• 한국인터넷방송통신학회논문지
• /
• 제16권1호
• /
• pp.291-299
• /
• 2016

본 논문에서는 임의의 주기적인 현상이나 특성은 위상구조와 밀접한 관련이 있음을 추론하고 이를 실험적으로 확인한다. 실험대상으로 주기적 특성이 있는 다양한 악기음을 선택하여 이를 유클리드 공간에 임베딩하고 이로부터 호몰로지 군을 계산하여 위상특성을 분석한다. 이를 위하여, 파형신호에서 추출한 패치모음을 패치 그래프로 구성한 다음, 대표적인 다양체 학습 방식인 통근시간 임베딩 기법을 이용하여 기하구조로 변환한다. 스펙트럼이 시간에 따라 가변적인 파형신호를 통근시간 임베딩할 때, 그에 따라 생성되는 기하구조는 변화하지만 그 신호 고유의 내재된 위상구조는 거의 변하지 않는다. 본 논문에서는 임베딩 데이터의 일부를 표본화하여 단순 복합체를 구성한 다음 이로부터 호몰로지를 계산하여 임베딩 기하구조의 위상특성을 분석하고, 이의 활용방안을 논의한다.

• 대한원격탐사학회지
• /
• 제36권1호
• /
• pp.15-27
• /
• 2020

Accurate knowledge of land use/land cover (LULC) features and their relative changes over upon the time are essential for sustainable urban management. Urban sprawl growth has been always also a worldwide concern that needs to carefully monitor particularly in a developing country where unplanned building constriction has been expanding at a high rate. Recently, remotely sensed imageries with a very high spatial/spectral resolution and state of the art machine learning approaches sent the urban classification and growth monitoring to a higher level. In this research, we classified the Quickbird satellite imagery by object-based image analysis of Dempster-Shafer (OBIA-DS) for the years of 2002 and 2015 at Karbala-Iraq. The real LULC changes including, residential sprawl expansion, amongst these years, were identified via change detection procedure. In accordance with extracted features of LULC and detected trend of urban pattern, the future LULC dynamic was simulated by using land transformation model (LTM) in geospatial information system (GIS) platform. Both classification and prediction stages were successfully validated using ground control points (GCPs) through accuracy assessment metric of Kappa coefficient that indicated 0.87 and 0.91 for 2002 and 2015 classification as well as 0.79 for prediction part. Detail results revealed a substantial growth in building over fifteen years that mostly replaced by agriculture and orchard field. The prediction scenario of LULC sprawl development for 2030 revealed a substantial decline in green and agriculture land as well as an extensive increment in build-up area especially at the countryside of the city without following the residential pattern standard. The proposed method helps urban decision-makers to identify the detail temporal-spatial growth pattern of highly populated cities like Karbala. Additionally, the results of this study can be considered as a probable future map in order to design enough future social services and amenities for the local inhabitants.

• 전자공학회논문지CI
• /
• 제49권2호
• /
• pp.53-60
• /
• 2012

최근접 이웃 분류에서 입력 데이터의 클래스는 선택된 근접 학습 데이터들 중에서 가장 빈번한 클래스로 예측된다. 최근접분류 학습은 학습 단계가 없으나, 준비된 데이터가 모두 예측 분류에 참여하여 일반화 성능이 학습 데이터의 질에 의존된다. 그러므로 학습 데이터가 많아지면 높은 기억 장치 용량과 예측 분류 시 높은 계산 시간이 요구된다. 본 논문에서는 분리 경계면에 위치한 학습 데이터들로 구성된 새로운 학습 데이터를 생성시켜 분류 예측을 수행하는 프로토타입 선택 알고리즘을 제안한다. 제안하는 알고리즘에서는 분리 경계 영역에 위치한 데이터를 Tomek links와 거리를 이용하여 선별하며, 이미 선택된 데이터와 클래스와 거리 관계 분석을 이용하여 프로토타입 집합에 추가 여부를 결정한다. 실험에서 선택된 프로토타입의 수는 원래 학습 데이터에 비해 적은 수의 데이터 집합이 되어 최근접 분류의 적용 시 기억장소의 축소와 빠른 예측 시간을 제공할수 있다.

