• The Journal of the Acoustical Society of Korea
• /
• v.42 no.2
• /
• pp.102-111
• /
• 2023

Automatic Music Transcription (AMT) is a task that detects and recognizes musical note events from a given audio recording. In this paper, we focus on reducing the latency of real-time AMT systems on piano music. Although neural AMT models have been adapted for real-time piano transcription, they suffer from high latency, which hinders their usefulness in interactive scenarios. To tackle this issue, we explore several techniques for reducing the intrinsic latency of a neural network for piano transcription, including reducing window and hop sizes of Fast Fourier Transformation (FFT), modifying convolutional layer's kernel size, and shifting the label in the time-axis to train the model to predict onset earlier. Our experiments demonstrate that combining these approaches can lower latency while maintaining high transcription accuracy. Specifically, our modified model achieved note F1 scores of 92.67 % and 90.51 % with latencies of 96 ms and 64 ms, respectively, compared to the baseline model's note F1 score of 93.43 % with a latency of 160 ms. This methodology has potential for training AMT models for various interactive scenarios, including providing real-time feedback for piano education.

• Journal of Biomedical Engineering Research
• /
• v.36 no.4
• /
• pp.95-102
• /
• 2015

Epilepsy is a chronic neurological disease which produces repeated seizures. Over 30% of epileptic patients cannot be treated with anti-epileptic drugs, and surgical resection may cause loss of brain functions. Seizure suppression by electrical stimulation is currently being investigated as a new treatment method as clinical evidence has shown that electrical stimulation to brain could suppress seizure activity. In this paper, design of a real-time closed-loop neurostimulation system for epileptic seizure suppression is presented. The system records neural signals, detects seizures and delivers electrical stimulation. The system consists of a 6-channel electrode, front-end amplifiers, a data acquisition board by National Instruments, and a neurostimulator and Generic Osorio-Frei algorithm was applied for seizure detection. The algorithm was verified through simulation using electroencephalogram data, and the operation of whole system was verified through simulation and in- vivo test.

• The Korean Journal of Physiology and Pharmacology
• /
• v.11 no.6
• /
• pp.247-251
• /
• 2007

Changes of single unit activity of CA1 hippocampus region were investigated in anesthetized Mongolian gerbils for six days following transient ischemia. Ischemia was produced immediately before the implantation of micro-wire recording electrodes. In control animals receiving pseudo-ischemic surgery, neither spontaneous neuronal activities ($5.70{\pm}0.4Hz$) nor the number of recorded neurons per animal changed significantly for six days. Correlative firings among simultaneously recorded neurons were weak (correlation coefficient > 0.6) in the control animals. Animals subjected to ischemia exhibited a significant elevation of neural firing at post-ischemic 12 hr ($9.95{\pm}0.9Hz$) and day 1 ($8.48{\pm}0.8Hz$), but a significant depression of activity at post-ischemic day 6 ($1.84{\pm}0.3Hz$) when compared to the activities of non-ischemic control animal. Ischemia significantly (correlation coefficient > 0.6) increased correlative firings among simultaneously recorded neurons, which were prominent especially during post-ischemic days 1, 2 and 6. Although the numbers of spontaneously active neurons recorded from control group varied within normal range during the experimental period, those from ischemic group changed in post-ischemic time-dependent manner. Temporal changes of the number of cells recorded per animal between control group and ischemic group were also significantly different (p = 0.0084, t = 3.271, df = 10). Cresyl violet staining indicated significant loss of CA1 cells at post-ischemic day 7. Overall, we showed post-ischemic time-dependent, differential changes of three characteristics, including spontaneous activity, network relationship and excitability of CA1 cells, suggesting sustained neural functions. Thus, histological observation of CA1 cell death till post-ischemic day 7 may not represent actual neuronal death.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.12
• /
• pp.85-94
• /
• 2018

