Long Range Wide Area Network (LoRaWAN) has emerged as a key enabler for Internet of Things (IoT) applications in smart cities, offering long-range connectivity with low power consumption. This study evaluates the performance of a large-scale operational LoRaWAN network deployed in Pafos, Cyprus, consisting of over 30,000 smart water meters. Leveraging twelve months of real-world data, we apply regression-based machine learning models (Decision Trees and XGBoost) to predict Estimated Signal Power (ESP), enabling enhanced network reliability and efficiency. Unlike prior studies that primarily rely on simulations or small-scale testbeds, this work is the first to analyze large-scale real-world LoRaWAN data, uncovering key environmental factors influencing signal propagation. Furthermore, we introduce a novel software tool that integrates machine learning-driven ESP predictions, allowing for automated network optimization. Unlike conventional models, this tool dynamically refines signal power predictions based on empirical data, making it a valuable asset for smart city planning and large-scale IoT deployments. To the best of our knowledge, this study represents the first comprehensive analysis focused on the features influencing and predicting ESP. The results demonstrate that our approach effectively tailors propagation predictions to urban environments, achieving high predictive accuracy across diverse conditions. This work contributes to the optimization of large-scale IoT deployments, paving the way for scalable and reliable smart city applications.

In this paper we will present a comprehensive comparison of two used Machine-to-Machine (M2M) communication protocols in the Internet of Things (IoT) scenarios: the Lightweight Machine-to-Machine (LwM2M) and the Extensible Messaging and Presence Protocol (XMPP). The discussion will cover their technical overviews, working mechanisms, and comparisons based on several factors such as protocol reliability, security (authentication and encryption), features, pros and cons, message overhead and transmission efficiency, packet size, and connection establishments. The LwM2M protocol is a fast IoT protocol developed by the Open Mobile Alliance (OMA). It is operated with the Constrained Application Protocol (CoAP) and is greatly famous for being utilized in device management and IoT data communication. Some advantages of LwM2M include providing higher efficiency, easy and stable data transfer, and low power consumption, which is beneficial in long-term and complicated IoT applications, thus making it a good candidate for different industries. On the other hand, the XMPP is a flexible, lightweight protocol that can handle CPU-constrained systems. It is primarily used in messaging and was not developed mainly for IoT applicationsLwM2M and XMPP have different purposes, structures, data processing times, transport, features, and IoT systems architecture. As for security, both protocols have high robust security features. Choosing between LwM2M and XMPP for a specific IoT project needs to be studied based on the requirements of the project to achieve the required aims precisely, as many factors must be taken into consideration when deciding which protocol to use.

Modern economic institutions rely heavily on sales' forecasting (SF) to have more efficient resource utilization. It is widely adopted in private and public financial institutions, businesses, industries, factories, and trading, among other places. SF can be considered an emerging example of employing machine learning for big data analysis because it has a wide range of data, from typical supermarkets up to huge malls and companies. This paper presents SF using a recurrent neural network (RNN) to obtain a forecast of a market product's sales. RNN is an advanced architecture of neural networks that has been adopted in this paper because of its wide adoption and usage for model-based predictions in many applications. A case study of a typical market has been selected, in which the data includes 800 products' sales over 49 weeks. The inputs/output have been divided into three past weeks' sales as inputs, which are used to predict the fourth week's sales as an output. The essential parameters of the RNN have been tuned through several training trials, which eventually gave reasonably accurate results measured by the root mean squared error (RMSE) of 0.039.

There are many opportunities and advantages that cloud computing adoption can bring to the healthcare field, as experts believe that it can help improve the level of healthcare services significantly and contribute to its regular and continuous innovation. This paper provides a comprehensive review of the current literature on the common limitations and problems facing the cloud in healthcare. A brief introduction to cloud computing and the benefits of its adoption is also provided, in addition to a review of the most important security protection standards applied in this field. This paper highlights the most important problems and challenges that still exist in cloud-based healthcare systems. Finally, relevant recent research is reviewed and the most recent initiatives that contribute to solving problems for healthcare applications are identified. It was concluded that these solutions and initiatives are not comprehensive in nature as they partially address issues related to data security in the cloud.

