• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.2
• /
• pp.30-41
• /
• 2006

This paper proposes an e-logistics system supporting efficient vehicle moving trajectory management. Recent advances in wireless communications have given rise to a number of location-based services including logistics vehicle tracking, cellular phone user's location finding, and location-based commerce. Logistics systems typically entail tracking vehicles for purposes of the logistics center knowing the whereabouts of the vehicles and/or consignments. Moreover, storing and managing location trajectory of continuously moving vehicles and consignments is necessary for supporting efficient logistics plan and consignment. The proposed system is able to manage spatial objects in GIS as well as logistic information in the mobile environment. And for the efficiently managing and retrieving of transporting trajectory of logistics, we extend previous moving object indexing method, TB-Tree, to use multi-version framework and evaluate data updating performance. It is able to apply the proposed method to develop mobile contents services based on continuously changing location of moving object in the mobile environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.69-73
• /
• 2022

In this paper, we propose a new method for measuring fine dust through a LoG(Laplacian of Gaussian)-based edge detection technique. CCTV-based images in a video are collected for fine dust measurement, and image ranges are designated through RoI(Region of Interest). After clustering by applying the GMM(Gaussian Mix Model) to the specified area, we detect edge through the LoG algorithm and measure the detected edge strength. The concentration of fine dust is determined based on the measured intensity data of the edge. In this paper, we propose algorithm as the effectiveness of experiment. As a result of collecting and applying CCTV image in the video installed around the laboratory of this school for a month from June to July, the measured result value was proved through this experiment to be sufficient to calculate the concentration and range of fine dust.

• Journal of Information Processing Systems
• /
• v.6 no.4
• /
• pp.481-500
• /
• 2010

The Internet explosion and the increase in crucial web applications such as ebanking and e-commerce, make essential the need for network security tools. One of such tools is an Intrusion detection system which can be classified based on detection approachs as being signature-based or anomaly-based. Even though intrusion detection systems are well defined, their cooperation with each other to detect attacks needs to be addressed. Consequently, a new architecture that allows them to cooperate in detecting attacks is proposed. The architecture uses Software Agents to provide scalability and distributability. It works in two modes: learning and detection. During learning mode, it generates a profile for each individual system using a fuzzy data mining algorithm. During detection mode, each system uses the FuzzyJess to match network traffic against its profile. The architecture was tested against a standard data set produced by MIT's Lincoln Laboratory and the primary results show its efficiency and capability to detect attacks. Finally, two new methods, the memory-window and memoryless-window, were developed for extracting useful parameters from raw packets. The parameters are used as detection metrics.

• International journal of advanced smart convergence
• /
• v.10 no.1
• /
• pp.1-11
• /
• 2021

Document page segmentation is an important step in building a quality optical character recognition module. The study examined already existing work on the topic of page segmentation and focused on the development of a segmentation model that has greater functional significance for application in an organization, as well as broad capabilities for managing the quality of the model. The main problems of document segmentation were highlighted, which include a complex background of intersecting objects. As classes for detection, not only classic text, table and figure were selected, but also additional types, such as signature, logo and table without borders (or with partially missing borders). This made it possible to pose a non-trivial task of detecting non-standard document elements. The authors compared existing neural network architectures for object detection based on published research data. The most suitable architecture was RetinaNet. To ensure the possibility of quality control of the model, a method based on neural network modeling using the RetinaNet architecture is proposed. During the study, several models were built, the quality of which was assessed on the test sample using the Mean average Precision metric. The best result among the constructed algorithms was shown by a model that includes four neural networks: the focus of the first neural network on detecting tables and tables without borders, the second - seals and signatures, the third - pictures and logos, and the fourth - text. As a result of the analysis, it was revealed that the approach based on four neural networks showed the best results in accordance with the objectives of the study on the test sample in the context of most classes of detection. The method proposed in the article can be used to recognize other objects. A promising direction in which the analysis can be continued is the segmentation of tables; the areas of the table that differ in function will act as classes: heading, cell with a name, cell with data, empty cell.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.135-155
• /
• 2024

