• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.246-252
• /
• 2018

Hand gestures are attracting attention as a NUI (Natural User Interface) of wearable devices such as smart glasses. Recently, to support efficient media consumption in IoT (Internet of Things) and wearable environments, the standardization of IoMT (Internet of Media Things) is in the progress in MPEG. In IoMT, it is assumed that hand gesture detection and recognition are performed on a separate device, and thus provides an interoperable interface between these modules. Meanwhile, deep learning based hand gesture recognition techniques have been recently actively studied to improve the recognition performance. In this paper, we propose a method of hand gesture recognition based on CNN (Convolutional Neural Network) for various applications such as media consumption in wearable devices which is one of the use cases of IoMT. The proposed method detects hand contour from stereo images acquisitioned by smart glasses using depth information and color information, constructs data sets to learn CNN, and then recognizes gestures from input hand contour images. Experimental results show that the proposed method achieves the average 95% hand gesture recognition rate.

• Journal of Navigation and Port Research
• /
• v.44 no.6
• /
• pp.557-563
• /
• 2020

Digital Twin Technology is currently being utilized in many industries and logistics seems soon to follow that trend. Currently, technology introduction to container terminals is restrictedly developing. In reviewing the existing literature, it became clear that research on the application of Digital Twin technology for container terminals is deficient. This study fulfilled AHP and IPA analysis causing fields to adjust priority at the container terminal. The result of analysis on the urgent necessity of adjustable fields' detailed elements from Digital Twin Technology, ATC, intelligent CCTV, and container yards, and showed that they were of the highest priority level. Also, VR/AR Equipment, AYT, Smart Container, Automated Container Delivery Facility, Refrigerated/Freezer Container, Wearable Device for Port Maintenance, and Smart Buoy were reviewed in detail. Our group suggests AQC, Berth, AGV, ASC, Apron, and Automated Mooring as potentially useful Digital Twin Technologies. Finally, our research suggests the OSS equipment, intermodal linkage facility, intelligent drone, and hazardous material storage are areas of low priority.

• The Journal of the Korea Contents Association
• /
• v.15 no.9
• /
• pp.37-46
• /
• 2015

Nowadays, given the popularity of wearable devices, The smartwatch is considered as the leading product category and taking the main share of wearable device market. So far smartwatch is only used as an accessorial device of smart phones due to its screen size. The objective of this study is to review literatures and find solutions to overcome the screen limitations. In the literature review, several methods are introduced including using other devices as output devices, other object as screens by projecting technologies, and enlarging screen size by flexible display. Based on that, possible solutions including seamless display and user-centered interaction methods were investigated. Future research directions were also introduced at the end of this study.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.8
• /
• pp.18-26
• /
• 2015

Measuring the heart rate during exercise is important to properly control the amount of exercise. With the recent advent of smart device usage, there is a dramatic increase in interest in devices for the real-time measurement of the heart rate during exercise. During intensive exercise, accurate heart rate estimation from wrist-type photoplethysmography (PPG) signals is a very difficult problem due to motion artifact (MA). In this study, we propose an efficient algorithm for an accurate estimation of the heart rate from wrist-type PPG signals. For the twelve data sets, the proposed algorithm achieves the average absolute error of 1.38 beat per minute (BPM) and the Pearson correlation between the estimates and the ground-truth of heart rate was 0.9922. The proposed algorithm presents the strengths in an accurate estimation together with a fast computation speed, which is attractive in application to wearable devices.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1345-1352
• /
• 2023

With the development of virtual reality (VR) and blockchain technology, Metaverse is being used in various fields such as games, education, and social networking. At the same time, shipments of wearable devices such as smartwatches are growing every year, becoming more and more integrated into people's daily lives. This study presents a new possibility of reflecting the user's body signals measured through the combination of the two phenomena in the metaverse character. Various biometric information such as the user's heart rate and amount of exercise collected through the smartwatch are reflected on the character in the metaverse, allowing the user's physical condition to be reflected in the virtual world. Through this, Metaverse is expected to provide a new experience that can be called 'extended reality' beyond simple virtual reality, improve user's satisfaction with Metaverse, and suggest a direction for the development of smartwatches.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.3
• /
• pp.225-232
• /
• 2015