The purpose of this paper was to propose a model that recognizes potential users' emotional response toward design by classifying Electroencephalography(EEG). Studies in neuroscience and psychology have made an effort to recognize subjects' emotional response by analyzing EEG data. And this approach has been adopted in design since it is critical to monitor users' subjective response in the preface of design. Moreover, the building design process cannot be reversed after construction, recognizing clients' affection toward design alternatives plays important role. An experiment was conducted to record subjects' EEG data while they view their most/least liked images of small-house designs selected by them among the eight given images. After the recording, a subjective questionnaire, PANAS, was distributed to the subjects in order to describe their own affection score in quantitative way. Google TensorFlow was used to build and train the model. Dataset for model training and testing consist of feature columns for recorded EEG data and labels for the questionnaire results. After training and testing, the measured accuracy of the model was 0.975 which was higher than the other machine learning based classification methods. The proposed model may suggest one quantitative way of evaluating design alternatives. In addition, this method may support designer while designing the facilities for people like disabled or children who are not able to express their own feelings toward alternatives.

• Journal of Sasang Constitutional Medicine
• /
• v.33 no.4
• /
• pp.1-9
• /
• 2021

Objectives The purpose of this study was to check whether the classification of the individual's Body Mass Index (BMI) could be predicted by analyzing the voice data constructed at the Korean medicine data center (KDC) using machine learning. Methods In this study, we proposed a convolutional neural network (CNN)-based BMI classification model. The subjects of this study were Korean adults who had completed voice recording and BMI measurement in 2006-2015 among the data established at the Korean Medicine Data Center. Among them, 2,825 data were used for training to build the model, and 566 data were used to assess the performance of the model. As an input feature of CNN, Mel-frequency cepstral coefficient (MFCC) extracted from vowel utterances was used. A model was constructed to predict a total of four groups according to gender and BMI criteria: overweight male, normal male, overweight female, and normal female. Results & Conclusions Performance evaluation was conducted using F1-score and Accuracy. As a result of the prediction for four groups, The average accuracy was 0.6016, and the average F1-score was 0.5922. Although it showed good performance in gender discrimination, it is judged that performance improvement through follow-up studies is necessary for distinguishing BMI within gender. As research on deep learning is active, performance improvement is expected through future research.

• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.147-156
• /
• 2023

Efforts to employ smart home sensors to monitor the indoor activities of elderly single residents have been made to assess the feasibility of a safe and healthy lifestyle. However, the bathroom remains an area of blind spot. In this study, we have developed and evaluated a new edge computer device that can automatically detect water usage activities in the bathroom and record the activity log on a cloud server. Three kinds of sound as flushing, showering, and washing using wash basin generated during water usage were recorded and cut into 1-second scenes. These sound clips were then converted into a 2-dimensional image using MEL-spectrogram. Sound data augmentation techniques were adopted to obtain better learning effect from smaller number of data sets. These techniques, some of which are applied in time domain and others in frequency domain, increased the number of training data set by 30 times. A deep learning model, called CRNN, combining Convolutional Neural Network and Recurrent Neural Network was employed. The edge device was implemented using Raspberry Pi 4 and was equipped with a condenser microphone and amplifier to run the pre-trained model in real-time. The detected activities were recorded as text-based activity logs on a Firebase server. Performance was evaluated in two bathrooms for the three water usage activities, resulting in an accuracy of 96.1% and 88.2%, and F1 Score of 96.1% and 87.8%, respectively. Most of the classification errors were observed in the water sound from washing. In conclusion, this system demonstrates the potential for use in recording the activities as a lifelog of elderly single residents to a cloud server over the long-term.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.9-13
• /
• 2023

