• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.777-784
• /
• 2019

A pre-fire awareness and automatic notification system are required because it is possible to minimize the damage if the fire situation is precisely detected after a fire occurs in a place where people are unusual or in a mountainous area. In this study, we developed a RaspberryPi-based fire recognition system using Faster-recurrent convolutional neural network (F-RCNN) and single shot multibox detector (SSD) and demonstrated a fire alarm system that works with power line communication. Image recognition was performed with a pie camera of RaspberryPi, and the detected fire image was transmitted to a monitoring PC through an inductive power line communication network. The frame rate per second (fps) for each learning model was 0.05 fps for Faster-RCNN and 1.4 fps for SSD. SSD was 28 times faster than F-RCNN.

• 한국벤처창업학회:학술대회논문집
• /
• 2018.11a
• /
• pp.187-192
• /
• 2018

현재 급변하는 정보기술, 다양성을 추구하는 시장의 니즈, 미리 예측하지 못한 다양한 형태의 경쟁자 등의 출현으로 인해 경영환경이 급변하고 있는 것은 더 이상 새로운 현상이라고 보기는 어렵다. 이와 같이 급변하는 경영 환경은 기업 간 경쟁 심화를 불러일으키고 있으며, 경쟁 심화는 생존 및 발전을 위해 기업 특성에 맞지 않는 무분별한 전략을 활용하면서 오히려 역효과를 내고 있다는 문제를 야기하고 있다. 특히 변화하고 있는 환경 내 벤처기업 및 창업기업들의 경우 창업 후 생존율이 점차 낮아지면서 일반 기업들에 비해 경쟁력을 갖춘 기업을 찾아보기 어려운 것이 현실이다. 이에 벤처기업들은 도태되지 않고 생존하기 위해경쟁력을 강화시킬 수 있는 다양한 전략을 구사하고 있다. 벤처기업은 하나의 비즈니스 생태계 내 유기적 생명체로서 진화하기 위해 제품이나 산업의 수명주기와 마찬가지로 창업기, 초기 성장기, 고도 성장기, 성숙기, 쇠퇴기 등의 정형화된 단계를 거친다. 따라서 벤처기업은 무차별적인 전략을 통해 기업의 생존 및 성장을 도모 하는 것이 아니라 해당 기업이 놓인 수명주기 단계별로 전략, 조직 구조, 의사결정방식, 통제유형 등을 상이하게 판단하고 이에 적절한 전략을 수행해야 한다. 예를 들어, 동일 생산요소를 투입하더라도 이를 적용할 수 있는 지식이 있는 경우 더 높은 가치 창출이 가능(Aghion & Howitt, 1992) 하지만 창업 초창기의 기업은 고도 성장기의 기업보다 보유한 지식 수준 및 경험이 상대적으로 낮기 때문에 다양한 협력을 필요로 한다. 그러나 현재의 여러 선행연구들은 기업이 처한 상황을 고려하지 않은 단편적인 대처 방안이거나 혹은 부분적인 방법론을 제공하는 수준에 그치고 있다는 한계가 있다(이병헌 외, 2014). 따라서 본 연구에서는 '2016년 벤처기업정밀실태조사' 데이터를 기반으로 기업의 외부 협력 정도 및 벤처기업 지원제도 활용 정도가 경쟁력과 성과에 미치는 영향이 기업의 수명주기별로 상이하다고 보고 관련 전략 프레임워크를 제시하고자 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1280-1287
• /
• 2020

This paper proposes a vision-based food recognition method for automated production of custom cakes. A small camera module mounted on a food art printer recognizes objects' shape and estimates their center points through image processing. Through the perspective transformation, the top-view image is obtained from the original image taken at an oblique position. The line and circular hough transformations are applied to recognize square and circular shapes respectively. In addition, the center of gravity of each figure are accurately detected in units of pixels. The test results show that the shape recognition rate is more than 98.75% under 180 ~ 250 lux of light and the positioning error rate is less than 0.87% under 50 ~ 120 lux. These values sufficiently meet the needs of the corresponding market. In addition, the processing delay is also less than 0.5 seconds per frame, so the proposed algorithm is suitable for commercial purpose.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.1-8
• /
• 2022

In this paper, we propose a fire detection system based on CCTV images using an object tracking technology with YOLOv4 model capable of real-time object detection and a DeepSORT algorithm. The fire detection model was learned from 10800 pieces of learning data and verified through 1,000 separate test sets. Subsequently, the fire detection rate in a single image and fire detection maintenance performance in the image were increased by tracking the detected fire area through the DeepSORT algorithm. It is verified that a fire detection rate for one frame in video data or single image could be detected in real time within 0.1 second. In this paper, our AI fire detection system is more stable and faster than the existing fire accident detection system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.4
• /
• pp.559-569
• /
• 2022

Infrastructure engineering is a field that supports construction (assembly) as a representative industry that creates high added value and jobs by combining science and technology with knowledge, though its importance is underestimated. According to a report from the Ministry of Land, Infrastructure and Transport (Korea), the value-added rate (65.3%) of the engineering industry and the employment inducement coefficient (14 employees per billion won) are three times higher than in manufacturing. In particular,the forward value chain (such as project management and basic design) accounts for less than 10~15% of the total project cost but determines the overall price and quality of the infrastructure facilities. In this study, a work break-down system, design support module and database development method for road design projects for design platform development is presented. Based on the presented development method, a cloud-based infrastructure design platform's prototype is developed. The developed infrastructure engineering platform is expected to provide a web-based design work environment without time/space restrictions and greatly contribute to winning overseas business orders and securing competitiveness.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.87-92
• /
• 2023

