• Journal of the Korea Society of Computer and Information
• /
• v.14 no.4
• /
• pp.47-57
• /
• 2009

Event detection and recognition is an active and challenging topic recent in Computer Vision. This paper describes a new method for recognizing events caused by human motion from video sequences in an office environment. The proposed approach analyzes human motions using Motion History Image (MHI) sequences, and is invariant to body shapes. types or colors of clothes and positions of target objects. The proposed method has two advantages; one is thant the proposed method is less sensitive to illumination changes comparing with the method using color information of objects of interest, and the other is scale invariance comparing with the method using a prior knowledge like appearances or shapes of objects of interest. Combined with edge detection, geometrical characteristics of the human shape in the MHI sequences are considered as the features. An advantage of the proposed method is that the event detection framework is easy to extend by inserting the descriptions of events. In addition, the proposed method is the core technology for event detection systems based on context-aware computing as well as surveillance systems based on computer vision techniques.

• Journal of Advanced Navigation Technology
• /
• v.28 no.4
• /
• pp.497-506
• /
• 2024

In this study, we proposed security information and event management for ship as a technology to respond to maritime cybersecurity regulations and evolving cyber threats. We analyze the main technologies of network management system and security information and event management, which are representative technologies for responding to ship cyber security, and propose SIEM for ships based on this. Optimized for ships based on the International Maritime Organization's Maritime Cyber Threat Management Guidelines, IACS UR E26, 27, etc. Derive the main functions of the SIEM for ship, linkage and normalization plan for the ship's heterogeneous equipment, ship's cyber threat and ship detection policy to identify ship's cyber security threats, and ship's operating environment and operating personnel.

• Applied Biological Chemistry
• /
• v.50 no.4
• /
• pp.245-252
• /
• 2007

FTA (fault tree analysis), an analytical method for system failure management, was employed in the management of faults in running PCR analysis. PCR is executed through several processes, in which the process of PCR machine operation was selected for the analysis by FTA. The reason for choosing the simplest process in the PCR analysis was to adopt it as a first trial to test a feasibility of the FTA approach. First, fault events-top event, intermediate event, basic events-were identified by survey on expert knowledge of PCR. Then those events were correlated deductively to build a fault tree in hierarchical structure. The fault tree was evaluated qualitatively and quantitatively, yielding minimal cut sets, structural importance, common cause vulnerability, simulation of probability of occurrence of top event, cut set importance, item importance and sensitivity. The top event was 'errors in the step of PCR machine operation in running PCR analysis'. The major intermediate events were 'failures in instrument' and 'errors in actions in experiment'. The basic events were four events, one event and one event based on human errors, instrument failure and energy source failure, respectively. Those events were combined with Boolean logic gates-AND or OR, constructing a fault tree. In the qualitative evaluation of the tree, the basic events-'errors in preparing the reaction mixture', 'errors in setting temperature and time of PCR machine', 'failure of electrical power during running PCR machine', 'errors in selecting adequate PCR machine'-proved the most critical in the occurrence of the fault of the top event. In the quantitative evaluation, the list of the critical events were not the same as that from the qualitative evaluation. It was because the probability value of PCR machine failure, not on the list above though, increased with used time, and the probability of the events of electricity failure and defective of PCR machine were given zero due to rare likelihood of the events in general. It was concluded that this feasibility study is worth being a means to introduce the novel technique, FTA, to the management of faults in running PCR analysis.

• Journal of Internet Computing and Services
• /
• v.12 no.1
• /
• pp.55-70
• /
• 2011

In this paper, we propose a policy-driven RFID data management event definition language, which is possibly applicable as a partial standard for SSI (Software System Infrastructure) Part 4 (Application Interface, 24791-4) defined by ISO/IEC JTC 1/SC 31/WG 4 (RFID for Item Management). The SSI's RFID application interface part is originally defined for providing a unified interface of the RFID middleware functionality―data management, device management, device interface and security functions. However, the current specifications are too circumstantial to be understood by the application developers who used to lack the professional and technological backgrounds of the RFID middleware functionality. As an impeccable solution, we use the concept of event-constraint policy that is not only representing semantic contents of RFID domains but also providing transparencies with higher level abstractions to RFID applications, and that is able to provide a means of specifying event-constraints for filtering a huge number of raw data caught from the associated RF readers. Conclusively, we try to embody the proposed concept by newly defining an XML-based RFID event policy definition language, which is abbreviated to rXPDL. Additionally, we expect that the specification of rXPDL proposed in the paper becomes a technological basis for the domestic as well as the international standards that are able to be extensively applied to RFID and ubiquitous sensor networks.

