Browsing by Author "Seog Han, Dong"

Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    An Accurate Indoor User Position Estimator For Multiple Anchor UWB Localization
    (IEEE, 2020) Poulose, Alwin; Emeršic, Žiga; Eyobu, Odongo Steven; Seog Han, Dong
    UWB-based positioning systems have been proven to provide a significant high level of accuracy hence offering a huge potential for a variety of indoor applications. However, the major challenges related to UWB localization are multipath effects, excess delay, clock drift, signal interferences and system computational time to estimate the user position. To compensate for these challenges, the UWB system uses multiple anchors in the experiment area and this gives accurate position results with minimum localization errors. However, the use of multiple anchors in the UWB system means processing large amounts of data in the system controller for localization, which leads to high computational time to estimate the current user position. To reduce the complexity of the UWB systems, we propose a position estimator for multiple anchor indoor localization, which uses the extended Kalman filter (EKF). The proposed UWB-EKF estimator was mathematically analysed and the simulation results were compared with classical localization algorithms considering the mean localization errors. In the simulation, three classical localization algorithms: linearized least square estimation (LLSE), weighted centroid estimation (WCE) and maximum likelihood estimation (MLE) were used for performance comparison. Thorough extensive simulation done in this study achieves results which demonstrate the effectiveness of the proposed UWB-EKF estimator for multiple anchor UWB indoor localization.
  • Thumbnail Image
    Item
    ANN-based Stride Detection Us ing Smartphones for Pedestrian Dead Reckoning
    (IEEE, 2018) Kim, Youngwoo; Eyobu, Odongo Steven; Seog Han, Dong
    Position awareness is a very important issue for internet of thing (IoT) applications using smartphones. Pedestrian dead reckoning (PDR) is one of the methods used to estimate a user’s indoor position. The accuracy of a stride detection is very important to guarantee the estimation accuracy of the user location. This paper proposes an algorithm to detect the stride using acceleration spectrogram feature by utilizing the accelerometer in a smartphone. An artificial neural network (ANN) technology is applied to detect the stride. The proposed algorithm has an accuracy of 97.7% for stride detection.
  • Thumbnail Image
    Item
    Augmented CWT Features for Deep Learning-Based Indoor Localization Using WiFi RSSI Data
    (Applied Sciences, 2021) Ssekidde, Paul; Eyobu, Odongo Steven; Seog Han, Dong; Oyana, Tonny J.
    Localization is one of the current challenges in indoor navigation research. The conventional global positioning system (GPS) is affected by weak signal strengths due to high levels of signal interference and fading in indoor environments. Therefore, new positioning solutions tailored for indoor environments need to be developed. In this paper, we propose a deep learning approach for indoor localization. However, the performance of a deep learning system depends on the quality of the feature representation. This paper introduces two novel feature set extractions based on the continuous wavelet transforms (CWT) of the received signal strength indicators’ (RSSI) data. The two novel CWT feature sets were augmented with additive white Gaussian noise. The first feature set is CWT image-based, and the second is composed of the CWT PSD numerical data that were dimensionally equalized using principal component analysis (PCA). These proposed image and numerical data feature sets were both evaluated using CNN and ANN models with the goal of identifying the room that the human subject was in and estimating the precise location of the human subject in that particular room. Extensive experiments were conducted to generate the proposed augmented CWT feature set and numerical CWT PSD feature set using two analyzing functions, namely, Morlet and Morse. For validation purposes, the performance of the two proposed feature sets were compared with each other and other existing feature set formulations. The accuracy, precision and recall results show that the proposed feature sets performed better than the conventional feature sets used to validate the study. Similarly, the mean localization error generated by the proposed feature set predictions was less than those of the conventional feature sets used in indoor localization. More particularly, the proposed augmented CWT-image feature set outperformed the augmented CWT-PSD numerical feature set. The results also show that the Morse-based feature sets trained with CNN produced the best indoor positioning results compared to all Morlet and ANN-based feature set formulations.
  • Thumbnail Image
    Item
    A broadcast scheme for vehicle-to-pedestrian safety message dissemination
    (International Journal of Distributed Sensor Networks, 2017) Eyobu, Odongo Steven; Joo, Jhihoon; Seog Han, Dong
    Ensuring cooperative awareness by periodic message beaconing in vehicular environments is necessary to address pedes- trian safety. However, high periodic basic safety message broadcasting in dense vehicular environments makes accessing the communication channel very competitive. Furthermore, high-frequency periodic broadcasting causes fast device energy dissipation which is a key issue for small computing devices used in wireless sensor and mobile communications. Therefore, in order to achieve reliable message dissemination for vehicle-to-pedestrian safety, energy loss minimization mechanisms for pedestrian mobile devices should be developed. This article proposes controlling the number of broad- casts by eliminating periodic safety message broadcasts from pedestrian nodes; these nodes only receive broadcasts from vehicles and then conditionally communicate with the vehicles when safety alerts are raised. When the pedestrian nodes do not receive messages from any vehicle for a specified period, pedestrian nodes broadcast a high-priority message advertising their position. Furthermore, for the pedestrian, adaptive message emission rates and transmission duration are proposed based on defined vehicle-to-pedestrian separation distances. This approach reduces the pedestrian device energy consumption and end-to-end delay and improves the packet delivery ratio compared to the vehicular broadcast approach for safety messages defined in the IEEE 802.11 standard.
