing yield. As silicon wafer slicing directly impacts production costs, semiconductor manufacturers are especially concerned with increasing and maintaining the yield, as well as identifying why yields decline. The criteria for establishing the proposed algorithm are derived from a literature review and interviews with a group of experts in semiconductor manufacturing. The modified Delphi method is then adopted to analyze those results. The proposed algorithm also incorporates the analytic hierarchy process (AHP) to determine the weights of evaluation. Additionally, the proposed algorithm can select the evaluation outcomes to identify the worst machine of precision. Finally, results of the exponential weighted moving average (EWMA) control chart demonstrate the feasibility of the proposed AHP-based algorithm in effectively selecting the evaluation outcomes and evaluating the precision of the worst performing machines. So, through collect data (the quality and quantity) to judge the result by AHP, it is the key to help the engineer can find out the manufacturing process yield quickly effectively.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.237-245
• /
• 2022

The prominence of IoTs (Internet of Things) and exponential advancement of computer networks has resulted in massive essential applications. Recognizing various cyber-attacks or anomalies in networks and establishing effective intrusion recognition systems are becoming increasingly vital to current security. MLTs (Machine Learning Techniques) can be developed for such data-driven intelligent recognition systems. Researchers have employed a TFDNNs (Tensor Flow Deep Neural Networks) and DCNNs (Deep Convolution Neural Networks) to recognize pirated software and malwares efficiently. However, tuning the amount of neurons in multiple layers with activation functions leads to learning error rates, degrading classifier's reliability. HTFDNNs ( Hybrid tensor flow DNNs) and MRNs (Modified Residual Networks) or Resnet CNNs were presented to recognize software piracy and malwares. This study proposes HTFDNNs to identify stolen software starting with plagiarized source codes. This work uses Tokens and weights for filtering noises while focusing on token's for identifying source code thefts. DLTs (Deep learning techniques) are then used to detect plagiarized sources. Data from Google Code Jam is used for finding software piracy. MRNs visualize colour images for identifying harms in networks using IoTs. Malware samples of Maling dataset is used for tests in this work.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.735-743
• /
• 2002

In this paper, we propose three new text-independent speaker identification methods. At first, to exclude the frames not having enough features of speaker's vocal from calculation of the maximum likelihood, we propose the FS(Frame Selection) method. This approach selects the important frames by evaluating the difference between the biggest likelihood and the second in each frame, and uses only the frames in calculating the score of likelihood. Our secondly proposed, called the Hybrid, is a combined version of the FS and WMR(Weighting Model Rank). This method determines the claimed speaker using exponential function weights, instead of likelihood itself, only on the selected frames obtained from the FS method. The last proposed, called MWMR (Modified WMR), considers both original likelihood itself and its relative position, when the claimed speaker is determined. It is different from the WMR that take into account only the relative position of likelihood. Through the experiments of the speaker identification, we show that the all the proposed have higher identification rates than the ML. In addition, the Hybrid and MWMR have higher identification rate about 2% and about 3% than WMR, respectively.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.35 no.2
• /
• pp.156-164
• /
• 1990

A field experiment was conducted to study both the distribution characteristics of photosynthetically active radiation (PAR) in the soybean canopy and their relationships with dry matter production. The soybean cultivars 'Hwanggeumkong' and 'Paldalkong' were sown with the spaces of 60$\times$15cm and 30$\times$15cm at Suwon on May 20 and on June 20 in 1989. The ratio of PAR to the total shortwave radiation was estimated by the empirical equation derived from sunshine hours and direct incoming radiation. The functional relationships between the PAR interception and the leaf area index were expressed as a function of Beer's law. The extinction coefficients(k) in the functions ranged from 0.77 to 0.92. The values of k were greater at higher planting density, but they were affected neither by planting dates nor by varieties. The reflection ratio of PAR($\alpha$) was determined by the exponential function as below; $\alpha$=$\alpha$p-($\alpha$p-$\alpha$o) exp(-kㆍLAI) where $\alpha$p was the reflectance at the maximum LAI and $\alpha$o was that of the bare soil. The ap ranged from 0.025 to 0.035 and $\alpha$o ranged from 0.11 to 0.12, respectively. The reflected PAR ranged from 0.049 to 0.064 and the transmitted PAR ranged from 0.168 to 0.340 until maximum dry weights were observed. The slope from the linear regression of dry matter on absorbed PAR, conversion efficiency, ranged from 1.30 to 2.3g MJ$^{-1}$ during the growing season until maximum dry weight was reached. The total dry matter yield above ground (TDM) increased with the increases in the conversion efficiency. TDM was higher in Hwanggeumkong than Paldalkong and higher in the space of 30$\times$15cm than 60$\times$15cm, Paldalkong showed higher harvest index than Hwanggeumkong. than Hwanggeumkong.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.1
• /
• pp.68-76
• /
• 1999

The intuitive understanding of the dynamic pattern generation in asymmetric networks may be useful for developing models of dynamic information processing. In this paper, dynamic behavior of the ring connection neural network in which each neuron is only to its nearest neurons with binary synaptic weights of ±1, has been inconnected vestigated Simulation results show that dynamic behavior of the network can be classified into only three categories: fixed points, limit cycles with basin and limit cycles with no basin. Furthermore, the number and the type of limit cycles generated by the networks have been derived through analytical method. The sufficient conditions for a state vector of n-neuron network to produce a limit cycle of n- or 2n-period are also given The results show that the estimated number of limit cycle is an exponential function of n. On the basis of this study, cyclic connection neural network may be capable of storing a large number of dynamic information.

• Korean Journal of Ichthyology
• /
• v.23 no.3
• /
• pp.179-186
• /
• 2011

Slime flounder, Microstomus achne is distributed in the coastal waters of Korea, west sea of Japan, BoHai, Yellow sea and East china sea. They are mainly caught by bottom trawl net during winter, from December to March. Sexual maturation of slime flounder were investigated using samples collected from commercial catch in the southern coast of Korea from November, 2006 to March, 2007. The ovary of the slime flounder is a conical bag in shape and is bilateral structure develops lengthily from the posterior of the abdomen to the end of the anal fin. The testis also is bilateral in structure, usually located in small size in the abdomen. In females, the gonadosomatic index (GSI) were peaked in January (12.46), then decreased rapidly thereafter. Female GSI values plummeted to 2.72 in March just after spawning. Male GSI values were peaked in December (2.46) before in the spawning season, then decreased slowly thereafter. The reproductive cycle would be classified into three successive developmental stages : maturation stage (November to January), ripe and spawning stage (December to February), degenerative and resting stage (February to March). Relationships between the fish sizes in total length (TL) and the number of ovarian eggs (F), the body weights (BW) and the number of ovarian eggs were indicated by the exponential equation respectively: F=29.027TL-767.8 (r$^2$=0.7686), F=0.3998BW+24.288 (r$^2$=0.8919).

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.