مشخصات پژوهش

Community detection in multilayer networks is very important because it helps to understand many real-world systems. In social networks, for example, people connect in different ways like friendship, work, or communication [11], and in biological networks, there are different layers such as genetic, metabolic, and protein interactions [12]. If we ignore multilayer structure and treat system like single-layer network, important information can be lost and wrong community patterns can appear [13]. Traditional methods often fail to consider the differences between layers and their importance, so their results may not be accurate. Also, robustness and clarity of detected communities are very necessary [14]. Without measuring how strongly nodes are connected in their local neighborhood in each layer, the detected communities may be influenced by noise or weak connections. Recent studies show that using layer-specific neighborhood strength can improve the quality of community detection [15]. Moreover, not all layers have same influence: some layers are more meaningful or have stronger signal, so using a consensus mechanism that weights layers according to their importance can give better and more meaningful communities [16], [17]. This idea is very useful in applications like transportation networks with multiple modes (road, rail, air), where layers have different importance for system performance [18]. Finally, proposing a method that combines intra-layer neighborhood strength with inter-layer weighted consensus can fill a gap in literature. Many existing methods either combine layers too simple or treat all layers equally, so they may fail when layers have different qualities or importance. This kind of model can improve both theory and practice of multilayer network analysis and help detect stable and meaningful communities in real and complex systems. Addressing these challenges is essential not only for advancing the field of network science but also for enabling da