• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.93-102
• /
• 2023

Data processing through the cloud causes many problems, such as latency and increased communication costs in the communication process. Therefore, many researchers study edge computing in the IoT, and autonomous driving is a representative application. In indoor self-driving, unlike outdoor, GPS and traffic information cannot be used, so the surrounding environment must be recognized using sensors. An efficient autonomous driving system is required because it is a mobile environment with resource constraints. This paper proposes a machine-learning method using neural networks for autonomous driving in an indoor environment. The neural network model predicts the most appropriate driving command for the current location based on the distance data measured by the LiDAR sensor. We designed six learning models to evaluate according to the number of input data of the proposed neural networks. In addition, we made an autonomous vehicle based on Raspberry Pi for driving and learning and an indoor driving track produced for collecting data and evaluation. Finally, we compared six neural network models in terms of accuracy, response time, and battery consumption, and the effect of the number of input data on performance was confirmed.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.5
• /
• pp.157-165
• /
• 2009

In this paper, we propose a distributed model that recognize ADLs of human can be occurred in daily living places. We collect and analyze user's environmental, location or activity information by simple sensor attached home devices or utensils. Based on these information, we provide a lifecare services by inferring the user's life pattern and health condition. But in order to provide a lifecare services well-refined activity recognition data are required and without enough inferred information it is very hard to build an ADL activity recognition model for high-level situation awareness. The sequence that generated by sensors are very helpful to infer the activities so we utilize the sequence to analyze an activity pattern and propose a distributed linear time inference algorithm. This algorithm is appropriate to recognize activities in small area like home, office or hospital. For performance evaluation, we test with an open data from MIT Media Lab and the recognition result shows over 75% accuracy.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.69-74
• /
• 2022

Even after the drunk driving law was revised through the Yoon Chang-ho Act in 2019, the proportion of habitual offenders among all drunk drivers in 2021 was 4.7%, up 0.5% from 2018. In addition, drunk driving is not easily stopped due to the addiction of alcohol, and there is a high probability of recidivism in accidents as it is often driven again. Therefore, in this paper, to prevent this, when alcohol is measured using its own sensor rather than a manual police measure, the vehicle stops and related data such as the current location and time are automatically saved. Since it is not possible to develop directly on the car, this system was developed by converging various technologies and sensors such as Arduino board, Firebase, and GPS based on the IoT environment in consideration of the simulation environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1653-1659
• /
• 2022

Virtual reality content provides users with a high sense of immersion by using HMD devices. However, while wearing the HMD device, it is difficult to determine the user's location or distance from obstacles, resulting in injuries due to physical collisions. In this paper, we propose a reminder module to prevent accidents by notifying the risk of collision with obstacles while wearing the HMD device. The proposed module receives the user's state from the acceleration and gyro sensor and determines the motion that is likely to cause a collision. If there is an obstacle in the expected collision range, a buzzer sounds to the wearer. As a result of the experiment, the accuracy of obstacle detection in the state of wearing the HMD was 86.6% in the 1st stage and 83.3% in the 2nd stage, confirming the performance of the accident prevention reminder.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.291-295
• /
• 2022

This paper deal with the advanced thchnology of water supply line breakege detection system in singsan green city. the technology apply for construction eco oriented high-tech city to merge residant, industial, tour reasure parts for songsan green city furture direction achivement and response for a life style change of people in the city. Breakege detection system consist of smart prevention seat, pipeline breakege detection sensor, analysis software, server. etc.. Central control unit sent the data to hwa sung city water supply office by WCDMA in SKY. the data are states about water supply pipeline, Location.etc. This system maintain the long term life cycle of water supply plpeline by the prevention the leakege event through ackonwledge information of evnet occurrence locaion. and used to realtime sense method about demage information of the pipeline and prevent to brekege facilities during excavation work.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.897-902
• /
• 2023

