Mobile Crowd Sensing (MCS) acts as a key component of Internet of Things (IoTs), which has attracted much attention. In an MCS system, participants play an important role, since all the data is collected and provided by them. It is challenging but essential to recruit credible participants and motive them to contribute high quality data. In this paper, we propose a learning-based credible participant recruitment strategy (LC-PRS), which aims to maximize the platform and participants’ profits at the same time via MCS participation. Specifically, the LC-PRS consists of two mechanisms, that a learning-based reward allocation mechanism (L-RAM) first calculates the maximum offered reward for different locations based on the number of participants in each location. Under a budget constraint, the proposed L-RAM prefers to collect sensing data from locations which relatively few data has so far been collected. Furthermore, for each location, we develop a credible participant recruitment mechanism (C-PRM), which employs semi-Markov model and game theory to predict quality of data provided by each participant and to recruit participants based on the predictions and the maximum offered reward calculated by L-RAM. We formally show LC-PRS has the desirable properties of computational efficiency, selection efficiency, individual rationality and truthfulness. We evaluate the proposed scheme via simulation using three real datasets. Extensive simulation results well justify the effectiveness of the proposed approach in comparison with other two methods.

In high-speed mobile scenarios characteristic of the Fifth Generation Mobile Networks (5G) environment, the user video experience may be compromised due to concurrent access by numerous users and frequent base station transitions. Addressing this issue, this study introduces a cross-layer resource allocation model that integrates environmental awareness and is tailored for the exigencies of high-speed mobile networks. The paper delves into the challenges engendered by rapid mobility and extensive user access within the 5G environment and critiques the constraints of prevalent resource allocation methodologies. The model delineated herein is conceptualized as an optimization challenge and characterized as a nonlinear, NP-hard problem. In response to this challenge, this study advocates a novel streaming media transmission algorithm underpinned by edge computing, in tandem with an environment-aware wireless resource allocation algorithm. The article articulates the foundational principles and operational modalities of these algorithms, underscoring the significance of environmental cognizance in resource distribution and the efficacy of edge computing in increasing video transmission efficiency. Empirical validation, achieved through simulation experiments, corroborates the efficacy of the proposed approach. Comparative analysis reveals that, relative to conventional methodologies, the proposed framework significantly improves video transmission quality and user experience, particularly in contexts characterized by frequent network fluctuations and high user densities. This research contributes novel insights and pragmatic solutions to optimize video transmission in existing 5G and prospective network paradigms.

Vision-Language Models (VLMs) built on contrastive learning, such as CLIP, demonstrate great transferability and excel in downstream tasks like zero-shot classification and retrieval. To further enhance the performance of VLMs, existing methods have introduced additional parameter modules or fine-tuned VLMs on downstream datasets. However, these methods often fall short in scenarios where labeled data for downstream tasks is either unavailable or insufficient for fine-tuning, and the training of additional parameter modules may considerably impair the existing transferability of VLMs on open-set tasks. To alleviate this issue, we introduce WaveDN, a wavelet-based distribution normalization method that can boost the VLMs' performance on downstream tasks without parametric modules or labeled data. Initially, wavelet distributions are extracted from the embeddings of the sampled, unlabeled test samples. Subsequently, WaveDN conducts a hierarchical normalization across the wavelet coefficients of all embeddings, thereby incorporating the distributional characteristics of the test data. Finally, the normalized embeddings are reconstructed via inverse wavelet transformation, facilitating the computation of similarity metrics between the samples. Through extensive experiments on two downstream tasks, using a total of 14 datasets covering text-image and text-audio modal data, WaveDN has demonstrated superiority compared to state-of-the-art methods.