• 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 Journal of Fisheries Business Administration
• /
• v.29 no.2
• /
• pp.111-141
• /
• 1998

Why are auctions so prevalent in fisheries fields\ulcorner One answer is, perhaps, that fisheries products have no standard value. The price of any catch of fish (at least of fish destined for the fresh fish market) depends on the demand and supply conditions at a specific moment of time, influenced by prospective market developments and prices must be remade for each transaction. There are various auction schemes including written-bid method in Korea. It is difficult to make decision the application of auction selling in market distribution. One reason is the absence of adequate data on which to base firm statements. There is very little precise information about the relative volume handled by auction scheme as compared with other sales schemes Because of the paucity reliable data, one must depend largely on qualitative in attempting to above this problem. This paper is designed to examine which auction scheme is more efficient as a economic tool by introducing the three auctions, as samples, utilized in Koheung peninsula. Koheung coast with abundant fisheries resource, locates on the Middle-South part in Korea and has three auction firm operating by fisheries cooperatives. fur selling of dry fish included sea weed, live fish and fresh fish respectively, As a result, 1 found that there are three interesting auction schemes as follow : 1. More than one winners are selected as buyers. The highest bidder can at first get fishes he wants to buy, second winner can get surplus fishes after the highest bidder employes one's privilege with the highest pay, and next winner would be a buyer if fishes would be left in sequence after being sold with higher price. Every fisherman can sell one' s fishes with equal unit price if he delivery it to the winner within one day. Therefore, all the vendors feel they are equal members of fisheries cooperation. 2. Written-bid pricing on the cover of handy book. It is easy to write and to erase the figure more than on the small black board, and is convenient also to keep in the pocket. 3. Auctioning on the fixed platform with fixed fish tank is a very fast auction scheme in spite of short displaying time. Auctioneer presides bidding at one place on the fixed platform, instead of moving, vendors should carry a container of live fishes in the fish tank into showing table in front of would-be buyers and auctioneer. Although the applicability of the auction system to a marketing problem depends in part on subjective considerations by those making decision, basically it is a matter of comparative economic efficiency. In general, if the scheme maximizes returns in relation to the effort expanded by both buyers and sellers, it will be utilized. If it does not, a more efficiency may take place over a period of time, but, even more important, those making decisions may become aware of the potentialities of new schemes. Therefore, in order to applicate the three interesting auction schemes introduced in this paper to other fisheries market, it is necessary not only to analyze many other auction schemes but also to compare the economic efficiency those schemes utilizing in other fisheries market.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.1-9
• /
• 2012

LCD(Liquid Crystal Display) commonly used as an output device has a drawback of slow response time compared with CRT display. This drawback causes motion blur especially when an abrupt intensity change occurs in an image sequence as time goes on. To overcome the problem of slow response time overdriving technique has been used in TCON of LCD. In this technique, the previous frame data has to be compressed and stored in an external memory. Considering both chip size of TCON and computational complexity, AM-BTC has been applied to the 8bit HD display driver. However, the conventional method is not suitable for 10 bit Full HD because 10 bit Full HD data is much larger than that of 8 bit HD data. Being applied to 10 bit Full HD display driver, the conventional method increase cost by enlarging the external memory size of TCON or deteriorates image quality. In this paper, we propose dual BTC image coding technique for Full HD display driver that is an adaptive coding scheme according to morphological information of each sample block. Through experiments, it is verified that the proposed Dual BTC method performs better than the conventional method not only quantitatively but also qualitatively.

• Journal of the Korean Magnetic Resonance Society
• /
• v.5 no.2
• /
• pp.99-109
• /
• 2001

