A Road Defect Detection System Using Smartphones.

We propose a novel approach to detecting road defects by leveraging smartphones. This approach presents an automatic data collection mechanism and a deep learning model for road defect detection on smartphones. The automatic data collection mechanism provides a practical and reliable way to collect and label data for road defect detection research, significantly facilitating the execution of investigations in this research field. By leveraging the automatically collected data, we designed a CNN-based model to classify speed bumps, manholes, and potholes, which outperforms conventional models in both accuracy and processing speed. The proposed system represents a highly practical and scalable technology that can be implemented using commercial smartphones, thereby presenting substantial promise for real-world applications.

Practical and Accurate Indoor Localization System Using Deep Learning.

Indoor localization is an important technology for providing various location-based services to smartphones. Among the various indoor localization technologies, pedestrian dead reckoning using inertial measurement units is a simple and highly practical solution for indoor localization. In this study, we propose a smartphone-based indoor localization system using pedestrian dead reckoning. To create a deep learning model for estimating the moving speed, accelerometer data and GPS values were used as input data and data labels, respectively. This is a practical solution compared with conventional indoor localization mechanisms using deep learning. We improved the positioning accuracy via data preprocessing, data augmentation, deep learning modeling, and correction of heading direction. In a horseshoe-shaped indoor building of 240 m in length, the experimental results show a distance error of approximately 3 to 5 m.

Enabling WLAN and WPAN Coexistence via Cross-Technology Communication.

In the limited frequency spectrum shared by various wireless communication technologies, cross-technology interference is an important factor which determines communication performance. A variety of coexistence methods to reduce the impact of this interference have been studied, but most of them cannot explicitly coordinate the shared spectrum and are not practical. This paper presents an explicit coexistence mechanism using cross-technology communication among heterogeneous wireless technologies. This mimics "carrier sense multiple access with collision avoidance" (CSMA/CA) via bidirectional cross-technology communication, which is called CTC-CSMA/CA. It allows communication between heterogeneous wireless technologies in order to achieve CSMA/CA. This accurately assigns required channel resources by directly sending and receiving feedback. CTC-CSMA/CA is a highly compatible technology because it does not require any modification to the IEEE 802.11 standard or any extra hardware. In addition, Zigbee can operate with a low duty cycle by synchronizing it to a periodic Wi-Fi beacon. We implemented CTC-CSMA/CA using a commodity Wi-Fi access point and a commercial Zigbee platform. Our experiments showed that the channels are coordinated more accurately by our method, which significantly improves Zigbee throughput, than by conventional schemes. We expect the proposed scheme to be an important application case in designing future cross-technology communication.

An Adaptive Spreading Factor Selection Scheme for a Single Channel LoRa Modem.

When the low power wide area network (LPWAN) was developed for the internet of things (IoT), it attracted significant attention. LoRa, which is one of the LPWAN technologies, provides low-power and long-range wireless communication using a frequency band under 1 GHz. A long-range wide area network (LoRaWAN) provides a simple star topology network that is not scalable; it supports multi-data rates by adjusting the spreading factor, code rate, and bandwidth. This paper proposes an adaptive spreading factor selection scheme for corresponding spreading factors (SFs) between a transmitter and receiver. The scheme enables the maximum throughput and minimum network cost, using cheap single channel LoRa modules. It provides iterative SF inspection and an SF selection algorithm that allows each link to communicate at independent data rates. We implemented a multi-hop LoRa network and evaluated the performance of experiments in various network topologies. The adaptive spreading factor selection (ASFS) scheme showed outstanding end-to-end throughput, peaking at three times the performance of standalone modems. We expect the ASFS scheme will be a suitable technology for applications requiring high throughput on a multi-hop network.

Indoor Smartphone Localization Based on LOS and NLOS Identification.

Accurate localization technology is essential for providing location-based services. Global positioning system (GPS) is a typical localization technology that has been used in various fields. However, various indoor localization techniques are required because GPS signals cannot be received in indoor environments. Typical indoor localization methods use the time of arrival, angle of arrival, or the strength of the wireless communication signal to determine the location. In this paper, we propose an indoor localization scheme using signal strength that can be easily implemented in a smartphone. The proposed algorithm uses a trilateration method to estimate the position of the smartphone. The accuracy of the trilateration method depends on the distance estimation error. We first determine whether the propagation path is line-of-sight (LOS) or non-line-of-sight (NLOS), and distance estimation is performed accordingly. This LOS and NLOS identification method decreases the distance estimation error. The proposed algorithm is implemented as a smartphone application. The experimental results show that distance estimation error is significantly reduced, resulting in accurate localization.

Link-state-estimation-based transmission power control in wireless body area networks.

This paper presents a novel transmission power control protocol to extend the lifetime of sensor nodes and to increase the link reliability in wireless body area networks (WBANs). We first experimentally investigate the properties of the link states using the received signal strength indicator (RSSI). We then propose a practical transmission power control protocol based on both short- and long-term link-state estimations. Both the short- and long-term link-state estimations enable the transceiver to adapt the transmission power level and target the RSSI threshold range, respectively, to simultaneously satisfy the requirements of energy efficiency and link reliability. Finally, the performance of the proposed protocol is experimentally evaluated in two experimental scenarios-body posture change and dynamic body motion-and compared with the typical WBAN transmission power control protocols, a real-time reactive scheme, and a dynamic postural position inference mechanism. From the experimental results, it is found that the proposed protocol increases the lifetime of the sensor nodes by a maximum of 9.86% and enhances the link reliability by reducing the packet loss by a maximum of 3.02%.

RSSI/LQI-based transmission power control for body area networks in healthcare environment.

This paper presents a novel transmission power control protocol for body area networks. Conventional transmission power control protocols adjust the transmission power on the basis of the received signal strength indication (RSSI). However, in case of the presence of interference, the RSSI is not a correct indicator to determine the link state. We first present the empirical evidence for this and then propose a practical protocol to discriminate between the signal attenuation and interference using the RSSI and link quality indication (LQI). This protocol controls the transmission power and avoids interference based on the link state. Finally, we discuss the implementation of the proposed protocol on Tmote Sky and evaluate the performance in the presence and absence of interference. The experimental results showed that the proposed protocol has high energy-efficiency and reliability, even in the presence of interference.

A beacon interval shifting scheme for interference mitigation in body area networks.

This paper investigates the issue of interference avoidance in body area networks (BANs). IEEE 802.15 Task Group 6 presented several schemes to reduce such interference, but these schemes are still not proper solutions for BANs. We present a novel distributed TDMA-based beacon interval shifting scheme that reduces interference in the BANs. A design goal of the scheme is to avoid the wakeup period of each BAN coinciding with other networks by employing carrier sensing before a beacon transmission. We analyze the beacon interval shifting scheme and investigate the proper back-off length when the channel is busy. We compare the performance of the proposed scheme with the schemes presented in IEEE 802.15 Task Group 6 using an OMNeT++ simulation. The simulation results show that the proposed scheme has a lower packet loss, energy consumption, and delivery-latency than the schemes of IEEE 802.15 Task Group 6.