CCTV has been known to possess high level of objectivity and utility. Hence, the government has recently focused on replacing low quality CCTV with higher quality ones or even by adding high resolution CCTV. However, converting all existing low-quality CCTV to high quality can be extremely costly. Furthermore, low quality videos prior to CCTV replacement are likely to be of poor quality and thus not utilized correctly. In order to solve these problems, this paper proposes a method to improve videos quality of images using SRGAN(Super Resolution Generative Advisory Networks). Through experiments, we have proven that it is possible to improve low quality CCTV videos clearly. For this experiment, a total of 4 types of CCTV videos were used and 10,000 images were sampled from each type. Those images could then be used for machine learning. The fact that the pre-process for machine learning has been done manually and the long time that required for machine learning seems to be complementary.

There is a case where the core content of another person's work is decorated as though it is his own thoughts by changing own thoughts without showing the source. Plagiarism test of copykiller free service used in plagiarism check is performed by comparing plagiarism more than 6th word. However, it is not enough to judge it as a plagiarism with a six - word match if it is replaced with a similar word. Therefore, in this paper, we construct word clusters by using DBSCAN algorithm, find synonyms, convert the words in the clusters into representative synonyms, and construct L-R tables through L-R parsing. We then propose a method for determining the similarity of documents by applying weights to the thesaurus and weights for each paragraph of the thesis.

In this paper, we propose a new method to improve low light image. In order to improve the image quality of a night image with a moving object as much as the quality of a daytime image, the following tasks were performed. Firstly, we reduce the noisy of the input night image and improve the night image by the tone mapping method. Secondly, we segment the input night image into a foreground with motion and a background without motion. The motion is detected using both the difference between the current frame and the previous frame and the difference between the current frame and the night background image. The background region of the night image takes pixels from corresponding positions in the daytime image. The foreground regions of the night image take the pixels from the corresponding positions of the image which is improved by the tone mapping method. Experimental results show that the proposed method can improve the visual quality more clearly than the existing methods.

In this paper, we propose a new algorithm that is robust against the effects of objects that are relatively unaffected by camera motion and can accurately detect camera motion even in high resolution images. First, for more accurate camera motion detection, a global motion filter based on entropy of a motion vector is used to distinguish the background and the object. A block matching algorithm is used to find exact motion vectors. In addition, a matched filter with the angle of the ideal motion vector of each block is used. Motion vectors including 4 kinds of diagonal direction, zoom in, and zoom out are added additionally. The experiment shows that the precision, recall, and accuracy of camera motion detection compared to the recent results is improved by 12.5%, 8.6% and 9.5%, respectively.

Conventional active sonar technology has relied heavily on the hearing of sonar operator, but recently, many techniques for automatic detection and classification have been studied. In this paper, we extract the image data from the spectrogram of the active sonar signal and classify the extracted data using CNN(convolutional neural networks), which has recently presented excellent performance improvement in the field of pattern recognition. First, we divided entire data set into eight classes depending on the ratio containing the target. Then, experiments were conducted to classify the eight classes data using proposed CNN structure, and the results were analyzed.

We propose a method for driving loudspeakers from class D audio power amplifiers in current mode, instead of in conventional voltage mode, which was impossible with the feedback circuitry. Unlike analog audio amplifiers, Class D audio power amplifiers have signal delay between the input and output signals, which makes it difficult to apply the feedback circuitry for current-mode driving. The idea of the pre-distortion scheme used for the compensation of the non-linearity of RF power amplifiers is adapted to remedy the impedance variation effect of the loudspeakers for current driving. The method uses the speaker model for the pre-distorter to compensate for the speaker impedance variation with frequency. The simulation and test results confirms the validity of the proposed method.

Respiration is the process of moving air into and out of the lung. Respiration changes the temperature in the chamber while exchanging energy. Especially the temperature of the face. Respiration monitoring using an infrared camera measures the temperature change caused by breathing. The conventional method assumes that motion is not considered and measures respiration. These assumptions can not accurately measure the respiration rate when breathing moves. In addition, the respiration rate measurement is performed by counting the number of peaks of the breathing waveform by displaying the position of the peak in a specific window, and there is a disadvantage that the breathing rate can not be measured accurately. In this paper, we use KLT tracking and block matching to calibrate limited weak movements during breathing and extract respiration waveform. In order to increase the accuracy of the respiration rate, the position of the peak used in the breath calculation is calculated by converting from a single point to a high resolution. Through this process, the respiration signal could be extracted even in weak motion, and the respiration rate could be measured robustly even in various time windows.

MQTT is a lightweight messaging protocol that can be used for low power IoT devices. The MQTT basically uses single MQTT broker to indirectly share message information between publishers and subscribers. This approach has a weakness in regard to traffic overflow, connection fault, security, etc. In this paper, we propose a distributed MQTT broker architecture that solves the problems in single MQTT broker structure. The distributed MQTT broker architecture is expected to support new application services that cannot be supported by a conventional MQTT architecture. We have designed and implemented a distributed MQTT broker architecture based on the RPL protocol that has been widely used for IoT network. The experiment results show that the proposed MQTT broker architecture represents better publishing/subscribing latency and network stability than the conventional MQTT broker architecture.

Most of the automotive electronic systems are equipped with control software. ISO 26262 standard has been published to prevent unreasonable risk due to E/E system malfunction. And many automotive companies apply ISO 26262 for safe series product. In ISO 26262 standard, the product quality improves through deductive and inductive safety analysis in all processes including system and software development phase. However, there are few studies on software safety analysis than systems. In the paper, we study the software FMEA(Failure Mode Effect Analysis) technique for product quality of vehicular embedded software. And we propose an effective guideline of software FMEA as EPB industrial practice.

Personal sound amplifiers(PSAPs) provide accessible and affordable healthcare to individuals with hearing disability. Many studies are in progress for affordable PSAP development, but still people do not have a best fitting profile for the PSAP depending on their hearing test. As a result, they do not have a personalized and profiled music and sound, which are very helpful for those who has hearing problems. In this paper, we propose a device and mobile system to provide music with an equalizer value according to the hearing condition of an individual to prevent the hearing loss. In order to overcome the limit of frequency band of the equalizer in a smart phone, we developed bluetooth controlled equalizer based on the fitting profiles.

Writing letters or patterns on a virtual space by moving a person's gaze is called "eye writing," which is a promising tool for various human-computer interface applications. This paper investigates the use of conventional eye writing recognition algorithms for the purpose of user-independent recognition of eye-written characters. Two algorithms are presented to build the user-independent system: eye-written region extraction using wavelet coefficients and template generation. The experimental results of the proposed system demonstrated that with dynamic positional warping, an F1 score of 79.61% was achieved for 12 eye-written patterns, thereby indicating the possibility of user-independent use of eye writing.