• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.49-55
• /
• 2015

According to the statistics of traffic accidents over recent 5 years, traffic accidents during the night times happened more than the day times. There are various causes to occur traffic accidents and the one of the major causes is inappropriate or missing street lights that make driver's sight confused and causes the traffic accidents. In this paper, with smartphones, we designed and implemented a lane luminance measurement application which stores the information of driver's location, driving, and lane luminance into database in real time to figure out the inappropriate street light facilities and the area that does not have any street lights. This application is implemented under Native C/C++ environment using android NDK and it improves the operation speed than code written in Java or other languages. To measure the luminance of road, the input image with RGB color space is converted to image with YCbCr color space and Y value returns the luminance of road. The application detects the road lane and calculates the road lane luminance into the database sever. Also this application receives the road video image using smart phone's camera and improves the computational cost by allocating the ROI(Region of interest) of input images. The ROI of image is converted to Grayscale image and then applied the canny edge detector to extract the outline of lanes. After that, we applied hough line transform method to achieve the candidated lane group. The both sides of lane is selected by lane detection algorithm that utilizes the gradient of candidated lanes. When the both lanes of road are detected, we set up a triangle area with a height 20 pixels down from intersection of lanes and the luminance of road is estimated from this triangle area. Y value is calculated from the extracted each R, G, B value of pixels in the triangle. The average Y value of pixels is ranged between from 0 to 100 value to inform a luminance of road and each pixel values are represented with color between black and green. We store car location using smartphone's GPS sensor into the database server after analyzing the road lane video image with luminance of road about 60 meters ahead by wireless communication every 10 minutes. We expect that those collected road luminance information can warn drivers about safe driving or effectively improve the renovation plans of road luminance management.

• The KIPS Transactions:PartC
• /
• v.10C no.6
• /
• pp.683-694
• /
• 2003

We present X-tree Diff, a change detection algorithm for tree-structured data. Our work is motivated by need to monitor massive volume of web documents and detect suspicious changes, called defacement attack on web sites. From this context, our algorithm should be very efficient in speed and use of memory space. X-tree Diff uses a special ordered labeled tree, X-tree, to represent XML/HTML documents. X-tree nodes have a special field, tMD, which stores a 128-bit hash value representing the structure and data of subtrees, so match identical subtrees form the old and new versions. During this process, X-tree Diff uses the Rule of Delaying Ambiguous Matchings, implying that it perform exact matching where a node in the old version has one-to one corrspondence with the corresponding node in the new, by delaying all the others. It drastically reduces the possibility of wrong matchings. X-tree Diff propagates such exact matchings upwards in Step 2, and obtain more matchings downwsards from roots in Step 3. In step 4, nodes to ve inserted or deleted are decided, We aldo show thst X-tree Diff runs on O(n), woere n is the number of noses in X-trees, in worst case as well as in average case, This result is even better than that of BULD Diff algorithm, which is O(n log(n)) in worst case, We experimented X-tree Diff on reat data, which are about 11,000 home pages from about 20 wev sites, instead of synthetic documets manipulated for experimented for ex[erimentation. Currently, X-treeDiff algorithm is being used in a commeercial hacking detection system, called the WIDS(Web-Document Intrusion Detection System), which is to find changes occured in registered websites, and report suspicious changes to users.

• Korean Journal of Soil Science and Fertilizer
• /
• v.39 no.5
• /
• pp.274-279
• /
• 2006

The exact estimation of crop evapotranspiration containing reference or potential evapotranspiration is necessary for decision of crop water requirements. This study was carried out for the evaluation and application of various meteorological elements used for the calculation of reference evapotranspiration (RET) by FAO Penman-Monteith (PM) model. Meteorological elements including temperature, net radiation, soil heat flux, albedo, relative humidity, wind speed measured by meteorological instruments are required for RET calculation by FAO PM model. The average of albedo measured for crop growing period was 0.20, ranging from 0.12 to 0.23, and was slightly lower than 0.23. Determinant coefficients by measured albedo and green grass albedo were 0.97, 0.95 and standard errors were 0.74, 0.80 respectively. Usefulness of deductive regression models was admitted. To assess an influence of soil heat flux (G) on FAO PM, RET with G=0 was compared with RETs using G at 5cm soil depth ($G_{5cm}$) and G at surface ($G_{0cm}$). As the results, RET estimated by G=0 was well agreed with RET calculated by measured G. Therefore, estimated net radiation, G=0 and albedo of green grass could be used for RET calculation by FAO PM.

