• Journal of Animal Science and Technology
• /
• v.63 no.6
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

• Journal of Digital Convergence
• /
• v.15 no.1
• /
• pp.381-391
• /
• 2017

Biometric technology is a technology for authenticating a user using the physical or behavioral features of the inherent characteristics of the individual. With the necessity and efficiency of the technology in the fields of finance, security, access control, medical welfare, inspection, and entertainment, the service range has been expanding. Biometrics using biometric information such as fingerprints and faces have been exposed to counterfeit and disguised threats and become a social problem. Recent studies using a bio-signal from the inside of the body other than the bio-information of the external body are being developed. This paper analyzes the recent research and technology of biometric systems using bio-signals, ECG, heart sounds, EEG, and EMG to present the skills needed for the development direction. In the future, utilizing the deep learning to build and analyze database to manage bio-signal based big data for the complex condition of individuals, biometrics technologies suitable for real time environment are expected to be researched.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.23-32
• /
• 2024

NVS (Novel View Synthesis) is a field in computer vision that reconstructs new views of a scene from a set of input views. Real-time rendering and high performance are essential for NVS technology to be effectively utilized in various applications. Recently, 3D-GS (3D Gaussian Splatting) has gained popularity due to its faster training and inference times compared to those of NeRF (Neural Radiance Fields)-based methodologies. However, since 3D-GS reconstructs a 3D (Three-Dimensional) scene by splitting and cloning (Density Control) Gaussian points, the number of Gaussian points continuously increases, causing the model to become heavier as training progresses. To address this issue, we propose two methodologies: 1) Gaussian blending, an improved density control methodology that removes unnecessary Gaussian points, and 2) a performance enhancement methodology using a depth estimation model to minimize the loss in representation caused by the blending of Gaussian points. Experiments on the Tanks and Temples Dataset show that the proposed methodologies reduce the number of Gaussian points by up to 4% while maintaining performance.

• Korean Journal of Agricultural Science
• /
• v.46 no.2
• /
• pp.381-393
• /
• 2019

A smart farm is a system that combines information and communication technology (ICT), internet of things (IoT), and agricultural technology that enable a farm to operate with minimal labor and to automatically control of a greenhouse environment. Machine learning based on recently data-driven techniques has emerged with big data technologies and high-performance computing to create opportunities to quantify data intensive processes in agricultural operational environments. This paper presents research on the application of machine learning technology to diagnose the growth status of crops and predicting the harvest time of strawberries in a greenhouse according to image processing techniques. To classify the growth stages of the strawberries, we used object inference and detection with machine learning model based on deep learning neural networks and TensorFlow. The classification accuracy was compared based on the training data volume and training epoch. As a result, it was able to classify with an accuracy of over 90% with 200 training images and 8,000 training steps. The detection and classification of the strawberry maturities could be identified with an accuracy of over 90% at the mature and over mature stages of the strawberries. Concurrently, the experimental results are promising, and they show that this approach can be applied to develop a machine learning model for predicting the strawberry harvesting time and can be used to provide key decision support information to both farmers and policy makers about optimal harvest times and harvest planning.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.537-540
• /
• 2018

본 논문은 Jetson_TX2(임베디드 보드)의 ROS(Robot Operating System)기반으로 맵 지도를 작성하고, SLAM 및 DQN(Deep Q-Network)을 이용한 목적지까지의 이동명령(목표 선속도, 목표 각속도)을 자이로센서로 측정한 현재 각속도를 이용하여 Cortex-M3의 기반의 MCU(Micro Controllor Unit)에 하달하여 엔코더(encoder) 모터에서 측정한 현재 선속도와 자이로센서에서 측정한 각속도 값을 이용하여 PID제어를 통한 실내 자율주행 서비스 로봇.