• Journal of Information Science Theory and Practice
• /
• 제7권4호
• /
• pp.33-44
• /
• 2019

Altmetrics measure the frequency of references about an article on social media platforms, like Twitter. This paper studies a variety of factors that affect the popularity of articles (i.e., the number of article mentions) in the field of psychology on Twitter. Firstly, in this study, we classify Twitter users mentioning research articles as academic versus non-academic users and experts versus non-experts, using a machine learning approach. Then we build a negative binomial regression model with the number of Twitter mentions of an article as a dependant variable, and nine Twitter related factors (the number of followers, number of friends, number of status, number of lists, number of favourites, number of retweets, number of likes, ratio of academic users, and ratio of expert users) and seven article related factors (the number of authors, title length, abstract length, abstract readability, number of institutions, citation count, and availability of research funding) as independent variables. From our findings, if a research article is mentioned by Twitter users with a greater number of friends, status, favourites, and lists, by tweets with a large number of retweets and likes, and largely by Twitter users with academic and expertise knowledge on the field of psychology, the article gains more Twitter mentions. In addition, articles with a greater number of authors, title length, abstract length, and citation count, and articles with research funding get more attention from Twitter users.

• 품질경영학회지
• /
• 제47권3호
• /
• pp.537-552
• /
• 2019

Purpose: The development of information technology makes it easy to utilize high-dimensional categorical data. In this regard, the purpose of this study is to propose a novel method to select the proper categorical variables in high-dimensional categorical data. Methods: The proposed feature selection method consists of three steps: (1) The first step defines the goodness-to-pick measure. In this paper, a categorical variable is relevant if it has relationships among other variables. According to the above definition of relevant variables, the goodness-to-pick measure calculates the normalized conditional entropy with other variables. (2) The second step finds the relevant feature subset from the original variables set. This step decides whether a variable is relevant or not. (3) The third step eliminates redundancy variables from the relevant feature subset. Results: Our experimental results showed that the proposed feature selection method generally yielded better classification performance than without feature selection in high-dimensional categorical data, especially as the number of irrelevant categorical variables increase. Besides, as the number of irrelevant categorical variables that have imbalanced categorical values is increasing, the difference in accuracy between the proposed method and the existing methods being compared increases. Conclusion: According to experimental results, we confirmed that the proposed method makes it possible to consistently produce high classification accuracy rates in high-dimensional categorical data. Therefore, the proposed method is promising to be used effectively in high-dimensional situation.

• 한국전자통신학회논문지
• /
• 제16권3호
• /
• pp.401-406
• /
• 2021

최근 들어, 음향 이벤트 검출을 위하여 CRNN(: Convolutional Recurrent Neural Network) 구조에 기반 한 평균-교사 모델이 대표적으로 사용되고 있다. 평균-교사 모델은 두 개의 병렬 형태의 CRNN을 가진 구조이며, 이들의 출력들의 일치성을 학습 기준으로 사용함으로서 약-전사 레이블(label)과 비-전사 레이블 음향 데이터에 대해서도 효과적인 학습이 가능하다. 본 연구에서는 최신의 평균-교사 모델에 로그-멜 스펙트럼에 대한 차분 특징을 추가적으로 사용함으로서 보다 나은 성능을 이루고자 하였다. DCASE 2018/2019 Challenge Task 4용 학습 및 테스트 데이터를 이용한 음향 이벤트 검출 실험에서 제안된 차분특징을 이용한 평균-교사모델은 기존의 방식에 비해서 최대 8.1%의 상대적 ER(: Error Rate)의 향상을 얻을 수 있었다.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.267-275
• /
• 2021