Authors investigated neuronal changes of local cellular metabolism in the cerebral lesions of Parkinsonian symptomatic side between before and after stereotactic neurosurgery by follow-up 1H magnetic resonance spectroscopy (MRS). Patients with Parkinson's disease (PD) (n = 15) and age-matched normal controls (n = 15) underwen MRS examinations using a stimulated echo acquisition mode (STEAM) pulse sequence that provided 2${\times}$2${\times}$2 ㎤ (8ml) volume of interest in the regions of substantia nigra, thalamus, and lentiform nucleus. Spectral parameters were 20 ms TE, 2000 ms TR, 128 averages,2500 Hz spectral width, and 2048 data points. Raw data were processed by the SAGE data analysis package (GE Medical Systems). Peak areas of N-acetylaspartate (NAA), creatine (Cr), choline-containing compounds (Cho), inositols (Ins), and the sum (Glx) of glutamate and GABA were calculated by means of fitting the spectrum to a summation of Lorentzian curves using Marquardt algorithm. After blindly processed, we evaluated neuronal alterations of observable metabolite ratios between before and after stereotactic neurosurgery using Pearson product-moment analysis (SPSS, Ver. 6.0). A significant reduction of NAA/Cho ratio was observed in the cerebral lesion in substantia nigra of PD patient related to the symptomatic side after neurosurgery (P : 0.03). In thalamus, NAA/Cho ratio was also significantly decreased in the cerebral lesion including the electrode-surgical region (P : 0.03). A significant reduction of NAA/Cho ratio in lentiform nucleus was not oberved, but tended toward significant reduction after neurosurgery (P = 0.08). In particular, remarkable lactate signal was noted from the surgical thalamic lesions of 6 among 8 patients and internal segments of globus pallidus of 6 among 7 patients, respectively. Significant metabolic alterations of NAA/Cho ratio might reflect functional changes of neuropathological processes in the lesion of substantia nigra, thalamus, and lentiform nucleus, and could be a valuable finding fur evaluation of Parkinson's disease after neurosurgery. Increase of lactate signals, being remarkable in surgical lesions, could be consistent with a common consequence of neurosurgical necrosis. Thus, IH MRS could be a useful modality to evaluate the diagnostic and prognostic implications fur Parkinsons disease after functional neurosurgery.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.3
• /
• pp.388-397
• /
• 2009

There are many tasks which require robotic manipulators interaction with environment. It consists of three control problems, i.e., position control, impact control and force control. The position control means the way of reaching to the environment. The moment of touching to the environment yields the impact control problem and the force control is to maintain the desired force trajectory after the impact with the environment. These three control problems occur in sequence, so each control algorithm can be developed independently. Especially for redundant manipulators, each of these three control problems has been important independent research topic. For example, joint torque minimization and impulse minimization are typical techniques for such control problems. The three control problems are considered as a single task in this paper. The position control strategy is developed to improve the performance of the task, i.e., minimization of the individual joint torques and impulse. Therefore, initial conditions of the impact control problem are optimized at the previous position control algorithm. Such a control strategy yields improved result of the impact control. Similarly, the initial conditions for the force control problem are indirectly optimized by the previous position control and impact control strategies. The force control algorithm uses the individual joint torque minimization concept. It also minimizes the force disturbances. The simulation results show the proposed control strategy works well.

• The Journal of Art Theory & Practice
• /
• no.3
• /
• pp.51-66
• /
• 2005

With the advent of the time when the competitiveness of a nation or a city can be evaluated by the extent of cultural reception, the art exhibitions, like other genres of art, are actively held in various ways by different institutions. The spaces of exhibition offered not only by public museums and galleries but also by private galleries, alternative spaces and open-air exhibition spots are being increased. Likewise, the number of exhibitions organized on a large scale by Biennales and local governments is on the increase. In accordance with actual tendency, the Ministry of Culture and Tourism has planned to increase the number of museums and galleries up to 500 by the year of 2011. Under these circumstances, the actual situation shows that the central and local governments are adopting beneficial measures to support the private galleries such as permission of construction on green belt areas and tax deduction. That is, our society has come to realize that the necessity and importance of public as well as private galleries to play their roles as cultural and educational institution. Now, the number of galleries is growing. Exhibitions are held everywhere. Therefore, spectators have more chance to visit them than before. With these conditions and the growing number of amateurs, social interest in curator organizing exhibitions is getting popular. Because of the rise of curatorial popularity on the social level, the influence of curators which is exercised within the gallery seems to become gradually enlarged. In reality, it is true that the curatorial influence cannot be ignored more than ever for appear in various fields their new features made from their professional cometence. The function of gallery is more strengthened and its position is more heightened than those in 80s. For these reasons, the curators whose playground is the gallery, they may be regarded as invisible power to the artists. Futhermore, their influence as such seems to be more likely because our world of art does not still have any reliable system of art criticism. Nevertheless, considering the actual situation in which national and public galleries as cultural institution would rather exist on the local sentiments or political dynamics than on autonomy, there must be some restrictions for the galleries and the curators to obtain the power. In this context, the actual moment is looked upon as transitional period to make the curatorship settled down. Before discussing the power relevant to curatorship, we are going to examine first the role and function of curator and then the new curatorial role and function at the age of information. Finally, we will see in sequence the development and problems of curatorship, the power and dilemmas of curator.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.10
• /
• pp.17-30
• /
• 2009

