• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.33-41
• /
• 2006

This paper presents a method that automatically recognizes products into model type, which it flows with the conveyor belt. The specific interlaced image are occurred by moving image when we use the NTSC based camera. It is impossible to process interlaced images, so a suitable post-processing is required. For the purpose of this processing, after it remove interlaced images using de-interlacing method, it leads rectangle region of object by thresholding. And then, after rectangle region is separated into several blocks through edge detection, we calculate pixel numbers per each block, re-classify using its average, and classify products into model type. Through experiments, we know that the proposed method represent high classification ratio.

• Journal of the Korea Safety Management & Science
• /
• v.9 no.3
• /
• pp.165-171
• /
• 2007

Dependent models in quality statistics are classified as serially autocorrelated model, multivariate model and dependent sample model. Dependent sample model is most efficient in time and cost to obtain samples among the above models. This paper proposes to implement parametric and nonparametric models into production system depended on demand pattern. Nonparametric models have distribution free and asymptotic distribution free techniques. Quality statistical models are classified into two categories ; the number of dependent sample and the type of data. The type of data consists of nominal, ordinal, interval and ratio data. The number of dependent sample divides into 2 samples and more than 3 samples.

• Journal of the Korean housing association
• /
• v.14 no.2
• /
• pp.63-75
• /
• 2003

The planning of access area, so called "core" plays an important role of planning for multifamily housing, especially multistory housing. For all possibility of various planning and design, this area has been mostly planned and designed in uniformity. And only few attempts have so far been made in studying core, on the contrary to the unit plan or plotplan. It is keenly needed to develop various skills of planning and design in this sector. The purpose of this study is to find out the usable elements of planning and design, those are correspondent to normative targets. For this end, most possible core types are classified in to three categories: circulation types in the housing block, axis types to the entrance of housing units and number of accessed housing units. And then, sizable developments for norm of core have been effectuating in view of function, relationships both with housing unit and block. Based on this classification of types and listed norm, several European examples are analyzed and evaluated by merits and demerits of their respective core types. In addition to this analysis, some adequate planning conditions, positive vs. negative types of core, and detailed planning elements are prepared with regard to the norm of core. It is noteworthy that a variety of possible core planning cases are available by means of combination of lower categories in the classified core types. It is expected that this study will render service for some helpful planning and design guide in the practice

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.27-35
• /
• 2021

NAND flash memory-based SSD needs an internal software, Flash Translation Layer(FTL) to provide traditional block device interface to the host because of its physical constraints, such as erase-before-write and large erase block. However, because useful host-side information cannot be delivered to FTL through the narrow block device interface, SSDs suffer from a variety of problems such as increasing garbage collection overhead, large tail-latency, and unpredictable I/O latency. Otherwise, the new type of SSD, open-channel SSD exposes the internal structure of SSD to the host so that underlying NAND flash memory can be managed directly by the host-level FTL. Especially, I/O data classification by using host-side information can achieve the reduction of garbage collection overhead. In this paper, we propose a new scheme to reduce garbage collection overhead of open-channel SSD by separating the journal from other file data for the journaling filesystem. Because journal has different lifespan with other file data, the Write Amplification Factor (WAF) caused by garbage collection can be reduced. The proposed scheme is implemented by modifying the host-level FTL of Linux and evaluated with both Fio and Filebench. According to the experiment results, the proposed scheme improves I/O performance by 46%~50% while reducing the WAF of open-channel SSDs by more than 33% compared to the previous one.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.1-9
• /
• 2021

Disaster alerts are text messages sent by government to people in the area in the event of a disaster. Since the number of disaster alerts has increased, the number of people who block disaster alerts is increasing as many unnecessary disaster alerts are being received. To solve this problem, this study proposes a deep learning model that automatically classifies disaster alerts by disaster type, and allows only necessary disaster alerts to be received according to the recipient. The proposed model embeds disaster alerts via KoBERT and classifies them by disaster type with LSTM. As a result of classifying disaster alerts using 3 combinations of parts of speech: [Noun], [Noun + Adjective + Verb] and [All parts], and 4 classification models: Proposed model, Keyword classification, Word2Vec + 1D-CNN and KoBERT + FFNN, the proposed model achieved the highest performance with 0.988954 accuracy.

