• Biomedical Engineering Letters
• /
• 제8권4호
• /
• pp.365-371
• /
• 2018

Uninterrupted monitoring of multiple subjects is required for mass causality events, in hospital environment or for sports by medical technicians or physicians. Movement of subjects under monitoring requires such system to be wireless, sometimes demands multiple transmitters and a receiver as a base station and monitored parameter must not be corrupted by any noise before further diagnosis. A Bluetooth Piconet network is visualized, where each subject carries a Bluetooth transmitter module that acquires vital sign continuously and relays to Bluetooth enabled device where, further signal processing is done. In this paper, a wireless network is realized to capture ECG of two subjects performing different activities like cycling, jogging, staircase climbing at 100 Hz frequency using prototyped Bluetooth module. The paper demonstrates removal of baseline drift using Fast Fourier Transform and Inverse Fast Fourier Transform and removal of high frequency noise using moving average and S-Golay algorithm. Experimental results highlight the efficacy of the proposed work to monitor any vital sign parameters of multiple subjects simultaneously. The importance of removing baseline drift before high frequency noise removal is shown using experimental results. It is possible to use Bluetooth Piconet frame work to capture ECG simultaneously for more than two subjects. For the applications where there will be larger body movement, baseline drift removal is a major concern and hence along with wireless transmission issues, baseline drift removal before high frequency noise removal is necessary for further feature extraction.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.27-33
• /
• 2021

The whole world now is dealing with Coronavirus, and it has turned to be one of the most widespread and long-lived pandemics of our times. Reports reveal that the infectious disease has taken toll of the almost 80% of the world's population. Amidst a lot of research going on with regards to the prediction on growth and transmission through Symptomatic carriers of the virus, it can't be ignored that pre-symptomatic and asymptomatic carriers also play a crucial role in spreading the reach of the virus. Classification Algorithm has been widely used to classify different types of COVID-19 carriers ranging from simple feature-based classification to Convolutional Neural Networks (CNNs). This research paper aims to present a novel technique using a Random Forest Machine learning algorithm with hyper-parameter tuning to classify different types COVID-19-carriers such that these carriers can be accurately characterized and hence dealt timely to contain the spread of the virus. The main idea for selecting Random Forest is that it works on the powerful concept of "the wisdom of crowd" which produces ensemble prediction. The results are quite convincing and the model records an accuracy score of 99.72 %. The results have been compared with the same dataset being subjected to K-Nearest Neighbour, logistic regression, support vector machine (SVM), and Decision Tree algorithms where the accuracy score has been recorded as 78.58%, 70.11%, 70.385,99% respectively, thus establishing the concreteness and suitability of our approach.

• 한국물환경학회지
• /
• 제39권1호
• /
• pp.46-60
• /
• 2023

Climate change causes fluctuations in water quality in the aquatic environment, which can cause changes in water circulation patterns and severe adverse effects on aquatic ecosystems in the future. Therefore, research is needed to predict and respond to water quality changes caused by climate change in advance. In this study, we tried to predict the dissolved oxygen (DO), chlorophyll-a, and turbidity of the Paldang reservoir for about two weeks using long short-term memory (LSTM) and gated recurrent units (GRU), which are deep learning algorithms based on recurrent neural networks. The model was built based on real-time water quality data and meteorological data. The observation period was set from July to September in the summer of 2021 (Period 1) and from March to May in the spring of 2022 (Period 2). We tried to select an algorithm with optimal predictive power for each water quality parameter. In addition, to improve the predictive power of the model, an important variable extraction technique using random forest was used to select only the important variables as input variables. In both Periods 1 and 2, the predictive power after extracting important variables was further improved. Except for DO in Period 2, GRU was selected as the best model in all water quality parameters. This methodology can be useful for preventive water quality management by identifying the variability of water quality in advance and predicting water quality in a short period.

