• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.63-72
• /
• 2020

This study aims to develop a video-based smart utterance deep analyser (SUDA) application that analyzes semiautomatically the utterances that child and mother produce during interactions over time. SUDA runs on the platform of Android, iPhones, and tablet PCs, and allows video recording and uploading to server. In this device, user modes are divided into three modes: expert mode, general mode and manager mode. In the expert mode which is useful for speech and language evaluation, the subject's utterances are analyzed semi-automatically by measuring speech and language factors such as disfluency, morpheme, syllable, word, articulation rate and response time, etc. In the general mode, the outcome of utterance analysis is provided in a graph form, and the manger mode is accessed only to the administrator controlling the entire system, such as utterance analysis and video deletion. SUDA helps to reduce clinicians' and researchers' work burden by saving time for utterance analysis. It also helps parents to receive detailed information about speech and language development of their child easily. Further, this device will contribute to building a big longitudinal data enough to explore predictors of stuttering recovery and persistence.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.9
• /
• pp.18-23
• /
• 2017

The shipyard quay process struggles to control workers and maintain a secure working environment because of the presence of at least 1,000 people. Therefore, safety accidents such as an explosion or a fire are likely to occur. With the recent increase in safety accidents at shipyards, the requirements for safety and process monitoring have been strengthened. Major shipyards are conducting researchto monitor the process in real time and to detect the work environment for safety. In this paper, we propose a safe and accurate evacuation route based on the information of the dangerous area and the user's location based on a mobile application to reduce the casualty accidents in the presence of many personnel in a concentrated area. To do this, we analyze the trend of the fire escape system on the ground building, compare various algorithms for escape route calculation, select appropriate algorithms for this study, and perform programming. A basic experiment was conducted to confirm the results. The proposed method is expected to be used in large ship construction sites, passenger ships and large public facilities to reduce accidents in the case of a safety accident.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.10
• /
• pp.2269-2276
• /
• 2010

This research shows how autonomous character agents work in 3D sports game and its application to advertising. It is a kind of interdisciplinary study between game and advertising. In other words, advertising can be used a beneficiary model in game industry. For the purpose of analyzing the role of agents, 3D table-tennis game and advertising tools are developed. The role of agents is booming up and focusing on the game by their voices and texts. In game, several famous brands are showed up as a mean of advertising. This study analyzed the role of agents and advertising from the game user's position. For validity and reliability of the research, questionnaires were analyzed. As a results, several facts are found. Firstly, the agents worked positively as a game boomer. More than half of the respondents answered the agents are useful for the game. Secondly, the advertising tools showed up on the game are helpful to understand the brand. In other words, the game is contributed to build up the brand image. These kinds of attempts may be significant in that the agents are performed as a parter of functional and woman-oriented game. And advertising brands when placed in the game could play the role of the game item or quest. The proposed method can provide the basic references for developing 3D game as an interdisciplinary study.

• Journal of Digital Contents Society
• /
• v.3 no.2
• /
• pp.211-220
• /
• 2002

It has not been long since the current form of PDA began to be used widely. The PDA, which first came out in a recognizable form in the market a decade ago, multiplying the number of users, has recently been developed in various forms. It began to make cutting-edge technology available in PDA, and to be subdivided into various forms appropriate for special purposes, which reflected the recent intense competition in the market. It included the function of mobile phone, in tandem with the original function of PDA, by which it brought about other synergy effects and corresponded with the purpose more solidly. Due to these recent changes, PDA has had a dramatically increasing number of users, as well as the wider scope of usage and practical application by introducing new technology. However, research is required in the fields of basic usage and interface. It is important to recognize that PDA is an apparatus that stores for the users contents and information suitable for them, and that responds to them in case of need. PDA therefore needs to convey what the users require more easily and speedily without errors, and to provide them with appropriate information and contents. This paper examined the extent to which the interface of PDA including the input of contents required by the user would be efficient by questionnaires. In addition, alternatives concerning a general application environment of PDA were suggested based on the result of this survey.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.227-235
• /
• 2006