In today's business landscape, companies are facing significant difficulties in achieving positive client interactions and maintaining customers' satisfaction. As a result, businesses are striving to focus on every aspect related to customers and their behaviors to compete in the industry. This has become increasingly important for building customers' loyalties, given the many opportunities available to customize services or products for each customer. To prevent customers from becoming dissatisfied and leaving, businesses are deploying various techniques to efficiently predict customers' behaviors and identify those who may churn or stop using the company's services or products. The rise of machine learning applications has significantly contributed to addressing the challenge of predicting customers' churn rates. Researchers worldwide are now moving towards applying machine learning techniques in this area. This paper aims to present a review of various studies conducted from 2019 to 2022 that utilized machine-learning techniques to predict customers' churn in the telecom industry. The paper summarizes the different machine learning algorithms that are used for customers' churn prediction, with a particular focus on the telecom industry, as well as their accuracy, to provide insights into the effectiveness of these techniques in addressing customers' churn in the telecom industry.

Blockchain technology is widely used in many security-related Internet of Things (IoT) paradigms due to its dynamic and distributed architecture, which assures secure and private network access. Smart cities are one of these IoT applications in which security and privacy play a vital role. This paper proposes a blockchain-based verification process for smart nodes communication within the smart city, demonstrating the implementation details of the proposed security verification process and discussing potential security attacks.

In time-triggered systems, adaptation is performed by using metascheduling approaches to ensure temporal predictability. Wireless sensor networks (WSNs) are growing to be used as a reliable, an energy-efficient, and a scalable network infrastructure for numerous Internet of Things (IoT) applications. Because of run-time changes because of failure events, a metascheduling system is required to address the changes by precomputing schedules for several context events at design time. Therefore, this paper proposes a metascheduler that solves a new scheduling problem for each adaptation scenario in IoT-WSN using our offline algorithm named discrete particle swarm optimization for reliable task allocation (DPSO-TA), resulting in a multi-schedule graph that combines the repeated schedules. In this work, a time-triggered IoT-WSN metascheduler is proposed that takes into considerations the node or link failures that are common in WSN. Single and two failure events are considered, where a graph for all feasible schedules is formed at the network design time. Such a large number of schedules causes a state space explosion problem, which is managed using a re-convergence method. Different application model sizes and network topologies are used to assess the proposed metascheduler under various failure event scenarios. The results show a reduction in the size of the multi-schedule graph by applying inputs with different deadline values and different number of tasks. Furthermore, the validity suggested by the proposed metascheduler, which is the ratio of valid to invalid schedules, is improved when compared to algorithms that schedule tasks to hosts with the shortest completion time or algorithms that select hosts for a set of sorted tasks based on energy consumed and task arrival time.

A wireless sensor network (WSN) constitutes of nodes that are used to sense a certain physical environment phenomena and sends these collected data to a remote node for further processing and decision making. With the proliferation of Internet of Things (IoT), WSN is evolving to be used as reliable, energy efficient, cost effective, and scalable network infrastructure for many IoT applications. To have a robust WSN with IoT (IoT-WSN), it is a challenge to allocate the tasks among different sensor nodes because the distribution of dependent tasks among wireless nodes must satisfy precedence and time constraints, minimize energy consumption, and prevent signal interference. The problem becomes more complex if a system requires high reliability in the event of link or node failures. This article presents an offline discrete particle swarm optimization algorithm for reliable task allocation (DPSO-TA) in IoT-WSN. DPSO-TA defines a utility function to optimize the task allocation problem by iteratively trying to improve the solution. The defined function is designed to satisfy goals, including saving energy, reducing task completion time, and minimizing the failure rates. A load balance mechanism is applied to make balancing of the tasks on several hosts. During the task allocation process, the frame replication and elimination for reliability (FRER) approach is used to support flow fault tolerance by replicating transmitted flows over redundant routes. DPSO-TA considers the periodicity of the time-trigged (TT) flows and applies a physical interference model to prevent signal interference on the transmitted flows through assigning them to conflict-free time slots. The analysis and simulation results show the optimization of DPSO-TA on timeliness, deadline missing ratio, failure rates, and energy efficiency comparing it with algorithms that allocate tasks to hosts that produce the minimum completion time or that use a traditional procedure to find the most suitable nodes during the task allocation process.

LoRa (Long Range) networks tend to be a prevailing technology for smart buildings applications. Its Chirp Spread Spectrum (CSS) modulation technique allows for higher receiver sensitivity. However, its unstable behaviour in terms of electromagnetic propagation motivated this paper to assess the influence of these parameters under temperature and humidity variations on the reliability of LoRa connectivity. The current work suggests a method that takes into consideration the indoor fluctuation of temperature and humidity. The current method is based on the Multi-Wall propagation Model (MWM) aiming at path loss calculation. Simulation results were verified with real- life measurements carried out in a Neapolis University Pafos (NUP) building. The simulation results are in good agreement with the measured data. Nevertheless, the study revealed that the environmental factors of temperature and humidity have a smooth effect on indoor path loss calculation.