• Journal of the Korea Safety Management & Science
• /
• v.22 no.1
• /
• pp.9-14
• /
• 2020

Artificial intelligence (AI) has been applied to most industries by enhancing automation and contributing greatly to efficient processes and high-quality production. This research analyzes the applications of AI-based automobile accident prevention systems. It deals with AI-based collision prevention systems that learn information from various sensors attached to cars and AI-based accident detection systems that automatically report accidents to the control center in the event of a collision. Based on the literature review, technological and institutional changes are taking place at the national levels, which recognize the effectiveness of the systems. In addition, start-ups at home and abroad as well as major car manufacturers are in the process of commercializing auto parts equipped with AI-based collision prevention technology.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.808-810
• /
• 2018

Pedestrian tracking is a particular problem of object tracking, and an important component in various vision-based applications, such as autonomous cars or surveillance systems. After several years of development, pedestrian tracking in videos is still a challenging problem because of various visual properties of objects and surrounding environment. In this research, we propose a tracking-by-detection system for pedestrian tracking, which incorporates Convolutional Neural Network (CNN) and color information. Pedestrians in video frames are localized by a CNN, then detected pedestrians are assigned to their corresponding tracklets based on similarities in color distributions. The experimental results show that our system was able to overcome various difficulties to produce highly accurate tracking results.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.168-173
• /
• 2024

This paper proposes a solution for innovating crime prevention and real-time response through the development of the Smart Drone Police System. The system integrates big data, artificial intelligence (AI), the Internet of Things (IoT), and autonomous drone driving technologies [2][5]. It stores and analyzes crime statistics from the Statistics Office and the Public Prosecutor's Office, as well as real-time data collected by drones, including location, video, and audio, in a cloud-based database [6][7]. By predicting high-risk areas and peak times for crimes, drones autonomously patrol these identified zones using a self-driving algorithm [5][8]. Equipped with video and voice recognition technologies, the drones detect dangerous situations in real-time and recognize threats using deep learning-based analysis, sending immediate alerts to the police control center [3][9]. When necessary, drones form an ad-hoc network to coordinate efforts in tracking suspects and blocking escape routes, providing crucial support for police dispatch and arrest operations [2][11]. To ensure sustained operation, solar and wireless charging technologies were introduced, enabling prolonged patrols that reduce operational costs while maintaining continuous surveillance and crime prevention [8][10]. Research confirms that the Smart Drone Police System is significantly more cost-effective than CCTV or patrol car-based systems, showing a 40% improvement in real-time response speed and a 25% increase in crime prevention effectiveness over traditional CCTV setups [1][2][14]. This system addresses police staffing shortages and contributes to building safer urban environments by enhancing response times and crime prevention capabilities [4].

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.529-532
• /
• 2021

본 논문은 서비스 로봇 분야에서 역할을 수행하는 ROS 및 딥러닝 기반 모듈형 6자유도 매니퓰레이터의 설계 방법 및 성능 개선 결과를 제시한다. 기구적 설계, 모터 선정, 역 기구학 해석 방법 및 지능적 제어 방법에 대한 개선점과 향후 연구과제에 대해 다루었다. 특히 고정된 작업 반경 안에 있는 물체를 검출하고 이동시키는 방법을 딥러닝학습에 의해 정확도를 증가시키며, 임의의 위치에 존재하는 다양한 작업환경에서도 성공적인 작업수행이 가능하도록 수직 다관절 모듈형 매니퓰레이터를 설계하고 주요 성능을 검증하였으며 사용자의 사용 목적에 맞게 다양한 환경에서의 임무 수행이 가능하도록 설계하였다.

• Journal of Korean Society for Quality Management
• /
• v.47 no.4
• /
• pp.783-793
• /
• 2019

Purpose: The purpose of this study is to apply the machine and deep learning methodology on error terms which are continuously auto-generated on the sensors with specific time period and prove the improvement effects of power generator prediction diagnosis system by comparing detection ability. Methods: The SVM(Support Vector Machine) and MLP(Multi Layer Perception) learning procedures were applied for predicting the target values and sequentially producing the error terms for confirming the detection improvement effects of suggested application. For checking the effectiveness of suggested procedures, several detection methodologies such as Cusum and EWMA were used for the comparison. Results: The statistical analysis result shows that without noticing the sequential trivial changes on current diagnosis system, suggested approach based on the error term diagnosis is sensing the changes in the very early stages. Conclusion: Using pattern of error terms as a diagnosis tool for the safety control process with SVM and MLP learning procedure, unusual symptoms could be detected earlier than current prediction system. By combining the suggested error term management methodology with current process seems to be meaningful for sustainable safety condition by early detecting the symptoms.