With the continuous development of the speech recognition system, the recognition rate for speech has developed rapidly, but it has a disadvantage in that it cannot accurately recognize the voice due to the noise generated by mixing various voices with the noise in the use environment. In order to increase the vocabulary recognition rate when processing speech with environmental noise, noise must be removed. Even in the existing HMM, CHMM, GMM, and DNN applied with AI models, unexpected noise occurs or quantization noise is basically added to the digital signal. When this happens, the source signal is altered or corrupted, which lowers the recognition rate. To solve this problem, each voice In order to efficiently extract the features of the speech signal for the frame, the MFCC was improved and processed. To remove the noise from the speech signal, the noise removal method using the Gaussian model applied noise deviation estimation was improved and applied. The performance evaluation of the proposed model was processed using a cross-correlation coefficient to evaluate the accuracy of speech. As a result of evaluating the recognition rate of the proposed method, it was confirmed that the difference in the average value of the correlation coefficient was improved by 0.53 dB.

• Journal of Internet of Things and Convergence
• /
• v.9 no.2
• /
• pp.11-17
• /
• 2023

Smoothing is to creating a transmission plan consisting of sections of frames that can be sent at the same transmission rate for compressed and stored video data. Various algorithms have been studied for the smoothing to minimize the number of transmission rate changes, the number of transmission rate changes, and the amount of transmission rate increase. This study evaluates the performance of a smoothing algorithm that minimizes the increase in transmission rates and maximizes the increase in transmission rates when the transmission rate is required to maximize the excess bandwidth to be secured by the server in an environment with limited server bandwidth. The available transmission rates and buffer sizes available in the server are set in various ways and evaluated by the number of fps changes, the minimum fps, the average fps, and fps variability. As a result of the comparison, the proposed algorithm showed excellent average fps and fps variability.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.249-249
• /
• 2022

국외에서 산지재해를 예방하기 위해 하천 유사량을 계측하는 기존의 재래식 채집기의 문제점을 보완한 간접계측장치인 하이드로폰의 개발 및 실용화를 위한 연구를 수행하고 있다. 하지만 국내의 경우 유사량을 계측하는 기술 수준은 선진국에 비해 기초단계에 머물러 있다. 이러한 문제를 해결하기 위해 국내에서 사용하기 적합한 간접계측장치를 개발하고자 한다. 간접계측장치인 하이드로폰은 횡단구조물의 끝단에 부착하여 설치하는 형태로 개발하였다. 충돌음향 계측을 위한 센서부는 파이프와 마이크로폰으로 구성하였으며, 구조물에 부착하기 위한 고정프레임과 연결장치로 제작되었다. 설치된 계측장치는 하상에서 이동중인 토사가 파이프에 충돌할 때 발생하는 소음을 계측하며 충돌음은 데이터로거로 취득된다. 계측된 음향 데이터는 정확한 소류사량 추정을 위해 충돌 횟수에 착안한 펄스 분석 방법과 진폭의 시간 적분치에 착안한 음압적분치 방법으로 비교·검토를 수행하였다. 소류사량 추정 관계식의 유의성 분석을 수행한 후 펄스 수 기반 추정 관계식과 음압적분치 기반 추정 관계식을 공급 소류사량과 비교시 각각 29%와 33%의 오차율을 나타내는 것을 확인할 수 있었다. 앞서 선정된 소류사량 추정 관계식의 신뢰성을 확보하기 위해 관계식으로 추정할 수 있는 예측구간 및 95% 신뢰구간을 분석하였으며, 분석 결과 펄스 수 기반 추정 관계식은 92.5%, 음압적분치 기반 추정 관계식은 90.9%로 두 관계식 모두 소류사량을 추정하기에 양호한 수준으로 일치하는 것을 확인할 수 있었다. 향후 추가적인 연구를 수행한다면 수문조사 시 부족했던 유사량 측정분야의 확대에 기여할 수 있을 것으로 예상되며, 이와 관련된 사업 및 기술발전에도 기여할 것으로 기대된다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.67-77
• /
• 2023

This study represents an innovative research conducted in the smart farm environment, developing a deep learning-based disease and pest detection model and applying it to the Intelligent Internet of Things (IoT) platform to explore new possibilities in the implementation of digital agricultural environments. The core of the research was the integration of the latest ImageNet models such as Pseudo-Labeling, RegNet, EfficientNet, and preprocessing methods to detect various diseases and pests in complex agricultural environments with high accuracy. To this end, ensemble learning techniques were applied to maximize the accuracy and stability of the model, and the model was evaluated using various performance indicators such as mean Average Precision (mAP), precision, recall, accuracy, and box loss. Additionally, the SHAP framework was utilized to gain a deeper understanding of the model's prediction criteria, making the decision-making process more transparent. This analysis provided significant insights into how the model considers various variables to detect diseases and pests.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.43-51
• /
• 2024

This paper proposes a method for acquiring and analyzing ocular data using a special-purpose diver mask targeted at divers who primarily engage in underwater activities. This involves tracking the user's gaze with the help of a custom-built ocular dataset and a YOLOv8-nano model developed for this purpose. The model achieved an average processing time of 45.52ms per frame and successfully recognized states of eyes being open or closed with 99% accuracy. Based on the analysis of the ocular data, a gaze tracking algorithm was developed that can map to real-world coordinates. The validation of this algorithm showed an average error rate of about 1% on the x-axis and about 6% on the y-axis.