• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• The Korean Journal of Physiology and Pharmacology
• /
• v.17 no.6
• /
• pp.505-510
• /
• 2013

Electroacupuncture (EA) is a modified form of acupuncture that utilizes electrical stimulation. We previously showed that EA stimulated rats were divided into responders that were sensitive to EA and non-responders that were insensitive to EA based on the tail flick latency (TFL) test. The dopamine beta-hydroxylase (DBH) gene was more abundantly expressed in the hypothalamus of responder rats than non-responder rats. To determine whether overexpression of DBH gene expression in the hypothalamus modulate EA analgesia, we constructed a DBH encoding adenovirus and which was then injected into the hypothalamus of SD rats. Microinjection of DBH or control GFP virus into the hypothalamus had no changes on the basal pain threshold measured by a TFL test without EA treatment. However, the analgesic effect of EA was significantly enhanced from seven days after microinjection of the DBH virus, but not after injection of the control GFP virus. DBH expression was significantly higher in the hypothalamus of DBH virus injected rat than control GFP virus or PBS injected rats. Moreover, expression of the DBH gene did not affect the body core temperature, body weight, motor function or learning and memory ability. Although the functional role of DBH in the hypothalamus in the analgesic effect of EA remains unclear, our findings suggest that expression of the DBH gene in the hypothalamus promotes EA analgesia without obvious side-effects.

• Journal of Internet Computing and Services
• /
• v.19 no.3
• /
• pp.15-23
• /
• 2018

A code reuse attack is an attack technique that can execute arbitrary code without injecting code directly into the stack by combining executable code fragments existing in program memory and executing them continuously. ROP(Return-Oriented Programming) attack is typical type of code reuse attack and serveral defense techniques have been proposed to deal with this. However, since existing methods use Rule-based method to detect attacks based on specific rules, there is a limitation that ROP attacks that do not correspond to previously defined rules can not be detected. In this paper, we introduce a method to detect ROP attack by learning command pattern used in ROP attack code using RNN(Recurrent Neural Network). We also show that the proposed method effectively detects ROP attacks by measuring False Positive Ratio, False Negative Ratio, and Accuracy for normal code and ROP attack code discrimination.

• Journal of the Korean Institute of Gas
• /
• v.23 no.5
• /
• pp.52-58
• /
• 2019

In this study, we have developed a forecasting model for city- gas acceptance. City-gas corporations have to report about city-gas sale volume next year to KOGAS. So it is a important thing to them. Factors influenced city-gas have differences corresponding to usage classification, however, in city-gas acceptence, it is hard to classificate. So we have considered tha outside temperature as factor that influence regardless of usage classification and the model development was carried out. ARIMA, one of the traditional time series analysis, and LSTM, a deep running technique, were used to construct forecasting models, and various Ensemble techniques were used to minimize the disadvantages of these two methods.Experiments and validation were conducted using data from JB Corp. from 2008 to 2018 for 11 years.The average of the error rate of the daily forecast was 0.48% for Ensemble LSTM, the average of the error rate of the monthly forecast was 2.46% for Ensemble LSTM, And the absolute value of the error rate is 5.24% for Ensemble LSTM.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.75-82
• /
• 2022

There are various exhibition halls, shopping malls, theme parks around us and analysis of interest in exhibits or contents is mainly done through questionnaires. These questionnaires are mainly depend on the subjective memory of the person being investigated, resulting in incorrect statistical results. Therefore, it is possible to identify an exhibition space with low interest by tracking the movement and counting the number of visitors. Based on this, it can be used as quantitative data for exhibits that need replacement. In this paper, we use deep learning-based artificial intelligence algorithms to recognize visitors, assign IDs to the recognized visitors, and continuously track them to identify the movement path. When visitors pass the counting line, the system is designed to count the number and transmit data to the server for integrated management.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.238-240
• /
• 2006