  • Thumbnail Image
    Item
    CMD: A Multichannel Coordination Scheme for Emergency Message Dissemination in IEEE 1609.4
    (Mobile Information Systems, 2018) Eyobu, Odongo Steven; Joo, Jhihoon; Seog Han, Dong
    (e IEEE 1609.4 legacy standard for multichannel communications in vehicular ad hoc networks (VANETs), specifies that the control channel (CCH) is dedicated to broadcast safety messages, while the service channels (SCHs) are dedicated to transmit infotainment service content. However, the SCHs can be used as an alternative to transmit high priority safety messages in the event that they are invoked during the service channel interval (SCHI). (is implies that there is a need to transmit safety messages across multiple available utilized channels to ensure that all vehicles receive the safety message. Transmission across multiple SCHs using the legacy IEEE 1609.4 requires multiple channel switching and therefore introduces further end-to-end delays. Given that safety messaging is a life critical application, it is important that optimal end-to-end delay performance is derived in multichannel VANET scenarios to ensure reliable safety message dissemination. To tackle this challenge, three primary con- tributions are in this article: first, a cooperative multichannel coordinator (CMD) selection approach based on the least average separation distance (LAD) to the vehicles that expect to tune to other SCHs and operates during the control channel interval (CCHI) is proposed. Second, a model to determine the optimal time intervals in which CMD operates during the CCHI is proposed. (ird, a contention back-off mechanism for safety message transmission during the SCHI is proposed. Computer simulations and mathematical analysis show that CMD performs better than the legacy IEEE 1609.4 and a selected state-of-the-art multichannel message dissemination scheme in terms of end-to-end delay and packet reception ratio.
  • Thumbnail Image
    Item
    Cooperative Multi-channel Dissemination of Safety Messages in VANETs
    (IEEE, 2016) Steven Eyobu, Odongo; Joo, Jhihoon; Seog Han, Dong
    IEEE 802.11p-based wireless access in vehicular environments (WAVE) multi-channel communication introduces communication clusters which limits on the dissemination efficiency of broadcast applications such as safety messaging. This paper proposes cooperative multi-channel information dissemination (CMD) which follows a channel coordination approach where the coordinator is selected based on the least average distance (LAD) to all service channels with the goal of relaying the emergency message to other service channels with minimum delay. On receipt of high priority emergency messages, each selected channel coordinators switches to a defined service channel and broadcasts the emergency message to it members. In the CMD approach, each vehicle assumes a single radio and the number of channel coordinators in each service channel cluster is determined based on the available service channels advertised and LAD to the advertised service channels. Computer simulations show that the proposed CMD performs well in terms of dissemination delay and dissemination rate.
  • Thumbnail Image
    Item
    Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network
    (Sensors, 2018) Eyobu, Odongo Steven; Seog Han, Dong
    Wearable inertial measurement unit (IMU) sensors are powerful enablers for acquisition of motion data. Specifically, in human activity recognition (HAR), IMU sensor data collected from human motion are categorically combined to formulate datasets that can be used for learning human activities. However, successful learning of human activities from motion data involves the design and use of proper feature representations of IMU sensor data and suitable classifiers. Furthermore, the scarcity of labelled data is an impeding factor in the process of understanding the performance capabilities of data-driven learning models. To tackle these challenges, two primary contributions are in this article: first; by using raw IMU sensor data, a spectrogram-based feature extraction approach is proposed. Second, an ensemble of data augmentations in feature space is proposed to take care of the data scarcity problem. Performance tests were conducted on a deep long term short term memory (LSTM) neural network architecture to explore the influence of feature representations and the augmentations on activity recognition accuracy. The proposed feature extraction approach combined with the data augmentation ensemble produces state-of-the-art accuracy results in HAR. A performance evaluation of each augmentation approach is performed to show the influence on classification accuracy. Finally, in addition to using our own dataset, the proposed data augmentation technique is evaluated against the University of California, Irvine (UCI) public online HAR dataset and yields state-of-the-art accuracy results at various learning rates.
  • Thumbnail Image
    Item
    Localization Error Analysis of Indoor Positioning System Based on UWB Measurements
    (IEEE, 2019) Poulose, Alwin; Eyobu, Odongo Steven; Kim, Myeongjin; Seog Han, Dong
    Ultra wide band (UWB) systems use time information instead of the popular received signal strength indication (RSSI). UWB is known for its high position accuracy in localization. RSSI-based localization is easily affected by signal attenuation and has a poor localization accuracy as compared to the time of arrival (TOA) technique. In this paper, different localization algorithms for the UWB system were analytically reviewed. The performance of the localization algorithms is discussed in terms of root mean square and cumulative distribution function of localization errors. The experiment results demonstrate the effectiveness of different localization algorithms for UWB indoor positioning. The fingerprint estimation algorithm shows better performance compared to linearized least square estimation and weighted centroid estimation algorithms. The experimental results show that the linearized least square algorithm has poor performance for UWB indoor localization.
  • Thumbnail Image
    Item
    Measurement Based V2V Path Loss Analysis in Urban NLOS Scenarios
    (IEEE, 2016) Joo, Jhihoon; Eyobu, Odongo Steven; Seog Han, Dong
    The importance of an accurate path loss model of vehicular environments is critical for the vehicular communication system design. However, estimating the path loss in vehicular environments is difficult due to high dynamics and low antenna heights. In this paper, we propose a line-of-sight (LOS) path loss model in vehicle-to-vehicle (V2V) scenarios and provide deep analysis of shadow fading in urban non-LOS (NLOS) scenarios by the deductive method with the proposed LOS model. The results can be utilized as reference material for further analysis of V2V path loss measurements.