• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.121-131
• /
• 2014

Traffic speed is an important measure in transportation. It can be employed for various purposes, including traffic congestion detection, travel time estimation, and road design. Consequently, accurate speed prediction is essential in the development of intelligent transportation systems. In this paper, we present an analysis and speed prediction of a certain road section in Busan, South Korea. In previous works, only historical data of the target link are used for prediction. Here, we extract features from real traffic data by considering the neighboring links. After obtaining the candidate features, linear regression, model tree, and k-nearest neighbor (k-NN) are employed for both feature selection and speed prediction. The experiment results show that k-NN outperforms model tree and linear regression for the given dataset. Compared to the other predictors, k-NN significantly reduces the error measures that we use, including mean absolute percentage error (MAPE) and root mean square error (RMSE).

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.1-14
• /
• 2014

Both researchers and practitioners are showing an increased interested in interactive exhibition services. Interactive exhibition services are designed to directly respond to visitor responses in real time, so as to fully engage visitors' interest and enhance their satisfaction. In order to install an effective interactive exhibition service, it is essential to adopt intelligent technologies that enable accurate estimation of a visitor's emotional state from responses to exhibited stimulus. Studies undertaken so far have attempted to estimate the human emotional state, most of them doing so by gauging either facial expressions or audio responses. However, the most recent research suggests that, a multimodal approach that uses people's multiple responses simultaneously may lead to better estimation. Given this context, we propose a new multimodal emotional state estimation model that uses various responses including facial expressions, gestures, and movements measured by the Microsoft Kinect Sensor. In order to effectively handle a large amount of sensory data, we propose to use stratified sampling-based MRA (multiple regression analysis) as our estimation method. To validate the usefulness of the proposed model, we collected 602,599 responses and emotional state data with 274 variables from 15 people. When we applied our model to the data set, we found that our model estimated the levels of valence and arousal in the 10~15% error range. Since our proposed model is simple and stable, we expect that it will be applied not only in intelligent exhibition services, but also in other areas such as e-learning and personalized advertising.

• Journal of Biosystems Engineering
• /
• v.29 no.4
• /
• pp.341-346
• /
• 2004

Recent livestock people concern not only increase of production, but also superior quality of animal-breeding environment. So far, the optimization of the breeding and air environment has been focused on the production increase. In the very near future, the optimization will be emphasized on the environment for the animal welfare and health. Especially, cattle farming demands the precision livestock farming and special attention has to be given to the management of feeding, animal health and fertility. The management of individual animal is the first step for precision livestock farming and animal welfare, and recognizing each individual is important for that. Though electronic identification of a cattle such as RFID(Radio Frequency Identification) has many advantages, RFID implementations practically involve several problems such as the reading speed and distance. In that sense, computer vision might be more effective than RFID for the identification of an individual animal. The researches on the identification of cattle via image processing were mostly performed with the cows having black-white patterns of the Holstein. But, the native Korean and Japanese cattle do not have any definite pattern on the body. The purpose of this research is to identify the Japanese black cattle that does not have a body pattern using computer vision technology and neural network algorithm. Twelve heads of Japanese black cattle have been tested to verify the proposed scheme. The values of input parameters were specified and then computed using the face images of cattle. The images of cattle faces were trained using associate neural network algorithm, and the algorithm was verified by the face images that were transformed using brightness, distortion, and noise factors. As a result, there was difference due to transform ratio of the brightness, distortion, and noise. And, the proposed algorithm could identify 100% in the range from -3 to +3 degrees of the brightness, from -2 to +4 degrees of the distortion, and from 0% to 60% of the noise transformed images. It is concluded that our system can not be applied in real time recognition of the moving cows, but can be used for the cattle being at a standstill.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.609-616
• /
• 2017

