• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3730-3744
• /
• 2020

This study proposes a deep learning-based evolutionary recommendation model for heterogeneous big data integration, for which collaborative filtering and a neural-network algorithm are employed. The proposed model is used to apply an individual's importance or sensory level to formulate a recommendation using the decision-making feedback. The evolutionary recommendation model is based on the Deep Neural Network (DNN), which is useful for analyzing and evaluating the feedback data among various neural-network algorithms, and the DNN is combined with collaborative filtering. The designed model is used to extract health information from data collected by the Korea National Health and Nutrition Examination Survey, and the collaborative filtering-based recommendation model was compared with the deep learning-based evolutionary recommendation model to evaluate its performance. The RMSE is used to evaluate the performance of the proposed model. According to the comparative analysis, the accuracy of the deep learning-based evolutionary recommendation model is superior to that of the collaborative filtering-based recommendation model.

• ETRI Journal
• /
• 제42권5호
• /
• pp.686-699
• /
• 2020

In this paper, we propose a supervised-learning-based spatial performance prediction (SLPP) framework for next-generation heterogeneous communication networks (HCNs). Adaptive asset placement, dynamic resource allocation, and load balancing are critical network functions in an HCN to ensure seamless network management and enhance service quality. Although many existing systems use measurement data to react to network performance changes, it is highly beneficial to perform accurate performance prediction for different systems to support various network functions. Recent advancements in complex statistical algorithms and computational efficiency have made machine-learning ubiquitous for accurate data-based prediction. A robust network performance prediction framework for optimizing performance and resource utilization through a linear discriminant analysis-based prediction approach has been proposed in this paper. Comparison results with different machine-learning techniques on real-world data demonstrate that SLPP provides superior accuracy and computational efficiency for both stationary and mobile user conditions.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.457-464
• /
• 2021

빅데이터 시대의 도래는 데이터에서 스스로 규칙을 배우는 딥러닝의 비약적인 발전을 가능하게 하였으며, 특히 CNN 알고리즘이 거둔 성과는 모델의 구조를 넘어 소스 데이터 자체를 조정하는 수준에 이르렀다. 하지만 기존의 이미지 처리 방법은 이미지 데이터 자체를 다룰 뿐, 해당 이미지가 생성된 이질적 환경을 충분히 고려하지 않았다. 이질적 환경에서 촬영된 이미지는 동일한 정보임에도 촬영 환경에 따라 각 이미지의 특징(Feature)이 상이하게 표현될 수 있다. 이는 각 이미지가 갖는 상이한 환경 정보뿐 아니라 이미지 고유의 정보조차 서로 상이한 특징으로 표현되며, 이로 인해 이들 이미지 정보는 서로 잡음(Noise)으로 작용해 모델의 분석 성능을 저해할 수 있음을 의미한다. 따라서 본 논문은 이질적 환경에서 생성된 이미지 데이터들을 동시에 사용하는 앤드-투-앤드(End-To-End) 구조의 적대적 학습(Adversarial Learning) 기반의 이미지 색 항상성 모델 성능 향상 방안을 제안한다. 구체적으로 제안 방법론은 이미지가 촬영된 환경인 도메인을 예측하는 '도메인 분류기'와 조명 값을 예측하는 '조명 예측기'의 상호 작용으로 동작하며, 도메인 분류의 성능을 떨어뜨리는 방향의 학습을 통해 도메인 특성을 제거한다. 제안 방법론의 성능을 평가하기 위해 이질적 환경에서 촬영된 이미지 데이터 셋 7,022장에 대한 색 항상성 실험을 수행한 결과, 제안 방법론이 기존 방법론에 비해 Angular Error 측면에서 우수한 성능을 나타냄을 확인하였다.

• 인터넷정보학회논문지
• /
• 제24권6호
• /
• pp.1-11
• /
• 2023

Federated learning (FL) is a ground breaking machine learning paradigm that allow smultiple participants to collaboratively train models in a cloud environment, all while maintaining the privacy of their raw data. This approach is in valuable in applications involving sensitive or geographically distributed data. However, one of the challenges in FL is dealing with heterogeneous and non-independent and identically distributed (non-IID) data across participants, which can result in suboptimal model performance compared to traditionalmachine learning methods. To tackle this, we introduce FedGCD, a novel FL algorithm that employs Graph Neural Network (GNN)-based community detection to enhance model convergence in federated settings. In our experiments, FedGCD consistently outperformed existing FL algorithms in various scenarios: for instance, in a non-IID environment, it achieved an accuracy of 0.9113, a precision of 0.8798,and an F1-Score of 0.8972. In a semi-IID setting, it demonstrated the highest accuracy at 0.9315 and an impressive F1-Score of 0.9312. We also introduce a new metric, nonIIDness, to quantitatively measure the degree of data heterogeneity. Our results indicate that FedGCD not only addresses the challenges of data heterogeneity and non-IIDness but also sets new benchmarks for FL algorithms. The community detection approach adopted in FedGCD has broader implications, suggesting that it could be adapted for other distributed machine learning scenarios, thereby improving model performance and convergence across a range of applications.

