Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability.

To save the energy during content delivery in green cities, caching contents on edge nodes which are placed near mobile social users has been advocated recently. However, how to allocate the limited caching resources with secure content delivery becomes a new challenge. Therefore, in this paper, we present a novel theoretical model to deliver secure content with edge nodes in order to save energy for green cities. Firstly, we present a reverse auction game to encourage edge nodes to cooperatively provide caching services with incentives. With the model, mobile users can determine the candidate of edge node to cache content based on the interaction between mobile users and edge nodes. Secondly, a trust management method is designed to evaluate the reliability of the selected candidate of edge node by considering the direct trust evaluation. Finally, the extensive simulations show that the proposal can save the energy with a secure content delivery where both the delay to obtain the content and the caching ratio can be improved compared with the conventional methods.

Container placement (CP) is a nontrivial problem in Container as a Service (CaaS). Many works in the literature solve it by using linear server energy-consumption models. However, the solutions of using a linear model makes different CPs indistinguishable with regard to energy consumption in a homogeneous host environment that has a same amount of active hosts. As such, these solutions are energy inefficient. In this paper, we demonstrate that an energy-saving gain can be achieved by optimizing the placement of containers under a nonlinear energy consumption model. Specifically, we leverage a strategy based on genetic algorithm (GA) to search the optimal solution. Unfortunately, the conventional GA incurs performance degradation when the virtual machine (VM) resource utilization is high. In order to solve this problem, we propose an improved genetic algorithm called IGA for efficiently searching the optimal CP solution by introducing two different exchange mutation operations and constructing a function as the control parameter to selectively control the usage of the two operations. Extensive experiments are carried out under different settings, and their results show that our strategy is better than the existing CP strategies, i.e., spread and binpack, on energy efficiency target. In addition, the introduced IGA is experimentally proved to be more effective compared with the First Fit, Particle Swarm Optimization (PSO) algorithm and conventional GA. Moreover, the results validate that our proposed strategy can search new CP solutions with better fitness and alleviate the performance degradation caused by the conventional GA when the VM resource utilization is high.

Caching contents in edge computing-enabled small cell base stations (ECSBSs) has become a promising technology for mitigating burdens of macro cell base stations and offloading data from mobile users. However, as ECSBSs may be malicious, providing a secure caching scheme becomes a challenge. In this paper, we propose a novel secure caching scheme in heterogeneous networks for multi-homing users. Firstly, to provide the cached contents, a trust mechanism is designed to verify the reliability of each ECSBS. Then, in order to guarantee the integrity of cached contents and preserve the privacy of mobile users, a Chinese remainder theorem (CRT) based privacy preservation protocol is proposed. Next, we investigate the interactions among mobile users and ECSBSs by Stackelberg game, where the trusted ECSBSs are selected to provide caching space for mobile users with multi-homing access. In addition, we analyze the Stackelberg equilibrium (SE) to jointly maximize the utilities of ECSBSs and mobile users. Extensive simulations validate the efficiency of the proposed scheme with the reliability and effectiveness to cache contents.