Advances in deep learning have transformed medical imaging, yet progress is hindered by data privacy regulations and fragmented datasets across institutions. To address these challenges, we propose FedVGM, a privacy-preserving federated learning framework for multi-modal medical image analysis. FedVGM integrates four imaging modalities, including brain MRI, breast ultrasound, chest X-ray, and lung CT, across 14 diagnostic classes without centralizing patient data. Using transfer learning and an ensemble of VGG16 and MobileNetV2, FedVGM achieves 97.7% $\pm$ 0.01 accuracy on the combined dataset and 91.9-99.1% across individual modalities. We evaluated three aggregation strategies and demonstrated median aggregation to be the most effective. To ensure clinical interpretability, we apply explainable AI techniques and validate results through performance metrics, statistical analysis, and k-fold cross-validation. FedVGM offers a robust, scalable solution for collaborative medical diagnostics, supporting clinical deployment while preserving data privacy.

Abstract Smart device manufacturers rely on insights from smart home (SH) data to update their devices, and similarly, service providers use it for predictive maintenance. In terms of data security and privacy, combining distributed federated learning (FL) with blockchain technology is being considered to prevent single point failure and model poising attacks. However, adding blockchain to a FL environment can worsen blockchain's scaling issues and create regular service interruptions at SH. This article presents a scalable Blockchain‐based Privacy‐preserving Federated Learning (BPFL) architecture for an SH ecosystem that integrates blockchain and FL. BPFL can automate SHs' services and distribute machine learning (ML) operations to update IoT manufacturer models and scale service provider services. The architecture uses a local peer as a gateway to connect SHs to the blockchain network and safeguard user data, transactions, and ML operations. Blockchain facilitates ecosystem access management and learning. The Stanford Cars and an IoT dataset have been used as test bed experiments, taking into account the nature of data (i.e. images and numeric). The experiments show that ledger optimisation can boost scalability by 40–60% in BCN by reducing transaction overhead by 60%. Simultaneously, it increases learning capacity by 10% compared to baseline FL techniques.

Ultra-reliable low-latency communication (uRLLC) and enhanced mobile broadband (eMBB) are two influential services of the emerging 5G cellular network. Latency and reliability are major concerns for uRLLC applications, whereas eMBB services claim for the maximum data rates. Owing to the trade-off among latency, reliability and spectral efficiency, sharing of radio resources between eMBB and uRLLC services, heads to a challenging scheduling dilemma. In this paper, we study the co-scheduling problem of eMBB and uRLLC traffic based upon the puncturing technique. Precisely, we formulate an optimization problem aiming to maximize the minimum expected achieved rate (MEAR) of eMBB user equipment (UE) while fulfilling the provisions of the uRLLC traffic. We decompose the original problem into two sub-problems, namely scheduling problem of eMBB UEs and uRLLC UEs while prevailing objective unchanged. Radio resources are scheduled among the eMBB UEs on a time slot basis, whereas it is handled for uRLLC UEs on a mini-slot basis. Moreover, for resolving the scheduling issue of eMBB UEs, we use penalty successive upper bound minimization (PSUM) based algorithm, whereas the optimal transportation model (TM) is adopted for solving the same problem of uRLLC UEs. Furthermore, a heuristic algorithm is also provided to solve the first sub-problem with lower complexity. Finally, the significance of the proposed approach over other baseline approaches is established through numerical analysis in terms of the MEAR and fairness scores of the eMBB UEs.

In this paper, we study the resource slicing problem in a dynamic multiplexing scenario of two distinct 5G services, namely Ultra-Reliable Low Latency Communications (URLLC) and enhanced Mobile BroadBand (eMBB). While eMBB services focus on high data rates, URLLC is very strict in terms of latency and reliability. In view of this, the resource slicing problem is formulated as an optimization problem that aims at maximizing the eMBB data rate subject to a URLLC reliability constraint, while considering the variance of the eMBB data rate to reduce the impact of immediately scheduled URLLC traffic on the eMBB reliability. To solve the formulated problem, an optimization-aided Deep Reinforcement Learning (DRL) based framework is proposed, including: 1) eMBB resource allocation phase, and 2) URLLC scheduling phase. In the first phase, the optimization problem is decomposed into three subproblems and then each subproblem is transformed into a convex form to obtain an approximate resource allocation solution. In the second phase, a DRL-based algorithm is proposed to intelligently distribute the incoming URLLC traffic among eMBB users. Simulation results show that our proposed approach can satisfy the stringent URLLC reliability while keeping the eMBB reliability higher than 90%.