The job allocation problem is a challenging in wireless systems, because the spatial and temporal distribution of dependent jobs to hosts must satisfy the precedence constraints, prevent communication interference and minimize energy consumption. In this paper, a new scheduler called Reliable Job Allocation scheduler (RJA) is proposed to improve the reliability of realtime wireless systems. The proposed scheduler uses an approach called Frame Replication and Elimination for Reliability (FRER) to replicate the communication flows through redundant routes. RJA considers the periodicity of Time-Triggered (TT) flows and the impact of the induced interference, by applying a physical interference model which is used to ensure that all flows are transmitted successfully in the assigned time-slots. The scheduling efficiency and the system reliability are improved through allocating jobs to hosts with high performance in terms of flow arrival time, energy consumption and failure rates. A reliability model is also introduced to determine the reliability of the system. The reliability model computes the reliability of each job depending on the reliability of all its incoming flows. The reliability of the leaf job, which has no forwarding flows, presents the global reliability of the overall system. RJA is compared with state-of-the-art TT schedulers that use either the shortest or load-aware routes to send flows without addressing reliability. The experimental results show that the reliability of the system computed by RJA is improved compared to the other schedulers while also ensuring scalability in the network design (i.e. increase of the number of jobs and hosts) and timeliness. We also study the impact of the injected link failures on the flow delivery ratio.

Fleets of cooperative drones are a powerful tool in monitoring critical scenarios requiring early anomaly discovery and intervention. Due to limited energy availability and application requirements, drones may visit target points in consecutive trips, with recharging and data offloading in between. To capture timeliness of intervention and prioritize early coverage, we propose the new notion of Weighted Progressive Coverage, which is based on the definition of time dependent weights. Weighted progressive coverage generalizes classic notions of coverage, as well as a new notion of accumulative coverage specifically designed to address trip scheduling. We show that weighted progressive coverage maximization is NP-hard and propose an efficient polynomial algorithm, called Greedy and Prune (GaP), with guaranteed approximation. By means of simulations we show that GaP performs close to the optimal solution and outperforms a previous approach in all the considered performance metrics, including coverage, average inspection delay, energy consumption, and computation time, in a wide range of application scenarios. Through prototype experiments we also confirm the theoretical and simulation analysis, and demonstrate the applicability of our algorithm in real scenarios.

Data gathering and critical events detection are two essential functionalities for Wireless Sensor Network (WSN). In this paper, we propose double mobile sinks network architecture, where two mobile sink nodes visit the Cluster Heads (CHs) to collect the captured data, which is very energy effective in terms of energy transmission efficiency and reliable compared with the case of having one static sink node. Moreover, the proposed architecture provides a capable scheme for supporting critical and non-critical data, which assures a timely delivery for any critical event to the remote monitoring and decision-making center with minimal interference to the non-critical data. Our proposed architecture shows a superior performance in terms of packets transmission delay, and requires low buffer occupancy for the CHs nodes when compared to related work in the literature. Finally, the paper provides a preliminary hardware design and implementation for the proposed architecture.

Time Sensitive Networking (TSN) is a group of standards to improve reliability, minimize jitter and ensure bounded latency by using scheduled traffic for safety critical realtime applications. Recently, the incorporation of Time-Triggered (TT) wireless technology into this kind of networked systems has been proposed because of its flexibility and easy design. Despite these benefits, the mutual interference between signals must be considered depending on the transmission intervals and the spatial proximity. Interference may prevent reception, cause the corruption of signals or affect on the signal quality. Most of the scheduling algorithms consider either the perspective of scheduling and routing restrictions, or the impact of interference on the wireless scheduling solutions. To address the interference restrictions besides the scheduling and routing restrictions, a Wireless Heuristic List Scheduler (WHLS) is proposed in this paper to determine the schedule. In this algorithm, TT messages of the computational jobs use the optimal routes with minimum latency from all available routes. In addition, the message is fragmented according to the timeslot size and assigned to several time-slots. In each time-slot all messages can be transmitted simultaneously by using a physical interference model. WHLS supports multi-cast communication while respecting the precedence constraints between computation jobs and periodicity restrictions. To evaluate the proposed scheduler, a basic List Scheduler (LS) that uses a static route (the least hop count) is implemented. The experimental results show that WHLS outperforms LS in all simulation tests, where schedulability, make span and execution time are used as parameters.