In this paper, we propose an algorithm to obtain more stable and high recognition rate by using left and right rotation information of input image in order to obtain a stable recognition rate in face recognition. The proposed algorithm uses the facial image as the input information in the web camera environment to reduce the size of the image and normalize the information about the brightness and color to obtain the improved recognition rate. We apply Principal Component Analysis (PCA) to the detected candidate regions to obtain feature vectors and classify faces. Also, In order to reduce the error rate range of the recognition rate, a set of data with the left and right $45^{\circ}$ rotation information is constructed considering the directionality of the input face image, and each feature vector is obtained with PCA. In order to obtain a stable recognition rate with the obtained feature vector, it is after scattered in the eigenspace and the final face is recognized by comparing euclidean distant distances to each feature. The PCA-based feature vector is low-dimensional data, but there is no problem in expressing the face, and the recognition speed can be fast because of the small amount of calculation. The method proposed in this paper can improve the safety and accuracy of recognition and recognition rate faster than other algorithms, and can be used for real-time recognition system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.2
• /
• pp.397-409
• /
• 2014

According to the Personal Information Protection Act(PIPA) which is legislated in March 2011, the individual or company that handles personal information, called Personal information processor, should encrypt some kinds of personal information kept in his Database. For convenience sake we call it DB Encryption in this paper. Law enforcement and the implementation agency accordingly are being strengthen the supervision that the status of DB Encryption is being properly applied and implemented as the PIPA. However, the process of DB Encryption is very complicate and difficult as well as there are many factors to consider in reality. For example, there are so many considerations and requirements in the process of DB Encryption like pre-analysis and design, real application and test, etc.. And also there are surely points to be considered in related system components, business process and time and costs. Like this, although there are plenty of factors significantly associated with DB Encryption, yet more concrete and realistic validation entry seems somewhat lacking. In this paper, we propose a realistic DB Encryption Assurance Framework that it is acceptable and resonable in the performance of the PIPA duty (the aspect of the individual or company) and standard direction of inspection and verification of DB Encryption (the aspect of law enforcement).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.691-695
• /
• 2012

수위표의 영점에서 수면까지의 높이로 정의되는 해발수위는 유량 및 유사량 등과 같은 관련 수문자료를 생산하는데 기본이 되는 자료이며, 하천 및 수공구조물의 설계 등에 기초자료로 이용될 뿐만 아니라 수자원의 효율적인 관리 및 수문순환 해석을 위한 가장 중요한 기초자료로서 국가 차원의 올바른 수자원 계획과 정책을 수립하는데 널리 활용된다. 이와 같이 해발수위자료의 이용 분야가 다양하고 그 자체로서도 중요한 의미를 가지는 점을 고려할 때 무엇보다도 중요한 것은 자료의 품질이 확보되어야 하는 것이다. 그러나 영점표고검정수준점 및 기준 수위표의 설치 이후 오랜 시간이 경과됨에 따라 노후화와 수위관측소 주변의 환경변화가 발생하게 되어 자료의 정확도가 매우 낮아지고 있다. 본 연구에서는 해발수위 자료의 품질향상을 위해 수위관측소의 영점표고검정수준점 및 수위표 영점표고에 대하여 수준측량 및 RTK(Real Time Kinematic) GPS(Global Positioning System) 측량을 병행하여 수행하였으며, 조사측량된 값을 활용하여 기존에 측량된 영점표고검정수준점 및 수위표 영점표고에 대한 검토를 수행하였다. 금강 및 삽교천 수계에 위치한 50개 수위관측소 대하여 기존 측량값과 비교 검토한 결과 영점표고검정수준점은 0.10m 이하(54.0%), 0.10m 초과 ~ 0.50m 이하(26.0%), 0.50m 초과 ~ 1.00m 이하(6.0%), 1.00m초과 ~ 1.50m 이하(2.0%), 1.50m 초과 ~ 2.00m 이하(2.0%), 2.00m 초과 ~ 3.00m 이하(4.0%), 3.00m 초과(6.0%)의 값을 나타냈으며, 수위표 영점표고는 0.10m 이하(50.0%), 0.10m 초과 ~ 0.50m 이하(32.0%), 0.50m 초과 ~ 1.00m 이하(10.0%), 1.00m초과 ~ 1.50m 이하(2.0%), 1.50m 초과 ~ 2.00m 이하(2.0%), 2.00m 초과 ~ 3.00m 이하(2.0%), 3.00m 초과(2.0%)의 값을 가졌다. 이와 같이 기존과 금회 측량자료를 비교 검토한 결과 대부분이 안정적으로 유지되고 있으나 일부 수위관측소에서 변동량이 크게 발생한 원인은 영점표고검정수준점의 노후화, 기준 수위표의 교체 및 위치 변동, 인위적인 하천공사 등으로 인하여 발생한 것으로 판단된다.

