Wireless Communication

Permanent URI for this collection

https://dspace.alquds.edu/handle/20.500.12213/95

The Wireless Communication Research Group is dedicated to advancing the frontiers of next-generation mobile and wireless technologies. With a core focus on 3G 4G 5G Mobile Networks, Wi-Fi, 6G,. Our group explores the full spectrum of wireless communication — from foundational signal processing techniques to large-scale network planning, optimization, and implementation. Our interdisciplinary research addresses key challenges in mobile network performance, spectrum efficiency, and quality of service, while also emphasizing sustainable and scalable infrastructure development. We conduct in-depth evaluations of wireless systems to improve coverage, quality, reliability, and throughput, ensuring our work directly impacts real-world deployment and future innovation. In parallel, we delve into smart systems, Internet of Things (IoT) integration, and the incorporation of artificial intelligence (AI) to enhance adaptive network behavior and intelligent resource management. Our work in spectrum management is shaping the way wireless technologies coexist and evolve in increasingly crowded frequency bands. Through rigorous experimentation and collaboration with academia and industry, the group aims to influence the design of future wireless networks and establish practical frameworks for 6G systems, AI-driven communication, and beyond. We are committed to driving innovation that connects people, devices, and services seamlessly and intelligently.

Browse

Now showing 1 - 5 of 10

Machine Learning Based Throughput Prediction for 4G/5G Mobile Networks Using Large Scale Dataset
(2026-08-25) Ali Jamoos
As cellular networks evolve from 4G LTE to 5G, throughput prediction becomes increasingly important for understanding user experience and supporting data-driven network optimization. However, real active-measurement datasets are often sparse, noisy, and technology-dependent, making throughput modeling a challenging regression problem. This paper presents a machine-learning-based framework for predicting downlink and uplink throughput in both 4G and 5G networks using large-scale active measurement dataset. The original dataset contains 367,104 samples and 81 parameters, including radio indicators, scheduling features, modulation statistics, transport block size information, and contextual variables. Due to the high sparsity of the throughput targets, the data were divided into four independent regression tasks: 4 G downlink, 4 G uplink, 5 G downlink, and 5 G uplink. After preprocessing, feature ranking, and outlier removal, several regression models were trained and evaluated using 10-fold cross-validation in MAT-LAB Regression Learner. The results show that tuned Bagged Trees achieved the best performance across all four datasets, reaching R2 values of 0.9017, 0.9605, 0.8436, and 0.8767 for 4G DL, 4G UL, 5G DL, and 5G UL, respectively. These results demonstrate that target-specific ensemble learning can effectively model the nonlinear relationship between radio/scheduling parameters and measured cellular throughput.
AQU-WiFiLoc: Context-Aware Indoor Localization Based on WiFi Fingerprinting
(2026-08-25) Ali Jamoos
This paper presents AQU-WiFiLoc, a context-aware indoor localization framework that augments Received Signal Strength Indicator (RSSI) based conventional Wi-Fi fingerprinting with Cisco Access Point (AP) telemetry and magnetic field signatures. A multi-modal dataset containing 1,343 fingerprints was collected from 14 rooms distributed across two floors of the Faculty of Engineering at Al-Quds University, Palestine. Initial experiments showed that all evaluated classifiers achieved perfect classification performance under clean conditions, indicating that the collected radio map provides highly discriminative room-level fingerprints. To evaluate robustness under more realistic operating conditions, additive Gaussian noise was introduced exclusively into test-set RSSI values while auxiliary contextual features remained unchanged. Four machine learning classifiers and six feature configurations were evaluated under progressively increasing RSSI degradation. Results demonstrate that contextual information significantly improves localization robustness. The proposed Context-Aware configuration achieved a macro F1-score of 98.5% using K-Nearest Neighbors under severe noise conditions with standard deviation of 10 dBm, outperforming the RSSI-only baseline. In addition, AP telemetry provided the strongest individual performance gain, highlighting the value of network-side context for robust indoor positioning.