• 한국음향학회지
• /
• 제42권4호
• /
• pp.357-363
• /
• 2023

다양한 신호가 혼합된 수중 신호로부터 각각의 신호를 분리하는 기술은 오랫동안 연구되어왔지만, 낮은 품질의 수중 신호의 특성 상 쉽게 해결되지 않는 문제이다. 현재 주로 사용되는 방법은 Short-time Fourier transform을 사용하여 수신된 음향신호의 스펙트로그램을 얻은 뒤, 주파수의 특성을 분석하여 신호를 분리하는 기술이다. 하지만 매개변수의 최적화가 까다롭고, 스펙트로그램으로 변환하는 과정에서 위상 정보들이 손실되는 한계점이 지적되었다. 본 연구에서는 이러한 문제를 해결하기 위해 긴 시계열 신호 처리에서 좋은 성능을 보인 Dual-path Recurrent Neural Network을 기반으로, 다중 채널 센서로부터 생성된 입력신호인 3차원 텐서를 처리할 수 있도록 변형된 Tripple-path Recurrent Neural Network을 제안한다. 제안하는 기술은 먼저 다중 채널 입력 신호를 짧은 조각으로 분할하고 조각 내 신호 간, 구성된 조각간, 그리고 채널 신호 간의 각각의 관계를 고려한 3차원 텐서를 생성하여 로컬 및 글로벌 특성을 학습한다. 제안된 기법은, 기존 방법에 비해 개선된 Root Mean Square Error 값과 Scale Invariant Signal to Noise Ratio을 가짐을 확인하였다.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• 마케팅과학연구
• /
• 제11권
• /
• pp.147-163
• /
• 2003

최근 들어 호텔 기업은 환경변화에 신속히 대처하고 경쟁우위 제고를 위해서 기업 겸영에 정보기술을 도입하는 것이 필수적인 부분이 되었다. 이에 따라 많은 호텔 기업들은 정보기술을 전략적으로 활용하기 위한 노력의 일환으로써, CRM(고객관계관리 ; customer relationship management)시스템을 구축하고 있다. CRM 시스템 도입이 호텔기업의 핵심적인 전략시스템으로 자리를 잡아가고, 도입에 따른 고객성과를 밝히기 위해서 본 논문에서는 CRM 시스템 구축이 고객성과에 미치는 영향을 규명하는 연구를 시도하였다. 본 연구를 위하여 CRM 시스템 구축요인과 고객성과에 대한 기존의 연구 결과를 토대로 문제해결을위한 가설을 설정하였으며, 이를 실증적으로 검증하기 위하여 현재 CRM 시스템을 운용하고 있는 특급호텔의 CRM 시스템 구축과 관련이 있는 종사자들을 대상으로 설문조사를 실시하였다. 본 연구의 결과들을 요약하면 첫째, CRM 구축 요인이 CRM 고객 성과에 영향을 미치는 것으로 조사되었다. 즉, 조직적 특성 요인, 경영환경 요인, 정보지향성 및 기술적 요인이 CRM 고객 성과에 영향을 미치는 것으로 나타났다. 본 연구를 시행하면서 나타난 한계점과 향후 연구과제는 다음과 같다. 첫째, CRM의 고객성과에 영향을 미치는 요인들은 기존의 선행연구를 검토하여 추출하였으나, 추가적인 변수들에 대한 고려가 필요하다고 판단된다. 둘째, CRM 시스템이 국내 기업들에 보급된 지 불과 2-3년 밖에 지나지 않아 선행연구들이 지극히 부족한 상태이고, 실증적 분석 연구 또한 부족하여 본 연구의 통계분석 결과를 기존 연구와 비교하여 해석하기에는 한계가 있다. 특히 호텔산업을 중심으로 한 선행연구가 전무한 상태여서 여러 가지 CRM 시스템의 고객 성과에 대한 선행 변수를 조사해 보았으나, 아직까지 선행연구의 부족으로 차후에 그 측정수단에 대한 연구가 앞으로 계속적으로 이루어져야 할 것이다. 향후 연구에서는 이런 문제점을 고려하여 보다 정밀한 이론적 검토와, 우리 나라 전 지역의 호텔을 대상으로 CRM 시스템의 구축현황과 문제점에 대해서 좀 더 세밀히 고찰하는 것이 필요할 것이다.

