• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.23-26
• /
• 2022

딥 러닝 모델은 블랙 박스 (Black Box) 모델로 예측에 대한 근거를 제시하지 못해 신뢰성이 떨어지는 단점이 존재한다. 이를 해결하기 위해 딥 러닝 모델에 설명력을 부여하는 설명 가능한 인공지능 (XAI) 분야 연구가 활발하게 이루어지고 있다. 본 논문에서는 모델 예측을 프로토타입을 통해 설명하는 딥 러닝 모델을 제시한다. 즉, "주어진 이미지는 티셔츠인데, 그 이유는 티셔츠를 대표하는 모양의 프로토타입과 닮았기 때문이다."의 형태로 딥 러닝 모델을 설명한다. 해당 모델은 Encoder, Prototype Layer, Classifier로 구성되어 있다. Encoder는 Feature를 추출하는 데 활용하고 Classifier를 통해 분류 작업을 수행한다. 모델이 제시하는 분류 결과를 설명하기 위해 Prototype Layer에서 가장 유사한 프로토타입을 찾아 설명을 제시한다. 실험 결과 프로토타입 생성 기반 설명 모델은 기존 이미지 분류 모델과 유사한 예측 정확도를 보였고, 예측에 대한 설명력까지 확보하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.29-36
• /
• 2022

In deep learning classification tasks, most models frequently assume that all labels are available for the training datasets. As such strategies to learn new concepts from unlabeled datasets are scarce. In fingerprint classification tasks, most of the fingerprint datasets are labelled using the subject/individual and fingerprint datasets labelled with finger type classes are scarce. In this paper, authors have developed approaches of classifying fingerprint images using the majorly known fingerprint classes. Our study provides a flexible method to learn new classes of fingerprints. Our classifier model combines both the clustering technique and use of deep learning to cluster and hence label the fingerprint images into appropriate classes. The K means clustering strategy explores the label uncertainty and high-density regions from unlabeled data to be clustered. Using similarity index, five clusters are created. Deep learning is then used to train a model using a publicly known fingerprint dataset with known finger class types. A prediction technique is then employed to predict the classes of the clusters from the trained model. Our proposed model is better and has less computational costs in learning new classes and hence significantly saving on labelling costs of fingerprint images.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.281-291
• /
• 2021

The Islamic jurisprudential legal system represents an essential component of the Islamic religion, that governs many aspects of Muslims' daily lives. This creates many questions that require interpretations by qualified specialists, or Muftis according to the main sources of legislation in Islam. The Islamic jurisprudence is usually classified into branches, according to which the questions can be categorized and classified. Such categorization has many applications in automated question-answering systems, and in manual systems in routing the questions to a specialized Mufti to answer specific topics. In this work we tackle the problem of automatic categorisation of Islamic jurisprudential legal questions using deep learning techniques. In this paper, we build a hierarchical deep learning model that first extracts the question text features at two levels: word and sentence representation, followed by a text classifier that acts upon the question representation. To evaluate our model, we build and release the largest publicly available dataset of Islamic questions and answers, along with their topics, for 52 topic categories. We evaluate different state-of-the art deep learning models, both for word and sentence embeddings, comparing recurrent and transformer-based techniques, and performing extensive ablation studies to show the effect of each model choice. Our hierarchical model is based on pre-trained models, taking advantage of the recent advancement of transfer learning techniques, focused on Arabic language.

• 대한원격탐사학회지
• /
• 제37권4호
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.225-234
• /
• 2019

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

• 한국컴퓨터정보학회논문지
• /
• 제25권3호
• /
• pp.27-32
• /
• 2020

본 논문에서는 금속스크랩이 쌓이는 스크랩박스의 적치 상태를 측정하는 알고리즘을 제안한다. 적치 상태 측정 문제를 다중 클래스 분류 문제로 정의하여, 딥러닝 기법을 이용해 스크랩박스 촬영 영상만으로 적치 상태를 구분하도록 하였다. Transfer Learning 방식으로 학습을 진행하였으며, 딥러닝 모델은 NASNet-A를 이용하였다. 더불어 분류 모델의 정확도를 높이기 위해 학습된 NASNet-A에 랜덤포레스트 분류기를 결합하였으며, 후처리를 통해 안전성을 높였다. 현장에서 수집된 4,195개의 데이터로 테스트한 결과 NASNet-A만 적용했을때 정확도 55%를 보였으며, 제안 방식인 Random Forest를 결합한 NASNet은 88%로 향상된 정확도를 달성하였다.

• Journal of Information Processing Systems
• /
• 제20권1호
• /
• pp.13-23
• /
• 2024

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

• 한국컴퓨터정보학회논문지
• /
• 제26권3호
• /
• pp.35-42
• /
• 2021

본 연구에서는 3차원 RGB-D Xtion2 카메라를 이용하여 보행자의 골격좌표를 추출한 결과를 바탕으로 동적인 특성(속도, 가속도)을 함께 고려하여 딥러닝 모델을 통해 사람을 인식하는 방법을 제안한다. 본 논문의 핵심목표는 RGB-D 카메라로 손쉽게 좌표를 추출하고 새롭게 생성한 동적인 특성을 기반으로 자체 고안한 1차원 합성곱 신경망 분류기 모델(1D-ConvNet)을 통해 자동으로 보행 패턴을 파악하는 것이다. 1D-ConvNet의 인식 정확도와 동적인 특성이 정확도에 미치는 영향을 알아보기 위한 실험을 수행하였다. 정확도는 F1 Score를 기준으로 측정하였고, 동적인 특성을 고려한 분류기 모델(JCSpeed)과 고려하지 않은 분류기 모델(JC)의 정확도 비교를 통해 영향력을 측정하였다. 그 결과 동적인 특성을 고려한 경우의 분류기 모델이 그렇지 않은 경우보다 F1 Score가 약 8% 높게 나타났다.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1387-1395
• /
• 2018

Core algorithm of deep learning Convolutional Neural Network(CNN) shows better performance than other machine learning algorithms. However, if there is not sufficient data, CNN can not achieve satisfactory performance even if the classifier is excellent. In this situation, it has been proven that the use of transfer learning can have a great effect. In this paper, we apply two transition learning methods(freezing, retraining) to three CNN models(ResNet-50, Inception-V3, DenseNet-121) and compare and analyze how the classification performance of CNN changes according to the methods. As a result of statistical significance test using various evaluation indicators, ResNet-50, Inception-V3, and DenseNet-121 differed by 1.18 times, 1.09 times, and 1.17 times, respectively. Based on this, we concluded that the retraining method may be more effective than the freezing method in case of transition learning in image classification problem.