• Journal of Animal Science and Technology
• /
• 제52권3호
• /
• pp.229-236
• /
• 2010

Effect of molasses addition to complete calf starter (CCS) and the following pellet processing was evaluated with 12 Holstein-Friesian (HF) calves (7-14 d old with $42\;{\pm}\;5.5\;kg$ average BW), with 6 calves (replicate) per treatment. The CCS was formulated with 65% concentrate calf starter and 35% local corn fodder. On the CCS, molasses was added either 5% (M5) or 10% (M10), then the mixture was pelleted and fed to the calves for 7 weeks. Molasses addition, regardless of addition level, improved (p<0.05) both the durability and hardness of the pellet which contains 35% of high fibrous local corn fodder. Upon feeding to calves, the feed intake and daily gain were numerically higher with 5% molasses addition compared to 10% molasses addition. Blood VFA level was remarkably higher (p<0.01) in calves fed M10 than calves fed M5. There was no difference (p>0.05) in blood glucose level between M5 and M10. Length and number of papillae were not different (p>0.05) by the addition levels of molasses. However, there was one exception in number of papillae at caudo-dorsal sac which were higher (p<0.05) number in M5 than M10 calves. Considering the quality of CCS pellet, calf performance and rumen development, there was no additional benefit of 10% molasses addition compared to 5%. From the results of this study, 5% molasses addition could be recommended for local farmer when they utilize local corn fodder to make CCS for HF calves in Indonesia.

• KIPS Transactions on Software and Data Engineering
• /
• 제9권10호
• /
• pp.309-316
• /
• 2020

We predict the mortality of the elderly patients visiting the emergency department who are over 65 years old using Feed Forward Neural Network (FFNN) and Convolutional Neural Network (CNN) respectively. Medical data consist of 99 features including basic information such as sex, age, temperature, and heart rate as well as past history, various blood tests and culture tests, and etc. Among these, we used random forest to select features by measuring the importance of features in the prediction of mortality. As a result, using the top 80 features with high importance is best in the mortality prediction. The performance of the FFNN and CNN is compared by using the selected features for training each neural network. To train CNN with images, we convert medical data to fixed size images. We acquire better results with CNN than with FFNN. With CNN for mortality prediction, F1 score and the AUC for test data are 56.9 and 92.1 respectively.

• Journal of The Korean Society of Agricultural Engineers
• /
• 제62권4호
• /
• pp.87-97
• /
• 2020

The livestock infections had been happened seasonally, but they have gradually changed to be irrelevant to seasons and have an aspect to rapidly spread after outbreak. Especially in Korea, proactive disinfection measures are very important because the livestock farms are located densely so high as to accelerate the spread of disease between farms. livestock disease outbreaks like HPAI and FMD occurred with high probability due to vehicles visiting the farms, this study is to evaluate the efficiency of livestock vehicle disinfection systems by investigating the disinfectant coverage according to the type of vehicle disinfection system and the type of vehicle quantitatively. In field experiments, water-sensitive papers (WSPs) were attached to 21 locations on the surface of four vehicles (sedan, SUV, truck, and feed transport), respectively, and exposed to disinfectants while the vehicle was sprayed in two vehicle disinfection systems (tunnel type and simplified type). The WSPs were scanned and image-processed to calculate the disinfectant coverage. The results showed that the tunnel-type vehicle disinfection system had a better disinfection performance with an average coverage of 90.27% for all vehicles compared to 32.62% of the simplified type system. The problem of the simplified system was a wide coefficient of variation (1.05-1.31) of the disinfectant coverage between 21 locations indicating a need for further improvement of nozzle location and arrangement.

• Journal of Aquaculture
• /
• 제10권1호
• /
• pp.77-85
• /
• 1997

A 6-week feeding trial was conducted to determine the nutritional value of various dietary animal protein sources in juvenile Koran rockfish. White fish meal (WFM), flounder muscle meal (FMM), blood meal (BM), casein & gelain (CG), egg white albumin (EWA) and squid liver powder (SLP) were used as the animal protein sources, Crude protein content and available energy of the experimental diets were 50% and 15.9 kJ/g, respectively. There were significant differences among all dietary groups in weight gain (WG), feed efficiency (FE), and protein effiency ratio (PER). WFM and FFM were the best animal protein sources among the dietary groups. FMM diet had significantly higher (P<0.05) WG, FE, and PER values than those of fish fed the WFM diet. WG, FE, PER, and specific growth rate (SGR) values of fish fed BM diet were significantly higher (P<0.05) than those of fish fed EWA diet. Significant differences were found in whole body composition, hemoglobin (Hb), hepatosomatic index (HSI), and hematocrit (Ht). These results showed that low-temperature processing of lyophilized flounder muscle meal resulted in superior performance of rockfish relative to the other evaluated animal protein sources.

