• 한국정보통신학회논문지
• /
• 제25권8호
• /
• pp.1013-1018
• /
• 2021

최근 자율주행 자동차가 일으킨 사고 때문에 인공지능의 윤리적 측면에 대한 논의가 활발히 진행되고 있다. 본 논문은 인공지능이 윤리적 요소와 필연적으로 결부되어 있음을 로봇-인공지능 윤리 관련 개념과 공학기술로부터 확인하고 윤리적 측면이 사후적으로 발생하는 것이 아니라 내장되어 있음을 논한다. 또한, 자율주행 자동차와 관련된 윤리적 문제의 실마리가 될 수 있는 트롤리 딜레마에 대한 해결방법을 고안한다. 우선적으로 베이지안 네트워크를 작성하고 전처리 과정을 거쳐 중요하고 영향력 있는 데이터만 남도록 하며, 네트워크의 정확한 수치를 계산하기 위해 크라우드 소싱과 외삽법을 이용한다. 이러한 과정을 통해 알고리즘 및 모델을 구현할 때에 인간의 주관이 필연적으로 포함될 수밖에 없음을 주장하고 인공지능 시스템에 관한 왜곡과 편향을 방지하기 위해 전공 교육과 구분되는 공학 교양 교육, 특히 윤리 교육의 필요성과 방향에 대해 논한다.

• Nuclear Engineering and Technology
• /
• 제53권7호
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• Wind and Structures
• /
• 제36권6호
• /
• pp.393-404
• /
• 2023

Skewness and kurtosis are important higher-order statistics for simulating non-Gaussian wind pressure series on low-rise buildings, but their predictions are less studied in comparison with those of the low order statistics as mean and rms. The distribution gradients of skewness and kurtosis on roofs are evidently higher than those of mean and rms, which increases their prediction difficulty. The conventional artificial neural networks (ANNs) used for predicting mean and rms show unsatisfactory accuracy in predicting skewness and kurtosis owing to the limited capacity of shallow learning of ANNs. In this work, the deep neural networks (DNNs) model with the ability of deep learning is introduced to predict the skewness and kurtosis on a low-rise building. For obtaining the optimal generalization of the DNNs model, the hyper parameters are automatically determined by Bayesian Optimization (BO). Moreover, for providing a benchmark for future studies on predicting higher order statistics, the data sets for training and testing the DNNs model are extracted from the internationally open NIST-UWO database, and the prediction errors of all taps are comprehensively quantified by various error metrices. The results show that the prediction accuracy in this study is apparently better than that in the literature, since the correlation coefficient between the predicted and experimental results is 0.99 and 0.75 in this paper and the literature respectively. In the untrained cornering wind direction, the distributions of skewness and kurtosis are well captured by DNNs on the whole building including the roof corner with strong non-normality, and the correlation coefficients between the predicted and experimental results are 0.99 and 0.95 for skewness and kurtosis respectively.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(1)
• /
• pp.189-192
• /
• 2000

This paper proposes a fuzzy-based random access controller with a superimposed frame structure (F$^2$RAC) fur voice/data-integrated wireless networks. F$^2$RAC adopts mini-slot technique for reducing contention cost, and these mini-slots of which number may dynamically vary from one frame to the next as a function of the traffic load are further partitioned into two regions for access requests coming from voice and data traffic with their respective QoS requirements. And F$^2$RAC is designed to properly determine the access regions and permission probabilities for enhancing the data packet delay while ensuring the voice packet dropping probability constraint. It mainly consists of the estimator with Pseudo-Bayesian algorithm and fuzzy logic controller with Sugeno-type of fuzzy rules. Simulation results prove that F$^2$RAC can guarantee QoS requirement of voice and provide the highest throughput efficiency and the smallest data packet delay amongst the different alternatives including PRMA［1］, IPRMA［2］, and SIR［3］.

• 제어로봇시스템학회논문지
• /
• 제19권6호
• /
• pp.513-519
• /
• 2013

The current vision-based approaches for emotion recognition, such as facial expression analysis, have many technical limitations in real circumstances, and are not suitable for applications that use them solely in practical environments. In this paper, we propose an approach for emotion recognition by combining extrinsic representations and intrinsic activities among the natural responses of humans which are given specific imuli for inducing emotional states. The intrinsic activities can be used to compensate the uncertainty of extrinsic representations of emotional states. This combination is done by using PRMs (Probabilistic Relational Models) which are extent version of bayesian networks and are learned by greedy-search algorithms and expectation-maximization algorithms. Previous research of facial expression-related extrinsic emotion features and physiological signal-based intrinsic emotion features are combined into the attributes of the PRMs in the emotion recognition domain. The maximum likelihood estimation with the given dependency structure and estimated parameter set is used to classify the label of the target emotional states.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2000년도 International Symposium on Bioinformatics
• /
• pp.59-60
• /
• 2000

