• Proceedings of the KOR-KST Conference
• /
• 1998.10a
• /
• pp.265-274
• /
• 1998

본 논문은 도로를 주행하는 차량의 지점속도에 대하여 단기간(short-term)으로 예측하는 네 가지의 모형들에 대한 개발 및 결과의 비교하고 평가했다. 사용된 기법들로는 다중회귀분석, 시계열분석(ARIMA), 인공 신경망, 칼만필터링 등이며, 모형의 구출을 위하여 다수의 독립변수 및 입력변수가 요구되는 다중회귀분석과 인공 신경망에서는 연속방정식에서 고려되는 변수들간의 단순상관계수 및 편상관계수의 계산을 통해서 입력변수가 설정이 되었으며, 시계열분석(ARIMA)과 칼만필터링 등 단일 입력 변수만을 요하는 모형에서는 바로 전 시간대와 현재시간대의간격동안 속도의 변화량을 입력변수로 설정하였다. 속도를 비롯해서 교통 데이터는 현장자료를 사용하였는데, 이는 서울의 한강 옆에 위치한 올림픽대로 중 한강대로에 위치한 검지기 3개를 통해서 천호동 방면으로 이동하는 교통류에 대해서 17시간 (00시~17시)동안 수집했다. 17시간 수집했는데 그중에 검지된 속도는 14km/h에서 98km/h까지 변하는 등, 수집된 자료에는 다양한 교통상태가 포함되어 있는데 이는 각 모형들의 정확한 예측력과 적응성을 평가하기 위함이었다. 각 모형은 예측하고자 하는 시점으로부터 1, 5, 10, 15분 후의 속도를 예측하는 것으로 총 4가지의 예측시간간격으로 각각 실험되었다. 결과는 전반적으로 신뢰성 있게 나왔으나 그중에서도 정확성면에서는 인공신경망과 칼만필터링이 우수했고 적응성면에서는 칼만필터리딩 탁월했다. 또한 1분 후의 속도를 예측하는 결과들은 모형들간에 거의 비슷한 정확도를 보여주었는데 이는 입력변수의 설정이 중요한 것임을 보여주는 것이라 판단된다. 있는 기법이다.적으로 세부적 차종분류로 접근한다.의 영향들을 고려함으로써 가로망 설계 과정에서 가로망의 상반된 역할인 이동성과 접근성의 비교가 가능한 보다 현실적인 가로망 설계 모형을 구축하고자 한다. 지금까지 소개된 가로망 설계모형들은 용량변화에 대한 설계변수의 형태에 따라 이산적 가로망 설계 모형과 연속적 가로망 설계모형으로 나뉘어지게 된다. 본 논문의 경우, 계산속도의 향상 측면에서는 연속적 가로망 설계 모형을 도입할 수 있지만, 이때 요구되는 도로용량이 이산적인 변수(차선 수)로 결정되어야만 신호제어 변수를 결정할 수 있기 때문에, 이산적 가로망 설계 모형이 사용된다. 하지만, 이산적 설계모형의 경우 조합최적화 문제이므로 정확한 최적해를 구하기 위해서는 상당한 시간이 소요되며, 경우에 따라서는 국부 최적해에 빠지게 된다. 이러한 문제를 극복하기 위해, 우선 이상적 모형의 근사화, 혹은 조합최적화문제를 위해 개발된 Simulated Annealing기법의 적용, 연속적 모형의 변수를 이산화하는 방법 등 다양한 모형들을 고려해 본 뒤, 적절한 모형을 적용할 것이다. 가로망 설계 모형에서 신호제어를 고려하기 위해서는 주어진 가로망에 대한 통행 배정과정에서 고려되는 통행시간을 링크통행시간과 교차로 지체시간을 동시에 고려해야 하는데, 이러한 문제의 해결을 위해서 최근 활발히 논의되고 있는 교차로에서의 신호제어에 대응하는 통행배정 모형을 도입하여 고려하고자 한다. 이를 위해서 지금까지 연구되어온 Global Solution Approach와 Iterative Approach를 비교, 검토한 뒤 모형에 보다 알맞은 방법을 선택한다. 차량의

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.397-403
• /
• 2017

In the modern society, psychological diseases and impulsive crimes due to stress are occurring. In order to reduce the stress, the existing treatment methods consisted of continuous visit counseling to determine the psychological state and prescribe medication or psychotherapy. Although this face-to-face counseling method is effective, it takes much time to determine the state of the patient, and there is a problem of treatment efficiency that is difficult to be continuously managed depending on the individual situation. In this paper, we propose an artificial intelligence emotion management system that emotions of user monitor in real time and induced to a table state. The system measures multiple bio-signals based on the PPG and the GSR sensors, preprocesses the data into appropriate data types, and classifies four typical emotional states such as pleasure, relax, sadness, and horror through the SVM algorithm. We verify that the emotion of the user is guided to a stable state by providing a real-time emotion management service when the classification result is judged to be a negative state such as sadness or fear through experiments.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.

