• ETRI Journal
• /
• 제43권2호
• /
• pp.272-287
• /
• 2021

This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.

• 정보과학회 논문지
• /
• 제44권4호
• /
• pp.433-438
• /
• 2017

오늘날의 네트워크는 고속화와 유비쿼터스 환경으로 인해 다양한 응용이 급속도로 생성되고 있으며 네트워크 트래픽도 매우 복잡해지고 있다. 이에 효율적인 네트워크 운용 및 관리를 위한 구체적인 단위의 트래픽 분류가 필수적이다. 다양한 트래픽 분류 방법이 연구되고 있는 가운데 아직 트래픽을 완벽하게 분류해내는 방법론은 개발되지 않은 실정이다. 이에 본 논문에서는 네트워크 플로우의 연관성 모델을 정의하고 이를 기반으로 트래픽을 분류하는 방법을 제안한다. 트래픽 분류를 위한 네트워크 플로우의 연관성 모델은 크게 유사성 모델과 연결성 모델로 이루어진다. 제안하는 방법론을 효과적으로 적용하기 위한 방안을 제시하며 실험을 통해 본 분류 방법론이 높은 정확도와 분석률의 방법론이라는 것을 증명한다.

• 대한원격탐사학회지
• /
• 제6권1호
• /
• pp.11-24
• /
• 1990

This is the study about the meteorological satellite cloud image classification by objective methods. For objective cloud classification, linear discriminant analysis was tried. In the linear discriminant analysis 27 cloud characteristic parameters were retrieved from GMS infrared image data. And, linear cloud classification model was developed from major parameters and cloud type coefficients. The model was applied to GMS IR image for weather forecasting operation and cloud image was classified into 5 types such as Sc, Cu, CiT, CiM and Cb. The classification results were reasonably compared with real image.

• 품질경영학회지
• /
• 제40권4호
• /
• pp.453-466
• /
• 2012

Purpose: The Kano model has been widely accepted as a method for classifying quality attributes for almost three decades since its introduction. However, the wordings of the five alternatives in the Kano's questionnaire has been criticised for unclear and confusable meanings. New wordings of the five alternatives are proposed in this paper. Methods: To evaluate the effectiveness of the proposed wordings, we classify 30 quality attributes of smartphones using the conventional wordings and the proposed wordings respectively. The two classification results are compared with the direct classification results by undergraduate students who learned the Kano model. Results: The classification results using the proposed wordings are much more consistent with the direct classification results than those using the conventional wordings. Conclusion: The proposed wordings are less confusable and easy to understand, and thus it results in more consistent with the direct classification.

• 전기전자학회논문지
• /
• 제26권4호
• /
• pp.639-646
• /
• 2022

딥러닝의 발전으로 딥러닝 모델들이 이미지 인식, 음성 인식 등 여러 분야에서 활발하게 사용 중이다. 하지만 이 딥러닝을 효과적으로 사용하기 위해서는 대형 데이터 세트가 필요하지만 이를 구축하기에는 많은 시간과 노력 그리고 비용이 필요하다. 본 논문에서는 웹 크롤링이라는 이미지 수집 방법을 통해서 이미지를 수집하고 데이터 전처리 과정을 거쳐 이미지 분류 모델에 사용할 수 있게 데이터 세트를 구축한다. 더 나아가 전이학습을 이미지 분류 모델에 접목해 카테고리값을 넣어 자동으로 이미지를 분류할 수 있는 경량화된 모델과 적은 훈련 시간 및 높은 정확도를 얻을 수 있는 이미지 분류 모델을 제안한다.

• 한국정보통신학회논문지
• /
• 제10권2호
• /
• pp.398-405
• /
• 2006

인간은 관심을 가지고 있는 영역(ROI)에 대하여 선택적으로 주의를 집중하여 사물의 특징 을 인식하게 된다. 본 연구에서는 이러한 인간의 선택적 지각 능력을 적용한 패턴 분류 모델을 제안한다. 먼저 일반적인 클러스터링 알고리즘에 의해 입력 패턴들을 대략적으로 분류하여 참조 클러스터 패턴을 형성하고, 생성된 클러스터의 참조 패턴들을 상호 연관시켜 선택적 지각맵(SPM : Selective Perception Map)을 구성한다. 패턴 분류 및 인식 과정에서는 생성된 SPM을 입력 패턴과 참조 패턴과의 거리 계산에서 가중치로 적용함으로써 인간의 선택적 지각 능력을 패턴 분류에 반영하게 된다. 다양하게 변형된 인쇄체 숫자 및 필기체 숫자 데이터(MNIST)를 통해 실험해 본 결과 SPM을 사용한 패턴 분류 모델이 효과적임을 증명하였다.

• 한국경영과학회지
• /
• 제26권4호
• /
• pp.55-70
• /
• 2001

Artificial neural network(ANN) models have been widely used for the classification problems in business such as bankruptcy prediction, credit evaluation, etc. Although the application of ANN to classification of consumers＇ choice behavior is a promising research area, there have been only a few researches. In general, most of the researches have reported that the classification performance of the ANN models were better than conventional statistical model Because the survey data on consumer behavior may include much noise and missing data, ANN model will be more robust than conventional statistical models welch need various assumptions. The purpose of this paper is to study the potential of the ANN model for forecasting consumers＇ choice behavior based on survey data. The data was collected by questionnaires to the shoppers of department stores and discount stores. Then the correct classification rates of the ANN models for the training and test sample with that of multiple discriminant analysis(MDA) and logistic regression(Logit) model. The performance of the ANN models were betted than the performance of the MDA and Logit model with respect to correct classification rate. By using input variables identified as significant in the stepwise MDA, the performance of the ANN models were improved.

• 품질경영학회지
• /
• 제51권1호
• /
• pp.119-129
• /
• 2023

Purpose: This study proposes a classification model for implementing condition-based maintenance (CBM) by monitoring the real-time status of a machine using acceleration sensor data collected from a vehicle. Methods: The classification model's performance was improved by applying Fourier transform to convert the acceleration sensor data from the time domain to the frequency domain. Additionally, the Generative Adversarial Network (GAN) algorithm was used to augment images and further enhance the classification model's performance. Results: Experimental results demonstrate that the GAN algorithm can effectively serve as an image augmentation technique to enhance the performance of the classification model. Consequently, the proposed approach yielded a significant improvement in the classification model's accuracy. Conclusion: While this study focused on the effectiveness of the GAN algorithm as an image augmentation method, further research is necessary to compare its performance with other image augmentation techniques. Additionally, it is essential to consider the potential for performance degradation due to class imbalance and conduct follow-up studies to address this issue.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.655-657
• /
• 2021

인공지능 알고리즘을 이용한 유방암의 조기진단에 관련된 연구는 최근들어 활발하게 진행되고 있으나, 사용자의 목적에 맞는 처리속도 및 정확도 등에 다양한 한계점을 보인다. 이러한 문제를 해결하기 위해, 본 논문에서는 ImageNet에서 학습된 ResNet 모델을 현미경 기반 암세포 이미지에서 활용이 가능한 다단계 전이 학습을 제안하고, 이를 다시 전이 학습하여 초음파 유방암 영상을 양성 및 악성으로 분류하는 실험을 진행하였다. 제안된 다단계 전이 학습 알고리즘은 초음파 유방암 영상을 분류하였을 때 96% 이상의 정확도를 보였으며, 향후 암 세포주 및 실시간 영상처리 등의 추가를 통해 보다 높은 활용도와 정확도를 보일 것으로 기대한다.