This paper is presented in the context of the First Indoor Pathloss Radio Map Prediction Challenge at IEEE ICASSP 2025. We propose a deep learning approach using a customized ResUNet architecture with physics-informed features for predicting radio maps in indoor environments. Our architecture progressively adapts to handle increasing task complexity, incorporating dual-stream processing for frequency generalization and specialized antenna gain processing with dilated convolutions. Experimental results demonstrate effective generalization across unknown indoor scenes, frequencies, and antenna patterns while maintaining computational efficiency.

With the exponential increase in data traffic, driven by the rapid growth of connected devices and high-bandwidth applications, precise prediction of network consumption becomes pivotal for optimizing telecommunications infrastructure. This challenge is intensified by the requirements of mobility prediction and Cellular Vehicle to Everything (C-V2X) applications, which necessitate high accuracy, low latency, and high reliability in network traffic prediction. In this paper, we propose a lightweight yet highly scalable Gated Temporal Graph Attention Network (Gated T-GAT) that forecasts network traffic volumes across complex environments, achieving state-of-the-art accuracy on critical short-horizon (15-minute) forecasts, an operationally critical window for telecom resource optimization. Our compact regression-based model, which integrates an MLP classifier with a Temporal-GAT, outperforms current multi-cell traffic models while eclipsing single-cell predictors. This work underscores the efficacy of coupling Temporal-GAT with an MLP classifier in managing large-scale network traffic, offering a scalable, efficient, and robust solution for high-demand forecasting scenarios.

The landscape of network management has undergone significant transformation with the advent of diverse Internet applications, smart devices, and the shift towards software-defined networks (SDN). This evolution has amplified the complexities of managing and measuring network traffic, necessitating more sophisticated and dynamic traffic classification methods to maintain optimal network performance and ensure user Quality-of-Experience (QoE). This paper presents a novel approach to network traffic classification, leveraging the capabilities of Gaussian Mixture Models (GMM) to classify network traffic based on user behavior patterns and temporal data. Our methodology distinctly categorizes network traffic into business or pleasure-oriented activities by analyzing various features such as the number of connected users, traffic volume, the day of the week, and the time of day. This classification is crucial not only for traffic management but also for understanding evolving network usage patterns, which are vital for ensuring robust network operations and efficient resource allocation.

Network traffic congestion is a crucial issue facing mobile operators at various locations depending on the time of day and year. Traffic congestion generally occurs at peak times in urban or suburban areas. This is because the evolved NodeBs’ (eNBs) maximum capacity is very quickly exceeded by the number of users since the resource blocks (RBs) and the bandwith are limited. To best manage network congestion, it is necessary to optimize the allocation of the network resources. The resource allocation problem, which is known to be NPhard, is commonly formulated as an optimization problem under constraints. The objective is to minimize the number of uncovered users for a service required on an eNB in a given scenario. The territory under study is the city of Lomé, the data used for the analysis come from the geographical data of the OpenStreetMap (OSM) database. We propose an approach allowing the dynamic configuration of the network based on a model for predicting users mobility and a heuristic for optimizing Long Term Evolution (LTE) network resources. A Greedy algorithm and a Tabu Search algorithm have been implemented and tested. The results showed the potential of the Tabu Search algorithm to outperform the Greedy algorithm.

Several studies have shown that the layout of an area's infrastructure has a strong impact on the mobility of the mobile network users. Each district in a city has one or more different type of activity areas. Depending on the type of activity areas that a district covers, several profiles emerge. These profiles are closely linked to the impact a district can have on LTE users mobility. In the current work, we propose a first approach to determine the profile of a district in a territory. The territory under study is the city of Lomé, the data used for this analysis come from the geographical data of the OSM database. An alternative approach is proposed that, in the case of missing data, determines the profile of a new district from knowledge built from other districts in the same study area. To validate the proposed approach, evaluations were conducted considering several types of distance (Mahalanobis distance, Euclidian distance,…). It appears that with the K-NN algorithm, using manhattan distance, we have 61 % accuracy in determining the profile of a new district based on the nearest district's profiles.

