Browsing by Author "Oyana, Tonny J."

Now showing 1 - 4 of 4
  • 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 Link Fabrication Attack Mitigation Approach (LiFAMA) for Software Defined Networks
    (Electronics, 2022) Katongole, Joseph; Odongo, Steven Eyobu; Kasyoka, Philemon; Oyana, Tonny J.
    In software defined networks (SDNs), the controller is a critical resource, yet it is a potential target for attacks as well. The conventional OpenFlow Discovery Protocol (OFPD) used in building the topological view for the controller has vulnerabilities that easily allow attackers to poison the network topology by creating fabricated links with malicious effects. OFDP makes use of the link layer discovery protocol (LLDP) to discover existing links. However, the LLDP is not efficient at fabricated link detection. Existing approaches to mitigating this problem have mostly been passive approaches that depend on observing unexpected behaviour. Examples of such behaviour include link latency and packet patterns to trigger attack alerts. The problem with the existing solutions is that their implementations cause longer link discovery time. This implies that a dense SDN would suffer from huge delays in the link discovery process. In this study, we propose a link fabrication attack (LFA) mitigation approach (LiFAMA), which is an active mitigation approach and one that minimises the link discovery time. The approach uses LLDP packet authentication together with keyed-hashbased message authentication code (HMAC) and a link verification database (PostgreSQL) that stores records of all known and verified links in the network. This approach was implemented in an emulated SDN environment using Mininet and a Python-based open-source OpenFlow (POX) controller. The results show that the approach detects fabricated links in an SDN in real time and helps mitigate them. Additionally, the link discovery time of LiFAMA out-competes that of an existing LFA mitigation approach.
  • Thumbnail Image
    Item
    A Multi-Model Fusion-Based Indoor Positioning System Using Smartphone Inertial Measurement Unit Sensor Data
    (IEEE, 2020) Adong, Priscilla; Eyobu, Odongo Steven; Oyana, Tonny J.; Han, Dong Seog
    We propose novel multi-model fusion-based step detection and step length estimation approaches that use the Kalman filter. The proposed step detection approach combines results from three conventional step detection algorithms, namely, findpeaks, localmax, and advanced zero crossing to obtain a single and more accurate step count estimate. The proposed step length estimation approach combines results from two popular step length estimation algorithms namely Weinberg’s and Kim’s methods. In our experiment, we consider five different smartphone placements, that is, when the smartphone is handheld, handheld with an arm swing, placed in the backpack, placed in a trousers’ back pocket and placed in a handbag. The system relies on inertia measurement unit sensors embedded in smartphones to generate accelerometer, gyroscope and magnetometer values from the human subject’s motion. Results from our experiments show that our proposed fusion based step detection and step length estimation approaches outperform the convectional step detection and step length estimation algorithms, respectively. Our Kalman fusion approach achieves a better step detection, step length estimation for all the five smart phone placements hence providing a better positioning accuracy. The performance of the proposed multimodel fusion-based positioning system was measured using the root mean square error (RMSE) of the displacement errors and step count errors exhibited by all the the step length and step count algorithms. The results show that the proposed Kalman fusion approach for step count estimation and step length estimation provides the least RMSE for all the smartphone placements. The proposed approach provides an average RMSE of 0.26 m in terms of the final position estimate for all the smartphone placements.
  • Thumbnail Image
    Item
    Women's Decision-Making Autonomy and ICT Utilization on Access to Antenatal Care Services: Survey Results From Jinja and Kampala Cities, Uganda
    (bioRxiv, 2019) Namatovu, Hasifah K.; Oyana, Tonny J.; Lubega, Jude T.
    There is growing evidence in Uganda that the non-attendance of antenatal care is largely influenced by the lack of decision-making autonomy, inadequate information and poor services offered in health facilities. Although previous studies have examined barriers and facilitators of antenatal care, a few of them have investigated the extent of decision making autonomy and ICT adoption among expectant mothers. A cross sectional design through focus group discussions and survey questionnaires was used to collect data. Three hundred and twenty households were randomly sampled in Kampala and Jinja districts. The Chi-square tests (χ2) for independence to analyze group differences among women’s socio-demographic characteristics and decision-making autonomy was used. Inclusion criteria included respondents aged 18 and 50 years, completion of primary school education, expectant mothers and mothers who gave birth two years prior to the study. A hundred and sixty-four respondents participated in this survey. About 59.5% of women lacked decision making autonomy. Midwives (37.6%) and village health teams (35%) were a major source of antenatal care information, and 49.5% of expectant mothers lacked ANC information. Ninety percent (90%) of mothers did not use any form of ICT’s to enhance their decisions yet 79% possessed mobile phones. We observed a strong association between antenatal care decision-making autonomy and women with higher education (χ2 = 8.63, ρ = 0.035), married (χ2 = 4.1, ρ = 0.043) and mature (36–50) (χ2 = 8.81, ρ = 0.032). The main findings in this study suggest that ICT adoption and decision making autonomy among expectant mothers is still low and less appreciated. Control measures and interventions should be geared towards empowering women to influence their decisions.