• Journal of the Korean Physical Society
• /
• v.73 no.12
• /
• pp.1908-1917
• /
• 2018

The binding affinity between the T-cell receptors (TCRs) and antigenic peptides mainly determines immunological recognition. It is not a trivial task that T cells identify the digital sequences of peptide amino acids by simply relying on the integrated binding affinity between TCRs and antigenic peptides. To address this problem, we examine whether the affinity-based discrimination of peptide sequences is learnable and generalizable by artificial neural networks (ANNs) that process the digital experimental amino acid sequence information of receptors and peptides. A pair of TCR and peptide sequences correspond to the input for ANNs, while the success or failure of the immunological recognition correspond to the output. The output is obtained by both theoretical model and experimental data. In either case, we confirmed that ANNs could learn the immunological recognition. We also found that a homogenized encoding of amino acid sequence was more effective for the supervised learning task.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.237-244
• /
• 2021

Clustering is a most powerful un-supervised machine learning techniques for division of instances into homogenous group, which is called cluster. This Clustering is mainly used for generating a good quality of cluster through which we can discover hidden patterns and knowledge from the large datasets. It has huge application in different field like in medicine field, healthcare, gene-expression, image processing, agriculture, fraud detection, profitability analysis etc. The goal of this paper is to explore both hierarchical as well as partitioning clustering and understanding their problem with various approaches for their solution. Among different clustering K-means is better than other clustering due to its linear time complexity. Further this paper also focused on data mining that dealing with high-dimensional datasets with their problems and their existing approaches for their relevancy

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1486-1501
• /
• 2021

The removal of accessories from the face is one of the essential pre-processing stages in the field of face recognition. However, despite its importance, a robust solution has not yet been provided. This paper proposes a network and dataset construction methodology to remove only the glasses from facial images effectively. To obtain an image with the glasses removed from an image with glasses by the supervised learning method, a network that converts them and a set of paired data for training is required. To this end, we created a large number of synthetic images of glasses being worn using facial attribute transformation networks. We adopted the conditional GAN (cGAN) frameworks for training. The trained network converts the in-the-wild face image with glasses into an image without glasses and operates stably even in situations wherein the faces are of diverse races and ages and having different styles of glasses.

• Journal of information and communication convergence engineering
• /
• v.18 no.4
• /
• pp.207-215
• /
• 2020

Part of speech (POS) tagging is an indispensable part of major NLP models. Its progress can be perceived on number of languages around the globe especially with respect to European languages. But considering Indian Languages, it has not got a major breakthrough due lack of supporting tools and resources. Particularly for Odia language it has not marked its dominancy yet. With a motive to make the language Odia fit into different NLP operations, this paper makes an attempt to develop a POS tagger for the said language on a HMM (Hidden Markov Model) platform. The tagger judiciously considers bigram HMM with dynamic Viterbi algorithm to give an output annotated text with maximum accuracy. The model is experimented on a corpus belonging to tourism domain accounting to a size of approximately 0.2 million tokens. With the proportion of training and testing as 3:1, the proposed model exhibits satisfactory result irrespective of limited training size.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.1-13
• /
• 2021

In this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.317-319
• /
• 2022

Rich morphology language such as Arabic needs more investigation and method to improve the sentiment analysis task. Using all document parts in the process of the sentiment analysis may add some unnecessary information to the classifier. Therefore, this paper shows the ongoing work to use sentence location as a feature with Arabic sentiment analysis. Our proposed method employs a supervised sentiment classification method by enriching the feature space model with some information from the document. The experiments and evaluations that were conducted in this work show that our proposed feature in the sentiment analysis for Arabic improves the performance of the classifier compared to the baseline model.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• pp.45-56
• /
• 2020

Despite extensive research, performance enhancement of keyphrase (KP) extraction remains a challenging problem in modern informatics. Recently, deep learning-based supervised approaches have exhibited state-of-the-art accuracies with respect to this problem, and several of the previously proposed methods utilize Bidirectional Encoder Representations from Transformers (BERT)-based language models. However, few studies have investigated the effective application of BERT-based fine-tuning techniques to the problem of KP extraction. In this paper, we consider the aforementioned problem in the context of scientific articles by investigating the fine-tuning characteristics of two distinct BERT models - BERT (i.e., base BERT model by Google) and SciBERT (i.e., a BERT model trained on scientific text). Three different datasets (WWW, KDD, and Inspec) comprising data obtained from the computer science domain are used to compare the results obtained by fine-tuning BERT and SciBERT in terms of KP extraction.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.11-16
• /
• 2022

Applying predictive analytics to predict software defects has improved the overall quality and decreased maintenance costs. Many supervised and unsupervised learning algorithms have been used for defect prediction on publicly available datasets. Most of these datasets suffer from an imbalance in the output classes. We study the impact of class imbalance in the defect datasets on the efficiency of the defect prediction model and propose a CPP method for handling imbalances in the dataset. The performance of the methods is evaluated using measures like Matthew's Correlation Coefficient (MCC), Recall, and Accuracy measures. The proposed sampling technique shows significant improvement in the efficiency of the classifier in predicting defects.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.145-148
• /
• 2022

준지도학습 기반의 동영상 이상행동감지는 구하기 어려운 프레임 단위 레이블이 필요하지 않아 더 많은 동영상을 학습에 활용 가능한 장점이 있어 관련 연구가 활발히 진행되고 있다. 최근 제안된 기법들은 주로 UCF-Crime 이라는 실제 CCTV 동영상 데이터셋을 활용하고 있는데, 본 데이터셋은 학습 영상과 테스트 영상에서 이상행동 클래스 별 분포도가 균등하지 않다. 본 연구에서는 해당 불균형으로 인해 학습 모델이 특정 행동 클래스에 과적합될 수 있음을 보이며, 이러한 불균형을 해결하기 위해 Class-Balanced Multiple Instance Learning Loss 를 제안한다. 이를 통해 기존에 특정 클래스에 편중되었던 모델이 이상행동 종류에 좀 더 균등한 성능을 낼 수 있음을 보여준다. 특히 단순히 클래스별 정확도가 제로섬(zero sum)으로 증감하는 것이 아니라 전체적인 이상행동 판별 정확도 또한 향상됨을 실험 결과를 통해 확인할 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.134-138
• /
• 2021

3 차원 휴먼 자세 추정 모델은 다시점 모델과 단시점 모델로 분류될 수 있다. 일반적으로 다시점 모델은 단시점 모델에 비하여 뛰어난 자세 추정 성능을 보인다. 단시점 모델의 경우 3 차원 자세 추정 성능의 향상은 많은 양의 학습 데이터를 필요로 한다. 하지만 3 차원 자세에 대한 참값을 획득하는 것은 쉬운 일이 아니다. 이러한 문제를 다루기 위해, 우리는 다시점 모델로부터 다시점 휴먼 자세 데이터에 대한 의사 참값을 생성하고, 이를 단시점 모델의 학습에 활용하는 방법을 제안한다. 또한, 우리는 각각의 다시점 영상으로부터 추정된 자세의 일관성을 고려하는 다시점 일관성 손실함수를 제안하여, 이것이 단시점 모델의 효과적인 학습에 도움을 준다는 것을 보인다.