• Food Science of Animal Resources
• /
• v.30 no.2
• /
• pp.277-285
• /
• 2010

The objective of this study was to manufacture spent layer chicken meat products by natural freeze-drying. The spent layers of chickens that were slaughtered at 80 wk were obtained from a local slaughter house and separated into two halves of carcasses. The samples were divided into the following groups: 1) control (non-curing), 2) curing, and 3) curing with 2% trehalose before drying. The cured meats were placed at $2^{\circ}C$ for 7 d and then transferred to a natural drying spot located in Injae City, Gangwondo, Korea. The experiment was conducted from January to March in 2008. The average temperature, RH, and wind speed were $-1.5^{\circ}C$, 63%, and 1.8 m/sec, respectively. The cured treatments showed higher pH, lower Aw and lower shear force value compared with the control. Based on the results of TBARS (2-thiobarbituric acid reactive substances) level and volatile basic nitrogen value, lipid oxidation and protein deterioration were inhibited in curing treatments during drying. Trehalose acted as a humectant because it maintained a lower water activity despite the relatively higher moisture content during drying. The polyunsaturated fatty acids content and sensory attributes were higher in cured treatments than in the control during drying. Most of the bacterial counts in the treated groups were lower by 2 Log CFU/g after 1 mon of drying, and Salmonella spp. and Listeria spp. were not found in any treatment. There was also no microbial safety problem associated with dried meat products. Based on the results of this experiment, dried meat products could be manufactured from precured spent layer chickens by natural freeze-drying during winter.

• Korean Journal of Breeding Science
• /
• v.41 no.3
• /
• pp.220-227
• /
• 2009

This study was conducted to select superior families based on the open-pollinated (OP) progeny tests of P. densiflora. A total of 232 OP families were analyzed for relative height growth. The OP progeny test trials were established at 1 to 4 sites from 1975 to 1987. To minimize temporal and spatial variation, we applied the standardization method for family selection. In each progeny test, superior and inferior families were selected at ages of 10, 20 and 30. Relative height growth rate (RHGR), growth speed at a given time unit, was comparatively high at age of 10 with range from 0.1 to 0.6 and showed a large variation among families. However, after age 15, the RHGR was low (average 0.04) and also the variation was not significantly different among families. To reduce selection errors due to age differences (from age 23 to 35) of tests, we made the family selection after age 15 when the values of RHGR were stable. Height growth at each age was transformed to be height growth at age 35 based on the RHGR. As the results, family CB2, CB3, KW99 and KW2 were selected as superior families and KW158, KW22, KB40 and GG1 were considered as inferior ones, respectively. Rank correlations (r) between test ages and selection age 35 were high and statistically significant; r = 0.881 between age 30 and 35, 0.653 between age 20 and 35, and -0.222 between age 10 and 35.

• Korean Journal of Breeding Science
• /
• v.41 no.3
• /
• pp.333-337
• /
• 2009

A new malting barley variety, "Daho", was developed from the cross between "Milyang85 and Suwon335" at the Department of Rice and Winter Cereal Crop (DRWCC) NICS, in 2007. An elite line, YMB2064-B-8-2-4-1-1, was selected in 2004 and designated as "Milyang134". It showed good agronomic performance in the regional adaptation yield trials (RYT) from 2005 to 2007 and was released with the name of "Daho", having high yielding and BaYMV resistance. The average heading and maturing dates of "Daho" were April 19 and May 27, which were 2 days later and 1 day earlier than those of "Jinyang", leading variety, at the regional adaptation yield trials (RYT), respectively. "Daho" had longer culm length (84 cm), more spikes per $m^2$ (915) and higher 1,000 grain weight (39.2 g) than those of "Jinyang" in paddy field condition. "Daho" was showed resistance to BaYMV at the regions of Naju, Jinju, and Milyang but moderately resistance at Iksan. However, the response of "Daho" to other environmental stresses was similar to "Jinyang". The yields of "Daho" at upland and paddy fields were about 5.20 MT/ha, 4.81 MT/ha, respectively, which is about 38%, 25% higher than those of "Jinyang" in the regional adaptation yield trials (RYT), respectively. It has higher grain assortment, germination capacity, water sensitivity and Kolback index but lower malt extract, diastatic power and filtration speed than those of "Jinyang".

