The Mobile Internet of Things (MIoT) represents a significant evolution of traditional IoT by enabling seamless connectivity for mobile devices and sensors in dynamic environments. Given the resource constraints and mobility challenges in MIoT networks, developing adaptive and energy-efficient routing strategies is important. This paper proposes a novel routing protocol that integrates Grey Wolf Optimization (GWO) and Recurrent Neural Networks (RNNs) to enhance energy efficiency, reliability, and responsiveness in MIoT systems. The protocol features dynamic clustering, predictive traffic load balancing, and multi-objective optimization for Cluster Head (CH) selection, where RNNs forecast traffic trends and GWO optimizes routing paths. Simulation results demonstrate that the proposed method reduces energy consumption, lowers end-to-end delays, and improves packet delivery ratio (PDR) and network reliability under both static and mobile conditions. Compared to existing methods such as the Krill Herd (KH) algorithm, Dynamic Multi-Sink Routing Protocol (DMS-RP), and Evolutionary Fuzzy Rule-based (EFR) models, the proposed solution exhibits superior performance, validating its scalability and effectiveness for real-world MIoT applications.

Graph contrastive learning has demonstrated outstanding performance in addressing the issue of label scarcity. It still has two limitations: 1) the stacking of graph layers often leads to over-smoothing, hard to distinguish the embeddings of distinct nodes; and 2) traditional algorithms typically model user preferences with a unified intention, neglecting the multifaceted and fine-grained motivations behind user-item interactions. To overcome these shortcomings, we propose an adaptive disentangled contrastive learning (AdaDCL) method tailored for recommendation systems. First, we perform disentangled modeling of global information intentions and introduce a cross-view contrastive learning task, employing a parameterized mask generator for adaptive augmentation. Second, we employ a layer attention mechanism to counter over-smoothing in GNNs, ensuring that meaningful semantic features are preserved across layers. Third, an adaptive hardness negative sampling (AHNS) strategy dynamically selects negative samples based on their hardness levels, reducing the risk of false positives and negatives while enhancing the robustness of contrastive learning. Comprehensive experiments on three benchmark datasets, including Gowalla, and comparisons against twelve state-of-the-art baseline models (e.g., DisenHAN), demonstrate that AdaDCL surpasses the classic LightGCN by 5.89% in Recall@20 and over 7% in NDCG@20 on the Gowalla dataset. These results highlight the effectiveness and generalizability of our approach.

Large-scale networks cannot be effectively addressed by global structure-based techniques due to their high temporal complexity, while local structure-based methods may overlook global information. To overcome these limitations, we propose a novel key node identification method for complex networks, named cycle structure, voting mechanism, ranking principle (CVR). This method adopts a multilevel processing approach and an enhanced voting mechanism. Initially, it incorporates the centrality of the network cycle structure and describes the topological locations of nodes within their neighborhoods. Subsequently, the traditional voting mechanism is refined by incorporating both global and local information from complex networks, providing a more accurate representation of relationships between nodes and the structures of neighborhoods in the network. The extended neighborhood ideology is then integrated with the improved voting mechanism, resulting in an effective method for identifying hidden key nodes. The effectiveness of the CVR method is validated through experiments on nine datasets using nine baseline methods, including the susceptible, infective, recovered (SIR) and linear threshold (LT) models, as well as experiments involving the seed selection technique for choosing initial infection nodes. Results show that CVR improves the infection rate by 4.7%–156.8% under varying infection probabilities in the SIR model.

Despite significant advancements in Internet of Things (IoT)-based smart cities, service discovery and composition continue to pose challenges. Current methodologies face limitations in optimizing Quality of Service (QoS) in diverse network conditions, thus creating a critical research gap. This study presents an original and innovative solution to this issue by introducing a novel three-layered Recurrent Neural Network (RNN) algorithm. Aimed at optimizing QoS in the context of IoT service discovery, our method incorporates user requirements into its evaluation matrix. It also integrates Long Short-Term Memory (LSTM) networks and a unique Black Widow Optimization (BWO) algorithm, collectively facilitating the selection and composition of optimal services for specific tasks. This approach allows the RNN algorithm to identify the top-K services based on QoS under varying network conditions. Our methodology’s novelty lies in implementing LSTM in the hidden layer and employing backpropagation through time (BPTT) for parameter updates, which enables the RNN to capture temporal patterns and intricate relationships between devices and services. Further, we use the BWO algorithm, which simulates the behavior of black widow spiders, to find the optimal combination of services to meet system requirements. This algorithm factors in both the attractive and repulsive forces between services to isolate the best candidate solutions. In comparison with existing methods, our approach shows superior performance in terms of latency, availability, and reliability. Thus, it provides an efficient and effective solution for service discovery and composition in IoT-based smart cities, bridging a significant gap in current research.

Community detection in large-scale networks is one of the main challenges in social networks analysis. Proposing a fast and accurate algorithm with low time complexity is vital for large-scale networks. In this paper, a fast community detection algorithm based on local balanced label diffusion (LBLD) is proposed. The LBLD algorithm starts with assigning node importance score to each node using a new local similarity measure. After that, top 5% important nodes are selected as initial rough cores to expand communities. In the first step, two neighbor nodes with highest similarity than others receive a same label. In the second step, based on the selected rough cores, the proposed algorithm diffuses labels in a balanced approach from both core and border nodes to expand communities. Next, a label selection step is performed to ensure that each node is surrendered by the most appropriate label. Finally, by utilizing a fast merge step, final communities are discovered. Besides, the proposed method not only has a fast convergence speed, but also provides stable and accurate results. Moreover, there is no randomness as well as adjustable parameter in the LBLD algorithm. Performed experiments on real-world and synthetic networks show the superiority of the LBLD method compared with examined algorithms.

As the community detection is able to facilitate the discovery of hidden information in complex networks, it has been drawn a lot of attention recently. However, due to the growth in computational power and data storage, the scale of these complex networks has grown dramatically. In order to detect communities by utilizing global approaches, it is required to have all the global information of the whole network; something which is impossible, because of the rapid growth in the size of the networks. In this paper, a local approach has been proposed based on the detection and expansion of core nodes. First, a community's central node (core node) which has a high level of embeddedness is detected based on the similarity between graph's nodes. By using this, the total weights of a weighted graph's edges created. Following by that, the expansion of these nodes will be considered, by utilizing the concept of node's membership based on the definition of strong community for weighted graphs. It can be seen that in detecting communities, the more accurate the weights of edges detected based on the node similarity, the more precise the local algorithm will be. In fact, the algorithm has the ability to detect all the graph's communities in a network using local information as well as identifying various roles of nodes, either being (core or outlier). Test results on both real-world and artificial networks prove that the quality of the communities which are detected by the proposed algorithm is better than the results which are achieved by other state-of-the-art algorithms in the complex networks.