• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.985-987
• /
• 2010

In this paper, we propose a maximum entropy-based emotion recognition model using individual average difference. In order to accurately recognize an user' s emotion, the proposed model utilizes the difference between the average of the given input physiological signals and the average of each emotion state' signals rather than only the input signal. For the purpose of alleviating data sparse -ness, the proposed model substitutes two simple symbols such as +(positive number)/-(negative number) for every average difference value, and calculates the average of physiological signals based on a second rather than the longer total emotion response time. With the aim of easily constructing the model, it utilizes a simple average difference calculation technique and a maximum entropy model, one of well-known machine learning techniques.

• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.252-260
• /
• 2023

A bullet launcher can be developed as a smart instrument, especially for use in the military section, that can track, identify, detect, mark, lock, and shoot a target by implementing an image-processing system. In this research, the application of object recognition system, laser encoding as a unique marker, 2-dimensional movement, and pneumatic as a shooter has been studied intensively. The results showed that object recognition system could detect various colors, patterns, sizes, and laser blinking. Measuring the average error value of the object distance by using the camera is ±4, ±5, and ±6% for circle, square and triangle form respectively. Meanwhile, the average accuracy of shots on objects is 95.24% and 85.71% in indoor and outdoor conditions respectively. Here, the average prototype response time is 1.11 s. Moreover, the highest accuracy rate of shooting results at 50 cm was obtained 98.32%.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.1
• /
• pp.102-108
• /
• 2016

Objectives : The deficit of recognition memory has been found as one of the common neurocognitive impairments in patients with schizophrenia. In addition, they were reported to fail to enhance the memory about emotional stimuli. Previous studies have shown that bilateral eye movements enhance the memory retrieval. Therefore, this study was conducted in order to investigate the memory enhancement of bilaterally alternating eye movements in schizophrenic patients. Methods : Twenty one patients with schizophrenia participated in this study. The participants learned faces (angry or neutral faces), and then performed a recognition memory task in relation to the faces after bilateral eye movements and central fixation. Recognition accuracy, response bias, and mean response time to hits were compared and analysed. Two-way repeated measure analysis of variance was performed for statistical analysis. Results : There was a significant effect of bilateral eye movements condition in mean response time(F=5.812, p<0.05) and response bias(F=10.366, p<0.01). Statistically significant interaction effects were not observed between eye movement condition and face emotion type. Conclusions : Irrespective of the emotional difference of facial stimuli, recognition memory processing was more enhanced after bilateral eye movements in patients with schizophrenia. Further study will be needed to investigate the underlying neural mechanism of bilateral eye movements-induced memory enhancement in patients with schizophrenia.

• Journal of Korean Neurosurgical Society
• /
• v.61 no.3
• /
• pp.292-301
• /
• 2018

Medulloblastoma is the most common malignant brain tumor of childhood and remains a major cause of cancer related mortality in children. Significant scientific advancements have transformed the understanding of medulloblastoma, leading to the recognition of four distinct clinical and molecular subgroups, namely wingless (WNT), sonic hedgehog, group 3, and group 4. Subgroup classification combined with the recognition of subgroup specific molecular alterations has also led to major changes in risk stratification of medulloblastoma patients and these changes have begun to alter clinical trial design, in which the newly recognized subgroups are being incorporated as individualized treatment arms. Despite these recent advancements, identification of effective targeted therapies remains a challenge for several reasons. First, significant molecular heterogeneity exists within the four subgroups, meaning this classification system alone may not be sufficient to predict response to a particular therapy. Second, the majority of novel agents are currently tested at the time of recurrence, after which significant selective pressures have been exerted by radiation and chemotherapy. Recent studies demonstrate selection of tumor sub-clones that exhibit genetic divergence from the primary tumor, exist within metastatic and recurrent tumor populations. Therefore, tumor resampling at the time of recurrence may become necessary to accurately select patients for personalized therapy.

• Journal of IKEEE
• /
• v.23 no.2
• /
• pp.358-363
• /
• 2019

In this paper, we implemented a welfare system for the elderly living alone, disabled, or babies to provide fast incident response in case of emergency situations. The proposed system can quickly recognize emergency situations using heart rate sensors and real-time image sharing. The sensors attached on a wrist band monitor the heart rate along with relevant bio signals of clients and send alarms to guardians in the emergency situations. At the same time, the real-time image signals are captured using OpenCV and sent to the guardians in order to give the exact information for fast and appropriate response to handle the situation. In the proposed system, the camera works only in the emergency situations so as to provide enough privacy to the client's every day life.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.7
• /
• pp.1557-1564
• /
• 2010

In this paper, we propose a maximum entropy-based emotion recognition model using the individual average difference of emotional signal, because an emotional signal pattern depends on each individual. In order to accurately recognize a user's emotion, the proposed model utilizes the difference between the average of the input emotional signals and the average of each emotional state's signals(such as positive emotional signals and negative emotional signals), rather than only the given input signal. With the aim of easily constructing the emotion recognition model without the professional knowledge of the emotion recognition, it utilizes a maximum entropy model, one of the best-performed and well-known machine learning techniques. Considering that it is difficult to obtain enough training data based on the numerical value of emotional signal for machine learning, the proposed model substitutes two simple symbols such as +(positive number)/-(negative number) for every average difference value, and calculates the average of emotional signals per second rather than the total emotion response time(10 seconds).

