Content caching is a promising approach in edge computing to cope with the explosive growth of mobile data on 5G networks, where contents are typically placed on local caches for fast and repetitive data access. Due to the capacity limit of caches, it is essential to predict the popularity of files and cache those popular ones. However, the fluctuated popularity of files makes the prediction a highly challenging task. To tackle this challenge, many recent works propose learning based approaches which gather the users' data centrally for training, but they bring a significant issue: users may not trust the central server and thus hesitate to upload their private data. In order to address this issue, we propose a Federated learning based Proactive Content Caching (FPCC) scheme, which does not require to gather users' data centrally for training. The FPCC is based on a hierarchical architecture in which the server aggregates the users' updates using federated averaging, and each user performs training on its local data using hybrid filtering on stacked autoencoders. The experimental results demonstrate that, without gathering user's private data, our scheme still outperforms other learning-based caching algorithms such as m--greedy and Thompson sampling in terms of cache efficiency.

Content Caching at the edge of vehicular networks has been considered as a promising technology to satisfy the increasing demands of computation-intensive and latency-sensitive vehicular applications for intelligent transportation. The existing content caching schemes, when used in vehicular networks, face two distinct challenges: 1) Vehicles connected to an edge server keep moving, making the content popularity varying and hard to predict. 2) Cached content is easily out-of-date since each connected vehicle stays in the area of an edge server for a short duration. To address these challenges, we propose a Mobility-aware Proactive edge Caching scheme based on Federated learning (MPCF). This new scheme enables multiple vehicles to collaboratively learn a global model for predicting content popularity with the private training data distributed on local vehicles. MPCF also employs a Context-aware Adversarial AutoEncoder to predict the highly dynamic content popularity. Besides, MPCF integrates a mobility-aware cache replacement policy, which allows the network edges to add/evict contents in response to the mobility patterns and preferences of vehicles. MPCF can greatly improve cache performance, effectively protect users' privacy and significantly reduce communication costs. Experimental results demonstrate that MPCF outperforms other baseline caching schemes in terms of the cache hit ratio in vehicular edge networks.

To cope with the increasing content requests from emerging vehicular applications, caching contents at edge nodes is imperative to reduce service latency and network traffic on the Internet-of-Vehicles (IoV). However, the inherent characteristics of IoV, including the high mobility of vehicles and restricted storage capability of edge nodes, cause many difficulties in the design of caching schemes. Driven by the recent advancements in machine learning, learning-based proactive caching schemes are able to accurately predict content popularity and improve cache efficiency, but they need gather and analyse users' content retrieval history and personal data, leading to privacy concerns. To address the above challenge, we propose a new proactive caching scheme based on peer-to-peer federated deep learning, where the global prediction model is trained from data scattered at vehicles to mitigate the privacy risks. In our proposed scheme, a vehicle acts as a parameter server to aggregate the updated global model from peers, instead of an edge node. A dual-weighted aggregation scheme is designed to achieve high global model accuracy. Moreover, to enhance the caching performance, a Collaborative Filtering based Variational AutoEncoder model is developed to predict the content popularity. The experimental results demonstrate that our proposed caching scheme largely outperforms typical baselines, such as Greedy and Most Recently Used caching.

No abstract

<p>In the context of deep-tissue disease biomarker detection and analyte sensing of biologically relevant species, the impact of photoacoustic imaging has been profound. However, most photoacoustic imaging agents to date are based on the repurposing of existing fluorescent dye platforms that exhibit non-optimal properties for photoacoustic applications (e.g., high fluorescence quantum yield). Herein, we introduce two effective modifications to the hemicyanine dye to afford PA-HD, a new dye scaffold optimized for photoacoustic probe development. We observed a significant increase in the photoacoustic output, representing an increase in sensitivity of 4.8-fold and a red-shift of the λ_abs from 690 nm to 745 nm to enable ratiometric imaging. Moreover, to demonstrate the generalizability and utility of our remodeling efforts, we developed three probes using common analyte-responsive triggers for beta-galactosidase activity (PA-HD-Gal), nitroreductase activity (PA-HD-NTR), and hydrogen peroxide (PA-HD-H₂O₂). The performance of each probe (responsiveness, selectivity) was evaluated <i>in vitro</i> and <i>in cellulo</i>. To showcase the enhance properties afforded by PA-HD for <i>in vivo</i> photoacoustic imaging, we employed an Alzheimer’s disease model to detect H₂O₂. In particular, the photoacoustic signal at 735 nm in the brains of 5xFAD mice (a murine model of Alzheimer’s disease) increased by 1.72 ± 0.20-fold relative to background indicating the presence of oxidative stress, whereas the change in wildtype mice was negligible (1.02 ± 0.14). These results were confirmed via ratiometric calibration which was not possible using the parent HD platform.</p>