• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.4
• /
• pp.307-326
• /
• 2021

Real-time sea level observations from tide gauges include missing and erroneous values. Classification as abnormal values can be done for the latter by the quality control procedure. Although the 3𝜎 (three standard deviations) rule has been applied in general to eliminate them, it is difficult to apply it to the sea-level data where extreme values can exist due to weather events, etc., or where erroneous values can exist even within the 3𝜎 range. An artificial intelligence model set designed in this study consists of non-annotated recurrent neural networks and ensemble techniques that do not require pre-labeling of the abnormal values. The developed model can identify an erroneous value less than 20 minutes of tide gauge recording an abnormal sea level. The validated model well separates normal and abnormal values during normal times and weather events. It was also confirmed that abnormal values can be detected even in the period of years when the sea level data have not been used for training. The artificial neural network algorithm utilized in this study is not limited to the coastal sea level, and hence it can be extended to the detection model of erroneous values in various oceanic and atmospheric data.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.278-284
• /
• 2003

Speech act is the speaker's intentions indicated through utterances. It is important for understanding natural language dialogues and generating responses. This paper proposes the method of two stage that increases the performance of the korean speech act decision. The first stage is to select features from the part of speech results in sentence and from the context that uses previous speech acts. We use x$^2$ statistics(CHI) for selecting features that have showed high performance in text categorization. The second stage is to determine speech act with selected features and Neural Network. The proposed method shows the possibility of automatic speech act decision using only POS results, makes good performance by using the higher informative features and speed up by decreasing the number of features. We tested the system using our proposed method in Korean dialogue corpus transcribed from recording in real fields, and this corpus consists of 10,285 utterances and 17 speech acts. We trained it with 8,349 utterances and have test it with 1,936 utterances, obtained the correct speech act for 1,709 utterances(88.3%). This result is about 8% higher accuracy than without selecting features.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.1-14
• /
• 2023

Soybeans are one of the world's top five staple crops and a major source of plant-based protein. Due to their susceptibility to climate change, which can significantly impact grain production, the National Agricultural Science Institute is conducting research on crop phenotypes through growth analysis of various soybean varieties. While the process of capturing growth progression photos of soybeans is automated, the verification, recording, and analysis of growth stages are currently done manually. In this paper, we designed and trained a YOLOv5s model to detect soybean leaf objects from image data of soybean plants and a Convolution Neural Network (CNN) model to judgement the unfolding status of the detected soybean leaves. We combined these two models and implemented an algorithm that distinguishes layers based on the coordinates of detected soybean leaves. As a result, we developed a program that takes time-series data of soybeans as input and performs growth analysis. The program can accurately determine the growth stages of soybeans up to the second or third compound leaves.

• The Korean Journal of Physiology and Pharmacology
• /
• v.7 no.6
• /
• pp.317-323
• /
• 2003

Interneuron diversity is one of the key factors to hinder understanding the mechanism of cortical neural network functions even with their important roles. We characterized inhibitory interneurons in layer II/III of the rat primary visual cortex, using patch-clamp recording and confocal reconstruction, and classified inhibitory interneurons into fast spiking (FS), late spiking (LS), burst spiking (BS), and regular spiking non-pyramidal (RSNP) neurons according to their electrophysiological characteristics. Global parameters to identify inhibitory interneurons were resting membrane potential (＞-70 mV) and action potential (AP) width (＜0.9 msec at half amplitude). FS could be differentiated from LS, based on smaller amplitude of the AP (＜∼50 mV) and shorter peak-to-trough time (P-T time) of the afterhyperpolarization (＜4 msec). In addition to the shorter AP width, RSNP had the higher input resistance (＞200 $M{Omega}$) and the shorter P-T time (＜20 msec) than those of regular spiking pyramidal neurons. Confocal reconstruction of recorded cells revealed characteristic morphology of each subtype of inhibitory interneurons. Thus, our results provide at least four subtypes of inhibitory interneurons in layer II/III of the rat primary visual cortex and a classification scheme of inhibitory interneurons.

• Journal of Hydrogen and New Energy
• /
• v.29 no.5
• /
• pp.523-529
• /
• 2018

Two liquids which are generally used as fuels of rockets are mixed and their mixing process is quantitatively investigated by the use of particle image velocimetry (PIV). As working fluids for the liquid mixing, Dimethylfuran (DMF) and JetA1 oils have been used. Since the specific gravity of DMF is larger than that of JetA1 oil, the DMF oil has been set at the lower part of the JetA1 oil. For better visualization of the mixing process, Rhodamin B powder has been blended into the DMF oil. An agitator having 3 blades has been used for mixing the two liquids. For quantitative visualization, a LCD monitor has been used as a light source. A color camera, camcoder, has been used for recording the mixing process. The images captured by the camcoder have been digitized into three color components, R, G, and B. The color intensities of R, G, and B have been used as the inputs of the neural network of which hidden layer has 20 neurons. Color-to-concentration calibration has been performed before commencing the main experiments. Once this calibration is completed, the temporal changes of the concentration of the DMF has been quantitatively analyzed by using the constructed measurement system.