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.4
• /
• pp.60-69
• /
• 2015

Labor attendance management has traditionally been carried out by writing a table for checking an attendance of labor, which requires a lot of time and effort. As electronic devices with additions such as barcodes, Quick Response codes, and Radio Frequency Identification(RFID) have been developed, however, automated labor attendance management systems have appeared. Recently, various types of labor recognition devices converged with biometrics (fingerprint, vein, face recognition, etc.) have been released. However, although these devices can be used to check attendance automatically, there is insufficient guidance when it comes to selecting the appropriate labor attendance management system for construction sites. Therefore, this study proposed a decision framework to determine which labor attendance management system would be suitable for a construction site and to select the labor recognition device. This study investigated different labor recognition devices, focusing on how they worked, and tested the performance of devices and their usability for construction labor attendance management. The test results showed that RFID is most suitable when verifying the attendance of many laborers over a short period of time. The devices for hand vein and fingerprint recognition did not function when there was a foreign material such as cement or paint on the laborer's hand, except for a deformed finger. Reflecting these test results, this study suggested a framework for selecting a labor attendance system and recognition device; this is expected to contribute to the development of more efficient labor management systems.

• ETRI Journal
• /
• v.38 no.4
• /
• pp.634-644
• /
• 2016

Channel-based radio-frequency fingerprinting such as a channel impulse response (CIR), channel transfer function (CTF), and frequency coherence function (FCF) have been recently proposed to improve the accuracy at the physical layer; however, their empirical performance, advantages, and limitations have not been well reported. This paper provides a comprehensive empirical performance evaluation of RF location fingerprinting, focusing on a comparison of received-signal strength, CIR-, CTF-, and FCF-based fingerprinting using the weighted k-nearest neighbor pattern recognition technique. Frequency domain channel measurements in the IEEE 802.11 band taken on a university campus were used to evaluate the accuracy of the fingerprinting types and their robustness to human-induced motion perturbations of the channel. The localization performance was analyzed, and the results are described using the spatial and temporal radio propagation characteristics. In particular, we introduce the coherence region to explain the spatial properties and investigate the impact of the Doppler spread in time-varying channels on the time coherence of RF fingerprint structures.

• The Plant Pathology Journal
• /
• v.32 no.4
• /
• pp.347-356
• /
• 2016

Plants protect themselves from pathogen attacks via several mechanisms, including hypersensitive cell death. Recognition of pathogen attack by the plant resistance gene triggers expression of carboxylesterase genes associated with hypersensitive response. We identified six transcripts of carboxylesterase genes, Vitis flexuosa carboxylesterase 5585 (VfCXE5585), Vf-CXE12827, VfCXE13132, VfCXE17159, VfCXE18231, and VfCXE47674, which showed different expression patterns upon transcriptome analysis of V. flexuosa inoculated with Elsinoe ampelina. The lengths of genes ranged from 1,098 to 1,629 bp, and their encoded proteins consisted of 309 to 335 amino acids. The predicted amino acid sequences showed hydrolase like domains in all six transcripts and contained two conserved motifs, GXSXG of serine hydrolase characteristics and HGGGF related to the carboxylesterase family. The deduced amino acid sequence also contained a potential catalytic triad consisted of serine, aspartic acid and histidine. Of the six transcripts, Vf-CXE12827 showed upregulated expression against E. ampelina at all time points. Three genes (VfCXE5585, VfCXE12827, and VfCXE13132) showed upregulation, while others (VfCXE17159, VfCXE18231, and VfCXE47674) were down regulated in grapevines infected with Botrytis cinerea. All transcripts showed upregulated expression against Rhizobium vitis at early and later time points except VfCXE12827, and were downregulated for up to 48 hours post inoculation (hpi) after upregulation at 1 hpi in response to R. vitis infection. All tested genes showed high and differential expression in response to pathogens, indicating that they all may play a role in defense pathways during pathogen infection in grapevines.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1673-1678
• /
• 2016

In the area of the speech recognition processing, background noises are caused the incorrect response to the speech input, therefore the speech recognition rates are decreased by the background noises. Accordingly, a more high level noise processing techniques are required since these kinds of noise countermeasures are not simple. Therefore, this paper proposes an algorithm to distinguish between the stationary background noises or non-stationary background noises and the speech signal having short time duration in the noisy environments. The proposed algorithm uses the characteristic parameter of the improved speech signal as an important measure in order to distinguish different types of the background noises and the speech signals. Next, this algorithm estimates various kinds of the background noises using a multi-layer perceptron neural network. In this experiment, it was experimentally clear the estimation of the background noises and the speech signals.