MPEG-21's digital item adaptation technology becomes a new way for universal multimedia access. It needs transcoder to change media resource's format and so on according to delivery context Then, the use of heavy transcoder with various transcoding functions integrated into one altogether is so complicated and difficult in supporting universal multimedia access. Unit transcoder Is useful is to resolve this question, in which a transcoder has only one transcoding function. This requires considering how to compose a set of unit transcoders. Thus, given a set for end-to-end different service quality pairs according to the character of application as defined by user, this study suggests how to compose complete unit transcoders that can always create one and more transcoding path(s) for each pair in the set. This method has a question of creating too many transcoding paths for each pair or end-to-end different service quality. Thus, this study also suggests the algorithm that generates minimum unit transcoder sets to support multimedia adaptation with minimum unit transcoder. The algorithm suggested was implemented into multimedia stream engine, and this paper describes the results of experiment for this algorithm.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.4
• /
• pp.34-45
• /
• 2004

Existing Semangeum's water balance analysis simplifies whole basin to single basin and achieved volume of effluence that produce by Kajiyama way to foundation. But Semangeum is complicated and various rice-wine strainer supply system. And there is difficulty to apply as elastic when water balance element is changed at free point. Divided to unit possession station for suitable water balance analysis model application to Semangeum in this study. And developed basin water balance model of GIS base that can do details analysis is bite about development and transfer of an appropriation in the budget of basin water resources. Achieved study including abstraction and concept design that use UML (unified modeling language) diagram for details analysis, stream network composition for rice-wine strainer supply system application, preprocessing of GIS base and postprocessing module development, model revision and verification etc. Support of this water balance analysis model is available to establish efficient water resources administration plan through outward flow process analysis of water resources. And support is considered to be possible in more convenient and, reasonable water resources administration way establishment by minimizing manual processing in systematic water resources government official to user and support diversified analysis system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.5
• /
• pp.271-279
• /
• 2014

In this paper, the two design techniques of the embedded system which provides a wireless image observation with temporary ad-hoc network are proposed and developed. The first method is based on the embedded system design technique for a nearly real-time wireless short observation application, having a specific remote monitoring node with a built-in image processing function, and having the maximum rate of 1 fps (frame per second) wireless image transmission capability of a $160{\times}128$size image. The second technique uses the embedded system for a general wireless long observation application, consisting of the main node, the remote monitoring node, and the system controller with built-in image processing function, and the capability of the wireless image transmission rate of 1/3 fps. The proposed system uses the wireless ad-hoc network which is widely accepted as a short range, low power, and bidirectional digital communication, the hardware are consisted of the general developed modules, a small digital camera, and a PC, and the embedded software based upon the Zigbee stack and the user interface software are developed and tested on the implemented module. The wireless environment analysis and the performance results are presented.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.179-186
• /
• 2024

In this paper, we design and implement an Internet of Things (IoT)-based chick incubation system. The system consists of three key components: the IoT incubator, the IoT server system, and the smartphone application. The IoT incubator is composed of an Arduino board, temperature and humidity sensors, a temperature and humidity controller, a ventilation controller, and an egg turning controller. The temperature and humidity sensors measure the temperature and humidity inside the IoT incubator and send the data to the temperature and humidity controller on the Arduino board. Additionally, it provides the function of transmitting temperature, humidity, and control history data to the IoT server via WiFi. It also offers automatic control of ventilation, egg turning, and temperature and humidity on a daily basis. The IoT server system receives data from the incubator, stores it in a database, and provides query data upon request from the smartphone. The smartphone application retrieves historical data through the server and monitors the temperature and humidity data of the IoT incubator in real-time, controlling the IoT incubator to ensure that the set temperature and humidity ranges are maintained. If the temperature and humidity data deviate from the set ranges, it sends alarms and emergency messages to the user. The IoT-based chick incubation system developed in this paper is a low-cost model due to its reduced manufacturing cost, making it highly beneficial for self-sustaining poultry farms.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.4
• /
• pp.975-983
• /
• 1998

In these days, information communication systems are based on both open distributed computing technologies and object-oriented techniques like inheritance, encapsulation and object reuse to support various system configuration and application. As information systems are interconnected through unsecure networks, the need for the secure information exchange is more critical than before. In this paper, we have designed and implemented a transparent CORBA-basce Security infrastructure with authentication, security context association, access control and security information management to support a secure applications in distributed object environment. SESAME Ver. 4 was adopted as an external security service to manage user privilege attributes and to distribute keys for data encryption, decryption and integrity. Using filter and transformer with an interface to Object Request Broker, it provides a transparent security service to applications. The filter objects are special classes that allow additional parameters to be inserted into messages before they are sent and removed just after they are received. The transformer objects are special classes that allow direct access to the byte stream of every messages for encryption and decryption before it is sent and just after it is received. This study is to implement the access control interceptor(ACI) and the secure invocation interceptor(SII) of secure ORB defined in CORBA using filter and transformer.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.