• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.9 no.3
• /
• pp.39-52
• /
• 1999

In this paper we propose a new watermarking technique for copyright protection of images. The proposed technique is based on a spatial masking method with a spatial scale parameter. In general it becomes more robust against various attacks but with some degradations on the image quality as the amplitude of the watermark increases. On the other hand it becomes perceptually more invisible but more vulnerable to various attacks as the amplitude of the watermark decreases. Thus it is quite complex to decide the compromise between the robustness of watermark and its visibility. We note that watermarking using the spread spectrum is not robust enought. That is there may be some areas in the image that are tolerable to strong watermark signals. However large smooth areas may not be strong enough. Thus in order to enhance the invisibility of watermarked image for those areas the spatial masking characteristics of the HVS(Human Visual System) should be exploited. That is for texture regions the magnitude of the watermark can be large whereas for those smooth regions the magnitude of the watermark can be small. As a result the proposed watermarking algorithm is intend to satisfy both the robustness of watermark and the quality of the image. The experimental results show that the proposed algorithm is robust to image deformations(such as compression adding noise image scaling clipping and collusion attack).

• Radiation Oncology Journal
• /
• v.28 no.3
• /
• pp.155-165
• /
• 2010

Purpose: In order to evaluate the positional uncertainty of internal organs during radiation therapy for treatment of liver cancer, we measured differences in inter- and intra-fractional variation of the tumor position and tidal amplitude using 4-dimentional computed radiograph (DCT) images and gated orthogonal setup kilovolt (KV) images taken on every treatment using the on board imaging (OBI) and real time position management (RPM) system. Materials and Methods: Twenty consecutive patients who underwent 3-dimensional (3D) conformal radiation therapy for treatment of liver cancer participated in this study. All patients received a 4DCT simulation with an RT16 scanner and an RPM system. Lipiodol, which was updated near the target volume after transarterial chemoembolization or diaphragm was chosen as a surrogate for the evaluation of the position difference of internal organs. Two reference orthogonal (anterior and lateral) digital reconstructed radiograph (DRR) images were generated using CT image sets of 0% and 50% into the respiratory phases. The maximum tidal amplitude of the surrogate was measured from 3D conformal treatment planning. After setting the patient up with laser markings on the skin, orthogonal gated setup images at 50% into the respiratory phase were acquired at each treatment session with OBI and registered on reference DRR images by setting each beam center. Online inter-fractional variation was determined with the surrogate. After adjusting the patient setup error, orthogonal setup images at 0% and 50% into the respiratory phases were obtained and tidal amplitude of the surrogate was measured. Measured tidal amplitude was compared with data from 4DCT. For evaluation of intra-fractional variation, an orthogonal gated setup image at 50% into the respiratory phase was promptly acquired after treatment and compared with the same image taken just before treatment. In addition, a statistical analysis for the quantitative evaluation was performed. Results: Medians of inter-fractional variation for twenty patients were 0.00 cm (range, -0.50 to 0.90 cm), 0.00 cm (range, -2.40 to 1.60 cm), and 0.00 cm (range, -1.10 to 0.50 cm) in the X (transaxial), Y (superior-inferior), and Z (anterior-posterior) directions, respectively. Significant inter-fractional variations over 0.5 cm were observed in four patients. Min addition, the median tidal amplitude differences between 4DCTs and the gated orthogonal setup images were -0.05 cm (range, -0.83 to 0.60 cm), -0.15 cm (range, -2.58 to 1.18 cm), and -0.02 cm (range, -1.37 to 0.59 cm) in the X, Y, and Z directions, respectively. Large differences of over 1 cm were detected in 3 patients in the Y direction, while differences of more than 0.5 but less than 1 cm were observed in 5 patients in Y and Z directions. Median intra-fractional variation was 0.00 cm (range, -0.30 to 0.40 cm), -0.03 cm (range, -1.14 to 0.50 cm), 0.05 cm (range, -0.30 to 0.50 cm) in the X, Y, and Z directions, respectively. Significant intra-fractional variation of over 1 cm was observed in 2 patients in Y direction. Conclusion: Gated setup images provided a clear image quality for the detection of organ motion without a motion artifact. Significant intra- and inter-fractional variation and tidal amplitude differences between 4DCT and gated setup images were detected in some patients during the radiation treatment period, and therefore, should be considered when setting up the target margin. Monitoring of positional uncertainty and its adaptive feedback system can enhance the accuracy of treatments.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.12
• /
• pp.1141-1153
• /
• 2010