• Journal of Pharmaceutical Investigation
• /
• 제39권3호
• /
• pp.185-199
• /
• 2009

Using a strain-controlled rheometer [Advanced Rheometric Expansion System (ARES)], the steady shear flow properties and the dynamic viscoelastic properties of $Antiphlamine-S^{(R)}$ lotion have been measured at $20^{\circ}C$ (storage temperature) and $37^{\circ}C$ (body temperature). In this article, the temperature dependence of the linear viscoelastic behavior was firstly reported from the experimental data obtained from a temperature-sweep test. The steady shear flow behavior was secondly reported and then the effect of shear rate on this behavior was discussed in detail. In addition, several inelastic-viscoplastic flow models including a yield stress parameter were employed to make a quantitative evaluation of the steady shear flow behavior, and then the applicability of these models was examined by calculating the various material parameters. The angular frequency dependence of the linear viscoelastic behavior was nextly explained and quantitatively predicted using a fractional derivative model. Finally, the strain amplitude dependence of the dynamic viscoelastic behavior was discussed in full to elucidate a nonlinear rheological behavior in large amplitude oscillatory shear flow fields. Main findings obtained from this study can be summarized as follows : (1) The linear viscoelastic behavior is almostly independent of temperature over a temperature range of $15{\sim}40^{circ}C$. (2) The steady shear viscosity is sharply decreased as an increase in shear rate, demonstrating a pronounced Non-Newtonian shear-thinning flow behavior. (3) The shear stress tends to approach a limiting constant value as a decrease in shear rate, exhibiting an existence of a yield stress. (4) The Herschel-Bulkley, Mizrahi-Berk and Heinz-Casson models are all applicable and have an equivalent validity to quantitatively describe the steady shear flow behavior of $Antiphlamine-S^{(R)}$ lotion whereas both the Bingham and Casson models do not give a good applicability. (5) In small amplitude oscillatory shear flow fields, the storage modulus is always greater than the loss modulus over an entire range of angular frequencies tested and both moduli show a slight dependence on angular frequency. This means that the linear viscoelastic behavior of $Antiphlamine-S^{(R)}$ lotion is dominated by an elastic nature rather than a viscous feature and that a gel-like structure is present in this system. (6) In large amplitude oscillatory shear flow fields, the storage modulus shows a nonlinear strain-thinning behavior at strain amplitude range larger than 10 % while the loss modulus exhibits a weak strain-overshoot behavior up to a strain amplitude of 50 % beyond which followed by a decrease in loss modulus with an increase in strain amplitude. (7) At sufficiently large strain amplitude range (${\gamma}_0$>100 %), the loss modulus is found to be greater than the storage modulus, indicating that a viscous property becomes superior to an elastic character in large shear deformations.

