• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.3
• /
• pp.119-127
• /
• 2020

The detection and recognition of abnormal driving becomes crucial for achieving safety in Intelligent Transportation Systems (ITS). This paper presents a feature extraction method based on spectral data to train a neural network model for driving behavior recognition. The proposed method uses a two stage signal processing approach to derive time-saving and efficient feature vectors. For the first stage, the feature vector set is obtained by calculating variances from each frequency bin containing the power spectrum data. The feature set is further reduced in the second stage where an intersection method is used to select more significant features that are finally applied for training a neural network model. A stream of live signals are fed to the trained model which recognizes the abnormal driving behaviors. The driving behaviors considered in this study are weaving, sudden braking and normal driving. The effectiveness of the proposed method is demonstrated by comparing with existing methods, which are Particle Swarm Optimization (PSO) and Convolution Neural Network (CNN). The experiments show that the proposed approach achieves satisfactory results with less computational complexity.

• International Journal of Contents
• /
• v.16 no.3
• /
• pp.1-17
• /
• 2020

Human motion recognition is essential for user-centric services such as surveillance-based security, elderly condition monitoring, exercise tracking, daily calories expend analysis, etc. It is typically based on the movement data analysis such as the acceleration and angular velocity of a target user. The existing motion recognition studies are only intended to measure the basic information (e.g., user's stride, number of steps, speed) or to recognize single motion (e.g., sitting, running, walking). Thus, a new mechanism is required to identify the transition of single motions for assessing a user's consecutive motion more accurately as well as recognizing the user's body and surrounding situations arising from the motion. Thus, in this paper, we collect the human movement data through Android smartphones in real time for five targeting single motions and propose a mechanism to recognize a consecutive motion including transitions among various motions and an occurred situation, with the state transition model to check if a vulnerable (life-threatening) condition, especially for the elderly, has occurred or not. Through implementation and experiments, we demonstrate that the proposed mechanism recognizes a consecutive motion and a user's situation accurately and quickly. As a result of the recognition experiment about mix sequence likened to daily motion, the proposed adoptive weighting method showed 4% (Holding time=15 sec), 88% (30 sec), 6.5% (60 sec) improvements compared to static method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.491-498
• /
• 2022

In our daily life, quality of sleeping is closely related to happiness index. Whether or not people perceive sleep disturbance as a chronic disease, people complain of many difficulties, and in their daily life, they often experience difficulty breathing during sleep. It is very important to automatically recognize breathing-related disorders during a sleep, but it is very difficult in reality. To solve this problem, this paper proposes a mobile-based non-contact sleeping monitoring for health management at home. Respiratory signals during the sleep are collected by using the sound sensor of the smartphone, the characteristics of the signals are extracted, and the frequency, amplitude, respiration rate, and pattern of respiration are analyzed. Although mobile health does not solve all problems, it aims at early detection and continuous management of individual health conditions, and shows the possibility of monitoring physiological data such as respiration during the sleep without additional sensors with a smartphone in the bedroom of an ordinary home.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.286-291
• /
• 2020

In this paper, we propose a system that recommends music through tempo-oriented music classification and sensor-based human activity recognition. The proposed method indexes music files using tempo-oriented music classification and recommends suitable music according to the recognized user's activity. For accurate music classification, a dynamic classification based on a modulation spectrum and a sequence classification based on a Mel-spectrogram are used in combination. In addition, simple accelerometer and gyroscope sensor data of the smartphone are applied to deep spiking neural networks to improve activity recognition performance. Finally, music recommendation is performed through a mapping table considering the relationship between the recognized activity and the indexed music file. The experimental results show that the proposed system is suitable for use in any practical mobile device with a music player.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.1
• /
• pp.20-29
• /
• 2021

This study developed a smartwatch and a wind speed system in accordance with the necessity of a device that provides the information required in marine leisure. Based on a marine leisure smartwatch with a multi-sensor, a gyro box, and a wind speed system, external data such as GPS, motion, humidity, temperature, air pressure, and heart rate can be collected. In addition, the collected external environment data can be managed through an application on a smartphone, which is an Android-based mobile device. The developed smartwatch and wind speed system are expected to contribute to increasing accessibility and revitalization of the marine leisure industry. In addition, in terms of safety and education, the need for a device that provides marine information is large, so it is expected to increase the possibility of entering the high value-added market and improve the product localization rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.570-576
• /
• 2020

