• The Journal of Korean Society for Radiation Therapy
• /
• v.27 no.2
• /
• pp.157-166
• /
• 2015

Purpose : Cyber-Knife tumor tracking system, based on the correlation relationship between the position of a tumor which moves in response to the real time respiratory cycle signal and respiration was obtained by the LED marker attached to the outside of the patient, the location of the tumor to predict in advance, the movement of the tumor in synchronization with the therapeutic device to track real-time tumor, is a system for treating. The purpose of this study, in the cyber knife tumor tracking radiation therapy, trying to evaluate the accuracy of tumor tracking radiation therapy system due to the change in the form of unpredictable sudden breathing due to cough and sleep. Materials and Methods : Breathing Log files that were used in the study, based on the Respiratory gating radiotherapy and Cyber-knife tracking radiosurgery breathing Log files of patients who received herein, measured using the Log files in the form of a Sinusoidal pattern and Sudden change pattern. it has been reconstituted as possible. Enter the reconstructed respiratory Log file cyber knife dynamic chest Phantom, so that it is possible to implement a motion due to respiration, add manufacturing the driving apparatus of the existing dynamic chest Phantom, Phantom the form of respiration we have developed a program that can be applied to. Movement of the phantom inside the target (Ball cube target) was driven by the displacement of three sizes of according to the size of the respiratory vertical (Superior-Inferior) direction to the 5 mm, 10 mm, 20 mm. Insert crosses two EBT3 films in phantom inside the target in response to changes in the target movement, the End-to-End (E2E) test provided in Cyber-Knife manufacturer depending on the form of the breathing five times each. It was determined by carrying. Accuracy of tumor tracking system is indicated by the target error by analyzing the inserted film, additional E2E test is analyzed by measuring the correlation error while being advanced. Results : If the target error is a sine curve breathing form, the size of the target of the movement is in response to the 5 mm, 10 mm, 20 mm, respectively, of the average $1.14{\pm}0.13mm$, $1.05{\pm}0.20mm$, with $2.37{\pm}0.17mm$, suddenly for it is variations in breathing, respective average $1.87{\pm}0.19mm$, $2.15{\pm}0.21mm$, and analyzed with $2.44{\pm}0.26mm$. If the correlation error can be defined by the length of the displacement vector in the target track is a sinusoidal breathing mode, the size of the target of the movement in response to 5 mm, 10 mm, 20 mm, respective average $0.84{\pm}0.01mm$, $0.70{\pm}0.13mm$, with $1.63{\pm}0.10mm$, if it is a variant of sudden breathing respective average $0.97{\pm}0.06mm$, $1.44{\pm}0.11mm$, and analyzed with $1.98{\pm}0.10mm$. The larger the correlation error values in both the both the respiratory form, the target error value is large. If the motion size of the target of the sine curve breathing form is greater than or equal to 20 mm, was measured at 1.5 mm or more is a recommendation value of both cyber knife manufacturer of both error value. Conclusion : There is a tendency that the correlation error value between about target error value magnitude of the target motion is large is increased, the error value becomes large in variation of rapid respiration than breathing the form of a sine curve. The more the shape of the breathing large movements regular shape of sine curves target accuracy of the tumor tracking system can be judged to be reduced. Using the algorithm of Cyber-Knife tumor tracking system, when there is a change in the sudden unpredictable respiratory due patient coughing during treatment enforcement is to stop the treatment, it is assumed to carry out the internal target validation process again, it is necessary to readjust the form of respiration. Patients under treatment is determined to be able to improve the treatment of accuracy to induce the observed form of regular breathing and put like to see the goggles monitor capable of the respiratory form of the person.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.1-20
• /
• 2013

Nowadays, social network is a huge communication platform for providing people to connect with one another and to bring users together to share common interests, experiences, and their daily activities. Users spend hours per day in maintaining personal information and interacting with other people via posting, commenting, messaging, games, social events, and applications. Due to the growth of user's distributed information in social network, there is a great potential to utilize the social data to enhance the quality of recommender system. There are some researches focusing on social network analysis that investigate how social network can be used in recommendation domain. Among these researches, we are interested in taking advantages of the interaction between a user and others in social network that can be determined and known as social relationship. Furthermore, mostly user's decisions before purchasing some products depend on suggestion of people who have either the same preferences or closer relationship. For this reason, we believe that user's relationship in social network can provide an effective way to increase the quality in prediction user's interests of recommender system. Therefore, social relationship between users encountered from social network is a common factor to improve the way of predicting user's preferences in the conventional approach. Recommender system is dramatically increasing in popularity and currently being used by many e-commerce sites such as Amazon.com, Last.fm, eBay.com, etc. Collaborative filtering (CF) method is one of the essential and powerful techniques in recommender system for suggesting the appropriate items to user by learning user's preferences. CF method focuses on user data and generates automatic prediction about user's interests by gathering information from users who share similar background and preferences. Specifically, the intension of CF method is to find users who have similar preferences and to suggest target user items that were mostly preferred by those nearest neighbor users. There are two basic units that need to be considered by CF method, the user and the item. Each user needs to provide his rating value on items i.e. movies, products, books, etc to indicate their interests on those items. In addition, CF uses the user-rating matrix to find a group of users who have similar rating with target user. Then, it predicts unknown rating value for items that target user has not rated. Currently, CF has been successfully implemented in both information filtering and e-commerce applications. However, it remains some important challenges such as cold start, data sparsity, and scalability reflected on quality and accuracy of prediction. In order to overcome these challenges, many researchers have proposed various kinds of CF method such as hybrid CF, trust-based CF, social network-based CF, etc. In the purpose of improving the recommendation performance and prediction accuracy of standard CF, in this paper we propose a method which integrates traditional CF technique with social relationship between users discovered from user's behavior in social network i.e. Facebook. We identify user's relationship from behavior of user such as posts and comments interacted with friends in Facebook. We believe that social relationship implicitly inferred from user's behavior can be likely applied to compensate the limitation of conventional approach. Therefore, we extract posts and comments of each user by using Facebook Graph API and calculate feature score among each term to obtain feature vector for computing similarity of user. Then, we combine the result with similarity value computed using traditional CF technique. Finally, our system provides a list of recommended items according to neighbor users who have the biggest total similarity value to the target user. In order to verify and evaluate our proposed method we have performed an experiment on data collected from our Movies Rating System. Prediction accuracy evaluation is conducted to demonstrate how much our algorithm gives the correctness of recommendation to user in terms of MAE. Then, the evaluation of performance is made to show the effectiveness of our method in terms of precision, recall, and F1-measure. Evaluation on coverage is also included in our experiment to see the ability of generating recommendation. The experimental results show that our proposed method outperform and more accurate in suggesting items to users with better performance. The effectiveness of user's behavior in social network particularly shows the significant improvement by up to 6% on recommendation accuracy. Moreover, experiment of recommendation performance shows that incorporating social relationship observed from user's behavior into CF is beneficial and useful to generate recommendation with 7% improvement of performance compared with benchmark methods. Finally, we confirm that interaction between users in social network is able to enhance the accuracy and give better recommendation in conventional approach.