In this paper, we present a novel approach to enhance data collection in Vehicular Ad-Hoc NETworks (VANETs). VANETs are a growing area of interest due to their unique characteristics and challenges, such as rapidly changing topology and frequent network disruptions. Efficient data collection is a critical issue in vehicular networks and has therefore become a focus of research. To address this challenge, we propose a stable clustering optimization solution based on adaptive multiple metrics. The cluster head selection is done based on both mobility metrics, such as position and relative speed, and Quality of Service (QoS) metrics, such as neighborhood degree and link quality. The proposed solution has been tested and evaluated through simulations using a vehicular mobility simulator in a realistic urban environment. The results show that the proposed approach provides more stable clusters with higher QoS, and allows for the selection of the appropriate cluster head to collect data from the vehicles and forward it to the destination.

Smart Car Parks (SCPs) based on Wireless Sensor Networks (WSNs) are one of the most interesting Internet of Things applications. This paper addresses the deployment optimization problem of two-tiered WSNs dedicated to fire monitoring in SCPs. Networks deployed inside the SCP consist of three types of nodes: Sensor Nodes (SNs) which cover the spots within the parking area, Relay Nodes (RNs) which forward alert messages generated by SNs, and the Sink node which is connected to the outside world (e.g, firefighters), through a high bandwidth connection. We propose an algorithm based on chaos theory and Whale Optimization Algorithm (WOA), which minimizes simultaneously the deployed number of SNs, RNs, and network diameter while ensuring coverage and connectivity. To evaluate the effectiveness of our proposal, we have conducted extensive tests. The results show that the Chaos WOA (CWOA) outperforms the original WOA in terms of solution quality and computation time and by comparison with an exact method, CWOA provides results very close to the optimal in terms of fitness value and is efficient in terms of computational time when the problem becomes more complex.

In this paper, we propose an Autocorrelation method for measuring the angle of arrival (AoA) of a weak LoRa signal. A weak LoRa signal has a negative SNR down to −20 dB. The objective is to detect a LoRa signal that operates at low transmission power (TX). Operating at low transmission power (TX) reduces power consumption and extends the battery life of LoRa devices. Besides, the transmission of weak signals strengthens the radio communication protocol, preventing an enemy device from accessing the location coordinates. The detecting algorithm consists of finding Autocorrelation peaks of the LoRa signal. We show that Autocorrelation peaks decrease when the signal is buried in the noise. However, using a large number of Fast Fourier Transform (FFT) will increase the Autocorrelation peaks and the signal-to-noise ratio (SNR). Once the peak of the LoRa signal is detected under the noise, the algorithm will calculate the AoA. All of the proposed algorithms are implemented using a Universal Software Radio Peripheral (USRP), Software Defined Radio (SDR) receiver with the help of GNU Radio software. We, therefore, believe that our Autocorrelation method can detect the LoRa signal accurately and measure the AoA at very low SNR in real_ time being usable for indoor positionning.

The massive machine-type communication will be at the core of ambient connectivity, requiring for energy-efficient systems. Earlier studies highlighted the efficiency of positioning approaches based on channel-state information (CSI) in different environments. Many works limited the solution assessment to a single room in a fully indoor testbed. This article extends the application of CSI for indoor–outdoor detection on an unprecedented large area and considers mMTC-oriented long-term evolution and fifth-generation Internet of Things in the sub-GHz frequency band. Hinged on a novel long-term evolution protocol dedicated for machine-type communications, the results focus on a unique packet exchange with a single access point to save battery life and simplify deployment. The study evaluates different input features and investigates the target positioning accuracy for multiple unsupervised and supervised dimensionality reduction methods. We present a new dimension reduction scheme consisting of an unsupervised funnel on top of a supervised dimension reduction approach. Results show that the introduced Funnel Fukunaga–Koontz transform outperforms other dimension reduction approaches, regardless of the input features and the number of locations.