This study uses beacons and smartphone Global Positioning System (GPS) receivers to establish a location-based disaster/hazard prediction system. Beacons are usually installed indoors to locate users using triangulation in the room, but this study is differentiated from previous studies because the system is used outdoors to collect information on registration location and temperature and humidity in hazardous areas. In addition, since it is installed outdoors, waterproof, dehumidifying, and dustproof functions in the beacons themselves are required, and in case of heat and humidity, the sensor must be exposed to the outside, so the waterproof function is supplemented with a separate container. Based on these functions, information on declining and vulnerable areas is identified in real time, and temperature/humidity information is collected. We also propose a system that provides weather and fine-dust information for the area concerned. User location data are acquired through beacons and smartphone GPS receivers, and when users transmit from declining or vulnerable areas, they can establish the data to identify dangerous areas. In addition, temperature/humidity data in a microspace can be collected and utilized to build data to cope with climate change. Data can be used to identify specific areas of decline in a microspace, and various analyses can be made through the accumulated data.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.17-22
• /
• 2020

Behavior-based authentication technology, which is currently being researched a lot, requires a long extraction of a lot of data to increase the recognition rate of authentication compared to other authentication technologies. This paper uses the touch sensor and the gyroscope embedded in the smartphone in the Android environment to measure five times to the user to use only the minimum data that is essential among the behavior feature data used in the behavior-based authentication study. By requesting, a total of six behavior feature data were collected by touching the five touch screen, and the mean value was calculated from the changes in data during the next touch measurement to measure the cosine similarity between the value and the measured value. After generating the allowable range of cosine similarity by performing, we propose a user behavior based authentication method that compares the cosine similarity value of the authentication attempt data. Through this paper, we succeeded in demonstrating high performance from the first EER of 37.6% to the final EER of 1.9% by adjusting the threshold applied to the cosine similarity authentication range even in a small number of feature data and experimenter environments.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.99-106
• /
• 2024

In this paper, we design and implement the HealthSchedule app, which records exercise data based on the GPS sensor embedded in smartphones. This app utilizes the smartphone's GPS sensor to collect real-time location information of the user and displays the movement path to the designated destination. It records the user's actual path using latitude and longitude coordinates. Users register exercise activities and destination points when scheduling, and initiate the exercise. When measuring the current location, a lime green departure marker is generated, and the movement path is displayed in blue, with the destination marker and a surrounding 25-meter radius circle shown in sky blue. Using the coordinates of the starting point or the previous location and the current GPS sensor-transmitted location coordinates, it measures the distance traveled, time taken, and calculates the speed. Furthermore, it accumulates measurement data to provide information on the total distance traveled, movement path, and overall average speed. Even when reaching the destination during exercise, the movement path continues to accumulate until the completion button is clicked. The completion button is activated when the user moves into the sky blue circular area with a radius of 25 meters, centered around the initially set destination. This means that the user must reach the designated destination, and if they wish to continue exercising without clicking the completion button, they can do so. Depending on the selected exercise type, the app displays the calories burned, aiming to increase user engagement and a sense of accomplishment.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.9
• /
• pp.107-113
• /
• 2017

In this paper, we propose a medication reminder system using IoT platforms and products to help old adults keep track of their medication schedule, one of 10 Korean instrumental activities in daily living (K-IADL). An interworking architecture based on the oneM2M standard platform is designed to allow various IoT products to be connected each other through interworking proxy entities. A prototype system for the medication reminder service is developed, which consists of a pair of off-the-shelf pill bottle and container box embedded with an NFC tag and reader respectively, three types of actuators including a LIFX LED lightbulb, Musaic speaker, Microsoft Band 2, and smartphone applications. The experiment shows that our medication reminder system can make alarms for old adults to take their pills appropriately considering where they are and when they have food inferred from data collected from sensors including ultrasonic sensor and rice cooker, fostering them to keep their medication routine.