The smart watch is the most popular wearable computing device because it takes a form of wristwatch. Many smart watches have adopted the touch screen interface due to the limited size of display. This paper focuses on touch key size and spacing that affect the usability about the touch key of smart watch. The experiments were made for four touch key sizes (width${\times}$height; $5{\times}5$, $5{\times}7$, $7{\times}5$, $7{\times}7mm$) and nine touch key spacing (vertical${\times}$horizontal; $0{\times}0$, $0{\times}1$, $0{\times}3$, $1{\times}0$, $1{\times}1$, $1{\times}3$, $3{\times}0$, $3{\times}1$, $3{\times}3mm$). The completion time, error rate, control discomfort and identification discomfort were measured. The touch key size $7{\times}7$, $7{\times}5$ and the touch key spacing $3{\times}3$, $1{\times}3$ provided the best results in terms of the completion time and the control discomfort, while the square touch key ($7{\times}7$, $5{\times}5$) provided the best performance for the error rate measure. The result of this study can help ergonomically design the touch interface of the smart watch.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.2
• /
• pp.129-132
• /
• 2017

A conventional pulse oximeter has high power consumption; thus, its mobility is severely limited. In this paper, we discuss the drawbacks of the existing pulse oximeters and propose a new ultra-low-power pulse oximeter that supports wireless data transmission for remotely monitoring vital signs, such as peripheral capillary oxygen saturation (SpO2) and beats per minute (BPM). We could notably reduce power consumption by using a low-frequency single clock in all well-customized modules. Also, our device is publicly certified, and thus, possibly engaged in clinical trials for commercial use.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.107-114
• /
• 2018

Recently, various wearable personal devices such as a smart watch have been developed and these personal devices are being miniaturized. The user desires to receive new services from personal devices as well as services that have been received from personal computers, anytime and anywhere. However, miniaturization of devices involves constraints on resources such as limited input and output and insufficient power. In order to solve these resource constraints, this paper proposes a resource collaboration system which provides a service by composing sharable resources in the resource sharing environment like IoT. the paper also propose a method to infer and recommend user-customized resources among various sharable resources. For this purpose, the paper defines an ontology for resource inference. This paper also classifies users behavior types based on a user model and then uses them for resource recommendation. The paper implements the proposed method as a prototype system on a personal device with limited resources developed for resource collaboration and shows the effectiveness of the proposed method by evaluating user satisfaction.

• International Journal of Advanced Culture Technology
• /
• v.7 no.1
• /
• pp.162-173
• /
• 2019

This study proposed 'Body Food,' an interactive tactile mat that provides interactive visual responses and induces physical activity in young children at the time of developing tactile and five senses, along with the touch of various stimuli. The product combines fiber materials and digital content to achieve a variety of visual and auditory responses in real time when children touch the fabric. User tests were conducted for 4-year-olds and the result was positive in terms of physical exercise and artistic experience, but quantitative testing is required to generalize it. In the future, we will complement physical and digital contents to realize more complete product.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.186-191
• /
• 2023

Neural Networks are widely used for huge variety of tasks solution. Machine Learning methods are used also for signal and time series analysis, including electrocardiograms. Contemporary wearable devices, both medical and non-medical type like smart watch, allow to gather the data in real time uninterruptedly. This allows us to transfer these data for analysis or make an analysis on the device, and thus provide preliminary diagnosis, or at least fix some serious deviations. Different methods are being used for this kind of analysis, ranging from medical-oriented using distinctive features of the signal to machine learning and deep learning approaches. Here we will demonstrate a neural network-based approach to this task by building an ensemble of 1D CNN classifiers and a final classifier of selection using logistic regression, random forest or support vector machine, and make the conclusions of the comparison with other approaches.