Smart application is developed in this paper by using an android-based platform to automatically determine the human emergency state (Lifesaver) by using different technology sensors of the mobile. In practice, this Lifesaver has many applications, and it can be easily combined with other applications as well to determine the emergency of humans. For example, if an old human falls due to some medical reasons, then this application is automatically determining the human state and then calls a person from this emergency contact list. Moreover, if the car accidentally crashes due to an accident, then the Lifesaver application is also helping to call a person who is on the emergency contact list to save human life. Therefore, the main objective of this project is to develop an application that can save human life. As a result, the proposed Lifesaver application is utilized to assist the person to get immediate attention in case of absence of help in four different situations. To develop the Lifesaver system, the GPS is also integrated to get the exact location of a human in case of emergency. Moreover, the emergency list of friends and authorities is also maintained to develop this application. To test and evaluate the Lifesaver system, the 50 different human data are collected with different age groups in the range of (40-70) and the performance of the Lifesaver application is also evaluated and compared with other state-of-the-art applications. On average, the Lifesaver system is achieved 95.5% detection accuracy and the value of 91.5 based on emergency index metric, which is outperformed compared to other applications in this domain.

• International journal of advanced smart convergence
• /
• 제10권1호
• /
• pp.1-11
• /
• 2021

Document page segmentation is an important step in building a quality optical character recognition module. The study examined already existing work on the topic of page segmentation and focused on the development of a segmentation model that has greater functional significance for application in an organization, as well as broad capabilities for managing the quality of the model. The main problems of document segmentation were highlighted, which include a complex background of intersecting objects. As classes for detection, not only classic text, table and figure were selected, but also additional types, such as signature, logo and table without borders (or with partially missing borders). This made it possible to pose a non-trivial task of detecting non-standard document elements. The authors compared existing neural network architectures for object detection based on published research data. The most suitable architecture was RetinaNet. To ensure the possibility of quality control of the model, a method based on neural network modeling using the RetinaNet architecture is proposed. During the study, several models were built, the quality of which was assessed on the test sample using the Mean average Precision metric. The best result among the constructed algorithms was shown by a model that includes four neural networks: the focus of the first neural network on detecting tables and tables without borders, the second - seals and signatures, the third - pictures and logos, and the fourth - text. As a result of the analysis, it was revealed that the approach based on four neural networks showed the best results in accordance with the objectives of the study on the test sample in the context of most classes of detection. The method proposed in the article can be used to recognize other objects. A promising direction in which the analysis can be continued is the segmentation of tables; the areas of the table that differ in function will act as classes: heading, cell with a name, cell with data, empty cell.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• 스마트미디어저널
• /
• 제12권5호
• /
• pp.28-35
• /
• 2023

본 연구에서는 음성감정인식의 적용 가능성과 실용성 향상을 위해 적은 수의 파라미터를 가지는 새로운 경량화 모델 RoutingConvNet(Routing Convolutional Neural Network)을 제안한다. 제안모델은 학습 가능한 매개변수를 줄이기 위해 양방향 MFCC(Mel-Frequency Cepstral Coefficient)를 채널 단위로 연결해 장기간의 감정 의존성을 학습하고 상황 특징을 추출한다. 저수준 특징 추출을 위해 경량심층 CNN을 구성하고, 음성신호에서의 채널 및 공간 신호에 대한 정보 확보를 위해 셀프어텐션(Self-attention)을 사용한다. 또한, 정확도 향상을 위해 동적 라우팅을 적용해 특징의 변형에 강인한 모델을 구성하였다. 제안모델은 음성감정 데이터셋(EMO-DB, RAVDESS, IEMOCAP)의 전반적인 실험에서 매개변수 감소와 정확도 향상을 보여주며 약 156,000개의 매개변수로 각각 87.86%, 83.44%, 66.06%의 정확도를 달성하였다. 본 연구에서는 경량화 대비 성능 평가를 위한 매개변수의 수, 정확도간 trade-off를 계산하는 지표를 제안하였다.