Winfred Ingabire

Mrs. Winfred Ingabire


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2021 in Algorithms
Verified
Journal Article
Open access
PDF file
WIWinfred Ingabire
Winfred Ingabire
Hadi LarijaniHadi Larijani
Hadi Larijani
Ryan GibsonRyan Gibson
Ryan Gibson
AQAYYAZ-UL-HAQ QURESHI
AYYAZ-UL-HAQ QURESHI
Accurate localization for wireless sensor end devices is critical, particularly for Internet of Things (IoT) location-based applications such as remote healthcare, where there is a need for quick response to emergency or maintenance services. Global Positioning Systems (GPS) are widely known for outdoor localization services; however, high-power consumption and hardware cost become a significant hindrance to dense wireless sensor networks in large-scale urban areas. Therefore, wireless technologies such as Long-Range Wide-Area Networks (LoRaWAN) are being investigated in different location-aware IoT applications due to having more advantages with low-cost, long-range, and low-power characteristics. Furthermore, various localization methods, including fingerprint localization techniques, are present in the literature but with different limitations. This study uses LoRaWAN Received Signal Strength Indicator (RSSI) values to predict the unknown X and Y position coordinates on a publicly available LoRaWAN dataset for Antwerp in Belgium using Random Neural Networks (RNN). The proposed localization system achieves an improved high-level accuracy for outdoor dense urban areas and outperforms the present conventional LoRa-based localization systems in other work, with a minimum mean localization error of 0.29 m.

16 June 2022 in Information
Verified
Journal Article
Open access
PDF file
WIWinfred Ingabire
Winfred Ingabire
Hadi LarijaniHadi Larijani
Hadi Larijani
Ryan GibsonRyan Gibson
Ryan Gibson
AQAYYAZ-UL-HAQ QURESHI
AYYAZ-UL-HAQ QURESHI
Global Positioning Systems (GPS) are frequently used as a potential solution for localization applications. However, GPS does not work indoors due to a lack of direct Line-of-Sight (LOS) satellite signals received from the End Device (ED) due to thick solid materials blocking the ultra-high frequency signals. Furthermore, fingerprint localization using Received Signal Strength Indicator (RSSI) values is typical for localization in indoor environments. Therefore, this paper develops a low-power intelligent localization system for indoor environments using Long-Range Wide-Area Networks (LoRaWAN) RSSI values with Random Neural Networks (RNN). The proposed localization system demonstrates 98.5% improvement in average localization error compared to related studies with a minimum average localization error of 0.12 m in the Line-of-Sight (LOS). The obtained results confirm LoRaWAN-RNN-based localization systems suitable for indoor environments in LOS applied in big sports halls, hospital wards, shopping malls, airports, and many more with the highest accuracy of 99.52%. Furthermore, a minimum average localization error of 13.94 m was obtained in the Non-Line-of-Sight (NLOS) scenario, and this result is appropriate for the management and control of vehicles in indoor car parks, industries, or any other fleet in a pre-defined area in the NLOS with the highest accuracy of 44.24%.

24 December 2024 in Animals
Verified
Journal Article
Open access
PDF file
Daria KernDaria Kern
Daria Kern
TSTobias Schiele
Tobias Schiele
UKUlrich Klauck
Ulrich Klauck
WIWinfred Ingabire
Winfred Ingabire
The chicken is the world’s most farmed animal. In this work, we introduce the Chicks4FreeID dataset, the first publicly available dataset focused on the reidentification of individual chickens. We begin by providing a comprehensive overview of the existing animal reidentification datasets. Next, we conduct closed-set reidentification experiments on the introduced dataset, using transformer-based feature extractors in combination with two different classifiers. We evaluate performance across domain transfer, supervised, and one-shot learning scenarios. The results demonstrate that transfer learning is particularly effective with limited data, and training from scratch is not necessarily advantageous even when sufficient data are available. Among the evaluated models, the vision transformer paired with a linear classifier achieves the highest performance, with a mean average precision of 97.0%, a top-1 accuracy of 95.1%, and a top-5 accuracy of 100.0%. Our evaluation suggests that the vision transformer architecture produces higher-quality embedding clusters than the Swin transformer architecture. All data and code are publicly shared under a CC BY 4.0 license.

7 July 2021
Verified
Book Chapter
Closed access
PDF file
WIWinfred Ingabire
Winfred Ingabire
HLHadi Larijani
Hadi Larijani
RGRyan M. Gibson
Ryan M. Gibson