In this paper, we propose a new energy–aware and density-based clustering and routing algorithms for gathering data in wireless sensor networks. It basically aims at distributing the energy consumption between nodes in the network. In our proposed protocol, we introduce a topology that partitions the network field into equally-sized layers where each layer is divided into equal clusters. Additionally, we introduce a density-based algorithm that takes into consideration the number of nodes in a cluster. Finally, we propose an energy aware relaying algorithm that uses free space channel propagation model among nodes and selects the relay nodes based on their energy levels and locations among others. The performance of our proposed protocol is assessed through carrying out numerous MATLAB experiments. Simulation results showed that our proposed protocol has a remarkable improvement against other related works in term of network lifetime.

With the proliferation of the Internet of Things (loT) and cloud based services, it becomes very essential to design and implement efficient mechanisms, to protect the users private information and secure them, taking into account the loT devices limited computational and storage capabilities. In addition, these devices are usually accessed by multiple users, and are connected to a cloud service provider, that have an access of the users data. In this paper, a privacy preserving framework is proposed that utilizes Fog layer, which act as intermediator between the loT devices and the cloud, where users data are anonymized and secured. Further, a case study in the field of healthcare is described that shows the importance of the proposed framework.

Wireless sensor networks have been used in several applications to perform remote monitoring for a certain Area of Interest. In this work, we propose to utilize an Unmanned Aerial Vehicle (UAV) to improve the ground network connectivity, act as a data mule that collects the captured data and off-load the ground sensor nodes, who have normally limited storage capacities. We have investigated the effect of several parameters that affect the communication between the UAV and the ground sensors such as the UAV height, communication channel weather conditions, and nodes' noise factor, and evaluated the network performance measured by the average packet loss rate, end-to-end delay, and throughput. We found out that when the nodes' transceivers have a relatively high noise factor (above 20), it is recommended to keep the UAV altitude around 150 meters or below. We also noticed that the performance degrades drastically when having severe weather conditions, which requires additional mechanisms for improving the transmission performance such as the usage of error correction codes and Multiple Input Multiple Output antennas.

A wireless sensor network (WSN) consists of a large number of sensor nodes. The nodes are represented by mobile ground robots and are deployed over an area to perform local sensing of the surroundings. Sensing and detection of critical events and vulnerabilities in such areas are highly desirable for a wide range of civil and military applications. Autonomy and energy efficiency are two key design issues of WSN robot nodes that ultimately impact performance and validity. A novel communication protocol is used for energy efficiency. The protocol allows WSN nodes to communicate with each other and send notification messages while optimizing energy consumption based on the alternation of use between CSMA and TDMA. It is embedded in an agent framework, results of which are still under investigation.

To deal with the congestion problem in a broadcast environment like V2V communication, we believe that receiving nodes should take a role in guiding transmitting nodes to set their transmission parameters e.g., Tx rate and power. This is important because only receiving nodes can evaluate whether or not safety applications requirements have been fulfilled. While most congestion control protocols rely on network-level metrics to optimize their transmission parameters, our proposed method uses a combination of application and network level performance metrics to assign transmission parameters. In the proposed method, nodes calculate the max tolerable time between periodic messages as well as the channel load, and share it with others. The shared data is used to guide neighboring nodes in regulating their messaging rate and Tx power. Receiving nodes adapt their rate or/and power based on their locations w.r.t to the node with degraded safety applications performance. The evaluation shows that our method maintains low inter packet reception time.

A prototype of a low-cost, wearable system is presented to assist persons with hearing impairments by detecting in-house alert sounds and estimating their direction of arrival (DOA). The prototype is composed of a circular microphone array, a small microcomputer, and motors for vibration alerting. The array includes five microphones uniformly distributed on the outer surface of a ring with circumference comparable to human waist. Each microphone is connected to one of the analog inputs of the microcomputer. The power of the microphone signals is analyzed to detect alert sounds. Upon the detection of an alert sound, a low-complexity time-difference of arrival method is used to determine the sound DOA with mean error of 14.1°. The user is notified about the detection of alert sound and its DOA by vibrating the closest motor to the sounds source. The time required to detect and localize an alert sound is around 35 msec.

Multi-core processors are gaining increasing importance in safety-relevant embedded real-time systems, where temporal guarantees must be ensured despite the sharing of on-chip resources such as processor cores and networks-on-a-chip. At the same time, many applications comprise workloads with different timing models including time-triggered and even-triggered communication. This paper introduces a scheduling model based on Mixed Integer Linear Programming (MILP) supporting the allocation of computational jobs to processing cores as well as the scheduling of messages and the selection of paths on networks-on-a-chip. The model supports dependencies between computational jobs and it combines both time-triggered and event-triggered messages. Phase-alignment of time-triggered messages is performed, while avoiding collisions between time-triggered messages and satisfying bandwidth constraints for event-triggered messages. Example scenarios are solved optimally using the IBM CPLEX optimizer yielding minimal computational and communication latencies.