LTE over unlicensed band (LTE-U) has emerged as an effective technique to overcome the challenge of spectrum scarcity. Using LTE-U along with advanced techniques such as carrier aggregation (CA), one can boost the performance of existing cellular networks. However, if not properly managed, the use of LTE-U can potentially degrade the performance of co-existing Wi-Fi access points which operate over the unlicensed frequency bands. Moreover, most of the existing works consider a macro base station (MBS) or a small cell base station (SBS) for their proposals. In this paper, an effective coexistence mechanism between LTE-U and Wi-Fi systems is studied. The goal is to enable the cellular network to use LTE-U with CA to meet the quality-of-service (QoS) of the users while protecting Wi-Fi access points (WAPs), considering multiple SBSs from different operators in a dense deployment scenario. Specifically, an LTE-U sum-rate maximization problem is formulated under a user QoS and WAP-LTE-U co-existence constraints. To solve this problem, a cooperative Nash bargaining game is proposed. This game allows LTE-U and WAPs to share time resource while protecting Wi-Fi system. For allocating unlicensed resource among LTE-U users, a heuristic algorithm is proposed. Simulation results show that the proposed method is better than the comparing methods regarding per user achieved rate, percentage of unsatisfied users and fairness. The result also shows that the proposed method protects Wi-Fi user far better way than basic listen-before-talk (LBT) does.

Daily-life oriented applications and multimedia entertainments through smart devices are creating immense stress to the current cellular foundation. To overwhelm from this loopholes, both academia and industry are trying their best by incorporating different technologies with existing ones using licensed spectrum. On the other side, Device-to-Device (D2D) communications are also being used to improve the spectrum efficiency and user experience by reutilizing licensed cellular spectrum. But with insufficient licensed spectrum, it is impossible to meet the demand of users in the current scenario. So, peoples are thinking to utilize unlicensed spectrum with licensed one to alleviate this scarcity issue and provide guaranteed Quality of Service (QoS) to the users. In this paper, we want to extend D2D communication and LTE-A network into the unlicensed spectrum. But this initiative will harm the performance of other technologies which are already working in the same unlicensed band. Moreover, if multiple mobile network operators (MNOs) use the same unlicensed band then they will diminish the benefits of each other. So this paper wants to maximize the sum-rate of LTE users and D2D pairs by allocating licensed and unlicensed subchannels considering their QoS requirements while protecting minimum requirements of WiFi Access Points (WAPs). Then we solve this problem with the help of Nash bargaining game (NBG) between Small Cell Base Stations (SBSs) and WAPs by the cooperative approach. Simulation results show the effectiveness and efficiency of the proposed approach.

Social networks have gained huge research interest, especially in viral marketing due to their rapid boom in the past years. It is very crucial to identify the influential users in the social networks for viral and target marketing. Influence maximization (IM) problem estimates such influential users in the social networks. With an initial seed set, the IM finds a maximum number of nodes that can be activated in the network under some diffusion models e.g. Linear Threshold model or Independent Cascade model. But previous works in this field have not studied about the minimum cost, termed as opportunity cost (OC), to motivate those seed nodes. In this work, we define a novel Reverse Influence Maximization (RIM) problem to determine the opportunity cost of influence maximization. Employing the influence propagation in opposite order, the RIM determines the minimum number of nodes that must be activated in order to motivate a set of target nodes. We propose Random RIM (R-RIM) and Randomized Linear Threshold RIM (RLT-RIM) models to tackle the RIM problem. We also perform a simulation to evaluate the performance of the algorithms using two real world datasets. The result shows that the proposed models determine the optimized opportunity cost with faster running time margin.

The demand for data rate is increasing exponentially in the cellular networks due to the emergence of more and more data-driven applications and smart-devices. Currently, these demands cannot be met by cellular networks with any single technology. As a consequence, Quality-of-service (QoS) needs to be sacrificed by some users. To provide guaranteed QoS to the users, researchers are considering massive MIMO, LTE-A, cooperative communications etc as the suitable candidate for the next generation cellular network. In this paper, we propose a collaborative communication mechanism with incentive for downlink in the cellular network for providing guaranteed QoS by utilizing multiple connectivity of the user's smart equipments. We formulate the problem as an optimization problem first and afterwards, we solve this problem with the help of matching theory. Simulation results are shown to represent performance of the technique.