• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.893-913
• /
• 2017

The handwriting based person identification systems use their designer's perceived structural properties of handwriting as features. In this paper, we present a system that uses those structural properties as features that graphologists and expert handwriting analyzers use for determining the writer's personality traits and for making other assessments. The advantage of these features is that their definition is based on sound historical knowledge (i.e., the knowledge discovered by graphologists, psychiatrists, forensic experts, and experts of other domains in analyzing the relationships between handwritten stroke characteristics and the phenomena that imbeds individuality in stroke). Hence, each stroke characteristic reflects a personality trait. We have measured the effectiveness of these features on a subset of handwritten Devnagari and Latin script datasets from the Center for Pattern Analysis and Recognition (CPAR-2012), which were written by 100 people where each person wrote three samples of the Devnagari and Latin text that we have designed for our experiments. The experiment yielded 100% correct identification on the training set. However, we observed an 88% and 89% correct identification rate when we experimented with 200 training samples and 100 test samples on handwritten Devnagari and Latin text. By introducing the majority voting based rejection criteria, the identification accuracy increased to 97% on both script sets.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.37-42
• /
• 2019

In this paper, we explore the details of three classic data augmentation methods and two generative model based oversampling methods. The three classic data augmentation methods are random sampling (RANDOM), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN). The two generative model based oversampling methods are Conditional Generative Adversarial Network (CGAN) and Wasserstein Generative Adversarial Network (WGAN). In imbalanced data, the whole instances are divided into majority class and minority class, where majority class occupies most of the instances in the training set and minority class only includes a few instances. Generative models have their own advantages when they are used to generate more plausible samples referring to the distribution of the minority class. We also adopt CGAN to compare the data augmentation performance with other methods. The experimental results show that WGAN-based oversampling technique is more stable than other approaches (RANDOM, SMOTE, ADASYN and CGAN) even with the very limited training datasets. However, when the imbalanced ratio is too small, generative model based approaches cannot achieve satisfying performance than the conventional data augmentation techniques. These results suggest us one of future research directions.

• Asia pacific journal of information systems
• /
• v.32 no.2
• /
• pp.226-248
• /
• 2022

The existing model for sentiment analysis of product reviews learned from past data and new data was labeled based on training. But new data was never used by the existing system for making a decision. The proposed Aspect-based multi-agent Deep Reinforcement learning Sentiment Analysis (ADRSA) model learned from its very first data without the help of any training dataset and labeled a sentence with aspect category and sentiment polarity. It keeps on learning from the new data and updates its knowledge for improving its intelligence. The decision of the proposed system changed over time based on the new data. So, the accuracy of the sentiment analysis using deep reinforcement learning was improved over supervised learning and unsupervised learning methods. Hence, the sentiments of premium customers on a particular site can be explored to other customers effectively. A dynamic environment with a strong knowledge base can help the system to remember the sentences and usage State Action Reward State Action (SARSA) algorithm with Bidirectional Encoder Representations from Transformers (BERT) model improved the performance of the proposed system in terms of accuracy when compared to the state of art methods.

• Journal of the Korea Computer Graphics Society
• /
• v.13 no.4
• /
• pp.29-36
• /
• 2007

The objective of this paper is to develop the motion recognition method for the rehabilitation program of the people with physical disabilities. Using the infrared ray LED, this method gets the information of the user's motion and tells the difference between the information we get and the pre-defined information. In order to get the fast recognition and comparison, this method positions the specific coordinates of infrared ray LED in the pre-classified sector which keeps certain distance and angle from the point of origin. The result in our experiment shows the speed over 20 frames per second in every motion, and we are satisfied the rate for the recognition of the motions which is near 98%.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.199-208
• /
• 2021

Automatic Post Editing(APE) is the study that automatically correcting errors included in the machine translated sentences. The goal of APE task is to generate error correcting models that improve translation quality, regardless of the translation system. For training these models, source sentence, machine translation, and post edit, which is manually edited by human translator, are utilized. Especially in the recent APE research, multilingual pretrained language models are being adopted, prior to the training by APE data. This study deals with multilingual pretrained language models adopted to the latest APE researches, and the specific application method for each APE study. Furthermore, based on the current research trend, we propose future research directions utilizing translation model or mBART model.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.372-377
• /
• 2007

