• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5C
• /
• pp.664-672
• /
• 2004

Widespread popularity of wireless data communication devices, coupled with the availability of higher bandwidths, has led to an increased user demand for content-rich media such as images and videos. Since such content often tends to be private, sensitive, or paid for, there exists a requirement for securing such communication. However, solutions that rely only on traditional compute-intensive security mechanisms are unsuitable for resource-constrained wireless and embedded devices. In this paper, we propose a selective partial image encryption scheme for image data hiding , which enables highly efficient secure communication of image data to and from resource constrained wireless devices. The encryption scheme is invoked during the image compression process, with the encryption being performed between the quantizer and the entropy coder stages. Three data selection schemes are proposed： subband selection, data bit selection and random selection. We show that these schemes make secure communication of images feasible for constrained embed-ded devices. In addition we demonstrate how these schemes can be dynamically configured to trade-off the amount of ded devices. In addition we demonstrate how these schemes can be dynamically configured to trade-off the amount of data hiding achieved with the computation requirements imposed on the wireless devices. Experiments conducted on over 500 test images reveal that, by using our techniques, the fraction of data to be encrypted with our scheme varies between 0.0244％ and 0.39％ of the original image size. The peak signal to noise ratios (PSNR) of the encrypted image were observed to vary between about 9.5㏈ to 7.5㏈. In addition, visual test indicate that our schemes are capable of providing a high degree of data hiding with much lower computational costs.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.1
• /
• pp.55-67
• /
• 2021

Hornbeams (Carpinus spp.), which are widely distributed in South Korea, are recognized as one of the most abundant species at climax stage in the temperate forests. Although the distribution and vegetation structure of the C. laxiflora community have been reported, little ecological information of C. tschonoskii is available. Little effort was made to examine the distribution shift of these species under the future climate conditions. This study was conducted to predict potential shifts in the distribution of C. laxiflora and C. tschonoskii in 2050s and 2090s under the two sets of climate change scenarios, RCP4.5 and RCP8.5. The MaxEnt model was used to predict the spatial distribution of two species using the occurrence data derived from the 6th National Forest Inventory data as well as climate and topography data. It was found that the main factors for the distribution of C. laxiflora were elevation, temperature seasonality, and mean annual precipitation. The distribution of C. tschonoskii, was influenced by temperature seasonality, mean annual precipitation, and mean diurnal rang. It was projected that the total habitat area of the C. laxiflora could increase by 1.05% and 1.11% under RCP 4.5 and RCP 8.5 scenarios, respectively. It was also predicted that the distributional area of C. tschonoskii could expand under the future climate conditions. These results highlighted that the climate change would have considerable impact on the spatial distribution of C. laxiflora and C. tschonoskii. These also suggested that ecological information derived from climate change impact assessment study can be used to develop proper forest management practices in response to climate change.

• 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.

• Sleep Medicine and Psychophysiology
• /
• v.24 no.1
• /
• pp.46-54
• /
• 2017

Objectives: Domestic violence is related to many psychiatric diseases, such as depression, anxiety disorder, and PTSD. Heart rate variability (HRV) is an index of autonomic control of the heart and is related to cardiovascular and emotional disorders. Although there have been some studies on the effects of domestic violence on women's mental health, relatively little information is available on HRV in this population. The aim of this study is to investigate demographic data, psychological features, and HRV in female victims of domestic violence and difference between Korean and foreign female victims. Methods: A total of 210 female victims of domestic violence (166 Korean women and 44 foreign women) were recruited for this study. Psychological symptoms were measured using the Hamilton Rating Scale for Anxiety (HAM-A), Hamilton Rating Scale for Depression (HAM-D), and Impact of Event Scale-Revised (IES-R). HRV measures were assessed by time-domain and frequency-domain analyses. Results: The mean score of HAM-A was 13.81, that of HAM-D was 12.92, and that of IES-R was 33.61 ; there were no significant differences between Korean and foreign women in these measures. In HRV time domain analyses, approximate entropy (ApEn) was significantly increased in foreign women compared to the Korean women. The square root of the mean of the sum of the squares of differences between adjacent NN intervals (RMSSD) was significantly decreased in foreign women compared to Korean women. There were no significant differences in the other HRV variables between Korean and foreign women. Conclusion: Female victims of domestic violence in Korea are associated with depression, anxiety, and PTSD symptoms. The physiologic factors of a female victim's nationality could be related to higher ApEn and lower RMSSD in foreign female victims. These findings have important implications for future study to study the relationships among ethnic and environmental factors and HRV variables.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.363-368
• /
• 2003

