• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.61-68
• /
• 2021

Recently, various technologies that use machine learning to classify malicious code have been studied. In order to enhance the effectiveness of machine learning, it is most important to extract properties to identify malicious codes and normal binaries. In this paper, we propose a feature extraction method for use in machine learning using recursive methods. The proposed method selects the final feature using recursive methods for individual features to maximize the performance of machine learning. In detail, we use the method of extracting the best performing features among individual feature at each stage, and then combining the extracted features. We extract features with the proposed method and apply them to machine learning algorithms such as Decision Tree, SVM, Random Forest, and KNN, to validate that machine learning performance improves as the steps continue.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.4
• /
• pp.3-13
• /
• 1998

본 논문은 음성 다이어링 시스템을 구현하기 위한 한국어 단독 숫자음 및 연속 숫 자음 인식에 관한 것이다. 단독 숫자음의 인식은 미지의 입력 음성을 재귀 신경망을 이용하 여 모델링된 각 모델에 인가하고, 신경 회로망의 출력 노드의 상태열을 검사하여 적절한 상 태 전이를 하며 최고의 확률값을 출력하는 모델을 인식된 결과로 출력한다. 연속 숫자음의 인식은 미지의 연속 숫자음을 재귀 신경 회로망을 이용한 연속 숫자음 모델에 입력하고, 신 경 회로망의 출력에 대하여 적절한 상태 전이에 대한 검사와 레벨 빌딩(Level Building)을 수행하여 최소의 오차를 가지는 모델열을 인식된 결과로 출력한다. 재귀 신경 회로망을 이 용하여 음절 모델을 만드는 과정에서 재귀 노드는 예상치가 주어지지 않으므로 신경 회로망 의 학습에서 제외되어 현저한 학습 속도의 저하를 가져온다. 따라서 본 논문에서는 재귀 신 경 회로망의 학습 속도를 향상시키기 위한 2가지 방법을 제안 한다. 첫 번째는 재귀 신경 회로망의 재귀 노드의 예상치를 실험적으로 주어줌으로써 학습 속도의 향상을 도모하였다. 두 번째는 음절 모델의 출력노드의 개수와 음절 모델의 세그먼트 경계를 알고리듬을 이용하 여 자동적으로 조절하였다. 실험결과, 단독어의 경우 음절 '에'에 포함하는 한국어 11개의 숫 자음에 대하여 화자 종속의 경우 97.3%, 화자 독립의 경우 80.5%의 인식률을 얻었으며, 연 속 숫자음의 경우는 21종류의 연속 숫자음에 대하여 화자 종속에서 88.2%, 화자 독립의 경 우 81.3%의 인식률을 얻을 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.142-147
• /
• 2012

본 논문에서는 신경망을 재귀적으로 사용하여 문장에서 지시 표현을 추출하고 분석하는 방법에 대해서 제안한다. 임의의 문장이 들어올 때, 문장을 구성하는 각 단어들은 통사론적 자질 벡터와 의미론적 자질 벡터로 나눌 수 있다. 이들 벡터들의 쌍을 인자로써 입력받는 신경망 구조를 제시할 수 있으며, 신경망의 출력 결과는 다시 재귀적으로 쌍인자 신경망에 입력으로써 주입된다. 신경망을 재귀적으로 학습시킴으로써, 문장 내의 지시 표현을 추출할 수 있다. 쌍인자 신경망 파싱 모델의 성능을 측정했고, 제안한 모델의 문제점과 가능성에 대해서 관찰하였다.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.61-73
• /
• 2024

Class imbalance is one of the significant challenges in deep learning tasks, particularly pronounced in areas with limited data. This study proposes a new approach that utilizes minimal labeled data for effectively classifying tomato leaf diseases. We introduced a recursive learning method using the YOLOv8 model. By utilizing the detection predictions of images on the training data as additional training data, the number of labeled data is progressively increased. Unlike conventional data augmentation and up-down sampling techniques, this method seeks to fundamentally solve the class imbalance problem by maximizing the utility of actual data. Based on the secured labeled data, tomato leaves were extracted, and diseases were classified using the EfficientNet model. This process achieved a high accuracy of 98.92%. Notably, a 12.9% improvement compared to the baseline was observed in the detection of Late blight diseases, which has the least amount of data. This research presents a methodology that addresses data imbalance issues while offering high-precision disease classification, with the expectation of application to other crops.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.112-112
• /
• 2020