Several radio frequency direction finding algorithms exist for Internet of Things (IoT) applications that use angle-of-arrival (AoA) measurements to estimate target position. However, providing reliable and accurate direction system capability still remains a challenge. In this paper, we are interested in measuring the angle-of-arrival (AoA) of LoRa RF signal by using a software-defined radio (SDR) platform implemented with antenna-array interferometry method. The proposed system can determine the node’s direction using only dual interferometry antenna. The two antennas are operated by an individual universal software radio peripheral (USRP) SDR receiver. Furthermore, a new paradigm of LoRa digital carrier signal detection is investigated using GNU Radio and USRP B210 operating at a center frequency of 868 MHz. We present a solution that builds on the LoRa modulation properties to determine the presence of the user’s signal in the channel. The phase difference of the detected signal received by the two-channel USRP B210 is used to estimate the node’s AoA. The entire experimental setup was implemented in the GNU Radio Companion (GRC) and measured in a 8m 8m office environment. The measurement results show an AoA ×with a mean error of less than 5 degrees approximately. We therefore believe that our AoA system can be easily calculated in real time without the need for complicated post-processing algorithms.

The exponential growth of the Internet-of-Things (IoT) technology paradigm has resulted in new applications and on-line services. Smart car park is one interesting example among others that can take advantage of applications based on wireless sensor networks (WSNs) Which constitute the core of IoT. This paper focuses on the deployment optimization problem of WSNs dedicated to the fire detection in a smart car park. In such networks, the nodes are classified into two categories: Sensor Nodes (SNs) deployed within the smart car park for targets coverage and Relay Nodes (RNs) whose task is to relay alert messages generated by the sensor nodes up to the sink node. In this study, we propose a Multi-Objective Binary Integer Linear Programming (MOBILP) which minimizes simultaneously the number of sensor nodes, relay nodes and the maximum distance from sensor nodes to the sink node, while ensuring coverage and connectivity. We have conducted extensive tests in order to evaluate the performance of our proposal. The results demonstrate that the MOBILP outperforms the existing approaches in terms of quality of solutions compared to a sequential deployment method, which consists to deploy SNs then RNs, and in terms of the ability to find other efficient solutions compared to a simultaneous deployment method using a mono-objective function, which consists to deploy SNs and RNs simultaneously.

Modeling and understanding people's mobility at a temporal and geographical space are very strict requirements for developing better strategies of urban public and private transportation systems as well as establishing improved business techniques. This work proposes a random-search based approach to instantiate statistical indicators through an improved mobility scenario which provides specific information about people attending one or several days for some events. Then, we recreate that scenario with virtual humans, proposing a synthetic and open dataset that matches the original statistical data. The results show the proposed approach is very efficient to model people's mobility, and the generated data has a low error rate compared to the original one.

A location-based service in the massive machine-type wireless communications (mMTC) must respect different requirements such as a minimal energy consumption at the target device or estimating the location in ambient connectivity. The solutions in mMTC must then consider localization approaches that provide target locations with few transmitted signals and with the support of only one anchor gateway. It is also major to use a relevant input data that manages the complex radio propagation mediums. In indoor environments, a solution builds on fingerprinting approach based on the channel state information (CSI) between the target device and a single anchor gateway. This paper presents a novel CSI fingerprinting localization method, E-Loc for mMTC dedicated to indoor systems in the Wi-Fi ambient connectivity context. E-Loc architecture is based on a convolutional neural network implementing inception models with an innovative design. CSI has been collected in a complex indoor environment, post-processed to handle the transmit power diversity, phase and timing offsets and fed to E-Loc. In various spatial distributions of training locations, E-Loc outperforms other tested solutions with a 99% confidence level for localization errors around 5 meters.

Vehicular Ad hoc NETworks (VANETs) are characterized by the rapidly changing topology and then a frequent network disruption. Hence, connectivity of moving vehicles presents an important challenge that critically influences the data transmission. Furthermore, data delivery ratio depends on routing protocols, applications type as well as environment characteristics. As a matter of fact, real experimentation in vehicular networks are costly and hard to deploy especially on large scale. Consequently, a vehicular mobility simulator is a good compromise to study how efficient are the data transmission mechanisms. In this paper, we comprehensively study the impact of the radio connectivity on data communication in vehicular networks. The analysis were realized based on a vehicular mobility simulator which runs a realistic scenario of mobility traffic in a real urban environment. A simple scenario of a safety application was implemented to examine the behavior of three well-known topology-based routing protocols. For the purpose of the analysis, we varied the simulation setup such as the density and the data traffic rate to determine the impact of the connectivity. The simulation results show that a realistic modelling of radio propagation has an important role in data transmission.

