• Korean Journal of Remote Sensing
• /
• v.13 no.1
• /
• pp.47-56
• /
• 1997

In this paper, remote sensing is used to estimate trophic state which is primary concern in a lake. In using remote sensing, this study estimated trophic state not with conventional method such as regression equations but with classification methods. As europhication is caused by the extraodinary proliferation of the algae, chlorophyll a and transparency are applied to remote sensing data.. Maximum Likelihood Classification and Minimum Distance Classification which are kinds of classification methods enabled trophic state to be confirmed in a lake. These are obtained as the result of applying remote sensing to classify trophic state in a lake. Firest, when we evaluate tropic state in a large area of water body, the application of remote sensing data can obtain more than 70% accuracies just in using basic classification methods. Second, in the aspect of classification, the accuracy of Minimum Distance Classification is usually better than that of Maximum Likelihood Classification. This result is caused that samples have normal distribution, but their numbers are a few to apply statistical method. Therefore, classification method is required such as artificial neural networks which are not influenced by statistical distribution. Third, this study enables the trophic state of water body to be analyzed and evaluated rapidly, periodically and visibly. Also, this study is good for forming proper countermeasure accompanying with trophic state progress extent in a lake and is useful for basic-data.

• 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.

• The Korean Journal of Archival Studies
• /
• no.14
• /
• pp.241-288
• /
• 2006

For cope with the participating government promoted local decentralization of the present time, local governments are coming to aim at the realization of local governance. Local governance refers to a way of solving public problems of urban area through partnership which is a collaboration and participation based on 'relationship' among diverse interested parties such as executive authority of policy, private sectors. First of all, it is most important task to make transparency and responsibility of all people and networks by themselves through sharing information. With like this kind of a background, local assembly is an momentos body of local governance because it is a decision making organization at the same time as a representative organization of local residents, and it has a relationship of 'check and balance' with chiefs of local governments as an organization monitoring and supervising the administration of an executive authority. Not the less, information about local assembly does not open to the public or exist. Even some informations open to the public, they are not enough to be settled distrust and low-valuation by civil society. Now Local assembly is face to a point that improve over all of record management. This study is based like this critical mind, then, it examines throughly local assembly's realities by suggestion with reforming plan of record management. Record can embody true values when record management practices indefatigably through prudential system from production until preservation. Accordingly, this study suggests management of transaction unit without the omission of record. Also this study is satisfy the condition of Korean record management system with proposals of record management policy and establishment of record center. At the conclusion of study, it puts effects into shape that local assembly secure transparency and responsibility and organize local governance by record management.

• Cross-Cultural Studies
• /
• v.48
• /
• pp.361-389
• /
• 2017

This essay examines 'precarity politics' by Judith Butler, a well-known gender theorist and queer philosopher, in Notes Towards a Performative Theory of Assembly (2015) focused on concepts as unchosen cohabitation of Hannah Arendt and unwilled proximity of Emmanuel Levinas. Butler's precarity politics is the condition of our dispossessed political beings with fundamental vulnerability and interdependency that cannot choose with whom we will live on this Earth. Butler's political ethics is twofold: on one hand, she examines significance of 'action'' the most significant vita activa in the public area, and 'plurality'' the condition-not only the necessary condition but the possible condition-for a political life suggested by Hannah Arendt in Human Condition; on the other hand, Butler reflects upon global precarity based on a diasporic precarious life in the social world towards freedom and equality. Unchosen cohabitation of plural humans on Earth, and global pervasion of precarity, that indicates "politically induced condition in which certain populations suffer from failing social and economic networks of support and become differentially exposed to injury, violence, and death," so called "differential distribution of precariousness," are practical possibilities of ethical and equal cohabitation of different ethnic groups in the social world. Ethical obligations or ethical demand to respond to others' suffering in distance and proximity originated from precarity politics, mentioned in Precarious Life, Parting Ways, and Frames of War, could be non-foundational joint of plural people living together globally. We should presume the 'reversibility' of distance and proximity in others' suffering, based on responsiveness and responsibility of others, if we want to stay attuned to the pain of others we never chose to live together. That is the significance of Butler's 'precarity politics' with 'ethical obligation' to accept 'unchosen plurality' of living population on Earth, and 'reversibility between of distance and proximity,' in her 'new plural and embodied body politics' or 'new corporeal ontology', through human primary vulnerability, fundamental interdependency, being exposed and responsive to suffering of others.

• Archives of design research
• /
• v.16 no.4
• /
• pp.185-196
• /
• 2003

The demand for an environment-friendly transportation system, equipped with low energy consumption, and low-or zero-pollution has been on the increase since the beginning of the World Trade Organization era. Simultaneously, the consistent growth of high-speed tram technology, combined with market share, has sparked a fierce competition among technologically-advanced countries like France, Germany, and Japan in an effort to keep the lead in high-speed train technology via extensive Research and development(R＆D) expenses. These countries are leaders in the race to implement the next-generation transportation system, build intercontinental rail way networks and export the high-speed train as a major industry commodity. The need to develop our own(Korean) 'high-speed train' technology and its core system technology layouts including original technology serves a few objectives: They boost the national competitive edge; they develop an environmental friendly rail road system that can cope with globalization and minimize the social and economic losses created by the growing traffic-congested delivery costs, environment pollution, and public discomforts. In turn, the 'G7 Project-Development of High Speed Railway Technology' held between 1996 and 2002 for a six-year period was focused on designing a domestic train capable of traveling at a speed of 350km/h combined and led to the actual implementation of engineering and producing the '2000 high-speed train:' This paper summarizes and introduces one of the G7 Projects-specifically, the design segment achievement within the development of train system engineering technology. It is true that the design aspect of the Korean domestic railway system program as a whole was lacking when compared with the advanced railroad countries whose early phase of train design emphasized the design aspect. However, having allowed the active participation of expert designers in the early phase of train design in the current project has led to a new era of domestic train development and the implementation of a way to meet demand flexibly with newly designed trains. The idea of a high-speed train in Korea and its design concept is well-conceived: a faster, more pleasant, and silent based Korean high-speed train that facilitates a new travel culture. A Korean-type of high-speed train is acknowledged by passengers who travel in such trains. The Korean high-speed prototype train has been born, combining aerodynamic air-cushioned design, which is the embodiment of Korean original design of forehead of power car minimized aerodynamic resistance using a curved car body profile, and the improvement of the interior design with ergonomics and the accommodation of the vestibule area through the study of passenger behavior and social culture that is based on the general passenger car.