Urban public health monitoring in smart cities focuses on the control of conditions and health challenges in urban environments. Considering the rapid spread of diseases and pandemics, it is important for health authorities to trace people carrying the virus. In smart cities, this tracing must be interoperable and intelligent, especially in indoor surfaces characterized by small distances between people. Therefore, to fight pandemics, it is necessary to start with the already-existing digital equipment of the Internet of Things, such as connected objects and smartphones. In this study, the developed system is employed to provide a social IoT network and suggest a strategy which allows reliable traceability without threatening the privacy of users. This IoT-based system allows respecting the social distance between persons sharing public services in smart cities without applying smartphone applications or severe confinement. It also permits a return to normal life in case of viral pandemic and ensures the much-desired balance between economy and health. The present study analyses previous proposed social distance systems then, unlike these studies, suggests an intelligent and distributed IoT based strategy for positioning students. Two scenarios of static and dynamic optimization-based placement of Bluetooth Low Energy devices are proposed and an experimental study shows the contribution and complementarity of the introduced contact tracing strategy with the applications on smartphones.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.3
• /
• pp.480-486
• /
• 2005

Recently, domestic interest about wireless internet is rising gradually. Characteristic of present domestic wireless market is that mobile communication businessmans appropriate each other different mobile platform. So, contents provider's development environment can not be same each other. This makes contents providers repeat same work. To solve this problem, standardization work of wireless internet market was begun. The three mobile communication companies and TTA (Telecommunications Technology Association), RRU(Radio Research Laboratory), ETRI(Electronics and Telecommunications Research Institute) progressed standardization. By the result, May 2002, WIPI that is wireless standard platform selected by mobile platform standard that is TTA organization standard. In this paper, 1 am going to examine the WIPI. WIPI can reduce mostly expense that happen when we use different platform. 1 design and embody common phrase function. Through this, 1 am going to show improvement of the character input speed in cellular phone. And I wish to discuss expected cost decrease effect. Investigate about platform of treatise that is used in domestic. analyze about the characteristic, merits and demerits. Chatting service and common phrase function design and embody. Finally, wish to discuss about advantage of common phrase function and practical use field.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.2
• /
• pp.523-535
• /
• 2017

Local intelligent services aim at controlling local services such as cooling or lightening services in a certain local area, using Internet-of-Things (IoT) sensor data in the area. As the IoT paradigm has evolved, local intelligent services have gained increasing attention. However, most of the local intelligent service mechanism proposed so far do not directly take the users' presence and service preference information into account for controlling local services. This study proposes an individual presence-and-preference-based local service system (IPP-LISS). We present a intelligent service control algorithm and implement a prototype system of IPP-LISS. Typically, the intelligence part of IPP-LISS including the prediction models, is generated on remote server in the cloud because of their compute-intense aspect. However, this can cause huge data traffic between IoT devices and servers in the cloud. The emerging mobile edge computing technology will be a promising solution of this challenge of IPP-LISS. In this paper, we implement IPP-LISS in the cloud, and then, based on the implementation result, we discuss applying the mobile edge computing technology to the IPP-LISS application.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.311-314
• /
• 2003

많은 공학 연구에서 실제 시스템을 활용한 검증은 매우 중요하다. 특히 제어공학의 경우 개발된 신 이론을 적용 및 검증할 수 있는 실험장비의 확보는 필수적이다. 그러나 현실적으로 적절한 실험장비를 확보하는 것은 비경제적이다. 인터넷을 활용하여 실험장비의 원격실험을 가능케 한 가상실험실은 제어공학 연구에 유용하다. 인터넷의 보급과 함께 가상실험실에 대한 연구가 활발히 진행되고 있으나, 대부분의 경우가 특정 시스템에 한정된 가상 실험실의 구축에 한정되어 있다. 본 논문에서는 기존 연구와 달리 다양한 실험 장비에 적용 가능하며 다양한 제어 기법을 제공하는 가상실험실의 구현을 제안한다. 제안된 가상실험실은 서버-클라이언트 구조를 가지며 다중 제어 인터페이스로 구현된다.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1203-1212
• /
• 2017

Intrusion detection systems (IDSs) are crucial in this overwhelming increase of attacks on the computing infrastructure. It intelligently detects malicious and predicts future attack patterns based on the classification analysis using machine learning and data mining techniques. This paper is devoted to thoroughly evaluate classifier ensembles for IDSs in IEEE 802.11 wireless network. Two ensemble techniques, i.e. voting and stacking are employed to combine the three base classifiers, i.e. decision tree (DT), random forest (RF), and support vector machine (SVM). We use area under ROC curve (AUC) value as a performance metric. Finally, we conduct two statistical significance tests to evaluate the performance differences among classifiers.