• Land and Housing Review
• /
• v.12 no.2
• /
• pp.121-139
• /
• 2021

Technical documents in the construction field are changing from paper documents to electronic ones. As a result, the industry witnesses a trend of using portable electronic devices in searching or retrieving necessary information such as relevant regulations. Despite the improvement in the accessibility to general technical documents, a limitation is still found in accessing the electronic documents on the regulations. We see the barrier for field engineers to enhance their technical knowledge. One of major barriers is that videos, animations, and virtual reality information to enhance the visual understanding of technical content related to regulations are not linked. It is the interactive electronic technical manual (IETM) that can address such issues. The IETM is an electronic document system that enables real-time information acquisition while operating in the form of conversations with users by linking multimedia functions to document types such as specifications and guidelines. This study establishes a model of the IETM that can be operated in the planning stage of a construction project. The study also verifies its usability with a hypothetical case study. This study aims to improve the usability of the IETM in the construction project by analyzing the application effect of the IETM using the AHP technique.

• Convergence Security Journal
• /
• v.17 no.5
• /
• pp.63-69
• /
• 2017

In the early 1990s, IETF(Internet Engineering TaskForce) had started the discussion on new address protocol that can modify and supplement various drawbacks of existing IPv4 address protocol with the introduction of CIDR(Classless Inter-Domain Routing) which is a temporary solution for IPv4 address depletion, NAT, private IP address. While various standards related to new address protocol has been proposed, the SIPP(Simple Internet Protocol Plus) was adopted among them because it is regarded as the most promising solution. And this protocol has been developed into current IPv6. The new concepts are introduced with modifying a lot of deficiencies in the exisitng IPv4 such as real-time data processing, performance on QoS, security and the efficiency of routing. Since many security threats in IPv6 environment still exist, the necessity of stable data communication environment has been brought up continuously. This paper deveopled one-way communication algorithm in IPv6 based on the high possibility of protecting the system from uncertain and potential risk factors if the data is transmitted in one way. After the analysis of existing IPv6 and ICMPv6, this paper suggests one-way communication algorithm as a solution for existing IPv6 and ICMPv6 environment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.18-29
• /
• 2022

Recently, cooperative intelligent transport systems (C-ITS) testbeds have been deployed in great numbers, and advanced autonomous driving research using V2X communication technology has been conducted actively worldwide. In particular, the broadcasting services in their beginning days, giving warning messages, basic safety messages, traffic information, etc., gradually developed into advanced network services, such as platooning, remote driving, and sensor sharing, that need to perform real-time. In addition, technologies improving these advanced network services' throughput and latency are being developed on many fronts to support these services. Notably, this research analyzed the network latency requirements of the advanced network services to develop a remote driving service for the droid type low-speed robot based on the 3GPP C-V2X communication technology. Subsequently, this remote driving service's performance was evaluated using system modeling (that included the operator behavior) and simulation. This evaluation showed that a respective core and access network latency of less than 30 ms was required to meet more than 90 % of the remote driving service's performance requirements under the given test conditions.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.