• 한국전자파학회논문지
• /
• 제26권4호
• /
• pp.404-413
• /
• 2015

대공 레이다에서 표적의 분류는 대 탄도탄 모드 수행의 가장 중요한 부분 중 하나이다. 대 탄도탄 모드에서는 항공기와 탄도탄을 분류하여 각 표적에 따른 대응 방법을 결정한다. 표적 분류의 속도와 정확도는 적의 공격에 대한 대응 능력과 직접적인 관련이 있으므로, 효율적이고 정확한 표적 분류 알고리즘이 필수적이다. 일반적으로, 레이다는 표적 분류를 위해 JEM(Jet Engine Modulation) 및 HRR(High Range Resolution), ISAR(Inverse Synthetic Array Radar) 영상 등을 사용하는데, 이러한 기법들은 표적 분류를 위한 별도의(광대역 등) 레이다 파형과 DB(Data Base) 및 분류 알고리즘을 요구한다. 본 논문은 별도의 파형 없이 실제 다기능 레이다에서 적용 가능한 표적 분류 기법을 제안한다. 특징 벡터로 추적 시 얻은 표적의 운동학적인 특징(kinematics features)을 이용하여 레이다 하드웨어 및 시간 관점에서 레이다 자원을 아끼고, 구현이 간단하여 빠르고 상대적으로 정확한 퍼지 논리(fuzzy logic)를 분류 알고리즘으로 사용하여 실제 환경에서의 적용성을 높였다. 항공기의 실측 데이터와 탄도탄의 모의 신호를 사용하여 제안한 분류 알고리즘의 성능과 적합성을 증명하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5015-5038
• /
• 2018

In this paper, a novel spectral-spatial joint sparse representation algorithm for hyperspectral image classification is proposed based on multi-layer superpixels in various scales. Superpixels of various scales can provide complete yet redundant correlated information of the class attribute for test pixels. Therefore, we design a joint sparse model for a test pixel by sampling similar pixels from its corresponding superpixels combinations. Firstly, multi-layer superpixels are extracted on the false color image of the HSI data by principal components analysis model. Secondly, a group of discriminative sampling pixels are exploited as reconstruction matrix of test pixel which can be jointly represented by the structured dictionary and recovered sparse coefficients. Thirdly, the orthogonal matching pursuit strategy is employed for estimating sparse vector for the test pixel. In each iteration, the approximation can be computed from the dictionary and corresponding sparse vector. Finally, the class label of test pixel can be directly determined with minimum reconstruction error between the reconstruction matrix and its approximation. The advantages of this algorithm lie in the development of complete neighborhood and homogeneous pixels to share a common sparsity pattern, and it is able to achieve more flexible joint sparse coding of spectral-spatial information. Experimental results on three real hyperspectral datasets show that the proposed joint sparse model can achieve better performance than a series of excellent sparse classification methods and superpixels-based classification methods.

• 한국컴퓨터정보학회논문지
• /
• 제27권11호
• /
• pp.29-38
• /
• 2022

본 논문에서는 멀티 센서가 장착된 스마트 인솔로 측정한 보행 데이터에 대해 앙상블 딥러닝 네트워크를 이용하여 보행의 타입을 분류하는 시스템을 제안한다. 보행 타입 분류 시스템은 인솔에 의해 측정된 데이터를 정규화하는 부분과 딥러닝 네트워크를 이용하여 보행의 특징을 추출하는 부분, 그리고 추출된 특징을 입력으로 보행의 타입을 분류하는 부분으로 구성되어 있다. 서로 다른 특성을 가지는 CNN과 LSTM을 기반으로 하는 네트워크를 독립적으로 학습하여 두 종류의 보행 특징 맵을 추출하였으며, 각각의 분류 결과를 결합하여 최종적인 앙상블 네트워크의 분류 결과를 도출하였다. 20~30대 성인의 걷기, 뛰기, 빠르게 걷기, 계단 오르기와 내려가기, 언덕 오르기와 내려가기의 7종류의 보행에 대해, 스마트 인솔을 이용하여 실측한 멀티 센서 데이터를 제안한 앙상블 네트워크로 분류해 본 결과 90% 이상의 높은 분류율을 보이는 것을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• 한국음향학회지
• /
• 제13권4호
• /
• pp.5-11
• /
• 1994

본 논문에서는 형식별 블럭분할에 기초한 다중신경망과 퍼지추론에 의한 한글 형식분류에 대해 연구하였다. 효과적인 자모분류를 위해 입력문자에 대해서 한글의 각 형식을 구성하는 자모의 영역으로 분할하는 블럭분할방법을 제한하였으며, 분할된 블럭이 형식에 따라 적응적으로 변화할 수 있도록 하였다. 또한 분류율의 향상을 위해 전체신경망과 부분신경망으로 이루어진 다중신경망을 구성하였으며, 퍼지추론에 의해 한글 형식을 판정하였다. 비교, 실험을 통하여 제안된 방법의 타당성을 검증하였으며, $92.6\%$의 분류율을 나타내므로서 유효성을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.392-412
• /
• 2018

Due to the semantic gap problem across different modalities, automatically retrieval from multimedia information still faces a main challenge. It is desirable to provide an effective joint model to bridge the gap and organize the relationships between them. In this work, we develop a deep image annotation and classification by fusing multi-modal semantic topics (DAC_mmst) model, which has the capacity for finding visual and non-visual topics by jointly modeling the image and loosely related text for deep image annotation while simultaneously learning and predicting the class label. More specifically, DAC_mmst depends on a non-parametric Bayesian model for estimating the best number of visual topics that can perfectly explain the image. To evaluate the effectiveness of our proposed algorithm, we collect a real-world dataset to conduct various experiments. The experimental results show our proposed DAC_mmst performs favorably in perplexity, image annotation and classification accuracy, comparing to several state-of-the-art methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• 전기학회논문지
• /
• 제61권5호
• /
• pp.757-762
• /
• 2012

In this paper, the multi feature extraction algorithm for estimation of wrist movements based on Electromyogram(EMG) is proposed. For the extraction of precise features from the EMG signals, the difference absolute mean value(DAMV), the mean absolute value(MAV), the root mean square(RMS) and the difference absolute standard deviation value(DASDV) to consider amplitude characteristic of EMG signals are used. We figure out a more accurate feature-set by combination of two features out of these, because of multi feature extraction algorithm is more precise than single feature method. Also, for the motion classification based on EMG, the linear discriminant analysis(LDA), the quadratic discriminant analysis(QDA) and k-nearest neighbor(k-NN) are used. We implemented a test targeting twenty adult male to identify the accuracy of EMG pattern classification of wrist movements such as up, down, right, left and rest. As a result of our study, the LDA, QDA and k-NN classification method using feature-set with MAV and DASDV showed respectively 87.59%, 89.06%, 91.75% accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2590-2606
• /
• 2017

Generally, research of classical image classification algorithms assume that training data and testing data are derived from the same domain with the same distribution. Unfortunately, in practical applications, this assumption is rarely met. Aiming at the problem, a domain adaption image classification approach based on multi-sparse representation is proposed in this paper. The existences of intermediate domains are hypothesized between the source and target domains. And each intermediate subspace is modeled through online dictionary learning with target data updating. On the one hand, the reconstruction error of the target data is guaranteed, on the other, the transition from the source domain to the target domain is as smooth as possible. An augmented feature representation produced by invariant sparse codes across the source, intermediate and target domain dictionaries is employed for across domain recognition. Experimental results verify the effectiveness of the proposed algorithm.

• 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.