Gas identification techniques using pattern recognition methods were developed from four micro-electronic gas sensors for noxious gas mixture analysis. The target gases for the air quality monitoring inside vehicles were two exhaust gases, carbon monoxide (CO) and nitrogen oxides (NOx), and two odor gases, ammonia (NH3) and formaldehyde (HCHO). Four MEMS gas sensors with sensing materials of Pd-SnO2 for CO, In2O3 for NOX, Ru-WO3 for NH3, and hybridized SnO2-ZnO material for HCHO were fabricated. In six binary mixed gas systems with oxidizing and reducing gases, the gas sensing behaviors and the sensor responses of these methods were examined for the discrimination of gas species. The gas sensitivity data was extracted and their patterns were determined using principal component analysis (PCA) techniques. The PCA plot results showed good separation among the mixed gas systems, suggesting that the gas mixture tests for noxious gases and their mixtures could be well classified and discriminated changes.

게임은 가장 중요한 콘텐츠로 자리매김하였다. 이러한 중요성에 따라, 패턴 인식 기술을 활용한 컴퓨터 게임 제작 사례가 점점 늘고 있다. 이것은 게임 속에서 벌어지는 세계가 점점 복잡해지고 게임의 흥미도에 대한 사용자의 욕구 가 증대하기 때문에 생기는 자연스런 현상이다. 이 논문은 신경망과 HMM을 이용한 사례를 집중적으로 살펴보며, SVM과 결정 트리를 사용한 경우도 언급한다. 최근의 논문에 대해 어떻게 특징을 추출하였는가, 어떤 분류기를 사용하 고 그것의 구조가 어떤지, 그리고 활용한 결과로 얻은 효과에 집중하여 사례를 조사하였다. 토론에서는 향후 전개 방 향과 연구 주제에 대해 언급한다.

The objective of this study is to evaluate the mechanical behaviors and structural integrity of the weldment of high strength steel by using an acoustic emission (AE) techniques. Monotonic simple tension and AE tests were conducted against the 3 kinds of welded specimen. In order to analysis the effectiveness of weldability, joinability and structural integrity, we used K-means clustering method as a unsupervised learning pattern recognition algorithm for obtained multi-variate AE main data sets, such as AE counts, energy, amplitude, hits, risetime, duration, counts to peak and rms signals. Through the experimental results, the effectiveness of the proposed method is discussed.

Innate immune response is initiated by the recognition of unique microbial molecular patterns through pattern recognition receptors (PRRs). The purpose of this study is to dissect the expression of various PRRs in gingival epithelial cells of differentiated versus undifferentiated states. Differentiation of immortalized human gingival epithelial HOK-16B cells was induced by culture in the presence of high Cα²+ at increased cell density. The expression levels of various PRRs in HOK-16B cells were examined by realtime reverse transcription polymerase chain reaction (RTPCR) and flow cytometry. In addition, the expression of human beta defensins (HBDs) was examined by real time RT-PCR and the amounts of secreted cytokines were measured by enzyme linked immunosorbent assay. In undifferentiated HOK-16B cells, NACHT-LRR-PYDcontaining protein (NALP) 2 was expressed most abundantly, and toll like receptor (TLR) 2, TLR4, nucleotide-binding oligomerization domain (NOD) 1, and NOD2 were expressed in substantial levels. However, TLR3, TLR7, TLR8, TLR9, ICE protease-activating factor (IPAF), and NALP6 were hardly expressed. In differentiated cells, the levels of NOD2, NALP2, and TLR4 were different from those in undifferentiated cells at RNA but not at protein levels. Interestingly, differentiated cells expressed the increased levels of HBD-1 and -3 but secreted reduced amount of IL-8. In conclusion, the repertoire of PRRs expressed by gingival epithelial cells is limited, and undifferentiated and differentiated cells express similar levels of PRRs.

