• 센서학회지
• /
• 제31권1호
• /
• pp.16-23
• /
• 2022

Cardiac disease is the most common cause of death worldwide. Therefore, detection and classification of electrocardiogram (ECG) signals are crucial to extend life expectancy. In this study, we aimed to implement an artificial intelligence signal recognition system in field programmable gate array (FPGA), which can recognize patterns of bio-signals such as ECG in edge devices that require batteries. Despite the increment in classification accuracy, deep learning models require exorbitant computational resources and power, which makes the mapping of deep neural networks slow and implementation on wearable devices challenging. To overcome these limitations, spiking neural networks (SNNs) have been applied. SNNs are biologically inspired, event-driven neural networks that compute and transfer information using discrete spikes, which require fewer operations and less complex hardware resources. Thus, they are more energy-efficient compared to other artificial neural networks algorithms.

• Bulletin of the Korean Chemical Society
• /
• 제34권1호
• /
• pp.159-163
• /
• 2013

A new Rhodamine B hydrazide hydrazone 1 has been synthesized and investigated as a colorimetric and fluorescent "off-on" sensor for the recognition of $Cu^{2+}$ in $CH_3CN/H_2O$ (1:1, v/v, HEPES 10 mM, pH = 7.0) solution. Sensor 1 displayed highly selective, sensitive and rapid recognition behavior toward $Cu^{2+}$ among a range of biologically and environmentally important metal ions. Sensor 1 bind $Cu^{2+}$ via a 1:1 stoichiometry with an association constant of $1.92{\times}10^6\;M^{-1}$, and the detection limit is evaluated to be $7.96{\times}10^{-8}\;M$. The $Cu^{2+}$ recognition event is reversible and is barely interfered by other coexisting metal ions.

• 한국음향학회지
• /
• 제33권4호
• /
• pp.248-254
• /
• 2014

음향 상황 인지(acoustic context awareness)는 다양하게 발생되는 음원들로부터 어떠한 장소인지 또는 어떠한 사건이 발생하는지를 판단하는 기술로 음향 이벤트 검출 또는 인식 보다 한 단계 더 복잡한 문제이다. 기존의 상황인지 기술은 음향 이벤트 검출 또는 인식 기술에 기반하여 현재 상황을 인지하는 방법을 사용하고 있다. 하지만 이와 같은 접근 방법은 여러 음원이 동시에 발생하거나 유사한 음원이 발생하는 실제 환경에서 정확한 상황 판단이 어렵다. 특히 버스와 지하철은 승객들에 의한 잡음으로 상황을 인지하기 힘들다. 이러한 문제를 극복하기 위해 본 논문에서는 유사한 음향 이벤트가 발생하는 버스와 지하철 상황을 인식할 수 있는 Bag of Words 기반의 상황 인지 알고리즘을 연구하고 코드북 생성을 위한 특징벡터를 제안한다. 제안하는 특징벡터의 효용성은 Support Vector Machine을 이용한 실험을 통해 검증했다.

• 한국지능시스템학회논문지
• /
• 제19권1호
• /
• pp.122-127
• /
• 2009

본 논문에서는 피험자가 A, B, C, D 글자를 말하는 상상을 할 때 사고중추에서와 Broca's area 에서 EEG 신호를 측정하였으며 이 신호를 Event-Related Spectral Perturbation (ERSP), Inter-Trial Coherence (ITC) 그리고 Event Related Potential (ERP) 방법을 통해 분석하여 보았다. 그 결과 F7, FT7 영역의 뇌파에서 각 문자를 보여주는 자극 제시 후 0$\sim$300ms 동안의 1$\sim$13Hz에서 높은 coherence를 보였으며, P300 이 뚜렷하게 나타나는 것을 확인할 수 있었다. 하지만 ERP를 통해 분석해본 결과 각 글자에 대한 차이를 구분하고자 하였던 처음 연구의 동기와 달리 각 글자를 말할 때 ERP가 약간의 차이를 보이기는 하였으나 각 문자에 대한 차이라거나 이 차이를 통해 문자를 구별할 수 있다고 하기는 어려웠다. 하지만 본 논문에서는 이 실험결과를 통해 기존에 운동관련 뇌 영역에 국한되어 있던 BCI 연구의 한계를 극복하고 보다 다양한 서비스를 제공할 수 있는 응용 시스템을 제안하였다.