Performance Evaluation of Palestinian Mobile Networks Based on Crowdsourcing Measurements
(IEEE, 2024-12-10) Ali Jamoos
The evaluation of mobile network performance involves assessing various key performance indicators (KPIs) that gauge the efficiency and effectiveness of these networks. The key performance indicators of the Palestinian mobile networks are usually monitored by the mobile network operators (MNOs) through their operation support subsystems and the carried-out drive tests. This include the received signal level, received signal quality, drop rate, handover success rate, packet loss, latency, throughput, etc. The Palestinian ministry of telecommunications and information technology (MTIT) together with the Palestinian Telecom Regulatory Authority (PTRA) also conduct performance measurements for the mobile networks through drive tests to monitor the quality of service (QoS) measurements delivered by each mobile operator and compare them with the standard KPIs benchmark limits. They aim to enhance user experience and network efficiency. However, these performance measurements either from the MNOs or the regulation agency are limited and do not reflect the exact end user experience. Therefore, in this paper, we address the performance evaluation of the Palestinian MNOs based on a large community of connected people smartphone crowdsourcing technique. Here, using smartphone crowdsourcing can collect continuous real-time data on network performance from a large number of smartphone users with various locations. Thus, the quality of experience (QoE) can be evaluated from the end user perspective with a bigger data set. In this paper, we have developed and implemented a smartphone application called “Signal Sense” for crowdsourced mobile network measurements. The performed measurements include location information, signal level, signal quality and throughput for 3G mobile networks in Palestine. The evaluation of these measurements reflects the relative performance of the Palestinian MNOs.
Performance Evaluation and Optimisation of JAWWAL 3G Mobile Network
(Engineering for Palestine Conference, Palestine Polytechnic University, 2025-09-29) Tarteel Khaled Sider; Safa Nassereldin; Ali Jamoos
In this paper, a comprehensive research study is carried out on the performance evaluation and optimization of the JAWWAL 3G mobile network in Palestine. Particularly, we present a case study on the planning, evaluation, optimization, and implementation of a 3G mobile network in Idna village, Hebron city, Palestine. The 3G mobile network performance is evaluated by using the so-called drive test through the key performance indicators (KPIs). After a driving test was conducted in the region, the initial network analysis and evaluation showed that the network coverage ratio is 21.5%, the network service quality ratio is 11.1%, the downlink throughput ratio is 6.1%, and the uplink throughput ratio is 35%. Based on these ratios, which are considered to be poorly evaluated, the area lacks coverage and quality of the network service. To overcome these drawbacks, we propose to plan and implement a new cell site in this area. Accordingly, after the planning and construction of the new cell site, the network has been analyzed and evaluated through a driving test. The results show considerable improvement in all KPIs. Indeed, the network coverage ratio is increased to 58.7%, the network service quality ratio is increased to 61.1%, the downlink throughput ratio is increased to 69.5%, and the uplink throughput ratio is increased to 74.5%.
Propagation Model Tuning for Terrestrial Microwave Links in Palestine
(IEEE, 2022-07-26) Ali Jamoos
In this paper, we have studied the terrestrial microwave links operated by the Palestinian mobile network operator (JAWWAL). Particularly, we have analyzed the path loss power measurements from 90 active terrestrial microwave links at three different frequencies which are 15GHz, 18GHz and 23GHz covering all geographical locations in the West Bank. The length of these microwave links varies from about 0.174Km to 33.864Km. The path loss power measurements were compared with that of the theoretical free-space propagation model as well as with the results obtained from Mentum Ellipse software simulation tool. The root mean square error results show that the free-space model is far away (7.64 dB) from the measured data. Therefore, we have suggested to tune the free-space propagation model based on linear least squares method. The proposed tuned free-space model yields better fit to the measured data with reduced root mean square error of 5.84 dB. In addition, the suggested tuned model yields comparable results to that obtain by Mentum Ellipse simulation.

Browse

Recent Submissions