• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.341-348
• /
• 2022

Wi-Fi Sensing, which uses Wi-Fi technology to sense the surrounding environments, has strong potentials in a variety of sensing applications. Recently several advanced deep learning-based solutions using CSI (Channel State Information) data have achieved high performance, but it is still difficult to use in practice without explicit data collection, which requires expensive adaptation efforts for model retraining. In this study, we propose a Channel State Information Automatic Labeling System (CALS) that automatically collects and labels training CSI data for deep learning-based Wi-Fi sensing systems. The proposed system allows the CSI data collection process to efficiently collect labeled CSI for labeling for supervised learning using computer vision technologies such as object detection algorithms. We built a prototype of CALS to demonstrate its efficiency and collected data to train deep learning models for detecting the presence of a person in an indoor environment, showing to achieve an accuracy of over 90% with the auto-labeled data sets generated by CALS.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.81-87
• /
• 2023

SAE J2601 and SAE J2799, the communication protocols between a hydrogen refueling station and a fuel cell electric vehicle, only cover hydrogen charging. In this paper, we measure the hydrogen detection, current, and voltage of a fuel cell electric vehicle and transmit the sensor data to the hydrogen refueling station by changing the WiFi protocol. A small-scale laboratory model was built using Raspberry Pi for sensing, controlling, and transmitting sensor data of a fuel cell electric vehicle. The sensor data was stored in the database of the hydrogen refueling station, and a dashboard was configured using Grafana to analyze the stored data. When hydrogen is detected, the dispenser valve of the hydrogen refueling station is locked. Then, we measured the average transmission delay according to the WiFi protocol. The results showed that IEEE 802.11a is the most suitable WiFi protocol for transmitting sensor data between the hydrogen refueling station and the fuel cell electric vehicle.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.4
• /
• pp.207-212
• /
• 2015

Wi-Fi Direct allows battery powered mobile devices to form a wireless ad hoc network. Since one member of the network called Group Owner (GO) takes the role of managing the network, the network lifetime is mainly affected by the energy efficiency of GO. Hence, Wi-Fi Direct defines power saving schemes that allow GO to save the energy by turning off its radio interface during the periods called absence periods. However, the Wi-Fi Direct specification does not specify how to set parameters (denoted by PS parameters) determining the schedule of the absence periods. In this paper, we therefore propose a novel traffic-aware power saving scheme for Wi-Fi Direct networks. In particular, the proposed scheme estimates the application-level traffic load and adaptively tunes the PS parameters according to the estimated value.

• Journal of the Korea Convergence Society
• /
• v.6 no.1
• /
• pp.1-5
• /
• 2015

In this paper, we describe the design of a fusion labeling system which is controlled by the Wi-Fi signals. The Current labeling system which is used in the industry is designed to work independently on the production line not connected with internet network services. For such reasons, it is very inconvenient for the labeling system to transfer such labeling data of the production line to the server computer. We propose a labeling system connected to the Wi-Fi service being able to send real-time transmission of labeling data. This system can supply the labeling data of production line to the server computer in realtime and improve the production quality than the existing system.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2010.04a
• /
• pp.299-300
• /
• 2010

This paper presents experimental results on frequency interference phenomena between WiFi and ZogBee communication systems which are used for wireless communication in a port. When communication systems use a frequency band in a region, it hurts communication reliability. Hence, understanding and analysis on frequency interference phenomena through experiments. With various experiments between WiFi and ZigBee, we find out that 26th channel of ZigBee collides with WiFi communication channels, which is unknown result yet.

• The KIPS Transactions:PartB
• /
• v.19B no.3
• /
• pp.177-182
• /
• 2012

We propose effective motion and observation models for the position of a WiFi-equipped smartphone user in large indoor environments. Three component motion models provide better proposal distribution of the pedestrian's motion. Our Gaussian interpolation-based observation model can generate likelihoods at locations for which no calibration data is available. These models being incorporated into the particle filter framework, our WiFi fingerprint-based localization algorithm can track the position of a smartphone user accurately in large indoor environments. Experiments carried with an Android smartphone in a multi-story building illustrate the performance of our WiFi localization algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.575-577
• /
• 2013

Recently most of the hand-held smart devices have WiFi communication facility. This makes WiFi AP(access point) popular and cheaper than before. These circumstance launches some services with AP providing location based services and device control services. In this paper, we propose a AP based control system. The control system consists of AP's, AP controller and Android application program. The AP can collect MAC address information of the associated smart devices and control connected devices. The AP controller maintains DB for smart device position information and device control information. Finally Android application program provides users location based service and device control service.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.7-10
• /
• 2012

In this thesis, Wi-Fi Direct which can communicate with other device without AP, we study how to be selected GO considering multi-user connection and we apply it to application. We give the weight how many time a device was GO and how many time the device connected with other devices in 24 hours. With this value, the device is selected to GO when other devices request the connection. We show that the application which we implemented select right GO.

• Electronics and Telecommunications Trends
• /
• v.33 no.5
• /
• pp.64-75
• /
• 2018

People usually check their social media, e-mail, and online news on their smartphones using their carrier network. During this process, much of the data traffic is offloaded to ubiquitous Wi-Fi networks. Such offloading will continue to increase rapidly because of flourishing public Wi-Fi networks located around the world. In this technical report, we first investigate domestic public Wi-Fi projects, and followed by foreign projects. In addition, we investigate the Wi-Fi technology evolution that has been standardized in IEEE 802. More and more people are tending to use Wi-Fi, not only at home or work, but also on public transport such as buses and trains. Hence, it is important to come up with ideas that can realize Wi-Fi onboard. The key technologies needed here are related to a mobile wireless backhaul between trains and trackside radio equipment, or between buses and roadside units. Thus, we also investigate the mobile wireless backhaul technologies and their trends.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.507-510
• /
• 2011

As the amount of the wireless mobile products like a 'Smart phone' used increases, the studies about the Location Based Service (LBS) is highly increasing. Outdoor location determination can use the GPS which is built-in in the wireless mobile products. However, it is not possible to use GPS inside the huge cruise bigger than a normal building, it is regarded to consider Indoor location determination which is appropriate at the inside environment. Wi-Fi (Wireless Fidelity) does not need an extra installation process because it is already installed here and there inside the building. In this respect, Wi-Fi has low price competitiveness compared to other wireless sensor products. In this paper, I will introduce 'Bayesian Algorithm' which can recognize useful space with Wi-Fi signal.