Underground construction such as tunneling can induce damages on the surrounding rock mass, due to the stress concentration of in situ stresses and excessive energy input during construction sequence, such as blasting. The developed damage on the rock mass can have substantial influence on the mechanical and hydraulic behaviors of the rock masses around a tunnel. In this study, investigation on the generation of damage around an opening in a jointed rock model under biaxial compression condition was conducted. The joint dip angles employed are 30, 45, and 60 degrees to the horizontal, and the synthetic rock mass was made using early strength cement and water. From the biaxial compression test, initiation and propagation of tensile cracks at norm to the joint angle were found. The propagated tensile cracks eventually developed rock blocks, which were dislodged from the rock mass. Furthermore, the propagation process of the tensile cracks varies with joint angle: lower joint angle model shows more stable and progressive tensile crack propagation. The development of the tensile crack can be explained under the hypothesis that the rock segment encompassed by the joint set is subjected to the developing moment, which can be induced by the geometric irregularity around the opening in the rock model. The experiment results were simulated by using discrete element method PFC 2D. From the simulation, as has been observed from the test, a rock mass with lower joint angle produces wider damage region and rock block by tensile cracks. In addition, a rock model with lower joint angle shows progressive tensile cracks generation around the opening from the investigation of the interacted tensile cracks.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.143-152
• /
• 2019

This paper presents two new techniques for solving the two problems of the water curtain: 'shape distortion' caused by gravity and 'resolution degradation' caused by fine satellite droplets around the shape. In the first method, when the user converts a three-dimensional model to a vertical sequence of slices, the slices are evenly spaced. The method is to adjust the time points at which the equi-distance slices are created by the nozzle array. In this method, even if the velocity of a water drop increases with time by gravity, the water drop slices maintain the equal interval at the moment of forming the whole shape, thereby preventing distortion. The second method is called the minimum time interval technique. The minimum time interval is the time between the open command of a nozzle and the next open command of the nozzle, so that consecutive water drops are clearly created without satellite drops. When the user converts a three-dimensional model to a sequence of slices, the slices are defined as close as possible, not evenly spaced, considering the minimum time interval of consecutive drops. The slices are arranged in short intervals in the top area of the shape, and the slices are arranged in long intervals in the bottom area of the shape. The minimum time interval is pre-determined by an experiment, and consists of the time from the open command of the nozzle to the time at which the nozzle is fully open, and the time in which the fully open state is maintained, and the time from the close command to the time at which the nozzle is fully closed. The second method produces water drop sculptures with higher resolution than does the first method.

• Journal of the Korea Computer Graphics Society
• /
• v.3 no.1
• /
• pp.57-67
• /
• 1997

The navigation of virtual space comes down to the manipulation of the virtual camera. The movement of the virtual cameras has 6 degrees of freedom. However, input devices such as mouses and joysticks are 2D. So, the movement of the camera that corresponds to the input device is 2D movement at the given moment. Therefore, the 3D movement of the camera can be implemented by means of the combination of 2D and 1D movements of the camera. Many of the virtual space navigation browser use several navigation modes to solve this problem. But, the criteria for distinguishing different modes are not clear, somed of the manipulations in each mode are repeated in other modes, and the kinesthetic correspondence of the input devices is often confusing. Hence the user has difficulty in making correct decisions when navigating the virtual space. To solve this problem, we use a single navigation metaphore in which different modes are organically integrated. In this paper we propose a helicopter pilot metaphor. Using the helicopter pilot metaphore means that the user navigates the virtual space like a pilot of a helicopter flying in space. In this paper, we distinguished six 2D movement spaces of the helicopter: (1) the movement on the horizontal plane, (2) the movement on the vertical plane,k (3) the pitch and yaw rotations about the current position, (4) the roll and pitch rotations about the current position, (5) the horizontal and vertical turning, and (6) the rotation about the target object. The six 3D movement spaces are visualized and displayed as a sequence of auxiliary windows. The user can select the desired movement space simply by jumping from one window to another. The user can select the desired movement by looking at the displaced 2D movement spaces. The movement of the camera in each movement space is controlled by the usual movements of the joystick.