The purpose of this paper is to analyze the characteristics of Silicon Photomultiplier (SiPM) for the realization of high-sensitivity radiation detection in portable detectors. Portable X-ray detectors offer the advantage of quickly accessing the patient's location and obtaining real-time images, allowing physicians to perform rapid diagnoses. However, this mobility comes with challenges in achieving accurate radiation detection. In existing detectors, SiPM is used for a simple purpose of detecting X-ray triggers. To verify the feasibility of high-sensitivity X-ray detection through SiPM, seven types of SiPM sensors were compared and selected, and their characteristics were analyzed. The SiPM used in the final test demonstrated the ability to distinguish signals at the ultra-low radiation level of 10 nGy, and it was observed that the slope of the signal rise curve varies with the X-ray tube voltage. Utilizing the characteristics of SiPM, which exhibits changes in signal level and duration with X-ray dose, it appears possible to achieve high-sensitivity measurements for X-ray detection.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.441-449
• /
• 2021

With advances in autonomous vehicles, there is a growing demand for more accurate position estimation. Especially, this is a case for a moving robot for the indoor operation which necessitates the higher accuracy in position estimation when the robot is required to execute the task at a predestined location. Thus, a method for improving the position estimation which is applicable to both the fixed and the moving object is proposed. The proposed method exploits the initial position estimation from Bluetooth beacon signals as observation signals. Then, it estimates the gravitational acceleration applied to each axis in an inertial frame coordinate through computing roll and pitch angles and combining them with magnetometer measurements to compute yaw angle. Finally, it refines the control inputs for an object with motion dynamics by computing acceleration on each axis, which is used for improving the performance of Kalman filter. The experimental assessment of the proposed algorithm shows that it improves the position estimation accuracy in comparison to a conventional Kalman filter in terms of average error distance at both the fixed and moving states.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.4
• /
• pp.184-190
• /
• 2006

Recently, Lee et al. have proposed an algorithm utilizing the signals from different paths by using bottom mounted simple linear array to estimate 3-D location of oceanic target. But this algorithm assumes that sound velocity is constant along depth of sea. Consequently, serious performance loss is appeared in real oceanic environment that sound speed is changed variously. In this paper, we present a 3-D near field localization algorithm for inhomogeneous sound speed. The proposed algorithm adopt localization function that utilize ray propagation model for multipath environment with linear sound speed profile(SSP), after that, the proposed algorithm searches for the instantaneous azimuth angle, range and depth from the localization cost function. Several simulations using linear SSP and non linear SSP similar to that of real oceans are used to demonstrate the performance of the proposed algorithm. The estimation error in range and depth is decreased by 100m and 50m respectively.

• Journal of Advanced Navigation Technology
• /
• v.28 no.4
• /
• pp.566-573
• /
• 2024

Applying autonomous driving technology to construction sites is very difficult due to safety issues. However, the application of various positioning and sensing devices, such as cameras and radars, to construction equipment is very active. Based on these technological trends, the government is making various efforts, including the Serious Accident Punishment Act and support for industrial safety management expenses, to reduce the incidence of accidents caused by construction equipment and industrial vehicles. And, related industries have been developing various safety equipment over the past few years and applying them to the field. In this paper, we investigate the current status of safety equipment-related technologies currently applied to construction equipment and industrial vehicles, and propose a direction for the development of safety technology in construction equipment based on artificial intelligence. Improving the safety and work efficiency of construction equipment based on the technology proposed in this paper should be reviewed through simulation in the future.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.109-123
• /
• 2024

Research into vision-based end-to-end autonomous driving systems utilizing deep learning and reinforcement learning has been steadily increasing. These systems typically encode continuous and high-dimensional vehicle states, such as location, velocity, orientation, and sensor data, into latent features, which are then decoded into a vehicular control policy. The complexity of urban driving environments necessitates the use of state representation learning through networks like Variational Autoencoders (VAEs) or Convolutional Neural Networks (CNNs). This paper analyzes the impact of different image state encoding methods on reinforcement learning performance in autonomous driving. Experiments were conducted in the CARLA simulator using RGB images and semantically segmented images captured by the vehicle's front camera. These images were encoded using VAE and Vision Transformer (ViT) networks. The study examines how these networks influence the agents' learning outcomes and experimentally demonstrates the role of each state representation technique in enhancing the learning efficiency and decision- making capabilities of autonomous driving systems.