For more than 2,500 years, surgical teaching has been based on the so called "see one, do one, teach one" paradigm, in which the surgical trainee learns by operating on patients under close supervision of peers and superiors. However, higher demands on the quality of patient care and rising malpractice costs have made it increasingly risky to train on patients. Minimally invasive surgery, in particular, has made it more difficult for an instructor to demonstrate the required manual skills. It has been recognized that, similar to flight simulators for pilots, virtual reality (VR) based surgical simulators promise a safer and more comprehensive way to train manual skills of medical personnel in general and surgeons in particular. One of the major challenges in the development of VR-based surgical trainers is the real-time and realistic simulation of interactions between surgical instruments and biological tissues. It involves multi-disciplinary research areas including soft tissue mechanical behavior, tool-tissue contact mechanics, computer haptics, computer graphics and robotics integrated into VR-based training systems. The research described in this paper addresses the problem of characterizing soft tissue properties for medical virtual environments. A system to measure in vivo mechanical properties of soft tissues was designed, and eleven sets of animal experiments were performed to measure in vivo and in vitro biomechanical properties of porcine intra-abdominal organs. Viscoelastic tissue parameters were then extracted by matching finite element model predictions with the empirical data. Finally, the tissue parameters were combined with geometric organ models segmented from the Visible Human Dataset and integrated into a minimally invasive surgical simulation system consisting of haptic interface devices and a graphic display.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.125-133
• /
• 2011

For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. As fingerprinting method, k-nearest neighbor(KNN) has been widely applied for indoor location in wireless location area networks(WLAN), but its performance is sensitive to number of neighbors k and positions of reference points(RPs). So intuitive fuzzy c-means(IFCM) clustering algorithm is applied to improve KNN, which is the KNN/IFCM hybrid algorithm presented in this paper. In the proposed algorithm, through KNN, k RPs are firstly chosen as the data samples of IFCM based on signal to noise ratio(SNR). Then, the k RPs are classified into different clusters through IFCM based on SNR. Experimental results indicate that the proposed KNN/IFCM hybrid algorithm generally outperforms KNN, KNN/FCM, KNN/PFCM algorithm when the locations error is less than 2m.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.109-115
• /
• 2011

As fingerprinting method, k-nearest neighbor(KNN) has been widely applied for indoor location in wireless location area networks(WLAN), but its performance is sensitive to number of neighbors k and positions of reference points(RPs). So artificial neural network(ANN) clustering algorithm is applied to improve KNN, which is the KNN/ANN hybrid algorithm presented in this paper. For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. In the proposed algorithm, through KNN, k RPs are firstly chosen as the data samples of ANN based on SNR. Then, the k RPs are classified into different clusters through ANN based on SNR. Experimental results indicate that the proposed KNN/ANN hybrid algorithm generally outperforms KNN algorithm when the locations error is less than 2m.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.169-189
• /
• 2005

In order to derive a better classifier with a limited number of training examples, active teaming alternately repeats the querying stage fur category labeling and the subsequent learning stage fur rebuilding the calssifier with the newly expanded training set. To relieve the user from the burden of labeling, especially in an on-line environment, it is important to minimize the number of querying steps as well as the total number of query examples. We can derive a good classifier in a small number of querying steps by using only a small number of examples if we can select multiple of diverse, representative, and ambiguous examples to present to the user at each querying step. In this paper, we propose a cluster-based batch query selection method which can select diverse, representative, and highly ambiguous examples for efficient active learning. Experiments with various text data sets have shown that our method can derive a better classifier than other methods which only take into account the ambiguity as the criterion to select multiple query examples.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.85-92
• /
• 2022

Demand for big data analysis and AI developers is increasing, but there is a lack of an education base to supply them. In this paper, by developing a cloud-based artificial intelligence education platform, the goal was to establish an environment in which practical practical training can be efficiently learned at low cost at educational institutions and IT companies. The development of the education platform was carried out by planning scenarios for each user, architecture design, screen design, implementation of development functions, and hardware construction. This training platform consists of a containerized workload, service management platform, lecture and development platform for instructors and students, and secured cloud stability through real-time alarm system and age test, CI/CD development environment, and reliability through docker image distribution. The development of this education platform is expected to expand opportunities to enter new businesses in the education field and contribute to fostering working-level human resources in the AI and big data fields.