• Journal of Digital Contents Society
• /
• v.19 no.9
• /
• pp.1779-1785
• /
• 2018

In this paper, we propose an error correction method to improve the accuracy of human activity recognition using sensor event data obtained by smart devices such as wearable and smartphone. In the context awareness through the smart device, errors inevitably occur in sensing the necessary context information due to the characteristics of the device, which degrades the prediction performance. In order to solve this problem, we apply Kalman filter's error correction algorithm to compensate the signal values obtained from 3-axis acceleration sensor of smart device. As a result, it was possible to effectively eliminate the error generated in the process of the data which is detected and reported by the 3-axis acceleration sensor constituting the time series data through the Kalman filter. It is expected that this research will improve the performance of the real-time context-aware system to be developed in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.534-539
• /
• 2008

This paper is about intelligent hexapod robot for the support walking of the aged person. The robot using various sensors and small camera has various abilities of forward backward walking, turing left or right, control the speed of walking, avoiding the obstacles and detecting risky situation of fire or gas. To let the aged feel soft and safe walking, we used special servo motor and developed hexapod walking mechanism and effective algorithm.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.71-78
• /
• 2013

In this paper, we propose a method to infer the user's behavior and situation through collected data from multi-sensor equipped with a smart clothing and it was implemented as a smartphone App. User context reasoning and behavior determine is very difficult using single sensor depending on the measured value of the sensor varies from environmental noise. So, the reasoning and the digital filter algorithms to determine user behavior reducing noise and are required. In this paper, we used EWMA, Kalman Filter and SVM processing behavior for 3-axis value as a representative value of one.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.4
• /
• pp.19-24
• /
• 2013

The problem of elderly people with weak physical health has become a very important issue in the aging society. Elderly people with very low judgment and decision-making skills often falls because of the degradation of the strength and balance. Due to the fall triggered off fractures, parenchyma damage, and casualties, generally fast emergency treatment is needed. In this paper, an automatic fall detection system consisting of a triaxial accelerometer and tilt sensor. Using the fall system, the performance of the system was analyzed in many situations. The experimental results showed more than 92% analytical skills.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.433-440
• /
• 2023

When the reflector is hit by a vehicle or returned by a storm, an event is generated by the impact sensor and a trigger is operated. The trigger processing algorithm of this paper compares the X, Y, and Z values of the gyro sensor with the registered values and proposes to drive them to the original values by the operation of the 3-axis driving motor. And by recognizing the vehicle license plate, if the vehicle is stolen or a social problem, information is provided to the police operation network. When the reflector is stolen or moved, it has a registered GPS value, so it operates the theft monitoring function to process it.

• Journal of the Korean Chemical Society
• /
• v.68 no.4
• /
• pp.185-190
• /
• 2024

Recently, it was reported that the benzobisoxazole (BBO) molecule can be used for independent modulation of the HOMO and LUMO energy levels. In this study, we utilized this interesting property of BBO to quantitatively investigate the substituent effects according the substituents. We designed and proposed four BBO model systems (1BBO, 2BBO, 3BBO and 4BBO) by extending the π-conjugation lengths based on a BBO molecule. Two directions of substitution (x-axis and y-axis) and 15 various substituents were considered. From strong correlation between the LUMO energy levels of x-axis substitution and HOMO energy levels of y-axis substitution calculated from DFT method, it is found that the standardization of substitution effects can be established from BBO model systems. In addition, we demonstrated that the HOMO values of y-axis substituted 3BBO show the best performance to define the order of substituent effects. Our proposed way can be used to expect the substituent effect of any arbitrary substituents and develop the organic sensors and organic light emitting diodes.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.79-86
• /
• 2008

This paper proposed the appropriate installation angle of skewed sensors for measuring vehicle wandering data, which are collected to figure out the location of dynamic weight of a moving vehicle on roadways. We developed a device using tape-switch sensors and a computer program and collected vehicle wandering data with the device and probe vehicles. As a result, the steeper the skewed sensor was installed, the lower the error was shown. However, we could not collect proper data when a skewed sensor was set up higher than $30^{\circ}$ due to tandem axle. Therefore, this study suggested the appropriate angle of skewed sensors as a degree of $20^{\circ}$ to $25^{\circ}$ for gathering wandering data.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.97-98
• /
• 2007

본 논문에서는 운동시간과 칼로리 소모량, 운동시신체운동정도를 3축가속도 센서를 이용하여 측정하는 건강밴드를 설계 하였다. 건강관리를 위해 하는 운동은 많은 양의 운동을 하는 것 보다 규칙성 건강을 관리를 해야 한다. 주거환경의 변화가 친환경적으로 되는 지금 체육시설을 이용하지 않고 쉽게 집 주변에서 운동을 원하는 사람이 많아지고 있기 때문에 건강밴드를 설계하여 보다 쉽게 규칙성 있게 도와주는 운동 보조 시스템을 설계 하여 각 운동별로 센서의 데이터를 측정하였다. 데이터론 측정한 결과 걷기, 조깅, 줄넘기의 3축가속도 센서의 측정간은 걷기에서는 X축의 센서의 변화량이 다른 축의 변화보다 변화량이 많이 심하였고 조깅의 경우 X, Y, Z축의 변화량이 전체적으로 걷기보다 변화가 많았다. 줄넘기에서는 걷기, 조깅과는 다르게 신체의 움직임이 상하로 많이 있는 운동이기 때문에 Y, Z축의 변화량이 X축의 변화량 보다 많이 측정되었다. 이러한 결과를 바탕으로 본 연구의 결과는 운동별 신체의 사용량 측정에 이용이 가능하다.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1972_1973
• /
• 2009

한의학에서는 사상체질(태양인, 태음인, 소양인, 소음인) 구분을 위해 손등피부의 특징 중 하나인 거침/미끄러움을 이용하여 한의사의 주관적인 판단으로 사상체질을 구분해 왔다. 한의사의 손등피부 거칠기의 주관적인 촉진을 정량적 및 객관적으로 진단하기 위하여 피부마찰력진단기기를 개발하였다. 피부마찰력진단기기는 3축 로드셀 센서를 이용하여 한의사가 손등피부를 만지는 것과 같은 움직임으로 측정하며, 측정된 물리량 중 피부의 거침/미끄러움으로 계산되는 운동마찰계수 값을 이용하여 손등피부의 특성을 나타내었다. 본 연구에서는 피부마찰력 진단기기를 이용하여 객관적으로 손등피부의 특성을 측정해 보고 사상체질 진단의 객관적인 지표를 찾는 것을 목표로 한다.