• International journal of advanced smart convergence
• /
• 제8권1호
• /
• pp.75-81
• /
• 2019

Data imbalance problem is common and causes serious problem in machine learning process. Sampling is one of the effective methods for solving data imbalance problem. Over-sampling increases the number of instances, so when over-sampling is applied in imbalanced data, it is applied to minority instances. Under-sampling reduces instances, which usually is performed on majority data. We apply under-sampling and over-sampling to imbalanced data and generate sampled data sets. From the generated data sets from sampling and original data set, we construct a heterogeneous ensemble of classifiers. We apply five different algorithms to the heterogeneous ensemble. Experimental results on an intrusion detection dataset as an imbalanced datasets show that our approach shows effective results.

• 한국인터넷방송통신학회논문지
• /
• 제18권5호
• /
• pp.171-177
• /
• 2018

최근 많은 이미지 데이터 셋들은 일반적인 특성을 추출하기 위한 다양한 데이터 클래스와 특징을 가지고 있다. 하지만 이러한 다양한 데이터 클래스와 특징으로 인해 해당 데이터 셋으로 훈련된 물체 검출 딥러닝 모델은 데이터 특성이 다른 환경에서 좋은 성능을 내지 못하는 단점을 보인다. 이 논문에서는 하위 카테고리 기반 물체 검출 방법과 오픈셋 물체 검출 방법을 이용하여 이를 극복하고, 강인한 물체 검출 딥러닝 모델을 훈련하기 위해 능동 준지도 학습 (Active Semi-Supervised Learning)을 이용한 다중 분기 트리 구조를 제안한다. 우리는 이 구조를 이용함으로써 데이터 특성이 다른 환경에서 적응할 수 있는 모델을 가질 수 있고, 나아가 이 모델을 이용하여 이전의 모델보다 높은 성능을 확보 할 수 있다.

• Genomics & Informatics
• /
• 제17권4호
• /
• pp.39.1-39.20
• /
• 2019

Analyzing patterns in data points embedded in linear and non-linear feature spaces is considered as one of the common research problems among different research areas, for example: data mining, machine learning, pattern recognition, and multivariate analysis. In this paper, data points are heterogeneous sets of biosequences (composite data points). A composite data point is a set of ordinary data points (e.g., set of feature vectors). We theoretically extend the derivation of the largest generalized eigenvalue-based distance metric D_ij(γ₁) in any linear and non-linear feature spaces. We prove that D_ij(γ₁) is a metric under any linear and non-linear feature transformation function. We show the sufficiency and efficiency of using the decision rule $\bar{{\delta}}_{{\Xi}i}$(i.e., mean of D_ij(γ₁)) in classification of heterogeneous sets of biosequences compared with the decision rules min_𝚵iand median_𝚵i. We analyze the impact of linear and non-linear transformation functions on classifying/clustering collections of heterogeneous sets of biosequences. The impact of the length of a sequence in a heterogeneous sequence-set generated by simulation on the classification and clustering results in linear and non-linear feature spaces is empirically shown in this paper. We propose a new concept: the limiting dispersion map of the existing clusters in heterogeneous sets of biosequences embedded in linear and nonlinear feature spaces, which is based on the limiting distribution of nucleotide compositions estimated from real data sets. Finally, the empirical conclusions and the scientific evidences are deduced from the experiments to support the theoretical side stated in this paper.

• 지능정보연구
• /
• 제22권4호
• /
• pp.193-215
• /
• 2016

최근 다양한 소셜 네트워크 서비스의 증가로 인해 사용자들은 각자의 목적 및 취향에 따라 여러 매체를 동시에 이용하는 경향을 보이고 있다. 또한 특정 주제에 대한 정보를 수집할 때에도 소셜 네트워크 서비스, 인터넷 뉴스, 블로그 등 여러 매체를 동시에 활용하는 것이 일반적이다. 하지만 다양한 매체를 통해 유통되는 문서들은 서로 유사한 주제, 심지어는 동일한 내용을 다루더라도 각 매체 별 정책 및 기준에 따라 각기 다른 카테고리로 관리되고 있으며, 이는 이종 매체를 아우르는 범위에서 특정 카테고리에 대한 탐색을 수행하고자 하는 시도에 걸림돌로 작용하고 있다. 이러한 제약을 극복하기 위해, 본 연구에서는 기존 매체 고유의 카테고리 체계는 그대로 유지하면서 이종 매체 간 카테고리 매핑을 수행하는 방법을 제시한다. 즉, 개별 문서를 다양한 매체의 관점에서 재분류하고 이러한 결과를 문서에 2차원 레이블로 저장함으로써, 이종 매체에 속한 다양한 문서들을 마치한 매체에 속한 것과 같이 동일한 카테고리 기준으로 탐색할 수 있는 논리적 장치를 제안한다. 본 논문에서는 국내 인터넷 뉴스 포털 사이트 두 곳의 뉴스 기사 6,000건에 대해 제안 방법론을 적용한 실험을 통해 각 기사에 매체와 카테고리 정보로 구성된 2차원 레이블을 부여하였으며, 매체 간, 지도 학습과 준지도 학습 간, 동질 학습 데이터와 이질학습 데이터 간의 정확도 비교 실험을 수행하였다. 특히 매우 흥미롭게도, 일부 카테고리에서 이질 학습 데이터를 사용한 준지도 학습의 분류 정확도가 지도 학습 및 동질 학습 데이터를 사용한 준지도 학습의 분류 정확도보다 높게 나타나는 현상을 발견하였다.