• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.63-72
• /
• 2018

The human voice is one of the easiest methods for the information transmission between human beings. The characteristics of voice can vary from person to person and include the speed of speech, the form and function of the vocal organ, the pitch tone, speech habits, and gender. The human voice is a key element of human communication. In the days of the Fourth Industrial Revolution, voices are also a major means of communication between humans and humans, between humans and machines, machines and machines. And for that reason, people are trying to communicate their intentions to others clearly. And in the process, it contains various additional information along with the linguistic information. The Information such as emotional status, health status, part of trust, presence of a lie, change due to drinking, etc. These linguistic and non-linguistic information can be used as a device for evaluating the individual's credit worthiness by appearing in various parameters through voice analysis. Especially, it can be obtained by analyzing the relationship between the characteristics of the fundamental frequency(basic tonality) of the vocal cords, and the characteristics of the resonance frequency of the vocal track.In the previous research, the necessity of various methods of credit evaluation and the characteristic change of the voice according to the change of credit status were studied. In this study, we propose a personal credit discriminator by machine learning through parameters extracted through voice.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.99-109
• /
• 2021

In recent machine learning studies, in order to consider the quality and completeness of data, derivation of non-functional requirements for data has been proposed from the viewpoint of requirements engineering. In particular, requirements engineers have defined data requirements in machine learning. In this study, data requirements were derived at the data acquisition (DAQ) stage, where data is collected and stored before data preprocessing. Through this, it is possible to express the requirements of all data required in the existing DAQ system, the presence of tasks (functions) satisfying them, and the relationship between the requirements and functions. In addition, it is possible to elicit requirements and to define the relationship, so that a software design document can be produced, and a systematic approach and direction can be established in terms of software design and maintenance. This research using existing DAQ system cases, scenarios and use cases for requirements engineering approach are created, and data requirements for each case are extracted based on them, and the relationship between requirements, functions, and goals is illustrated through goal modeling. Through the research results, it was possible to extract the non-functional requirements of the system, especially the data requirements, from the DAQ system using requirements engineering.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.1-6
• /
• 2022

Deep learning is a collection of algorithms that enable learning by summarizing the key contents of large amounts of data; it is being developed to diagnose lesions in the medical imaging field. To evaluate the accuracy of the cerebral hemorrhage diagnosis, we used a convolutional neural network (CNN) to derive the diagnostic accuracy of cerebral parenchyma computed tomography (CT) images and the cerebral parenchyma CT images of areas where cerebral hemorrhages are suspected of having occurred. We compared the accuracy of CNN with different numbers of hidden layers and discovered that CNN with more hidden layers resulted in higher accuracy. The analysis results of the derived CT images used in this study to determine the presence of cerebral hemorrhages are expected to be used as foundation data in studies related to the application of artificial intelligence in the medical imaging industry.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.2
• /
• pp.85-92
• /
• 2023

Respiratory infections such as COVID-19 mainly occur within enclosed spaces. The presence or absence of abnormal symptoms of respiratory infectious diseases is judged through initial symptoms such as fever, cough, sneezing and difficulty breathing, and constant monitoring of these early symptoms is required. In this paper, image matching correction was performed for the RGB camera module and the thermal imaging camera module, and the temperature of the thermal imaging camera module for the measurement environment was calibrated using a blackbody. To detection the target recommended by the standard, a deep learning-based object recognition algorithm and the inner canthus recognition model were developed, and the model accuracy was derived by applying a dataset of 100 experimenters. Also, the error according to the measured distance was corrected through the object distance measurement using the Lidar module and the linear regression correction module. To measure the performance of the proposed model, an experimental environment consisting of a motor stage, an infrared thermography temperature screening system and a blackbody was established, and the error accuracy within 0.28℃ was shown as a result of temperature measurement according to a variable distance between 1m and 3.5 m.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1721-1730
• /
• 2023