• Korean Journal of Breeding Science
• /
• v.41 no.3
• /
• pp.328-332
• /
• 2009

A new malting barley variety, "Oreum", was developed from the a cross between 'Kinuyutaka' and 'Samdobori' at the Honam Agricultural Research Institute (HARI) in 2006. An elite line, YMB2077-2B-24-1-2, was selected in 2003 and designated as 'Milyang132'. It showed good agronomic performance in the regional adaptation yield trials (RYT) from 2004 to 2006, and was released with the name of "Oreum" having high yielding and BaYMV resistance. The average heading and maturing dates of "Oreum" were April 18 and May 24, which were 2 days later than 'Jinyang', a leading variety, at RYT. "Oreum" had longer culm length (75 cm), more spikes per $m^2$ (990), and lighter 1,000 grain weight (35.2 g) than those of 'Jinyang' in paddy field conditions. It was showed resistance to BaYMV at the regions of Naju, Jinju and Milyang but moderate resistance at Iksan. However, the response to other environmental stresses of was similar to 'Jinyang' The yield potential of "Oreum" was about 5.43 MT/ha, 4.93 MT/ha in upland and paddy fields which was about 80%, 35% higher than Jinyang in the regional adaptation yield trials (RYT), respectively. It has good malting quality including high grain assortment, germination capacity ratio, water sensitivity and high the malt production and the extract and short filtration speed than those of 'Jinyang'.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.6
• /
• pp.111-121
• /
• 2019

Evapotranspiration (ET) of vegetation is one of the major components of the hydrologic cycle, and its accurate estimation is important for hydrologic water balance, irrigation management, crop yield simulation, and water resources planning and management. For agricultural crops, ET is often calculated in terms of a short or tall crop reference, such as well-watered, clipped grass (reference crop evapotranspiration, $ET_o$). The Penman-Monteith equation recommended by FAO (FAO 56-PM) has been accepted by researchers and practitioners, as the sole $ET_o$ method. However, its accuracy is contingent on high quality measurements of four meteorological variables, and its use has been limited by incomplete and/or inaccurate input data. Therefore, this study evaluated the applicability of Backpropagation Neural Network (BPNN) model for estimating $ET_o$ from less meteorological data than required by the FAO 56-PM. A total of six meteorological inputs, minimum temperature, average temperature, maximum temperature, relative humidity, wind speed and solar radiation, were divided into a series of input groups (a combination of one, two, three, four, five and six variables) and each combination of different meteorological dataset was evaluated for its level of accuracy in estimating $ET_o$. The overall findings of this study indicated that $ET_o$ could be reasonably estimated using less than all six meteorological data using BPNN. In addition, it was shown that the proper choice of neural network architecture could not only minimize the computational error, but also maximize the relationship between dependent and independent variables. The findings of this study would be of use in instances where data availability and/or accuracy are limited.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.5
• /
• pp.71-78
• /
• 2021

Green areas and the area of available horizontal surfaces are gradually decreasing due to the overcrowding of buildings. It is adversely affecting the urban climate and ecosystem. However, the recognition of the importance of green areas is gradually increasing. As a result, the importance of wall greening using vertical surfaces is growing. However, despite the fact that domestic wall greening guidelines and institutions related to orientations restrict planting. there was no study to determine whether there were actual differences in plant growth due to orientations. Therefore, this study compared and analyzed the plant growth characteristics by orientations to apply actual wall greening to cities. The experiment was conducted from May to September 2020. First of all, three octave walls were constructed to measure the temperature, the illumination, and the length of the plants once a week. The plants included Parthenocissus tricuspidata, Hedera rhombea, and Euonymus radicans cv. Aueonmarinata Rehd plants. As a result of the study, Parthenocissus tricuspidata was prolific in the north, and Hedera rhombea, and Euonymus radicans cv. Aueonmarinata Rehd plants were prolific in the south. All three types of plants were prolific in June-July, and the Parthenocissus tricuspidata was prolific in grass-growing, and in August, all the walls were 100% covered. Hedera rhombea had the lowest rate of herbaceous growth, and the vertical coverate was also lower at an average of 45%, but among the three plants, the sheath of the horizontal surface coverate was the highest. Euonymus radicans cv. Aueonmarinata Rehd was low in the speed of herbaceous growth, and finally, the walls were 100% covered except for the north and northwest directions. It was found that not all plants used for wall greening show the same growth, and the difference in growth varies more depending on plants than the effect of orientations. Therefore, it is better to identify the characteristics of plant growth and plant suitable plants for each directions.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.