• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2154-2168
• /
• 2022

Our work addresses the issues associated with usage of the semantic features by Bag of Words model, which requires construction of the dictionary. Extracting the relevant features and clustering them into code book or dictionary is computationally intensive and requires large storage area. Hence we propose to use a simple distribution of multiple shape based features, which is a mixture of gradients, radius and slope angles requiring very less computational cost and storage requirements but can serve as an equivalent image representative. The experimental work conducted on PASCAL VOC 2007 dataset exhibits marginally closer performance in terms of accuracy with the Bag of Word model using Self Organizing Map for clustering and very significant computational gain.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권4호
• /
• pp.277-284
• /
• 2012

Named entity recognition (NER) technique can play a crucial role in extracting information from the web. While NER systems with relatively high performances have been developed based on careful manipulation of terms with a statistical model, term mismatches often degrade the performance of such systems because the strings of all the candidate entities are not known a priori. Despite the importance of lexical-level term mismatches for NER systems, however, most NER approaches developed to date utilize only the term string itself and simple term-level features, and do not exploit the semantic features of terms which can handle the variations of terms effectively. As a solution to this problem, here we propose to match the semantic concepts of term units in restaurant named entities (NEs), where these units are automatically generated from multiple resolutions of a semantic tree. As a test experiment, we applied our restaurant NER scheme to 49,153 nouns in Korean restaurant web pages. Our scheme achieved an average accuracy of 87.89% when applied to test data, which was considerably better than the 78.70% accuracy obtained using the baseline system.

• 한국초등과학교육학회지:초등과학교육
• /
• 제40권1호
• /
• pp.66-80
• /
• 2021

This study is a case study that applies plant classification learning using machine learning to fourth graders in elementary school in online learning situations. In this study, a plant classification learning education program associated with 2015 revision science curriculum was developed by applying the Artificial Intelligence biological classification teaching Learning model. The study participants were 31 fourth graders who agreed to participate voluntarily. Plant classification learning using machine learning was applied six hours for three weeks. The results of this study are as follows. First, as a result of image analysis on artificial intelligence, participants were mainly aware of artificial intelligence as mechanical (27%), human (23%) and household goods (23%). Second, an artificial intelligence recognition survey by semantic discrimination found that artificial intelligence was recognized as smart, good, accurate, new, interesting, necessary, and diverse. Third, there was a difference between men and women in perception and emotion of artificial intelligence, and there was no difference in perception of the ability of artificial intelligence. Fourth, plant classification learning using machine learning in this study influenced changes in artificial intelligence perception. Fifth, plant classification learning using machine learning in this study had a positive effect on reasoning ability.

• 한국멀티미디어학회논문지
• /
• 제24권8호
• /
• pp.1026-1034
• /
• 2021

Tire wear and defect are important factors for safe driving condition. These defects are generally inspected by some specialized experts or very expensive equipments such as stereo depth camera and depth gauge. In this paper, we propose tire safety vision inspector based on deep neural network (DNN). The status of tire wear is categorized into three: 'safety', 'warning', and 'danger' based on depth of tire tread. We propose an attention mechanism for emphasizing the feature of tread area. The attention-based feature is concatenated to output feature maps of the last convolution layer of ResNet-101 to extract more robust feature. Through experiments, the proposed tire wear classification model improves 1.8% of accuracy compared to the existing ResNet-101 model. For detecting the tire defections, the developed tire defect detection model shows up-to 91% of accuracy using the Mask R-CNN model. From these results, we can see that the suggested models are useful for checking on the safety condition of working tire in real environment.

• Journal of Forest and Environmental Science
• /
• 제40권1호
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• ETRI Journal
• /
• 제44권3호
• /
• pp.413-425
• /
• 2022

The study of literary texts is one of the earliest disciplines practiced around the globe. Poetry is artistic writing in which words are carefully chosen and arranged for their meaning, sound, and rhythm. Poetry usually has a broad and profound sense that makes it difficult to be interpreted even by humans. The essence of poetry is Rasa, which signifies mood or emotion. In this paper, we propose a poetry classification-based approach to automatically extract similar poems from a repository. Specifically, we perform a novel Rasa-based classification of Hindi poetry. For the task, we primarily used lexical features in a bag-of-words model trained using the support vector machine classifier. In the model, we employed Hindi WordNet, Latent Semantic Indexing, and Word2Vec-based neural word embedding. To extract the rich feature vectors, we prepared a repository containing 37 717 poems collected from various sources. We evaluated the performance of the system on a manually constructed dataset containing 945 Hindi poems. Experimental results demonstrated that the proposed model attained satisfactory performance.