• The KIPS Transactions:PartD
• /
• 제8D권3호
• /
• pp.241-246
• /
• 2001

Area of software measurement in software engineering is active more than thirty years. There is a huge collection of researches but still no a concrete software cost estimation model. If we want to measure the cost-effort of a software project, we need to estimate the size of the software. A number of software metrics are identified in the literature ; the most frequently cited measures are LOC(line of code) and FPA(function point analysis). The FPA approach has features that overcome the major problems with using LOC as a measure of system size. This paper presents an neural networks(NN) models that related software development effort to software size measured in FPs and function element types. The research describes appropriate NN modeling in the context of a case study for 24 software development projects. Also, this paper compared the NN model with a regression analysis model and found the NN model has better estimative accuracy.

• The KIPS Transactions:PartD
• /
• 제8D권3호
• /
• pp.247-256
• /
• 2001

Software is developing toward having more large scale and many functions day by day. Also, user’s requirements level for software is being high, especially, requirements for software quality is being high continuously. Methods which can satisfy such User’s requirements is being studied in various viewpoint. First of all, study about quality evaluation system and methodology is energetically in progress in viewpoint to improve quality of software by feed-back software quality evaluation result to developers. In this paper, we define metrics according to a system and developed quality measurement tables according to internal characteristics system of quality characteristics, subcharacteritics, internal characteristics for reliability between quality characteristics of international standard, ISO/IEC 9126 about software quality. And we propose evaluation results about development products using internal characteristics.

• The KIPS Transactions:PartD
• /
• 제16D권6호
• /
• pp.845-850
• /
• 2009

Use of XML data has been increased with growth of Web 2.0 environment. XML is recognized its advantages by using based technology of RSS or ATOM for transferring information from blogs and news feed. Bitmap clustering is a method to keep index in main memory based on Relational DBMS, and which performed better than the other XML indexing methods during the evaluation. Existing method generates too many clusters, and it causes deterioration of result of searching quality. This paper proposes k-Bitmap clustering method that can generate user defined k clusters to solve above-mentioned problem. The proposed method also keeps additional inverted index for searching excluded terms from representative bits of k-Bitmap. We performed evaluation and the result shows that the users can control the number of clusters. Also our method has high recall value in single term search, and it guarantees the searching result includes all related documents for its query with keeping two indices.

• Journal of the Korean Society of Propulsion Engineers
• /
• 제4권3호
• /
• pp.55-63
• /
• 2000

Studies for tube spin forming have been implemented restrictively compared to spinning process, because of the complex of deformation mechanism. Especially there were not many studies by using FEM(Finite Element Method) for overcoming restriction of upper bound method. In this paper, the tube spinning process is analyzed to produce cylindrical body made by titanium alloy. In analysis, processing parameters was obtained by using upper bound method to consider material properties of titanium alloy and finite element analysis was implemented to investigate the flatness and the elongation of the titanium alloy workpiece by using ABAQUS code. The independent variables are ; material properties of workpiece, angles of roller, reduction of diameter. Three variables, two angles of roller and reduction of diameter are optimized by using the upper bound method. In this method, we can estimate the workable power, working force and reduction of diameter, and also the flatness and the elongation of workpiece by the finite elements analysis using ABAQUS/standard. The results indicates that these variables play a critical factors of spinning process for the titanium alloy and the optimum values of these variables.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• 제41권4호
• /
• pp.251-255
• /
• 2017

Burr generation is inevitable during the machining of a micro-pattern, and it is difficult to distinguish between the pattern and burr because they have a very small dimensions. In this study, a micro-pattern with a pitch of $60{\mu}m$and height of $1{\mu}m$ was fabricated on a cylindrical surface using a turning machine. The structure of a burr and its generation mechanism were determined, and a magnetic abrasive deburring process was used to improve the accuracy of the pattern. As a result, when fabricating a micro-pattern, it was shown that the direction of the burr was determined by the feed direction of the tool. The measured pattern height was $1.018{\mu}m$ when the magnetic flux density and spindle speed were respectively 40 mT and 1600 rpm, respectively, during magnetic abrasive deburring, which were determined to be the optimal conditions for processing.

• KIPS Transactions on Computer and Communication Systems
• /
• 제7권10호
• /
• pp.251-258
• /
• 2018

Ransomware, a malicious software that requires a ransom by encrypting a file, is becoming more threatening with its rapid propagation and intelligence. Rapid detection and risk analysis are required, but real-time analysis and reporting are lacking. In this paper, we propose a ransomware infection detection system using social big data mining technology to enable real-time analysis. The system analyzes the twitter stream in real time and crawls tweets with keywords related to ransomware. It also extracts keywords related to ransomware by crawling the news server through the news feed parser and extracts news or statistical data on the servers of the security company or search engine. The collected data is analyzed by data mining algorithms. By comparing the number of related tweets, google trends (statistical information), and articles related wannacry and locky ransomware infection spreading in 2017, we show that our system has the possibility of ransomware infection detection using tweets. Moreover, the performance of proposed system is shown through entropy and chi-square analysis.