In this study, we explored the potential of integrating interactive AI callbot technology into the medical consultation domain as part of a broader service development initiative. Aimed at enhancing patient satisfaction, the AI callbot was designed to efficiently address queries from hospitals' primary users, especially the elderly and those using phone services. By incorporating an AI-driven callbot into the hospital's customer service center, routine tasks such as appointment modifications and cancellations were efficiently managed by the AI Callbot Agent. On the other hand, tasks requiring more detailed attention or specialization were addressed by Human Agents, ensuring a balanced and collaborative approach. The deep learning model for voice recognition for this study was based on the Transformer model and fine-tuned to fit the medical field using a pre-trained model. Existing recording files were converted into learning data to perform SSL(self-supervised learning) Model was implemented. The ANN (Artificial neural network) neural network model was used to analyze voice signals and interpret them as text, and after actual application, the intent was enriched through reinforcement learning to continuously improve accuracy. In the case of TTS(Text To Speech), the Transformer model was applied to Text Analysis, Acoustic model, and Vocoder, and Google's Natural Language API was applied to recognize intent. As the research progresses, there are challenges to solve, such as interconnection issues between various EMR providers, problems with doctor's time slots, problems with two or more hospital appointments, and problems with patient use. However, there are specialized problems that are easy to make reservations. Implementation of the callbot service in hospitals appears to be applicable immediately.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.1
• /
• pp.38-46
• /
• 2024

In general, EEG signal analysis has been the subject of several studies due to its ability to provide an objective mode of recording brain stimulation, which is widely used in brain-computer interface research with applications in medical diagnosis and rehabilitation engineering. In this study, we developed EEG reception hardware to measure electroencephalograms and implemented a processing system, classifying it into server and data processing. It was conducted as an intermediate-stage research on the implementation of a brain-computer interface using electroencephalograms, and was implemented in the form of predicting the user's arm movements according to measured electroencephalogram data. Electroencephalogram measurements were performed using input from four electrodes through an analog-to-digital converter. After sending this to the server through a communication process, we designed and implemented a system flow in which the server classifies the electroencephalogram input using a convolutional neural network model and displays the results on the user terminal.

• Journal of Ginseng Research
• /
• v.24 no.3
• /
• pp.134-137
• /
• 2000

Spontaneous bursting activity was studied in rat thalamocortical slices using extracellular field potential recording to test the potential utilization of ginsenoside Rb$_1$ in controlling overactivated neural systems. In order to induce bursting activity, slices were perfused with Mg$\^$2+/-free artificial cerebrospinal fluid (ACSF). Two major types of spontaneous bursting activity, simple thalamocortical burst complexes (sTBCs) and complex thalamocortical burst complexes (cTBCs), were recorded in Mg$\^$2+/ -free ACSF. Ginsenoside Rb$_1$ selectively suppressed cTBCs. Duration and occurrence rate of cTBCs were reduced by 87.3${\pm}$10.2% and 85.3${\pm}$ 14.7% in the presence of 90 ${\mu}$M ginsenoside Rb$_1$ respectively, while amplitude and intraburst frequency were slightly changed by ginsenoside Rb$_1$. In contrast, ginsenoside Rb$_1$was much less effective in reducing duration and occurrence rate of sTBCs. We also tested effects of ginsenoside Rb$_1$ on bursting activity in the presence of a GABA$\sub$A/ receptor antagonist, bicuculline methiodide (BMI). Ginsenoside Rb$_1$ had no effect in suppressing BMI-induced bursting activities. These results suggest that ginsenoside Rbi may be useful in controlling seizure-like bursting activity under pathological conditions.

• Journal of Advanced Marine Engineering and Technology
• /
• v.36 no.5
• /
• pp.645-661
• /
• 2012

Recently, pirates are infesting on the sea and they have been hijacking the several vessels for example Samho Dream and Samho Jewelry of Korea. One of the items to reduce the risk is to adopt the invader detection system. If the pirates break in to the ship, the detection system can monitor the pirates and then call the security alarm. The crew can gain time to hide to the safe room and the report can be automatically sent to the control room to cope with the situation. For the invader detection, an unmanned observation system was proposed using the image detection algorithm that extracts the invader image from the recording image. To detect the motion area, the difference value was calculated between the current image and the prior image of the invader, and the 'AND' operator was used in calculated image and edge line. The image noise was reduced based on the morphology operation and then the image was transformed into morphological information. Finally, a neural network model was applied to recognize the invader. In the experimental results, it was confirmed that the proposed approach can improve the performance of the recognition in the invader monitoring system.