This paper introduces ONLIS(Overlay Multicast Network for Live IPTV Service), a novel overlay multicast network optimized to deliver live broadcast IPTV stream. We analyzed IPTV reference model of ITU-T IPTV standardization group in terms of network and stream delivery from the source networks to the customer networks. Based on the analysis, we divide IPTV reference model into 3 networks; source network, core network and access network, ION(Infrastructure-based Overlay Multicast Network) is employed for the source and core networks and PON(P2P-based Overlay Multicast Network) is applied to the access networks. ION provides an efficient, reliable and stable stream distribution with very negligible delay while PON provides bandwidth efficient and cost effective streaming with a little tolerable delay. The most important challenge in live P2P streaming is to reduce end-to-end delay without sacrificing stream quality. Actually, there is always a trade-off between delay & stream quality in conventional live P2P streaming system. To solve this problem, we propose two approaches. Firstly, we propose DSPT(Distributed Streaming P2P Tree) which takes advantage of combinational overlay multicasting. In DSPT, a peer doesn't fully rely on SP(Supplying Peer) to get the live stream, but it cooperates with its local ANR(Access Network Relay) to reduce delay and improve stream quality. When RP detects bandwidth drop in SP, it immediately switches the connection from SP to ANR and continues to receive stream without any packet loss. DSPT uses distributed P2P streaming technique to let the peer share the stream to the extent of its available bandwidth. This means, if RP can't receive the whole stream from SP due to lack of SP's uploading bandwidth, then it receives only partial stream from SP and the rest from the ANR. The proposed distributed P2P streaming improves P2P networking efficiency.

• Journal of Environmental Policy
• /
• v.12 no.3
• /
• pp.21-47
• /
• 2013

The aim is to analysis landslide vulnerability in Inje, Korea, using GCI(Geospatial Correlative Integration) and probability rainfalls based on geographic information system (GIS). In order to achieve this goal, identified indicators influencing landslides based on literature review. We include indicators of exposure to climate(rainfall probability), sensitivity(slope, aspect, curvature, geology, topography, soil drainage, soil material, soil thickness and soil texture) and adaptive capacity(timber diameter, timber type, timber density and timber age). All data were collected, processed, and compiled in a spatial database using GIS. Karisan-ri that had experienced 470 landslides by Typhoon Ewinia in 2006 was selected for analysis and verification. The 50% of landslide data were randomly selected to use as training data, while the other 50% being used for verification. The probability of landslides for target years (1 year, 3 years, 10 years, 50 years, and 100 years) was calculated assuming that landslides are triggered by 3-day cumulative rainfalls of 449 mm. Results show that number of slope has comparatively strong influence on landslide damage. And inclination of $25{\sim}30^{\circ}C$, the highest correlation landslide. Improved previous landslide vulnerability methodology by adopting GCI. Also, vulnerability map provides meaningful information for decision makers regarding priority areas for implementing landslide mitigation policies.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.15 no.4
• /
• pp.264-272
• /
• 2013

