• 반도체디스플레이기술학회지
• /
• 제22권1호
• /
• pp.11-17
• /
• 2023

This paper proposes a lightweight deep learning network for detecting an image splicing forgery. The research on image forgery detection using CNN, a deep learning network, and research on detecting and localizing forgery in pixel units are in progress. Among them, CAT-Net, which learns the discrete cosine transform coefficients of images together with images, was released in 2022. The DCT coefficients presented by CAT-Net are combined with the JPEG artifact learning module and the backbone model as pre-learning, and the weights are fixed. The dataset used for pre-training is not included in the public dataset, and the backbone model has a relatively large number of network parameters, which causes overfitting in a small dataset, hindering generalization performance. In this paper, this learning module is designed to learn the characterization depending on the DCT domain in real-time during network training without pre-training. The DCT RRU-Net proposed in this paper is a network that combines RRU-Net which detects forgery by learning only images and JPEG artifact learning module. It is confirmed that the network parameters are less than those of CAT-Net, the detection performance of forgery is better than that of RRU-Net, and the generalization performance for various datasets improves through the network architecture and training method of DCT RRU-Net.

• Industrial Engineering and Management Systems
• /
• 제15권2호
• /
• pp.148-155
• /
• 2016

Existing power plants may consume significant amounts of fuel and require high operating costs, partly because of poor electrical power output estimates. This paper suggests a continuous conditional random field (C-CRF) model to predict more precisely the full-load electrical power output of a base load operated combined cycle power plant. We introduce three feature functions to model association potential and one feature function to model interaction potential. Together, these functions compose the C-CRF model, and the model is transformed into a multivariate Gaussian distribution with which the operation parameters can be modeled more efficiently. The performance of our model in estimating power output was evaluated by means of a real dataset and our model outperformed existing methods. Moreover, our model can be used to estimate confidence intervals of the predicted output and calculate several probabilities.

• Geomechanics and Engineering
• /
• 제30권2호
• /
• pp.107-121
• /
• 2022

Coal pillar assessment is of broad importance to underground engineering structure, as the pillar failure can lead to enormous disasters. Because of the highly non-linear correlation between the pillar failure and its influential attributes, conventional forecasting techniques cannot generate accurate outcomes. To approximate the complex behavior of coal pillar, this paper elucidates a new idea to forecast the underground coal pillar stability using combined unsupervised-supervised learning. In order to build a database of the study, a total of 90 patterns of pillar cases were collected from authentic engineering structures. A state-of-the art feature depletion method, t-distribution symmetric neighbor embedding (t-SNE) has been employed to reduce significance of actual data features. Consequently, an unsupervised machine learning technique K-mean clustering was followed to reassign the t-SNE dimensionality reduced data in order to compute the relative class of coal pillar cases. Following that, the reassign dataset was divided into two parts: 70 percent for training dataset and 30 percent for testing dataset, respectively. The accuracy of the predicted data was then examined using support vector classifier (SVC) model performance measures such as precision, recall, and f₁-score. As a result, the proposed model can be employed for properly predicting the pillar failure class in a variety of underground rock engineering projects.

• International Journal of Computer Science & Network Security
• /
• 제23권6호
• /
• pp.202-206
• /
• 2023

Today, social media has become a vital tool. The world communicates and reaches the news and each other's opinions through social media accounts. Recently, considerable research has been done on analyzing social media due to its rich data content. At the same time, since the beginning of the COVID-19 pandemic, which has afflicted so many around the world, the search for a vaccine has been intense. There have been many studies analyzing people's feelings during a crisis. This study aims to understand people's opinions about available Coronavirus vaccines through a learning model that was developed for this purpose. The dataset was collected using Twitter's streaming Application Programming Interface (API) , then combined with another dataset that had already been collected. The final dataset was cleaned, then analyzed using Python. Polarity and subjectivity functions were used to obtain the results. The results showed that most people had positive opinions toward vaccines in general and toward the Pfizer one. Our study should help governments and decision-makers dispel people's fears and discover new symptoms linked to those listed by the World Health Organization.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.190-194
• /
• 2023

By looking the importance of communication, data delivery and access in various sectors including governmental, business and individual for any kind of data, it becomes mandatory to identify faults and flaws during cyber communication. To protect personal, governmental and business data from being misused from numerous advanced attacks, there is the need of cyber security. The information security provides massive protection to both the host machine as well as network. The learning methods are used for analyzing as well as preventing various attacks. Machine learning is one of the branch of Artificial Intelligence that plays a potential learning techniques to detect the cyber-attacks. In the proposed methodology, the Decision Tree (DT) which is also a kind of supervised learning model, is combined with the different cross-validation method to determine the accuracy and the execution time to identify the cyber-attacks from a very recent dataset of different network attack activities of network traffic in the UNSW-NB15 dataset. It is a hybrid method in which different types of attributes including Gini Index and Entropy of DT model has been implemented separately to identify the most accurate procedure to detect intrusion with respect to the execution time. The different DT methodologies including DT using Gini Index, DT using train-split method and DT using information entropy along with their respective subdivision such as using K-Fold validation, using Stratified K-Fold validation are implemented.