As awareness of the problem of global warming emerges around the world, the role of carbon sinks in settlement is increasingly emphasized to achieve carbon neutrality in urban areas. In order to manage carbon sinks in settlement, it is necessary to identify the current status of carbon sinks. Identifying the status of carbon sinks requires a lot of manpower and time and a corresponding budget. Therefore, in this study, a map predicting the location of trees was created using already established tree location information and Sentinel-2 satellite images targeting Seoul. To this end, after constructing a tree presence/absence dataset, structured data was generated using 16 types of vegetation indices information constructed from satellite images. After learning this by applying the Extreme Gradient Boosting (XGBoost) model, a tree prediction map was created. Afterward, the correlation between independent and dependent variables was investigated in model learning using the Shapely value of Shapley Additive exPlanations(SHAP). A comparative analysis was performed between maps produced for local parts of Seoul and sub-categorized land cover maps. In the case of the tree prediction model produced in this study, it was confirmed that even hard-to-detect street trees around the main street were predicted as trees.

• Korean Journal of Radiology
• /
• v.25 no.4
• /
• pp.374-383
• /
• 2024

Objective: To evaluate the diagnostic performance and image quality of 1.5-mm slice thickness MRI with deep learningbased image reconstruction (1.5-mm MRI + DLR) compared to routine 3-mm slice thickness MRI (routine MRI) and 1.5-mm slice thickness MRI without DLR (1.5-mm MRI without DLR) for evaluating temporal lobe epilepsy (TLE). Materials and Methods: This retrospective study included 117 MR image sets comprising 1.5-mm MRI + DLR, 1.5-mm MRI without DLR, and routine MRI from 117 consecutive patients (mean age, 41 years; 61 female; 34 patients with TLE and 83 without TLE). Two neuroradiologists evaluated the presence of hippocampal or temporal lobe lesions, volume loss, signal abnormalities, loss of internal structure of the hippocampus, and lesion conspicuity in the temporal lobe. Reference standards for TLE were independently constructed by neurologists using clinical and radiological findings. Subjective image quality, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were analyzed. Performance in diagnosing TLE, lesion findings, and image quality were compared among the three protocols. Results: The pooled sensitivity of 1.5-mm MRI + DLR (91.2%) for diagnosing TLE was higher than that of routine MRI (72.1%, P < 0.001). In the subgroup analysis, 1.5-mm MRI + DLR showed higher sensitivity for hippocampal lesions than routine MRI (92.7% vs. 75.0%, P = 0.001), with improved depiction of hippocampal T2 high signal intensity change (P = 0.016) and loss of internal structure (P < 0.001). However, the pooled specificity of 1.5-mm MRI + DLR (76.5%) was lower than that of routine MRI (89.2%, P = 0.004). Compared with 1.5-mm MRI without DLR, 1.5-mm MRI + DLR resulted in significantly improved pooled accuracy (91.2% vs. 73.1%, P = 0.010), image quality, SNR, and CNR (all, P < 0.001). Conclusion: The use of 1.5-mm MRI + DLR enhanced the performance of MRI in diagnosing TLE, particularly in hippocampal evaluation, because of improved depiction of hippocampal abnormalities and enhanced image quality.

• Journal of the Korean Society of Radiology
• /
• v.84 no.6
• /
• pp.1309-1323
• /
• 2023