The past few years have seen a dramatic increase in gene expression data on the basis of DNA microarrays or DNA chips. Going beyond a generic view on the genome, microarray data are able to distinguish between gene populations in different tissues of the same organism and in different states of cells belonging to the same tissue. This affords a cell-wide view of the metabolic and regulatory processes under different conditions, building an effective basis for new diagnoses and therapies of diseases. In this talk we present machine learning techniques for effective mining of DNA microarray data. A brief introduction to the research field of machine learning from the computer science and artificial intelligence point of view is followed by a review of recently-developed learning algorithms applied to the analysis of DNA chip gene expression data. Emphasis is put on graphical models, such as Bayesian networks, latent variable models, and generative topographic mapping. Finally, we report on our own results of applying these learning methods to two important problems: the identification of cell cycle-regulated genes and the discovery of cancer classes by gene expression monitoring. The data sets are provided by the competition CAMDA-2000, the Critical Assessment of Techniques for Microarray Data Mining.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2006년도 한국컴퓨터종합학술대회 논문집 Vol.33 No.1 (A)
• /
• pp.211-213
• /
• 2006

실시간으로 변화하는 컴퓨터 통신 환경에서 멀티미디어 응용 프로그램은 QoS를 만족하기 위해 안정적으로 튜닝 되고 재구성되는 것이 필요하다. 그러나 안정적으로 QoS를 보장하는 것은 응용 프로그램의 자원 예약이나 실시간 보장과 같은 메카니즘을 제공하지 않은 일반적인 목적의 시스템 상에서 수행될 때 많은 어려움을 가지게 된다. 특히, 예측 불가능한 개방형 환경에서 최우선 자원 할당에 의해 발생되는 자원의 유효성에 대응하기 위해 QoS 적응은 수행되어야 한다. 그러나 적응을 언제, 어떻게 조정해야 하고 폭 넓은 범위에서 응용 프로그램에 어떻게 적용시킬지를 알기 위해 일반적인 알고리즘을 제시해야할 필요가 있다. 이러한 목적을 위해, 본 논문에서는 멀티미디어 어플리케이션의 파라미터를 모델링하고, 파라미터간의 관계를 정량적으로 얻기 위해 계층적 QoS 프로빙 알고리즘을 적용한다. 이것을 기반으로 설계된 베이지안 네트워크를 이용하여 불확실한 정보를 확률값으로 처리함으로써 적응 행동을 예측하도록 한다. 마지막으로 실제 실험을 통해 제안된 미들웨어의 유용성을 확인한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권3호
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.2948-2963
• /
• 2015

In the field of computer vision, visual surveillance systems have recently become an important research topic. Growth in this area is being driven by both the increase in the availability of inexpensive computing devices and image sensors as well as the general inefficiency of manual surveillance and monitoring. In particular, the ultimate goal for many visual surveillance systems is to provide automatic activity recognition for events at a given site. A higher level of understanding of these activities requires certain lower-level computer vision tasks to be performed. So in this paper, we propose an intelligent activity recognition model that uses a structure learning method and a classification method. The structure learning method is provided as a K2-learning algorithm that generates Bayesian networks of causal relationships between sensors for a given activity. The statistical characteristics of the sensor values and the topological characteristics of the generated graphs are learned for each activity, and then a neural network is designed to classify the current activity according to the features extracted from the multiple sensor values that have been collected. Finally, the proposed method is implemented and tested by using PETS2013 benchmark data.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2012년도 학술발표회
• /
• pp.195-195
• /
• 2012

인공신경망 모형은 복잡하고 비선형의 입력과 출력 관계를 잘 반영할 수 있어서 유출 모델링에 널리 적용되어 왔다. 그러나 인공신경망 모형은 강우나 유역특성의 공간적 분포를 반영하는 것이 어려우며 물리적 개념이 결여되어 있는 단점이 있다. 본 연구에서는 유역특성과 물리적 개념을 반영할 수 있는 물리기반 모형과 인공신경망 모형의 장점들을 조합하여 물리기반 모형의 일 유출량 해석 능력을 향상하기 위하여 SWAT 모형과 인공신경망(ANN)을 연계하였다. SWAT-ANN 연계모형은 두 단계로 구성되어 진다. 첫 번째 단계에서는 관측 자료를 이용하여 SWAT 모형을 보정한다. 두 번째 단계에서는 첫 번째 단계에서 계산한 소유역별 SWAT 모형의 유출결과를 ANN의 입력자료로 이용하여 SWAT-ANN 연계모형을 구축한다. SCE-UA 최적화 방법을 적용하여 SWAT 모형의 매개변수들을 보정하였고, ANN 학습은 3층의 feed-forward 역전파 알고리즘에 기초한 Bayesian Regularization 방법을 적용하였다. ANN 은닉층의 뉴런 및 전달함수는 시행착오를 통하여 적절한 ANN 구조를 설정하여 SWAT-ANN 연계모형의 일유출량을 모의하였다. 여러 가지 통계적 오차기준을 이용하여 보청천 유역에서 SWAT-ANN 연계모형의 결과와 SWAT 단독 모형의 결과를 비교하였다. SWAT-ANN 연계모형이 SWAT 단독 모형보다 더 우수한 결과를 나타내어 일 유출량 해석을 위한 SWAT-ANN 연계모형의 유용성을 확인할 수 있었다.