We have successfully developed a more effective algorithm to extract the lineament in the area covered by wide alluvial deposits characterized by a relatively narrow range of brightness in the Landsat TM image, while the currently used algorithm is limited to the mountainous areas. In the new algorithm, flat areas mainly consisting of alluvial deposits were selected using the Local Enhancement from the Digital Elevation Model (DEM). The aspect values were obtained by 3${\times}$3 moving windowing of Zevenbergen & Thorno's Method, and then the slopes of the study area were determined using the aspect values. After the lineament factors in the alluvial deposits were revealed by comparing the threshold values, the first rank lineament under the alluvial deposits were extracted using the Hough transform In order to extract the final lineament, the lowest points under the alluvial deposits in a given topographic section perpendicular to the first rank lineament were determined through the spline interpolation, and then the final lineament were chosen through Hough transform using the lowest points. The algorithm developed in this study enables us to observe a clearer lineament in the areas covered by much larger alluvial deposits compared with the results extracted using the conventional existing algorithm. There exists, however, some differences between the first rank lineament, obtained using the aspect and the slope, and the final lineament. This study shows that the new algorithm more effectively extracts the lineament in the area covered with wide alluvlal deposits than in the areas of converging slope, areas with narrow alluvial deposits or valleys.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.836-848
• /
• 2019

This paper aims at providing a critical view over the cybernetics theory especially of first generation on which the artificial intelligence heavily depends nowadays. There has been a commonly accepted thought that the conception of artificial intelligence could not has been possible without being influenced by N. Wiener's cybernetic feedback based information system. Despite the founder of contemporary cybernetics' ethical concerns in order to avoid an increasing entropy phenomena(social violence, economic misery, wars) produced through a negative dynamics of the western modernity regarded as the most advanced form of humanism. In this civilizationally changing atmosphere, the newly born cybernetic technology was thus firmly believed as an antidote to these vices deeply rooted in humanism itself. But cybernetics has been turned out to be a self-organizing, self-controlling mechanical system that entails the possibility of telegraphing human brain (which are transformed into patterns) through the uploading of human brain neurons digitalized by the artificial intelligence embedded into computing technology. On this background emerges posthuman (or posthumanism) movement of which concepts have been theorized mainly by its ardent apostles like N. K. Hayles, Neil Bedington, Laurent Alexandre, Donna J. Haraway. The converging of NBIC Technologies leading to the opening of a much more digitalizing society has served as a catalyst to promote the posthuman representations and different narratives especially in the contemporary visual arts as well as in the study of humanities including philosophy and fictional literature. Once Bruno Latour wrote "Modernity is often defined in terms of humanism, either as a way of saluting the birth of 'man' or as a way of announcing his death. But this habit is itself modern, because it remains asymmetrical. It overlooks the simultaneous birth of 'nonhumaniy' - things, or objects, or beasts, - and the equally strange beginning of a crossed-out God, relegated to the sidelines."4) These highly suggestive ideas enable us to better understand what kind of human beings would emerge following the dazzlingly accelerating advancement of artificial intelligence technology. We wonder whether or not this newly born humankind would become essentially Homo Artificialis as a neuronal man stripping off his biological apparatus. However due to this unprecedented situation humans should deal with enormous challenges involving ethical, metaphysical, existential implications on their life.