• The Journal of the Korea Contents Association
• /
• v.17 no.9
• /
• pp.476-485
• /
• 2017

This study was analyzed obesity status by divided into six classification based on the body mass index(BMI) established by World Health Organization-Western Pacific Regional Office(WHO-WPRO) through National Health Insurance Service(NHIS). In the middle of process, problems of outlier solved by presenting the median repeated interpolation. Unlike linear and Lagrange interpolation, median repeated interpolation may be useful in multiple outlier contained dataset. As a result, we found that extreme low and obesity weight gradually increased and the frequency of normal body weight gradually decreased. Especially, the increase of obesity in men and women of lower age group is increasing. Overall, this study suggests that national measures need to be taken before health problems arising from obesity can spread to other social problems.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.795-800
• /
• 2016

In image classification, recent CNNs compete with human performance. However, there are limitations in more general recognition. Herein we deal with indoor images that contain too much information to be directly processed and require information reduction before recognition. To reduce the amount of data processing, typically variational inference or variational Bayesian methods are suggested for object detection. However, these methods suffer from the difficulty of marginalizing over the given space. In this study, we propose an image-text integrated recognition system using active vision based on Spatial Transformer Networks. The system attempts to efficiently sample a partial region of a given image for a given language information. Our experimental results demonstrate a significant improvement over traditional approaches. We also discuss the results of qualitative analysis of sampled images, model characteristics, and its limitations.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• The KIPS Transactions:PartC
• /
• v.13C no.5 s.108
• /
• pp.621-626
• /
• 2006

A mobile ad hoc network (MANET) is an infrastructureless network that supports multi-hop communication. For the MANET nodes wishing to communicate with nodes in the wired Internet, the global Internet connectivity is required and this functionality can be achieved with the help of the Internet gateway. For the support of reliability and flexibility, multiple Internet gateways can be provisioned for a MANET. In this case, load-balancing becomes one of the important issues since the network performance such as the network throughput can be improved if the loads of the gateways are well-balanced. In this paper, we categorize the load-balancing mechanisms and propose a new metric for load-balancing. Simulation results show that our proposed mechanism using the hop distance and the number of routing table entries as a load-balancing metric enhances the overall network throughput.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.4
• /
• pp.75-88
• /
• 2008

This paper presents a spatial-level nonparametric multi-focus image fusion technique based on kernel estimates of input image blocks' underlying class-conditional probability density functions. Image fusion is approached as a classification task whose posterior class probabilities, P($wi{\mid}Bikl$), are calculated with likelihood density functions that are estimated from the training patterns. For each of the C input images Ii, the proposed method defines i classes wi and forms the fused image Z(k,l) from a decision map represented by a set of $P{\times}Q$ blocks Bikl whose features maximize the discriminant function based on the Bayesian decision principle. Performance of the proposed technique is evaluated in terms of RMSE and Mutual Information (MI) as the output quality measures. The width of the kernel functions, ${\sigma}$, were made to vary, and different kernels and block sizes were applied in performance evaluation. The proposed scheme is tested with C=2 and C=3 input images and results exhibited good performance.

• Journal of Digital Contents Society
• /
• v.19 no.8
• /
• pp.1443-1451
• /
• 2018

The genre of digital games is not a fixed and invariable system, but a generative system of revisions and changes. The purpose of this study is to define a concept of alternative genre for digital games. The alternative genre of digital games should be presented in combinations of various genre elements and reflected the genre awareness of the user. In this context, user tags of the game transform the classical genre concept into a family resemblance based categorization and establish a user-driven bottom-up genre system. User tags as the form of alternative genre can spread the 'small' genre through multiplicity of genre elements and strengthen the communicative function of the genre.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.331-335
• /
• 2008

시맨틱 웹은 정보의 의미를 개념으로 정의하고 개념들 간의 관계성을 표현함으로써, 문서들 간의 단순 연결이 아닌 의미 연결을 통해서 보다 정확하고 효율적인 정보 검색이 가능하게 된다. 이러한 시맨틱 웹의 비전이 구체화되기 위해서는 웹 온톨로지(Web Ontology)를 기반으로 의미 정보로 구성된 시맨틱 문서들에 대한 추론을 통해서 웹상에 존재하는 엄청난 정보들 간의 관련성을 파악하고 사용자가 요구하는 정보를 보다 효율적으로 검색할 수 있는 시스템이 필수적이다. W3C에서 제안한 OWL은 대표적인 온톨로지 언어이다. 시맨틱 웹 상에서 OWL 데이타를 효율적으로 검색하기 위해서는 잘 구성되어진 저장 스키마를 구축해야 한다. 본 논문에서는 Jena2의 경우, 단일 테이블에 문서의 정보를 저장하기 때문에 단순 선택 연산 (Simple Selection), 조인 연산이 요구되는 질의에 대한 성능이 저하되고 대용량의 OWL데이터의 처리에 있어 성능이 저하되는 문제를 해결하기 위하여 본 논문에서는 OWL 문서의 의미를 Class, Property, Individual로 분류하여 각각의 데이터 정보들을 테이블에 저장하기 위한 다중 변환기와 OWL 변환기 기능을 가진 시멘텍 검색 엔진을 설계 및 구현하였다. 본 검색 엔진을 테스트한 결과, 단순정보검색 질의 시 Jena2에서 비정규화된 테이블 구조로 저장할 때보다 질의 응답 속도를 향상 시킬 수 있었고, 조인 연산 시 두 테이블의 크기로 인한 조인비용이 발생하는 문제점을 해결함으로써 빠른 검색 및 질의 속도를 보장할 수 있었다.