• Journal of KIISE:Databases
• /
• v.33 no.6
• /
• pp.620-630
• /
• 2006

Event-detection is an important application of sensor networks. Join operations can facilitate event-detection with a condition table predefined by a user. When join operations are used for event-detection, it is desirable, if possible, to do in-network join processing to reduce communication costs. In this paper, we propose an energy-efficient in-network join algorithm, called PBA. In PBA, each partition of a condition table is stored along the path from each node to the base station, and then in-network joins are performed on the path. Since each node can identify the parts to store in its storage by its level, PBA reduces the cost of disseminating a condition table considerably Moreover, while the existing method does not work well when the ratio of the size of the condition table to the density of the network is a little bit large, our proposed method PBA does not have such a restriction and works efficiently in most cases. The results of experiments show that PBA is efficient usually and especially provides significant cost reduction over existing one when a condition table is relatively large in comparison with the density of the network, or the routing tree of the network is high.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.10
• /
• pp.447-454
• /
• 2015

This paper proposes geographical name denoising by machine learning of event detection based on twitter. Recently, the increasing number of smart phone users are leading the growing user of SNS. Especially, the functions of short message (less than 140 words) and follow service make twitter has the power of conveying and diffusing the information more quickly. These characteristics and mobile optimised feature make twitter has fast information conveying speed, which can play a role of conveying disasters or events. Related research used the individuals of twitter user as the sensor of event detection to detect events that occur in reality. This research employed geographical name as the keyword by using the characteristic that an event occurs in a specific place. However, it ignored the denoising of relationship between geographical name and homograph, it became an important factor to lower the accuracy of event detection. In this paper, we used removing and forecasting, these two method to applied denoising technique. First after processing the filtering step by using noise related database building, we have determined the existence of geographical name by using the Naive Bayesian classification. Finally by using the experimental data, we earned the probability value of machine learning. On the basis of forecast technique which is proposed in this paper, the reliability of the need for denoising technique has turned out to be 89.6%.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.139-147
• /
• 2021

This paper introduces and implements a Sound Event Detection (SED) system based on weakly-supervised learning where only part of the data is labeled, and analyzes the effect of parameters. The SED system estimates the classes and onset/offset times of events in the acoustic signal. In order to train the model, all information on the event class and onset/offset times must be provided. Unfortunately, the onset/offset times are hard to be labeled exactly. Therefore, in the weakly-supervised task, the SED model is trained by "strongly labeled data" including the event class and activations, "weakly labeled data" including the event class, and "unlabeled data" without any label. Recently, the SED systems using the mean-teacher model are widely used for the task with several parameters. These parameters should be chosen carefully because they may affect the performance. In this paper, performance analysis was performed on parameters, such as the feature, moving average parameter, weight of the consistency cost function, ramp-up length, and maximum learning rate, using the data of DCASE 2020 Task 4. Effects and the optimal values of the parameters were discussed.

• The Journal of Industrial Distribution & Business
• /
• v.9 no.9
• /
• pp.63-74
• /
• 2018

Purpose - The current study is to compare the cognition of stakeholders on hosting a mega sports event between Korea and the United States. In particular, to understand their cognition and perceptual conflict towards hosting a mega sports event, the study employed conflict theory. Furthermore, the study reviewed the role of social capital in the process of managing the mega sports events. Research Design, Data, and Methodology - Of homogeneous sampling, purposeful sampling method and criterion-based selection approach were used to collect interview data from key stakeholders who have been involved in hosting a mega sports events in Korea and the United States. In-depth interview transcripts were reviewed multiple tiems after transcription to extract concepts and meanings that were pertinenet to the experience involving hosting a mega sports event. Further member checks was conducted to increase the credibility of the results. Results - Results can be summarized as followed: First, stakeholders of Korea have a strong desire for positive economic effects of a mega sports event, compared to those in the United States who are more concerned in enhancing the public interests and concerns. Second, in Korea, various socio-political issues emerged at the same time and conflicts among multiple stakeholders have aggravated the situations to coordinate the issues. This was because legal system supporting socio-trust has not been established. On the other hand, major stakeholders of the United States consisted of community members who have socio-trust and networks. Thereby these social resources have been found playing a key role in building social capital that assists the stakeholders to coordinate the current issues and to solve them. Conclusions - The current study analyzed the cognition and perceptual conflict of stakehoders in a mega sports event. Social capital has beend found as a key catalyst to increase a network and cooperation among stakeholders. In order to enhance social capital in managing a mega sports event hosted in Korea, legal systems that establish networks and relationships among the related stakeholders need to be developed. Furthermore, the systematic guideline needs to be developed, organizing the sub-committees according to the types of stakeholders and the categorized common needs.

• Journal of the Korean Chemical Society
• /
• v.51 no.1
• /
• pp.56-64
• /
• 2007

This study examined the influences of cognitive conflict and anxiety induced by a discrepant event and an alternative hypothesis, attention, and effort on conceptual change. Two hundred three students having misconceptions about density were selected from 462 seventh graders based on the results of a preconception test. Tests of cognitive responses and anxiety to a discrepant event were administered before and after presenting an alternative hypothesis. Computer-assisted instruction (CAI) was then provided to students as a conceptual change intervention. Tests assessing attention and effort allocated to the CAI, and conceptual understanding were administered as posttests. Cognitive conflict induced by a discrepant event was found to increase after presenting an alternative hypothesis. Pre-cognitive conflict induced by only a discrepant event exerted a direct effect on post-cognitive conflict induced by a discrepant event and an alternative hypothesis. Post-cognitive conflict had a direct effect on conceptual change. Pre-anxiety decreased after presenting an alternative hypothesis. Pre-anxiety influenced post-anxiety, and this influenced on conceptual change via effort negatively. Attention had a direct effect as well as an indirect effect on conceptual change via effort. These results suggest that the strategy presenting both a discrepant event and an alternative hypothesis to students in concept learning could facilitate conceptual change by inducing more cognitive conflict or active participation of students through the decrease of anxiety than that presenting a discrepant event only.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.