• Journal of Microbiology and Biotechnology
• /
• 제15권5호
• /
• pp.1028-1038
• /
• 2005

To elucidate phylogenetic relationships of Phellinus and its related genera, nuclear internal transcribed spacer and mitochondrial small subunit ribosomal DNA sequences from 65 strains were determined and compared. The combined dataset of two sequences increased informative characters and led to the production of trees with higher levels of resolution. Phylogenetic analysis of the combined dataset revealed thirteen evolutionary lineages and several unresolved species that were together subdivided into two large clusters consisting of oligonucleate species and binucleate species. These results coincided with previous cytological, morphological, and molecular studies. It is newly recognized that the Phellinus linteus complex forms a sister clade to Inonotus, and that Fulvifomes is somehow related to Inocutis. The Phellinus linteus complex of dimitic perennial taxa made an independent clade from Inonotus and suggested that hyphal miticity and fruitbody permanence had enough phylogenetic significance to keep the complex within the traditional genus Phellinus. Taxa lacking setae were clustered into Fulvifomes, Phylloporia, Inocutis, and Fomitiporia, and the first three were closely related sister groups, but Fomitiporia was a genus distantly related to them. Several taxa with branched setae were shown among distantly related genera. Molecular evidence indicated that the ancestral nuclear type could be a binucleate feature, and that there might be parallel gains of branched setae and parallel losses of setae in the Hymenochaetales.

• 컴퓨터교육학회논문지
• /
• 제19권4호
• /
• pp.59-66
• /
• 2016

협력 필터링 시스템에서 데이터 희소성 문제의 해결을 위해 공통평가항목수를 반영하는 방법이 연구되었다. 이러한 방법으로 널리 알려진 자카드 지수는 기존의 유사도 척도와 결합되어 성능을 개선할 수 있었다. 그러나, 다양한 데이터 환경에서 여러 유사도 척도들과 각각 결합했을 때의 성능 개선 효과에 대한 분석 연구는 미미하므로, 본 연구는 이에 대한 분석을 목적으로 한다. 우선 자카드 지수 자체를 유사도 척도로 사용했을때 희소한 데이터셋 상에서 전통적인 척도들보다 월등한 예측 성능을 보였고 추천 성능도 매우 우수하였다. 자카드 지수를 결합함으로써 기존 유사도 척도는 데이터 특성에 상관없이 성능이 대개 향상되었고, 특히 코사인 유사도는 희소한 데이터셋에서 가장 큰 향상을 이루었으나, 평균차이 제곱(Mean Squared Difference)의 유사도는 밀집된 데이터셋에서 오히려 저하된 예측 성능을 보였다. 따라서, 자카드 지수를 결합하여 사용하기 위해 데이터 환경 특성과 유사도 척도를 고려할 필요가 있다.

• 한국균학회지
• /
• 제51권2호
• /
• pp.147-153
• /
• 2023

Dark brown leaf molds growing in a vein-limited pattern have been continuously observed on the lower leaf surface of Fatoua villosa in Korea. Fifteen samples deposited in the Korea University herbarium were examined for fungal morphological characterization. Two monoconidial isolates were obtained in 2022, and molecular analysis was performed based on a combined multigene dataset of the internal transcribed spacer (ITS) region and partial actin (actA), translation elongation factor 1-alpha (tef1), and DNA-directed RNA polymerase II second-largest subunit (rpb2). Based on morphological features and molecular phylogenetic analysis, the fungus Pseudocercospora fatouae was identified. To the best of our knowledge, it is the first study reporting the presence of P. fatouae on F. villosa in Korea.

• ETRI Journal
• /
• 제46권2호
• /
• pp.250-262
• /
• 2024

Air-writing recognition is relevant in areas such as natural human-computer interaction, augmented reality, and virtual reality. A trajectory is the most natural way to represent air writing. We analyze the recognition accuracy of words written in air considering five features, namely, writing direction, curvature, trajectory, orthocenter, and ellipsoid, as well as different parameters of a hidden Markov model classifier. Experiments were performed on two representative datasets, whose sample trajectories were collected using a Leap Motion Controller from a fingertip performing air writing. Dataset D₁ contains 840 English words from 21 classes, and dataset D₂ contains 1600 English words from 40 classes. A genetic algorithm was combined with a hidden Markov model classifier to obtain the best subset of features. Combination ftrajectory, orthocenter, writing direction, curvatureg provided the best feature set, achieving recognition accuracies on datasets D₁ and D₂ of 98.81% and 83.58%, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.