• 대한전자공학회논문지SP
• /
• 제47권3호
• /
• pp.11-22
• /
• 2010

본 논문은 컨텍스트 기반의 지능형 영상 감시 시스템 구현에 관한 연구로써 기존 연구의 시공간적 제약성 및 실시간 처리가 어려운 단점을 보완하여 초당 30 프레임으로 이루어져 있는 저해상도 동영상(320*240)을 대상으로 다양한 환경에서 실시간 처리가 가능한 움직임 검출 및 장면 분석 알고리즘을 제안하고 이를 이용해 동영상 감시 시스템을 구축한다. 먼저 장면 분석을 수행하기 위한 전처리 과정인 움직임 검출 알고리즘에서는 연속된 프레임 중 의미 없는 유사 프레임과 배경을 제거하고 움직임 영역만을 검출하기 위해 웨이브렛 변환과 에지 히스토그램을 이용하여 샷의 경계를 검출한다. 다음으로 키프레임 선정 파라미터에 의해 샷 경계 내 대표 키프레임을 선정하며, 에지 히스토그램 및 수학적 형태론을 이용하여 움직임 영역만을 검출한다. 장면 분석 알고리즘에서는 검출된 객체의 수직 수평 비율과 질량 중심을 통해 재구성된 허프 변환 후의 각도를 이용해 독립 객체 분석을 수행하며, '서다, 걷다, 눕다, 앉다'의 4가지 기본 상황 정보를 정의한다. 또한 각 상황의 연결 상태 추정을 통해 일반 상황 및 위급 상황으로 구성되는 단순 상황 모델을 정의함으로써 장면 분석을 수행하며, 제안된 알고리즘의 실시간 처리 가능성을 확인하기 위해 시스템을 구성한다. 제안된 시스템은 저해상도 영상을 대상으로 인식률 면에서 평균 92.5%의 성능을 보였으며, 처리속도는 프레임 당 평균 0.74초로 실시간 처리가 가능함을 확인하였다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제26권1호
• /
• pp.71-82
• /
• 2003

T1강조 자기공명영상과 계층적 신경회로망을 이용하여 간경변증을 단계별로 분류하고자 제안한다. 데이터는 2001년 6월부터 12월까지 부산대학교병원에서 얻었으며, 각 단계별 분류는 정상, 1, 2, 3단계별로 분류하였다. 그리고 46명의 데이터를 분석하였다. T1강조 자기공명 간영상으로부터 정상간 실질과 간경변 결절을 추출하였다. 그 다음에 T1강조 자기공명 간 영상에서 간 경화증의 단계를 객관적으로 해석 분류하였다. 간경변 분류기 구현은 계층적 신경회로망을 이용하였고, 명암도 분석과 간 결절 특성을 통하여 정상간과 3단계의 간경변으로 구분하였다. 제안한 신경회로망 분류기는 오류 역전과 알고리즘을 이용하였다. 분류결과 인식율이 정상군은 100%, 1 단계는 82.3%, 2 단계는 86.7%, 3 단계는 83.7%의 분류율을 나타내었다. 신경회로망 분류 결과와 전문의 판독 결과를 서로 비교한 결과 인식률은 매우 높게 나타났다. 만일 더욱더 충분한 데이터나 파라미터를 가지고 지속적으로 수행한다면 간경변 환자들에게 임상적으로 지원하는 도구뿐만 아니라 의료전문 신경회로망으로도 기대된다.

• Journal of Preventive Medicine and Public Health
• /
• 제43권2호
• /
• pp.109-116
• /
• 2010

Objectives: The pandemic of novel influenza A (H1N1) virus has required decision-makers to act in the face of the substantial uncertainties. In this study, we evaluated the potential impact of the pandemic response strategies in the Republic of Korea using a mathematical model. Methods: We developed a deterministic model of a pandemic (H1N1) 2009 in a structured population using the demographic data from the Korean population and the epidemiological feature of the pandemic (H1N1) 2009. To estimate the parameter values for the deterministic model, we used the available data from the previous studies on pandemic influenza. The pandemic response strategies of the Republic of Korea for novel influenza A (H1N1) virus such as school closure, mass vaccination (70% of population in 30 days), and a policy for anti-viral drug (treatment or prophylaxis) were applied to the deterministic model. Results: The effect of two-week school closure on the attack rate was low regardless of the timing of the intervention. The earlier vaccination showed the effect of greater delays in reaching the peak of outbreaks. When it was no vaccination, vaccination at initiation of outbreak, vaccination 90 days after the initiation of outbreak and vaccination at the epidemic peak point, the total number of clinical cases for 400 days were 20.8 million, 4.4 million, 4.7 million and 12.6 million, respectively. The pandemic response strategies of the Republic of Korea delayed the peak of outbreaks (about 40 days) and decreased the number of cumulative clinical cases (8 million). Conclusions: Rapid vaccination was the most important factor to control the spread of pandemic influenza, and the response strategies of the Republic of Korea were shown to delay the spread of pandemic influenza in this deterministic model.