• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• Journal of Korean Elementary Science Education
• /
• v.37 no.2
• /
• pp.219-231
• /
• 2018

This study surveyed the elementary school teachers' use of visual representations and their perceptions of the functions of visual representations in the teaching of electricity unit. A total of 110 elementary teachers who have experiences in teaching electricity unit responded to online survey. The result showed firstly that most of the teachers use visual representations in their teaching and it is mostly limited to those presented in textbooks or images that they can get easily from internet search. Secondly, elementary teachers thought that they have high ability in using visual representations and low ability in understanding students' visual presentation ability. Thirdly, visual representations are more often preferred to be used as teacher-centered ways than student-centered ways for motivating students and conceptual understanding. However, in case of scientific inquiry, both teacher-centered and student-centered ways were equally preferred. Lastly, the teachers' perceptions of the functions of visual representations were categorized into 'teaching-instrumental function', 'learning-instrumental function', 'communicative-instrumental function' and 8 subcategories were found. The most frequent function was the 'information delivery function' in the 'teaching-instrumental function' category. Implications for teacher education and further studies were discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1700-1721
• /
• 2017

The problem of blocking artifacts is very common in block-based image and video compression, especially at very low bit rates. In this paper, we propose a post-processing method for JPEG-coded image deblocking via sparse representation and adaptive residual threshold. This method includes three steps. First, we obtain the dictionary by online dictionary learning and the compressed images. The dictionary is then modified by the histogram of oriented gradient (HOG) feature descriptor and K-means cluster. Second, an adaptive residual threshold for orthogonal matching pursuit (OMP) is proposed and used for sparse coding by combining blind image blocking assessment. At last, to take advantage of human visual system (HVS), the edge regions of the obtained deblocked image can be further modified by the edge regions of the compressed image. The experimental results show that our proposed method can keep the image more texture and edge information while reducing the image blocking artifacts.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3873-3887
• /
• 2018

In this paper, we propose a novel method to recover images corrupted by impulse noise. The proposed method uses two stages: noise detection and filtering. In the first stage, we use pixel values, rank-ordered logarithmic difference values, and median values to train a neural-network-based impulse noise detector. After training, we apply the network to detect noisy pixels in images. In the next stage, we use group-based weighted couple sparse representation to filter the noisy pixels. During this second stage, conventional methods generally use only clean pixels to recover corrupted pixels, which can yield unsuccessful dictionary learning if the noise density is high and the number of useful clean pixels is inadequate. Therefore, we use reconstructed pixels to balance the deficiency. Experimental results show that the proposed noise detector has better performance than the conventional noise detectors. Also, with the information of noisy pixel location, the proposed impulse-noise removal method performs better than the conventional methods, through the recovered images resulting in better quality.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.

• School Mathematics
• /
• v.4 no.4
• /
• pp.539-554
• /
• 2002

Mathematics is constructed by many signs, and learning mathematics involves the understanding and uses of them. This study reflects mathematical signs and their meanings, and considers how they can be introduced in learning. For these, we first investigated epistemological positions as Piaget, Vygotsky, anthropology, and interactionism. And we investigated semiotic models that Saussure and Peirce built each. Among these we adopted Peirce' triadic model that is consisted of interpretant, object (referent), and represen tamen(sign). In mathematic learning process, representations are transformed by translations and meanings are growed to the representation of another sign. And the meaning of sign grows by learner's interpretation. In terms of theoretical grounds, we settled that the understanding of mathematical signs involved the understanding of their representations and their meanings. On the foundation of above contents, we searched how we introduced signs to students and there were methods that approached to students representationally or inquiringly.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.1
• /
• pp.23-32
• /
• 2017

We can obtain useful knowledge from data by using a subgroup discovery algorithm. Subgroup discovery is a rule model learning method that finds data subgroups containing specific information from data and expresses them in a rule form. Subgroups are meaningful as they account for a high percentage of total data and tend to differ significantly from the overall data. Subgroup is expressed with conjunction of only literals previously. So, the scope of the rules that can be derived from the learning process is limited. In this paper, we propose a method to increase expressiveness of rules through internal disjunctive representation of attribute values. Also, we analyze the characteristics of existing subgroup discovery algorithms and propose an improved algorithm that complements their defects and takes advantage of them. Experiments are conducted with the traffic accident data given from Busan metropolitan city. The results shows that performance of the proposed method is better than that of existing methods. Rule set learned by proposed method has interesting and general rules more.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.622-624
• /
• 2004

강화 학습(Reinforcement Learning)을 실제 문제에 적용하는 데 있어 가장 큰 문제는 차원성의 저주(Curse of dimensionality)였다 문제가 커짐에 따라 목적을 이루기 위해서 더 많은 단계의 판단이 필요하고 이에 따라 문제의 해결이 지수적으로 어려워지게 된다. 이를 해결하기 위해 문제를 여러 단계로 나누어 단계별로 학습하는 계층적 강화 학습(Hierarchical Reinforcement Learning)이 제시된 바 있다 하지만 대부분의 계층적 강화 학습 방법들은 사전에 문제의 구조를 아는 것을 전제로 하며 큰 사이즈의 문제를 간단히 표현할 방법을 제시하지 않는다. 따라서 이들 방법들도 실제적인 문제에 바로 적용하기에는 적합하지 않다. 최근 이루어진 복잡계 네트워크(Complex Network)에 대한 연구에 착안하여 본 논문은 자기조직화하는 생장 네트워크(Self organizing growing network)를 기반으로 한 간단한 환경 표현 모델을 사용하는 강화 학습 알고리즘을 제안한다 네트웍은 복잡계 네트웍이 갖는 성질들을 유지하도록 자기 조직화되고, 노드들 간의 거리는 작은 세상 성질(Small World Property)에 따라 전체 네트웍의 큰 사이즈에 비해 짧게 유지된다. 즉 판단해야할 단계의 수가 적게 유지되기 때문에 이 방법으로 차원성의 저주를 피할 수 있다.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1391-1402
• /
• 2021

This paper focuses use context-sensitive spelling error correction using generative adversarial network. Generative adversarial network[1] are attracting attention as they solve data generation problems that have been a challenge in the field of deep learning. In this paper, sentences are generated using word embedding information and reflected in word distribution representation. We experiment with DCGAN[2] used for the stability of learning in the existing image processing and D2GAN[3] with double discriminator. In this paper, we experimented with how the composition of generative adversarial networks and the change of learning corpus influence the context-sensitive spelling error correction In the experiment, we correction the generated word embedding information and compare the performance with the actual word embedding information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2180-2197
• /
• 2019

With the proliferation of the Android malicious applications, malware becomes more capable of hiding or confusing its malicious intent through the use of code obfuscation, which has significantly weaken the effectiveness of the conventional defense mechanisms. Therefore, in order to effectively detect unknown malicious applications on the Android platform, we propose DroidVecDeep, an Android malware detection method using deep learning technique. First, we extract various features and rank them using Mean Decrease Impurity. Second, we transform the features into compact vectors based on word2vec. Finally, we train the classifier based on deep learning model. A comprehensive experimental study on a real sample collection was performed to compare various malware detection approaches. Experimental results demonstrate that the proposed method outperforms other Android malware detection techniques.