• Research in Vestibular Science
• /
• v.17 no.4
• /
• pp.142-151
• /
• 2018

Objectives: Excitability o medial vestibular nucleus (MVN) in the brainstem can be affected by changes in the arterial blood pressure. Several animal studies have demonstrated that acute hypotension results in the alteration of multiunit activities and expression of cFos protein in the MVN. In the field of extracellular electrophysiological recording, tetrode technology and spike sorting algorithms can easily identify single unit activity from multiunit activities in the brain. However, detailed properties of electrophysiological changes in single unit of the MVN during acute hypotension have been unknown. Methods: Therefore, we applied tetrode techniques and electrophysiological characterization methods to know the effect of acute hypotension on single unit activities of the MVN of rats. Results: Two or 3 types of unit could be classified according to the morphology of spikes and firing properties of neurons. Acute hypotension elicited 4 types of changes in spontaneous firing of single unit in the MVN. Most of these neurons showed excitatory responses for about within 1 minute after the induction of acute hypotension and then returned to the baseline activity 10 minutes after the injection of sodium nitroprusside. There was also gradual increase in spontaneous firing in some units. In contrast small proportion of units showed rapid reduction of firing rate just after acute hypotension. Conclusions: Therefore, application of tetrode technology and spike sorting algorithms is another method for the monitoring of electrical activity of vestibular nuclear during acute hypotension.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.775-793
• /
• 2023

Human decision-making is a complex behavior. A replication of human decision making offers a potential to enhance the capacity of intelligent systems by providing additional user assistance in decision making. By reducing the effort and task complexity on behalf of the user, such replication would improve the overall user experience, and affect the degree of intelligence exhibited by the system. This paper explores individuals' decision-making processes when using recommender systems, and its related outcomes. In this study, human decision-making (HDM) refers to the selection of an item from a given set of options that are shown as recommendations to a user. The goal of our study was to identify IS constructs that contribute towards such decision-making, thereby contributing towards creating a mental model of HDM. This was achieved through recording Electroencephalographic (EEG) readings of subjects while they performed a decision-making activity. Readings from 16 righthanded healthy avid readers reflect that reward, theory of mind, risk, calculation, task intention, emotion, sense of touch, ambiguity and decision making are the primary constructs that users employ while deciding from a given set of recommendations in an online bookstore. In all 10 distinct brain areas were identified. These brain areas that lead to their respective constructs were found to be cingulate gyrus, precentral gyrus, inferior parietal lobule, posterior cingulate, medial frontal gyrus, anterior cingulate, postcentral gyrus, superior frontal gyrus, inferior frontal gyrus, and middle frontal gyrus (also referred to as dorsolateral prefrontal gyrus (DLPFC)). The identified constructs would help in developing a design theory for enhancing user assistance, especially in the context of recommender systems.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.176-187
• /
• 2024

Recently, automated solutions using collaborative robots have been emerging in various industries. Their primary functions include Pick & Place, Peg in the Hole, fastening and assembly, welding, and more, which are being utilized and researched in various fields. The application of these robots varies depending on the characteristics of the grippers attached to the end of the collaborative robots. To grasp a variety of objects, a gripper with a high degree of freedom is required. In this paper, we propose a service automation system using a multi-degree-of-freedom gripper, collaborative robots, and vision sensors. Assuming various products are placed at a checkout counter, we use three cameras to recognize the objects, estimate their pose, and create grasping points for grasping. The grasping points are grasped by the multi-degree-of-freedom gripper, and experiments are conducted to recognize barcodes, a key task in service automation. To recognize objects, we used a CNN (Convolutional Neural Network) based algorithm and point cloud to estimate the object's 6D pose. Using the recognized object's 6d pose information, we create grasping points for the multi-degree-of-freedom gripper and perform re-grasping in a direction that facilitates barcode scanning. The experiment was conducted with four selected objects, progressing through identification, 6D pose estimation, and grasping, recording the success and failure of barcode recognition to prove the effectiveness of the proposed system.

• Korean Journal of Biological Psychiatry
• /
• v.8 no.2
• /
• pp.251-257
• /
• 2001

Backgrounds : Gamma band oscillatory activity is considered to be related to cognitive functions and illustrates that the concept of event-related oscillations bridges the gap between single neurons and neural assemblies. An event-related gamma oscillation is the time-locked responses of specific frequency, and can be identified by computing the amplitude frequency characteristics of the averaged event-related potentials(ERPs) after stimulation. Objectives : We purposed to present experimental paradigm to investigate ${\gamma}$-band oscillation activities from the recording of ERPs by using auditory oddball paradigm and investigate the difference of ${\gamma}$-band activity between schizophrenia and normal controls. Methods : The ERPs resulting from auditory stimuli with oddball paradigm in a group of schizophrenics(n=11), and also a group of age-, sex-, and handedness matched normal controls, were recorded by 128 channel EEG. The ${\gamma}$-band oscillatory activities were calculated by using time-frequency wavelet decomposition of the signal between 20 and 80Hz. The ${\gamma}$-band oscillatory activities of both groups were compared by t-test. Results : The ${\gamma}$-band oscillatory of the leads Fz, Cz, and Pz of both groups were represented well in the time-frequency maps. Significant increases of the ${\gamma}$-band activity in normal controls compared with schizophrenics were observed around 160 msec, 350 msec, and 800 msec after stimulation. Conclusions : Our results suggested that the increment in ${\gamma}$-band oscillatory activity during cognitive operations and decreased ${\gamma}$-band activity in schizophrenics may be associated with the cognitive dysfunctions and the pathophysiology of the schizophrenia.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.675-681
• /
• 2021

With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.