• Journal of Chest Surgery
• /
• v.21 no.4
• /
• pp.630-640
• /
• 1988

We clinically evaluated 222 cases of ventricular septal defect which we experienced at Department of Thoracic and Cardiovascular Surgery, Pusan National University Hospital between July 1981 and March 1988. These patients were occupied 46.2% of all congenital heart disease operated on its same period. Of 222 cases, 132 patients were male and 90 patients were female. Their age distribution ranged from 8 months to 34 years of age and their mean age was 10.3 years. Among these patients, 86 patients had associated cardiac anomalies, which were patent foramen ovale 43 cases[19.5%], Atrial septal defect 18 cases[8.1%], patent ductus arteriosus 8 cases[3.6%], aortic insufficiency 7 cases[3.2%], infundibular pulmonary stenosis 5 cases[2.3%] and etc. There was statistically significant correlationship between VSD size and Qp/Qs, Rp/Rs, Pp/Ps respectively. All cases were operated under cardiopulmonary bypass and 157 patients[70.7%] would be corrected through right atrial approach. 158 patients[71.2%] underwent closure of ventricular septal defect with primary closure and the remained patients[28.8%] with patch closure. In anatomical classification by Kirklin, type I constituted 23.4%, type II 73.4%, type III 0.5%, type I and type II 1.4%, and type II and type III 1.4%. Important postoperative EGG changes were noted in 57 cases[25.7%] and incomplete right bundle branch block was most common[12.6%]. 54 patients[24.3%] developed minor and major postoperative complications and 9 patients died of several complications and overall operative mortality was 4.1%.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.79-85
• /
• 2022

Anomaly detection is a method to detect and block abnormal data flows in general users' data sets. The previously known method is a method of detecting and defending an attack based on a signature using the signature of an already known attack. This has the advantage of a low false positive rate, but the problem is that it is very vulnerable to a zero-day vulnerability attack or a modified attack. However, in the case of anomaly detection, there is a disadvantage that the false positive rate is high, but it has the advantage of being able to identify, detect, and block zero-day vulnerability attacks or modified attacks, so related studies are being actively conducted. In this study, we want to deal with these anomaly detection mechanisms, and we propose a new mechanism that performs both anomaly detection and classification while supplementing the high false positive rate mentioned above. In this study, the experiment was conducted with five configurations considering the characteristics of various algorithms. As a result, the model showing the best accuracy was proposed as the result of this study. After detecting an attack by applying the Extra Tree and Three-layer ANN at the same time, the attack type is classified using the Extra Tree for the classified attack data. In this study, verification was performed on the NSL-KDD data set, and the accuracy was 99.8%, 99.1%, 98.9%, 98.7%, and 97.9% for Normal, Dos, Probe, U2R, and R2L, respectively. This configuration showed superior performance compared to other models.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• Journal of Korean Society of Water and Wastewater
• /
• v.19 no.3
• /
• pp.288-294
• /
• 2005

This study was conducted to evaluate the grit removal efficiency of tornado block-type vortex grit separator. Vortex grit separator was manufactured for this study, and it was characterized by the impeller and tornado block installed in separator. Impeller was installed to increase water velocity in the separator and tornado block was installed to increase the grit lifting efficiency. Pilot study was also conducted in A sewage treatment plant (STP) in Gyeonggi province from November 2003 to May 2004 (64 days). Major findings are as follows. 1. Impeller was proven to increase water velocity in the grit separator, especially in low flow rate. This influence will increase separation ratio of organics from grits, preventing those organics from sedimentation. 2. Sand (with 0.2~0.3mm size) removal efficiency was over 98 % and 96 %, at the flow rate of $500m^3/day$ and $750m^3/day$ under the condition that impeller rotation velocity kept at 15 rpm. Originally that grit separator was designed to have the capacity of $500m^3/day$. $750m^3/day$ was tried to investigate the performance of this type of grit separator under overload condition. Stable grit removal was still available to the extent of 150% of designed capacity. 3. It took less than 3 minutes for the grit separator to completely lift out 3 kgs of 0.2-0.3 mm sized, settled sand at the bottom to 2,060 mm high above water surface. But it showed the tendency to spend a little more time on lifting the grit as the grit size and the vertical height of the lift increased. 4. During experimental duration in A STP, it was found that the average amount of inlet grit was about 981 g/day (160~1,685 g/day) under $500m^3/day$ of operation condition, but it varied so severely during the experimental duration. After classification of discharged grit according to its size, grit with 0.3-0.42 mm size was found as largest part of output.

• Journal of Chest Surgery
• /
• v.23 no.5
• /
• pp.871-880
• /
• 1990

We clinically evaluated 182 cases of the ventricular septal defect that we experienced at the Department of Thoracic and Cardiovascular Surgery, Maryknoll Hospital from March 1986 through June 1990. Of the 182 cases, 95 patients were male and 87 patients were female. Their age distribution ranged from 8 month to 37 years and their mean age was 8.1 years. The most common chief complaint was frequent upper respiratory infection. Among them, 46 patients had associated cardiac anomalies, which were subdivided as follow; 9 cases of patent foramen ovale, 8 cases of infundibular stenosis, 6 cases of pulmonary valvular stenosis, 4 cases of left superior vena cava, and etc. The most common preoperative abnormal EKG finding was left ventricular hypertrophy in 22 cases. Ninety-three patients[51.1%] underwent simple closure of the VSD and the rest[48.0%] underwent patch closure. In anatomical classification by Kirklin type I constituted 24.2%; type II, 74.8%, type III, 0.7%, and the mixed type of type I and II, 0.5%, The important postoperative EKG changes were noted in 38 cases[20.9%], 18 cases of which were incomplete right bundle branch block. Thirty-three patients[18.1%] developed minor and major complications, and five patients died, overall operative mortality being 2.7%.