Norshahida Saba

Norshahida Saba

Auto-generated profile, based on publicly available information

Norshahida Saba

Department of Information and Communications Engineering, Aalto University, Espoo, Finland

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
18 September 2023 in IEEE Transactions on Machine Learning in Communications and Networking
Verified
Journal Article
Open access
YDYongchao Dang
Yongchao Dang
AKAlp Karakoc
Alp Karakoc
SNSaba Norshahida
Saba Norshahida
RJRiku Jantti
Riku Jantti
With the upcoming 5G and beyond wireless communication system, cellular-connected Unmanned Aerial Vehicles (UAVs) are emerging as a new pattern to give assistance for target searching, emergency rescue, and network recovery. Such cellular-connected UAV systems highly rely on accurate and secure navigation systems, e.g. the Globe Navigation System (GPS). However, civil GPS services are unencrypted and vulnerable to spoofing attacks that can manipulate UAVs’ location and abort the UAVs’ mission. This paper leverage 3D radio map and machine learning methods to detect and mitigate GPS spoofing attacks for cellular-connected UAVs. Precisely, the edge UAV flight controller uses ray tracing tools deterministic channel models, and Kriging methods to construct a theoretical 3D radio map. Then the machine learning methods, such as Multi-Layer Perceptrons (MLP), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN), are employed to detect GPS spoofing by analyzing the UAV/base station reported Received Signal Strength (RSS) values and the theoretical radio map RSS values. Once spoofing is detected, the particle filter is applied to relocate the UAV and mitigate GPS deviation. The experiment results indicate that the Universal Kriging (UK) with exponential covariance function has the lowest standard errors for radio map construction. Moreover, the MLP achieves the highest spoofing detection accuracy with different spoofing margins because of the statistic prepossessing relieving environmental impacts, while the CNN has a comparable detection accuracy with less training time than MLP since CNN inputs are raw RSS data. Furthermore, the particle filter-based GPS spoofing mitigation can relocate the UAV to the real position within an error of 10 meters using 100 particles.

28 August 2025 in IEEE Access
Verified
Journal Article
Open access
NSNorshahida Saba
Norshahida Saba
PLPasi Lassila
Pasi Lassila
KRKalle Ruttik
Kalle Ruttik
RJRiku Jantti
Riku Jantti
JSJari Salo
Jari Salo
Fixed Wireless Access (FWA) offers a practical broadband solution in areas where fiber deployment is challenging, especially in rural regions. This study introduces a 3D point-cloud-based radio network planning framework for 5G FWA using both sub-6 GHz and 26 GHz bands. By incorporating detailed environmental features, the method classifies links as Line-of-Sight (LoS) or Non-Line-of-Sight (NLoS) and evaluates the effect of antenna elevation on LoS availability. Users in LoS are assigned to 26 GHz for higher throughput, while NLoS users fallback to 3.5 GHz. Network performance is analyzed at both link and flow levels under no interference and maximum interference conditions. The link-level results show that up to 7% of the 4,999 households fallback to 3.5 GHz under maximum interference, compared to 6.2% under no interference. At the flow level, various load balancing strategies are evaluated to assess their impact on flow-level throughput and overall system stability. The framework is validated using real data from a rural area in Pornainen, Finland. Findings demonstrate effective spectrum use and highlight the importance of proactive load balancing and infrastructure planning.

27 June 2025 in IEEE Access
Verified
Journal Article
Open access
NSNorshahida Saba
Norshahida Saba
JSJari Salo
Jari Salo
KRKalle Ruttik
Kalle Ruttik
RJRiku Jantti
Riku Jantti
The deployment of 5G millimeter-wave (mmWave) for cellular services faces challenges due to significant signal attenuation from blockages to the signal. 5G Fixed Wireless Access (FWA) has emerged as a promising mmWave application. The economical viability of high frequency FWA typically requires line-of-sight (LoS) connections. The amount of LoS FWA links can be increased by increasing the height of the antenna. In this paper, we introduce a novel approach for optimizing per-household cost effectiveness of a 5G FWA network. For estimation of the LoS connections, our approach relies on a highly accurate channel model derived from point cloud-data with terrain height information. Our empirical measurements confirm that the digital 3D point-cloud map model delivers significantly higher precision compared to other models. We examine howthe heights of base transceiver station (BTS) towers and customer premise equipment (CPE) antennas impact the availability of FWA services in a real-world rural setting with 764 houses. For instance, with BTSs set at a height of 70 meters from the ground and CPEs height elevated up to 2 meters from the roof, we achieve a LoS coverage of 62.57%. By factoring in practical deployment costs for BTS and CPE antenna heights, we identify optimal heights that minimize the mmWave network investment per customer.