2020, Vol.15, No.3

Journal of Knowledge Information Technology and Systems 2023 KCI Impact Factor : 0.89

pISSN : 1975-7700 / eISSN : 2734-0570
https://journal.kci.go.kr/kkits

Among the several deep learning research areas, image classification is a fundamental area and has been widely applied to many practical applications. Image classification is to determine which category the given image belongs to. Since the image classification is a typical supervised learning, test images and the corresponding answers, i.e., labels are also given. And, with the given test images and labels, a neural network is trained to minimize a loss function defined by error between the label and the inference result. Therefore, as the loss decreases, the inference accuracy increases. As a result, the accuracy is a criteria of the performance of the neural network in image classification. In this paper, a new method for high accuracy image classification is suggested. Authors thinks that recognizing things mean seeing the shape of the things. With the intuition, in the proposed method, additional edge information is applied to the image and around 3% accuracy improvement is achieved in the experiment. In order to clarify the improvement, compared feature maps in the hidden layers are visualized and analyzed. And, it is also confirmed that the feature map of the proposed method is more clear and sharp than that of the conventional one. Another merit of the proposed method is that this method can easily improve the accuracy of the conventionally existing neural networks through the transfer learning because the proposed method just modifies the first layer of the conventional neural networks.

Environmental pollution is getting serious around the world recently. Economic losses from air pollution and threats from ultra fine dust are becoming social problems. Currently, measurements are made through wood and optical measuring equipment, but there is a problem where measurements and human sense of corrective action do not match. This paper aimed to implement an algorithm of judgment to match the measured value with the human sense of visibility. Using IoT-based cameras in buildings, measured photo information is sent to the server to make corrective distance measurements, and real-time transmitted photos and existing measured photo information are processed in high-speed operation through Tensorflow, requiring high-reliability corrective distance. An algorithm that is supplemented with a SVM nonlinear regression model algorithm for existing corrective distance determination algorithms has been implemented to automate with algorithms similar to those that are directly judged by humans. In this study, a support vector machine (SVM) nonlinear regression model algorithm is used to perform high-speed computation using Tensorflow, and a system implementation model is proposed to improve reliability of the corrective judgment algorithm model.

This study presents simulated results using AWAM for the combat effectiveness of the Warrior Platform improvement. The Army is promoting for a three-stage project that will improve the effectiveness in five fields, including the survivability of warrior, in order to upgrade the platform(i.e. gears, equipments, clothing, etc). This study analyzed the improvement effects of the Dot sight, magnifying glass, bulletproof clothing, and bulletproof helmet of the first stage project, focusing on viability and lethality. Advancement of Dot sight and magnifying glass increases firearms hit rate, and improvement of bulletproof clothing and helmet progress the protection of body parts. The firearms hit rate data were obtained through combat experiments using KCTC Miles equipment. In addition to a degree of improvement of body part protection, the manual data were analyzed and entered as the AWAM's basic data. The analysis indicator utilizes the probability of kill in terms of lethality and the probability of survive in terms of the viability as the main indicator, but also additional consideration is given to the loss exchange rate. The enemy and allied platoon scale of experimental group was organized. The eight scenarios were applied to simulate and produce results in order to statistically compare before and after improvement. The analysis showed that the probability of enemy kill in terms of lethality increased by an average of 1.5 times. Multiple regression analyses also confirmed that the survival rate of the allies, contribution of firearms, and the firing rate of the firearms have a crucial impact on the loss exchange rate. This study has a significant in that the results were quantitatively analyzed by applying statistical techniques and by linking the combat experiments with the simulation to verify the effectiveness of the Warrior Platform improvement for the first time in the Army.