Purpose To assess the quality of four images obtained using single-breath-hold (SBH), single-shot fast spin-echo (SSFSE) and multiple-breath-hold (MBH) SSFSE with and without deep-learning based reconstruction (DLR) in patients with Crohn's disease. Materials and Methods This study included 61 patients who underwent MR enterography (MRE) for Crohn's disease. The following images were compared: SBH-SSFSE with (SBH-DLR) and without (SBH-conventional reconstruction [CR]) DLR and MBH-SSFSE with (MBH-DLR) and without (MBH-CR) DLR. Two radiologists independently reviewed the overall image quality, artifacts, sharpness, and motion-related signal loss using a 5-point scale. Three inflammatory parameters were evaluated in the ileum, the terminal ileum, and the colon. Moreover, the presence of a spatial misalignment was evaluated. Signal-to-noise ratio (SNR) was calculated at two locations for each sequence. Results DLR significantly improved the image quality, artifacts, and sharpness of the SBH images. No significant differences in scores between MBH-CR and SBH-DLR were detected. SBH-DLR had the highest SNR (p < 0.001). The inter-reader agreement for inflammatory parameters was good to excellent (κ = 0.76-0.95) and the inter-sequence agreement was nearly perfect (κ = 0.92-0.94). Misalignment artifacts were observed more frequently in the MBH images than in the SBH images (p < 0.001). Conclusion SBH-DLR demonstrated equivalent quality and performance compared to MBH-CR. Furthermore, it can be acquired in less than half the time, without multiple BHs and reduce slice misalignments.

• Annals of Clinical Neurophysiology
• /
• v.1 no.1
• /
• pp.1-9
• /
• 1999

Since Hans Berger reported the first paper on the human electroencephalogram in 1920s, huge technological advance have made it possible to use a number of electrophysiological approaches to neurological diagnosis in clinical neurology. In majority of the neurology training hospitals they have facilities of electroencephalography(EEG), electromyography(EMG), evoked potentials(EP), polysomnography(PSG), electronystagmography(ENG) and, transcranial doppler(TCD) ete. Clinicials and electrophysiologists should understand the technologic characteristics and general applications of each electrophysiological studies to get useful informations with using them in clinics. It is generally agreed that items of these tests are selected under the clinical examination, the tests are performed by the experts, and the test results are interpretated under the clinical background. Otherwise these tests are sometimes useless and lead clinicians to misunderstand the lesion site, the nature of disease, or the disease course. In this sense the clinical utility of neurophysiological tests could be summerized in the followings. First, the abnormal functioning of the nervous system and its environments can be demonstrated when the history and neurological examinations are equivocal. Second, the presence of clinically unsuspected malfunction in the nervous system can be revealed by those tests. Finally the objective changes can be monitored over time in the patient's status. Also intraoperative monitoring technique becomes one of the important procedures when the major operations in the posterior fossa or in the spinal cord are performed. In 1996, the Korean Society for Clinical Neurophysiology(KSCN) was founded with the hope that it will provide the members with the comfortable place for discussing their clinical and academic experience, exchanging new informations, and learning new techniques of the neurophysiological tests. The KSCN could collaborate with the International Federation of Clinical Neurophysiology(IFCN) to improve the level of the clinical neurophysiologic field in Korea as will as in Asian region.1 In this paper the clinical neurophysiological tests which are commonly used in clinical neurology and which will be delt with and educated by the KSCN in the future will be discussed briefly in order of EEG, EMG, EP, PSG, TCD, ENG, and Intraoperative monitoring.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.10-18
• /
• 2014

As the standard of living and leisure time of contemporary people is increasing, people who have interest not only in physical health activities but also in mental health activities are increasing. Also, people who have interest in sports activities, which include entertaining factors are gradually increasing. SporTainment is a compound of the words 'Sports' and 'Entertainment' and it possesses the meaning of doing sports and entertainment simultaneously. In addition, in the immersive media technology field, researches, which increase the feeling of existence and immersion through the stimulation of the consumer's emotional feedback technology, have been actively conducted. Such, emotional feedback technologies are based on fun and excitement and are activities, in which learning effects are included such as games, education, national defense etc. In addition, the emotional feedback technology is expanding in applied services, which maximize the feeling of existence and immersion of the consumers by adding reality effects in the virtual environment. In this research, the presence of the user was increased by developing a realistic bike simulation for the use of SporTainment, which combine emotional effects and reappearance devices in the bike simulation.