Although IEEE 802.11 Wireless LAN (WLAN) is of a great interest nowadays, it lacks the efficient capability of supporting real-time streaming which is due to mainly the contention nature of wireless media. In this paper, we extend our earlier work concerning improving video traffic over wireless networks through effectively studying the dependencies between video frames and their implications on the overall network performance. In other words, we propose very efficient and novel algorithms that aim to minimize the cost of possible losses by intelligently and selectively discard frames based on their contribution to picture quality, namely, partial and intelligent-partial frame discarding policies considering the dependencies between video frames. The performance metrics that are employed to evaluate the performance of the proposed algorithms include the rate of non-decodable frames and peak signal-to-noise ratio (PSNR). Our results are promising and show significant improvements in the perceived video quality over what is relevant in the current literature.

In this paper, we propose an optimization framework for real-time voice transmission over wireless tandem channels prone to both bit errors and packet erasures. Utilizing a hybrid media dependent and media independent error correction scheme, our proposed framework is capable of protecting voice packets against both types of errors. For each group of frames associated with one speech spurt, the framework finds the optimal parity assignment of each voice frame according to its perceptual importance such that the quality of the received group of frames is maximized. Our performance evaluation results show that the proposed scheme outperforms a number of alternative schemes and has a low computational complexity.

In this paper, we present an optimization framework for transmitting high quality audio sequences over error-prone wireless links. Our framework introduces apparatus and technique to optimally protect a stored audio sequence transmitted over a wireless link while considering the packetization overhead of audio frames. Utilizing rate compatible punctured Reed-Solomon (RS) codes and dynamic programming, it identifies the optimal assignment of parity to audio frames according to their perceptual importance such that the segmented SNR of the received audio sequence is maximized. Our framework covers two cases. In the first case, a frame grouping technique is proposed to packetize audio frames and protect them against temporarily correlated bit errors introduced by a fading wireless channel. In this case, each packet is treated as a channel coding codeword. In the second case, a one-dimensional RS coder is applied vertically to a sequence of horizontally formed packets associated with an audio sequence in order to protect the sequence against both bit errors introduced by fading wireless channels and packet erasures introduced by network buffering. Our numerical results capture the performance advantage of our framework compared to existing techniques proposed in the literature of audio transmission. We also note that our framework can be generically applied to a variety of audio coders, making it attractive in terms of implementation.

In this paper, we propose a statistical optimization framework for transmitting audio sequences over wireless links. Our proposed framework protects audio frames against both temporally correlated random bit errors introduced by a fading channel and packet erasures caused by network buffering. Forming a two-dimensional grid of symbols, our framework forms horizontal packets that are compensated only vertically against both types of errors. The utilized one-dimensional error correction coding scheme of our framework assigns parity bits according to the perceptual importance of frames such that the Segmented SNR of a received audio sequence is maximized. In addition, the proposed framework suggests an effective way of reducing the packetization overhead of small audio frames.

In this paper, we present a new policy for admitting voice over IP (VoIP) sessions over wireless networks. Our proposed policy receives the admission information advertised by the VoIP gateway on the wired network, and uses it to decide whether a new VoIP session can be admitted or not. The proposed policy can be easily integrated with the current call admission control algorithms used in wireless networks. We show that implementing the proposed policy increases the number of successful VoIP sessions admitted to the access point polling list, thus improving the wireless network utilization.

In this paper, we present an optimal UEP framework for transmitting packetized audio streams over MIMO wireless links. Our proposed framework aims at maximizing the expected end-to-end Segmented SNR of a received audio sequence. It reduces the packetization overhead of small audio frames while protecting audio streams against temporarily correlated bit errors introduced by wireless transmission medium. To reduce the packetization overhead, our framework suggests a frame grouping technique distributing the transmission overhead of one packet among multiple audio frames. To mitigate the effects of random bit errors, our framework utilizes a UEP RS channel coding scheme to assign parity bits according to the combined perceptual importance of frames embedded in individual packets.

Implementation of current real time services (of which one of the more important is Voice over IP) on the current Internet face many obstacles, among them the issue of routing. Quality of service (QoS) routing, attempts to provide real time services with the required guarantees to achieve acceptable performance. In this paper we study VoIP routing using the Quality of Service (QSR) network simulator utilizing the Widest-Shortest routing algorithm to provide QoS using different metrics. We show that this algorithm using a modified cost metric based on the hop- normalized is able to route real time traffic away from congested links thus providing acceptable jitter, end-to- end delay and throughput to satisfy real time services requirements.