• 대한영양사협회학술지
• /
• 제25권2호
• /
• pp.129-141
• /
• 2019

This study was conducted to determine parents' recognition of the Center for children's foodservice management (CCFSM) and to compare preschoolers' satisfaction for meals served by childcare centers and some aspects regarding the vegetable intake according to the parents' recognition of CCFSM. The subjects were 255 parents, whose children were 2~5 year old and attended a childcare center, were grouped according to the recognition of CCFSM (high recognition, HR, 27.5%; medium recognition, MR, 47.4%; low recognition, LR, 25.1%). Information was obtained by a self-administered questionnaire and data were analyzed by SPSS 25.0. Only 58.6% of HR and 10.7% of MR answered the they had participated education/event held by the CCFSM. More parents in the HR group (88.6%) acknowledged the helpfulness of CCFSM on the children's food habits compared to those in the MR group (63.6%) (P<0.001). Compared to the MR and LR groups, more parents in the HR group answered not only that they were 'satisfied'/'very satisfied' with the meals served by childcare centers (P<0.05), but also they tended to think that their children were also satisfied (P=0.061). Up to 31.2% of parents in the LR group answered that there was no need for education to increase the vegetable intake of their child compared to 14.3% and 17.4% in the HR and MR groups, respectively (P<0.05). Moreover, up to 26.6% of parents answered that school cook planned menus compared to 5.7% and 13.2% in the HR and MR group, respectively (P<0.001). In conclusion, the results provided the association between parents' high recognition of CCFSM and preschoolers' satisfaction for meals from childcare centers as well as a better chance for a desirable food life regarding vegetable intake.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.196-204
• /
• 2017

Behavior of intelligent video surveillance system is recognized by analyzing the pattern of the object of interest by using the frame information of video inputted from the camera and analyzes the behavior. Detection of object's certain behaviors in the crowd has become a critical problem because in the event of terror strikes. Recognition of object's certain behaviors is an important but difficult problem in the area of computer vision. As the realization of big data utilizing machine learning, data mining techniques, the amount of video through the CCTV, Smart-phone and Drone's video has increased dramatically. In this paper, we propose a multiple-sliding window method to recognize the cumulative change as one piece in order to improve the accuracy of the recognition. The experimental results demonstrated the method was robust and efficient learning units in the classification of certain behaviors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.321-344
• /
• 2017

Smart homes are the new generation of homes where pervasive computing is employed to make the lives of the residents more convenient. Human activity recognition (HAR) is a fundamental task in these environments. Since critical decisions will be made based on HAR results, accurate recognition of human activities with low uncertainty is of crucial importance. In this paper, a novel HAR method based on a difference of convex programming (DCP) problem is represented, which manages to handle uncertainty. For this purpose, given an input sensor data stream, a primary belief in each activity is calculated for the sensor events. Since the primary beliefs are calculated based on some abstractions, they naturally bear an amount of uncertainty. To mitigate the effect of the uncertainty, a DCP problem is defined and solved to yield secondary beliefs. In this procedure, the uncertainty stemming from a sensor event is alleviated by its neighboring sensor events in the input stream. The final activity inference is based on the secondary beliefs. The proposed method is evaluated using a well-known and publicly available dataset. It is compared to four HAR schemes, which are based on temporal probabilistic graphical models, and a convex optimization-based HAR procedure, as benchmarks. The proposed method outperforms the benchmarks, having an acceptable accuracy of 82.61%, and an average F-measure of 82.3%.