Climate changes have caused not only changes in the frequency and intensity of extreme climate events, but also temperature and precipitation. The damages on agricultural production system will be increased by heavy rainfall and snow. In this study we assessed vulnerability of crop cultivation facility and animal husbandry facility by heavy rain in 232 agricultural districts. The climate data of 2000 years were used for vulnerability analysis on present status and the data derived from A1B scenario were used for the assessment in the years of 2020, 2050 and 2100, respectively. Vulnerability of local districts was evaluated by three indices such as climate exposure, sensitivity and adaptive capacity, and each index was determined from selected alternative variables. Collected data were normalized and then multiplied by weight value that was elicited in delphi investigation. Jeonla-do and Gangwon-do showed higher climate exposures than the other provinces. The higher sensitivity to abnormal weather was observed from the regions that have large-scale cultivation facility complex compared to the other regions and vulnerability to abnormal weather also was higher at these provinces. In the projected estimation based on the SRES A1B, the vulnerability of controlled agricultural facility in Korea totally increased, especially was dramatic between 2000's and 2020 year.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• Journal of Wetlands Research
• /
• v.18 no.4
• /
• pp.474-480
• /
• 2016

In this study, formation background of biodiversity and its changes in the process of geologic history, and effects of climate change on biodiversity and human were discussed and the alternatives to reduce the effects of climate change were suggested. Biodiversity is 'the variety of life' and refers collectively to variation at all levels of biological organization. That is, biodiversity encompasses the genes, species and ecosystems and their interactions. It provides the basis for ecosystems and the services on which all people fundamentally depend. Nevertheless, today, biodiversity is increasingly threatened, usually as the result of human activity. Diverse organisms on earth, which are estimated as 10 to 30 million species, are the result of adaptation and evolution to various environments through long history of four billion years since the birth of life. Countlessly many organisms composing biodiversity have specific characteristics, respectively and are interrelated with each other through diverse relationship. Environment of the earth, on which we live, has also created for long years through extensive relationship and interaction of those organisms. We mankind also live through interrelationship with the other organisms as an organism. The man cannot lives without the other organisms around him. Even though so, human beings accelerate mean extinction rate about 1,000 times compared with that of the past for recent several years. We have to conserve biodiversity for plentiful life of our future generation and are responsible for sustainable use of biodiversity. Korea has achieved faster economic growth than any other countries in the world. On the other hand, Korea had hold originally rich biodiversity as it is not only a peninsula country stretched lengthily from north to south but also three sides are surrounded by sea. But they disappeared increasingly in the process of fast economic growth. Korean people have created specific Korean culture by coexistence with nature through a long history of agriculture, forestry, and fishery. But in recent years, the relationship between Korean and nature became far in the processes of introduction of western culture and development of science and technology and specific natural feature born from harmonious combination between nature and culture disappears more and more. Population of Korea is expected to be reduced as contrasted with world population growing continuously. At this time, we need to restore biodiversity damaged in the processes of rapid population growth and economic development in concert with recovery of natural ecosystem due to population decrease. There were grand extinction events of five times since the birth of life on the earth. Modern extinction is very rapid and human activity is major causal factor. In these respects, it is distinguished from the past one. Climate change is real. Biodiversity is very vulnerable to climate change. If organisms did not find a survival method such as 'adaptation through evolution', 'movement to the other place where they can exist', and so on in the changed environment, they would extinct. In this respect, if climate change is continued, biodiversity should be damaged greatly. Furthermore, climate change would also influence on human life and socio-economic environment through change of biodiversity. Therefore, we need to grasp the effects that climate change influences on biodiversity more actively and further to prepare the alternatives to reduce the damage. Change of phenology, change of distribution range including vegetation shift, disharmony of interaction among organisms, reduction of reproduction and growth rates due to odd food chain, degradation of coral reef, and so on are emerged as the effects of climate change on biodiversity. Expansion of infectious disease, reduction of food production, change of cultivation range of crops, change of fishing ground and time, and so on appear as the effects on human. To solve climate change problem, first of all, we need to mitigate climate change by reducing discharge of warming gases. But even though we now stop discharge of warming gases, climate change is expected to be continued for the time being. In this respect, preparing adaptive strategy of climate change can be more realistic. Continuous monitoring to observe the effects of climate change on biodiversity and establishment of monitoring system have to be preceded over all others. Insurance of diverse ecological spaces where biodiversity can establish, assisted migration, and establishment of horizontal network from south to north and vertical one from lowland to upland ecological networks could be recommended as the alternatives to aid adaptation of biodiversity to the changing climate.