유아들의 놀이 도구 중 하나인 스토리 북 게임은 책을 펼친 뒤, 해당 내용을 눈으로 보면서 이야기 전개에 따라 해당하는 페이지로 이동하면서 이야기를 엮어가는 게임이다. 스토리 북 게임은 유아들에게 게임과 학습의 기능을 접목시킨 것으로 사고력 증진을 위해서 많이 활용되고 있으나 시각적 효과의 한계와 청각적 효과를 제공하지 못하는 단점을 보완하기 위해서는 멀티미디어 매체와의 접목이 불가피하다. 하지만 현재의 도서와 멀티 미디어 매체의 접목은 수동적 접근으로 이루어지고 있으나 게임이 진행되는 동안 정확한 위치로 빠르게 이동하여 시각적, 청각적 효과를 제공함에는 한계를 가지고 있다. 이러한 단점을 해소하기 위해 스토리 북 게임용도서의 콘텐츠 상에 펜으로 갖다 대면 콘텐츠의 내용을 판별하고 펜에서 외부기기인 IPTV로 판별된 내용을 전달하고 TV로 콘텐츠의 내용을 출력할 수 있게끔 콘텐츠 패턴 인식 및 블루투스를 지원하는 지능형 펜 설계를 제안한다. 이는 기존의 도서에서 제공되지 않는 출판물에 대한 직접 인덱싱 기능을 부가함으로 빠른 접근으로 게임 참여자인 유아들의 집중력 향상 및 이야기 전개의 재미를 높이는 효과를 보인다.

The objective of this study is to evaluate the mechanical behaviors and structural integrity of the weldment of high strength steel by using an acoustic emission (AE) techniques. Simple tension and AE tests were conducted against the 3 kind of welding test specimens. In order to analysis the effectiveness of weldability, joinability and structural integrity, we used K-means clustering method as a unsupervised learning pattern recognition algorithm for obtained multivariate AE main data sets, such as AE counts, energy, amplitude, hits, risetime, duration, counts to peak and rms signals. Through the experimental results, the effectiveness of the proposed method is discussed.

본 논문에서는 구조물의 전역적인 손상도 평가와 국부 구조 연결부의 손상 검색을 동시에 수행할 수 있는 하이브리드 구조 손상 모니터링 체계가 제시되었다. 하이브리드 손상 모니터링 체계는 진동기반 기법과 전기/역학적 임피던스 기법으로 구성되었다. 진동기반 기법은 구조물의 모드특징의 변화를 사용하여 구조물의 전역적 특성의 변화를 감지하고, 전기/역학적 임피던스 기법은 PZT 센서의 저항 변화를 사용하여 국부 구조 연결부의 손상 여부를 검출한다. 제안된 하이브리드 모니터링 체계를 검증하기 위해 구조 연결부의 볼트 풀림 상황을 손상 시나리오로 선택하였으며, 가속도 응답과 임피던스 응답 신호가 계측되었다. 실험 결과, 제안된 하이브리드 모니터링 체계를 통해 구조물의 전역적 손상 상태와 국부 구조 연결부의 손상을 정확하게 모니터링 할 수 있었다.

주어진 시스템에서 정보와 정보흐름에 대한 패턴인식을 하기 위해서는, 정보를 내포하고 있는 문맥이 내용에 따라서 다른 단어나 다른 정보를 추론하여 원래의미를 전달함에 있어 오도할 수 있기 때문에, 문맥의 분해에서 정보 조각의 묶음 형태로 전환하는 작업에서부터 연구는 시작되어야만 한다. 많은 연구자들이 정보의 저장, 재표현, 부호화, 검색 등에 관해 효과적인 방법론을 찾고자 노력해 오고 있다. 유사한 노력의 일환으로 본 논문에서는 군이론과 상황이론을 응용해

To understand the pattern recognition from dataset, a study should be started from the decomposition process of context into a collection of data pieces because the context may infer different words or information. Many researchers have been focused on finding an effective methodology for data storage, retrieval, representation, and discovery. As a similar endeavor, this paper proposes a new modeling method using group theory and situation theory. This paper provides how to construct a semi-group as a modeling method for pattern recognition from huge dataset. This process of construction of semi‐groups can be used as a retrieval tool for the decomposed information if necessary.

A survey was carried out to investigate into high school girls' food intake pattern and their behavior for weight control. The average height and weight of the subjects were 161cm and 52.9kg, while 53.3% of them usually had breakfast which 83.7% of them had steamed rice and dishes,64.7% of residue (46.7%) them often skipped breakfast because they didn't have to eat. Most of them had lunch which prepared from home at lunch time (75.7%), they cheesed foods at first by taste(71.9%), but they almost didn't consider the nutritional aspects, also they had very small amount of fruits and vegetables. They had snack more than once a day(93.4%), As snack, they used mainly cookies(39%), Ramyun and Ddukbocki(31.5%),and breads(17.6%). Meal time was shown to be short such as 10 or 20 minutes(40.7%), dinner was thought to be the most important meal(66.9%) In spite of their weight was standard(56.68%), they thought their style as fatty(48.1%) and they wanted to reduce weight(90.4%). 90.3% of all subjects were interested in weight control and students with standard sizes(52.7%) and/or/(p<0.05) lean weights(27 1%) had concerning about weight control significantly. The motive of attempt to weight control was shown to be effected by mass communication(49.1%) mainly, When they tried to lose their weight, 66.7% of them depended on their own judgement, while only 1.1% asked for the advice of a doctor. The most effective way to control weight was thought to increase the amount of exercise(52.7%) and to control the amount of food (32.2%).