하천에서 유해화학물질 유입 사고 발생 시 수환경 피해를 최소화하기 위해 신속한 초기 대응이 필요하다. 따라서, 본 연구에서는 수환경 화학사고 대응 시스템 구축을 위해 하천 실시간 모니터링 지점에서 관측된 유해화학물질의 농도 자료를 이용하여 발생원의 유입 지점과 유입량을 역추적하는 프레임워크를 개발하였다. 본 연구에서 제시하는 프레임워크는 첫 번째로 하천 저장대 모형(Transient Storage Zone Model; TSM)과 HEC-RAS 모형을 이용하여 다양한 유량의 수리 조건에서 화학사고 시나리오를 생성하는 단계, 두번째로 생성된 시나리오의 유입 지점과 유입량에 대한 시간-농도 곡선 (BreakThrough Curve; BTC)을 21개의 곡선특징 (BTC feature)으로 추출하는 단계, 최종적으로 재귀적 특징 선택법(Recursive Feature Elimination; RFE)을 이용하여 의사결정나무 모형, 랜덤포레스트 모형, Xgboost 모형, 선형 서포트 벡터 머신, 커널 서포트 벡터 머신 그리고 Ridge 모형에 대한 모형별 주요 특징을 학습하고 성능을 비교하여 각각 유입 위치와 유입 질량 예측에 대한 최적 모형 및 특징 조합을 제시하는 단계로 구축하였다. 또한, 현장 적용성 제고를 위해 시간-농도 곡선을 2가지 경우 (Whole BTC와 Fractured BTC)로 가정하여 기계학습 모형을 학습시켜 모의결과를 비교하였다. 제시된 프레임워크의 검증을 위해서 낙동강 지류인 감천에 적용하여 모형을 구축하고 시나리오 자료 기반 검증과 Rhodamine WT를 이용한 추적자 실험자료를 이용한 검증을 수행하였다. 기계학습 모형들의 비교 검증 결과, 각 모형은 가중항 기반과 불순도 감소량 기반 특징 중요도 산출 방식에 따라 주요 특징이 상이하게 산출되었으며, 전체 시간-농도 곡선 (WBTC)과 부분 시간-농도 곡선 (FBTC)별 최적 모형도 다르게 산출되었다. 유입 위치 정확도 및 유입 질량 예측에 대한 R²는 대부분의 모형이 90% 이상의 우수한 결과를 나타냈다.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.415-423
• /
• 2018

In recent years, Computer-based learning, such as machine learning and deep learning in the computer field, is attracting attention. They start learning from the lowest level and propagate the result to the highest level to calculate the final result. Research literature has shown that systematic learning and growth can yield good results. However, systematic models based on systematic models are hard to find, compared to various and extensive research attempts. To this end, this paper proposes the first TNT(Transitive Nested Triangle)model, which is a growth and fusion model that can be used in various aspects. This model can be said to be a recursive model in which each function formed through geometric forms an organic hierarchical relationship, and the result is used again as they grow and converge to the top. That is, it is an analytical method called 'Horizontal Sibling Merges and Upward Convergence'. This model is applicable to various aspects. In this study, we focus on explaining the TNT model.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.127-132
• /
• 2006

K-NN (k-Nearest Neighbors), which is a well-known instance-based learning algorithm, simply stores entire training patterns in memory, and uses a distance function to classify a test pattern. K-NN is proven to show satisfactory performance, but it is notorious formemory usage and lengthy computation. Various studies have been found in the literature in order to minimize memory usage and computation time, and NGE (Nested Generalized Exemplar) theory is one of them. In this paper, we propose RPA (Recursive Partition Averaging) and IRPA (Incremental RPA) which is an incremental version of RPA. RPA partitions the entire pattern space recursively, and generates representatives from each partition. Also, due to the fact that RPA is prone to produce excessive number of partitions as the number of features in a pattern increases, we present IRPA which reduces the number of representative patterns by processing the training set in an incremental manner. Our proposed methods have been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.3
• /
• pp.11-25
• /
• 2012

We present the method to infer Context-Free Grammars by applying genetic algorithm to the Binary Third-order Recurrent Neural Networks(BTRNN). BTRNN is a multiple-layered architecture of recurrent neural networks, each of which is corresponding to an input symbol, and is combined with external stack. All parameters of BTRNN are represented as binary numbers and each state transition is performed with any stack operation simultaneously. We apply Genetic Algorithm to BTRNN chromosomes and obtain the optimal BTRNN inferring context-free grammar of positive and negative input patterns. This proposed method infers BTRNN, which includes the number of its states equal to or less than those of existing methods of Discrete Recurrent Neural Networks, with less examples and less learning trials. Also BTRNN is superior to the recent method of chromosomes representing grammars at recognition time complexity because of performing deterministic state transitions and stack operations at parsing process. If the number of non-terminals is p, the number of terminals q, the length of an input string k, and the max number of BTRNN states m, the parallel processing time is O(k) and the sequential processing time is O(km).

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.11-17
• /
• 2007

One of the popular methods used for pattern classification is the MBR (Memory-Based Reasoning) algorithm. Since it simply computes distances between a test pattern and training patterns or hyperplanes stored in memory, and then assigns the class of the nearest training pattern, it cannot explain how the classification result is obtained. In order to overcome this problem, we propose an incremental teaming algorithm based on RPA (Recursive Partition Averaging) to extract IF-THEN rules that describe regularities inherent in training patterns. But rules generated by RPA eventually show an overfitting phenomenon, because they depend too strongly on the details of given training patterns. Also RPA produces more number of rules than necessary, due to over-partitioning of the pattern space. Consequently, we present the IREA (Incremental Rule Extraction Algorithm) that overcomes overfitting problem by removing useless conditions from rules and reduces the number of rules at the same time. We verify the performance of proposed algorithm using benchmark data sets from UCI Machine Learning Repository.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.