• International Journal of Knowledge Content Development & Technology
• /
• 제7권1호
• /
• pp.101-120
• /
• 2017

Healthcare professionals have edited many health questions (HQs) and their answers for healthcare consumers on the Internet. The HQs provide both readable and reliable health information, and hence retrieval of those HQs that are relevant to a given question is essential for health education and promotion through the Internet. However, retrieval of relevant HQs needs to be based on the recognition of the intention of each HQ, which is difficult to be done by predefining syntactic and semantic rules. We thus model the intention recognition problem as a text classification problem, and develop two techniques to improve a learning-based text classifier for the problem. The two techniques improve the classifier by location-based and area-based feature weightings, respectively. Experimental results show that, the two techniques can work together to significantly improve a Support Vector Machine classifier in both the recognition of HQ intentions and the retrieval of relevant HQs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1275-1292
• /
• 2021

As a fine-grained classification problem, aspect-level sentiment classification predicts the sentiment polarity for different aspects in context. To address this issue, researchers have widely used attention mechanisms to abstract the relationship between context and aspects. Still, it is difficult to effectively obtain a more profound semantic representation, and the strong correlation between local context features and the aspect-based sentiment is rarely considered. In this paper, a hybrid attention capsule network for aspect-level sentiment classification (ABASCap) was proposed. In this model, the multi-head self-attention was improved, and a context mask mechanism based on adjustable context window was proposed, so as to effectively obtain the internal association between aspects and context. Moreover, the dynamic routing algorithm and activation function in capsule network were optimized to meet the task requirements. Finally, sufficient experiments were conducted on three benchmark datasets in different domains. Compared with other baseline models, ABASCap achieved better classification results, and outperformed the state-of-the-art methods in this task after incorporating pre-training BERT.

• 감성과학
• /
• 제13권1호
• /
• pp.47-60
• /
• 2010

기존 웹 페이지 자동분류 연구는 일반적으로 학습 기반인 kNN(k-Nearest Neighbor), SVM(Support Vector Machine)과 통계 기반인 Bayesian classifier, NNA(Neural Network Algorithm)등 여러 종류의 분류작업에서 입증된 분류 기법을 사용하여 웹 페이지를 분류하였다. 하지만 인터넷 상의 방대한 양의 웹 페이지와 각 페이지로부터 나오는 많은 양의 자질들을 처리하기에는 공간적, 시간적 문제에 직면하게 된다. 그리고 분류 대상을 표현하기 위해 흔히 사용하는 단일(uni-gram) 자질 기반에서는 자질들 간의 관계 분석을 통해 자질에 정확한 의미를 부여하기 힘들다. 특히 본 논문의 분류 대상인 한글 웹 페이지의 자질인 한글 단어는 중의적인 의미를 가지는 경우가 많기 때문에 이러한 중의성이 분류 작업에 많은 영향을 미칠 수 있다. 잠재적 의미 분석 LSA(Latent Semantic Analysis) 분류기법은 선형 기법인 특이치 분해 SVD(Singular Value Decomposition)을 통해 행렬의 분해 및 차원 축소(dimension reduction)를 수행하여 대용량 데이터 집합의 분류를 효율적으로 수행하고, 또한 차원 축소를 통해 새로운 의미공간을 생성하여 자질들의 중의적 의미를 분석할 수 있으며 이 새로운 의미공간상에 분류 대상을 표현함으로써 분류 대상의 잠재적 의미를 분석할 수 있다. 하지만 LSA의 차원 축소는 전체 데이터의 표현 정도만을 고려할 뿐 분류하고자 하는 범주를 고려하지 않으며 또한 서로 다른 범주 간의 차별성을 고려하지 않기 때문에 축소된 차원 상에서 분류 시 서로 다른 범주 데이터간의 모호한 경계로 인해 안정된 분류 성능을 나타내지 못한다. 이에 본 논문은 새로운 의미공간(semantic space) 상에서 서로 다른 범주사이의 명확한 구분을 위한 특별한 차원 선택을 수행하여 최적의 차원 선택과 안정된 분류성능을 보이는 최적의 지도적 LSA을 소개한다. 제안한 지도적 LSA 방법은 기본 LSA 및 다른 지도적 LSA 방법들에 비해 저 차원 상에서 안정되고 더 높은 성능을 보였다. 또한 추가로 자질 생성 및 선택 시 불용어의 제거와 자질에 대한 가중치를 통계적인 학습을 통해 얻음으로써 더 높은 학습효과를 유도하였다.