네트워크상에서 발생하는 다양한 형태의 대량의 데이터를 정확하고 효율적으로 분석하기 위해 설계되고 있는 마이닝 시스템들은 목표지향적으로 훈련데이터들을 어떻게 구축하여 다룰 것인지에 대한 문제보다는 대부분 얼마나 많은 데이터 마이닝 기법을 지원하고 이를 적용할 수 있는지 등의 기법에 초점을 두고 있다. 따라서, 점점 더 에이전트화, 분산화, 자동화 및 은닉화 되는 최근의 보안공격기법을 정확하게 탐지하기 위한 방법은 미흡한 실정이다. 본 연구에서는 유비쿼터스 환경 내에서 발생 가능한 문제 중 복잡하고 지능화된 침입패턴의 탐지를 위해 데이터 마이닝 기법과 결함허용방법을 이용하는 개선된 학습알고리즘과 후처리 방법에 의한 RTPID(Refinement Training and Post-processing for Intrusion Detection)시스템을 제안한다. 본 논문에서의 RTPID 시스템은 active learning과 post-processing을 이용하여, 네트워크 내에서 발생 가능한 침입형태들을 정확하고 효율적으로 다루어 분석하고 있다. 이는 기법에만 초점을 맞춘 기존의 데이터마이닝 분석을 개선하고 있으며, 특히 제안된 분석 프로세스를 진행하는 동안 능동학습방법의 장점을 수용하여 학습효과는 높이며 비용을 감소시킬 수 있는 자가학습방법(self learning)방법의 효과를 기대할 수 있다. 이는 관리자의 개입을 최소화하는 학습방법이면서 동시에 False Positive와 False Negative 의 오류를 매우 효율적으로 개선하는 방법으로 기대된다. 본 논문의 제안방법은 분석도구나 시스템에 의존하지 않기 때문에, 유사한 문제를 안고 있는 여러 분야의 네트웍 환경에 적용될 수 있다.더욱 높은성능을 가짐을 알 수 있다.의 각 노드의 전력이 위험할 때 에러 패킷을 발생하는 기법을 추가하였다. NS-2 시뮬레이터를 이용하여 실험을 한 결과, 제안한 기법이 AOMDV에 비해 경로 탐색 횟수가 최대 36.57% 까지 감소되었음을 알 수 있었다.의 작용보다 더 강력함을 시사하고 있다.TEX>로 최고값을 나타내었으며 그 후 감소하여 담금 10일에는 $1.61{\sim}2.34%$였다. 시험구간에는 KKR, SKR이 비교적 높은 값을 나타내었다. 무기질 함량은 발효기간이 경과할수록 증하였고 Ca는 $2.95{\sim}36.76$, Cu는 $0.01{\sim}0.14$, Fe는 $0.71{\sim}3.23$, K는 $110.89{\sim}517.33$, Mg는 $34.78{\sim}122.40$, Mn은 $0.56{\sim}5.98$, Na는 $0.19{\sim}14.36$, Zn은 $0.90{\sim}5.71ppm$을 나타내었으며, 시험구별로 보면 WNR, BNR구가 Na만 제외한 다른 무기성분 함량이 가장 높았다.O to reduce I/O cost by reusing data already present in the memory of other nodes. Finally, chunking and on-line compression mechanisms are included in both models. We demonstrate that we can obtain significantly high-performanc

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.361-368
• /
• 2004

The purpose of this study is to propose a new on-line nonlinear PCA(OL-NPCA) method for a nonlinear feature extraction from the incremental data. Kernel PCA(KPCA) is widely used for nonlinear feature extraction, however, it has been pointed out that KPCA has the following problems. First, applying KPCA to N patterns requires storing and finding the eigenvectors of a N${\times}$N kernel matrix, which is infeasible for a large number of data N. Second problem is that in order to update the eigenvectors with an another data, the whole eigenspace should be recomputed. OL-NPCA overcomes these problems by incremental eigenspace update method with a feature mapping function. According to the experimental results, which comes from applying OL-NPCA to a toy and a large data problem, OL-NPCA shows following advantages. First, OL-NPCA is more efficient in memory requirement than KPCA. Second advantage is that OL-NPCA is comparable in performance to KPCA. Furthermore, performance of OL-NPCA can be easily improved by re-learning the data.

• Korean Journal of Medicinal Crop Science
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2004

Prolyl endopeptidase (PEP) is proline-specific serine protease, cleaving peptide bonds on the biologically active neuropeptides such as substance P, vassopressin, and thyrotropin-releasing hormone and is, therefore, suggested to play important roles in learning and memory process. In this work, the inhibitory effect of plant extracts on PEP was investigated. Out of 200 plant extracts, Prunus mume, Pyrola. japonica, Hypericum ascyron, Astilbe chinensis var. typica, and Elaeagnus umbellata inhibited more than 90% of PEP activity at the concentration of 5 ppm.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.10
• /
• pp.487-492
• /
• 2017

Clustering is a technique which is used to measure similarities between data in big data analysis and data mining field. Among various clustering methods, k-Modes algorithm is representatively used for categorical data. To increase the performance of iterative-centric tasks such as k-Modes, a distributed and concurrent framework Spark has been received great attention recently because it overcomes the limitation of Hadoop. Spark provides an environment that can process large amount of data in main memory using the concept of abstract objects called RDD. Spark provides Mllib, a dedicated library for machine learning, but Mllib only includes k-means that can process only continuous data, so there is a limitation that categorical data processing is impossible. In this paper, we design RDD for k-Modes algorithm for categorical data clustering in spark environment and implement an algorithm that can operate effectively. Experiments show that the proposed algorithm increases linearly in the spark environment.

• Journal of the Korean Geosynthetics Society
• /
• v.21 no.2
• /
• pp.11-19
• /
• 2022

In this paper, we propose a GoogleNet transfer learning and CNN-LSTM combination method to improve the time-series prediction performance for crack detection using crack data captured inside the sewer pipes. LSTM can solve the long-term dependency problem of CNN, so spatial and temporal characteristics can be considered at the same time. The predictive performance of the proposed method is excellent in all test variables as a result of comparing the RMSE(Root Mean Square Error) for time series sections using the crack data inside the sewer pipe. In addition, as a result of examining the prediction performance at the time of data generation, the proposed method was verified that it is effective in predicting crack detection by comparing with the existing CNN-only model. If the proposed method and experimental results obtained through this study are utilized, it can be applied in various fields such as the environment and humanities where time series data occurs frequently as well as crack data of concrete structures.