• 정보처리학회논문지B
• /
• 제18B권3호
• /
• pp.109-116
• /
• 2011

본 논문에서는 기계적인 조작 장치 없이 손동작만으로 컴퓨터를 조작할 수 있는 차세대 인터페이스인 에어 인터페이스를 구현하였다. 에어 인터페이스 시스템 구현을 위해 먼저 적외선의 전반사 원리를 이용하였으며, 이후 획득된 적외선 영상에서 손 영역을 분할한다. 매 프레임에서 분할된 손 영역은 이벤트 처리를 위한 손동작 인식부의 입력으로 사용되고, 최종적으로 개별 제어 이벤트에 맵핑된 손동작 인식을 통하여 일반적인 제어를 수행하게 된다. 본 연구에서는 손영역 검출과 추적, 손동작 인식과정을 위해 구현되어진 영상처리 및 인식 기법들이 소개되며, 개발된 에어 인터페이스 시스템은 길거리 광고, 프레젠테이션, 키오스크 등의 그 활용성이 매우 클 것으로 기대된다.

• Genomics & Informatics
• /
• 제17권2호
• /
• pp.15.1-15.7
• /
• 2019

Automatically detecting mentions of pharmaceutical drugs and chemical substances is key for the subsequent extraction of relations of chemicals with other biomedical entities such as genes, proteins, diseases, adverse reactions or symptoms. The identification of drug mentions is also a prior step for complex event types such as drug dosage recognition, duration of medical treatments or drug repurposing. Formally, this task is known as named entity recognition (NER), meaning automatically identifying mentions of predefined entities of interest in running text. In the domain of medical texts, for chemical entity recognition (CER), techniques based on hand-crafted rules and graph-based models can provide adequate performance. In the recent years, the field of natural language processing has mainly pivoted to deep learning and state-of-the-art results for most tasks involving natural language are usually obtained with artificial neural networks. Competitive resources for drug name recognition in English medical texts are already available and heavily used, while for other languages such as Spanish these tools, although clearly needed were missing. In this work, we adapt an existing neural NER system, NeuroNER, to the particular domain of Spanish clinical case texts, and extend the neural network to be able to take into account additional features apart from the plain text. NeuroNER can be considered a competitive baseline system for Spanish drug and CER promoted by the Spanish national plan for the advancement of language technologies (Plan TL).

• 한국음향학회지
• /
• 제42권5호
• /
• pp.395-401
• /
• 2023

음향 이벤트 검출(Sound Event Detection, SED)은 음향 신호에서 관심 있는 음향의 종류와 발생 구간을 검출하는 기술로, 음향 감시 시스템 및 모니터링 시스템 등 다양한 분야에서 활용되고 있다. 최근 음향 신호 분석에 관한 국제 경연 대회(Detection and Classification of Acoustic Scenes and Events, DCASE) Task 4를 통해 다양한 방법이 소개되고 있다. 본 연구는 다양한 영역에서 성능 향상을 이끌고 있는 Dense Convolutional Networks(DenseNet)을 음향 이벤트 검출에 적용하기 위해 설계 변수에 따른 성능 변화를 비교 및 분석한다. 실험에서는 DenseNet with Bottleneck and Compression(DenseNet-BC)와 순환신경망(Recurrent Neural Network, RNN)의 한 종류인 양방향 게이트 순환 유닛(Bidirectional Gated Recurrent Unit, Bi-GRU)을 결합한 DenseRNN 모델을 설계하고, 평균 교사 모델(Mean Teacher Model)을 통해 모델을 학습한다. DCASE task4의 성능 평가 기준에 따라 이벤트 기반 f-score를 바탕으로 설계 변수에 따른 DenseRNN의 성능 변화를 분석한다. 실험 결과에서 DenseRNN의 복잡도가 높을수록 성능이 향상되지만 일정 수준에 도달하면 유사한 성능을 보임을 확인할 수 있다. 또한, 학습과정에서 중도탈락을 적용하지 않는 경우, 모델이 효과적으로 학습됨을 확인할 수 있다.