This paper proposes a pattern recognition and classification algorithm based on a circular structure that can reflect the characteristics of the sEMG (surface electromyogram) signal measured in the arm without putting the placement limitation of electrodes. In order to recognize the same pattern at all times despite the electrode locations, the data acquisition of the circular structure is proposed so that all sEMG channels can be connected to one another. For the performance verification of the sEMG pattern recognition and classification using the developed algorithm, several experiments are conducted. First, although there are no differences in the sEMG signals themselves, the similar patterns are much better identified in the case of the circular structure algorithm than that of conventional linear ones. Second, a comparative analysis is shown with the supervised learning schemes such as MLP, CNN, and LSTM. In the results, the classification recognition accuracy of the circular structure is above 98% in all postures. It is much higher than the results obtained when the linear structure is used. The recognition difference between the circular and linear structures was the biggest with about 4% when the MLP network was used.

This paper presents a multiple DoFs (degrees-of-freedom) prosthetic forearm and sEMG (surface electromyogram) pattern recognition and motion intent classification of forearm amputee. The developed prosthetic forearm has 9 DoFs hand and single-DoF wrist, and the socket is designed considering wearability. In addition, the pattern recognition based on sEMG is proposed for prosthetic control. Several experiments were conducted to substantiate the performance of the prosthetic forearm. First, the developed prosthetic forearm could perform various motions required for activity of daily living of forearm amputee. It was able to control according to shape and size of the object. Additionally, the amputee was able to perform ‘tying up shoe’ using the prosthetic forearm. Secondly, pattern recognition and classification experiments using the sEMG signals were performed to find out whether it could classify the motions according to the user’s intents. For this purpose, sEMG signals were applied to the multilayer perceptron (MLP) for training and testing. As a result, overall classification accuracy arrived at 99.6% for all participants, and all the postures showed more than 97% accuracy.

Surface electromyogram (sEMG), which is a bio-electrical signal originated from action potentials of nerves and muscle fibers activated by motor neurons, has been widely used for recognizing motion intention of robotic prosthesis for amputees because it enables a device to be operated intuitively by users without any artificial and additional work. In this paper, we propose a training-free unsupervised sEMG pattern recognition algorithm. It is useful for the gesture recognition for the amputees from whom we cannot achieve motion labels for the previous supervised pattern recognition algorithms. Using the proposed algorithm, we can classify the sEMG signals for gesture recognition and the calculated threshold probability value can be used as a sensitivity parameter for pattern registration. The proposed algorithm was verified by a case study of a patient with partial-hand amputation.

In this paper, damage assessment technology based on statistical pattern recognition technology was developed for maintenance of structure and the performance of the developed technology was verified by vibration test. The damage assessment technique uses the improved Mahalanobis distance theory, which is a statistical pattern recognition technique, and developed to take account of the variability between the measured data. In order to verify the damage evaluation performance of the developed technology, a cable damage test was conducted for a cable-stayed bridge. Experimental results show that the developed damage assessment technology has the capability of extracting information that can determine the location of damage due to cable damage.

Traditionally the steady-state central section of the vowel length has been assumed to characterize the vowel quality. However, since Peterson and Barney (1952), this position has been challenged especially for American English monophthongal vowels. In this paper, introduced are low-ordered 12 mel-scale frequency cepstral coefficients (MFCC), which can characterize the shape of the oral cavity filter for monophthongal vowel production in the mel-scale domain. Four pattern recognition classification models are fitted to the measurements of spectral and cepstral parameters at multiple sections of the vowel duration along with F0, Gender and Duration for the AE vowel signals in the hVd syllable in Hillenbrand et al. (1995). It turns out that pattern recognition classifiers with the cepstral properties outperform those with spectral properties, reaching the perception level of American English listeners’.