Many applications in Internet of Things (IoT) require an ubiquitous localization to provide their services. Whereas the global navigation satellite systems are mainly used in outdoor environment, multiple solutions based on mobile sensors or wireless communication infrastructures exist for indoor localization. One of them is the fingerprinting approach which consists in collecting the signals at known locations in a studied area and estimating the locations of new incoming signals thanks to the collected database. This approach interests many researches due to its connection with machine learning concepts. In this paper we propose to implement a deep learning architecture for a fingerprinting localization based on Wi-Fi channel frequency responses in IoT context. Our solution, DelFin reduces the median and 90-th percentile localization errors up to 50% and 47% respectively compared to other fingerprinting methods. DelFin has been tested with different spatial distributions of training locations in the studied area and still performed the best results.

The VANET are mainly characterized by the high nodes velocity, high nodes density at road intersections and traffic jams and severe radio signals degradation caused by obstacles present in the external environment. This make the direct application of routing protocols defined for MANET not suitable for VANET. In this paper we consider a simulation environment representing a real city map with its terrain characteristics and urban infrastructures and analyze the most common protocols developed for MANETs. The objective is to identify the appropriate and inappropriate routing strategies for vehicular networks. So, we examine the behavior of each protocol varying the vehicular density and the data traffic rate to determine the mechanisms that enable them to have a good efficiency and those that cause their performance degradation. The results show that when the effect of obstacles on the radio signals is ignored the reactive protocols outperform the proactive protocols while when the impact of the obstacles is taken into account, the results are almost similar.

Nowadays, Indoor Positioning Systems capitalize on the existing wireless local area network infrastructure and are very popular and attractive. However, most systems only focus on the network deployment for positioning but overlook that the original purpose of these WLAN infrastructures is providing the required connectivity. In this paper, we propose an innovative approach where WLAN planning and positioning error reduction are modeled as an optimization problem and tackled together during the WLAN planning process. A Mono-objective algorithm called Variable Neighborhood Search (VNS) is implemented. The simulations results demonstrate that this approach is highly efficient in solving the indoor positioning optimization problem.

In recent years, the indoor positioning systems using the existing wireless local area network and Location fingerprinting schemes are the most popular system. The accuracy of the system is the most important indicator. In this paper we present experimental studies to emphasize on location error. Two experimentation stages are realized. The first one is based on selected reference points. The second one is based on precision indicators. The obtained results give more insights for environment parameters and their impact on location error. Finally, we propose an optimization algorithm to effectively increase the location accuracy.

Frequency assignment is one of the main issues in radio networks planning. The multiple interferences are seldom taken into account in literature. There is not a framework with their modeling. A hypergraph modeling of the network gives a more realistic representation of this phenomenon. We generalize theT-coloring problem for graphs to hypergraphs. We apply this new modeling to IEEE 802.11b/g wireless networks and study its interest.

In this article we address the frequency management during WLAN planning. Frequency management refers to channels interference and SINR computation. We propose a new approach where location selection and frequency assignment are tackled together during WLAN planning process. Two steps characterize this approach. Firstly we use all the available channels for frequency assignment. Secondly multiple signals are taken into account to compute the SINR. Several experimental results show the benefits of this new approach.

Two types of applications use indoor positioning, services linked with mobility, such as guided tour or meeting systems, and the active security of a wireless network which locates intrusive unauthorized mobile terminals. Indoor positioning cannot be managed by a geostationary system like GPS. In fact, current researches are being conducted to conceive indoor positioning using wireless networks such as WiFi. We study such a mechanism and compare the accuracy of our results to other solutions. Our model is based on the Friis relation, which expresses signal strength as a function of distance, in a free space environment. The Friis-based model is adapted to fit the conditions of implementation. The positioning function is combined with a mobility prediction mechanism and constitutes the mobility service in a video on demand system called MoVie (mobile video).

Distributed object-oriented computing allows efficient use of the Network Of Workstations (NOW) paradigm. However, the underlying middlewares used to develop and deploy such applications do not provide developers with any standard supervision mechanism so that they know exactly what happens during their applications execution. This paper analyzes distributed CORBA and JAVA-based applications to point out functional and management supervision information which has to be gathered from the objects. Developers will use this information to improve the Quality of Service (QoS) of their distributed object-oriented applications (DOA).