Growing awareness of wellness has prompted people to consider whether their dietary patterns align with their health and fitness goals. In response, researchers have introduced various wearable dietary monitoring systems and dietary assessment approaches. However, these solutions are either limited to identifying foods with simple ingredients or insufficient in providing an analysis of individual dietary behaviors with domain-specific knowledge. In this article, we present DietGlance , a system that automatically monitors dietary behaviors in daily routines and delivers personalized analysis from knowledge sources. DietGlance first detects ingestive episodes from multimodal inputs using eyeglasses, capturing privacy-preserving meal images of various dishes being consumed. Based on the inferred food items and consumed quantities from these images, DietGlance further provides nutritional analysis and personalized dietary suggestions, empowered by the retrieval-augmented generation module on a reliable nutrition library. A short-term user study (N = 33) and a 4-week longitudinal study (N = 16) demonstrate the usability and effectiveness of DietGlance , offering insights and implications for future AI-assisted dietary monitoring and personalized healthcare intervention systems using eyewear.

Causality has been integrated with machine learning in uncovering and understanding the causal relationship between variables and observed outcomes. However, the centralized training setting of causal machine learning is not adaptable to most practical scenarios, where datasets are distributed, stored, and unsharable due to privacy concerns. Federated learning (FL), a distributed learning framework that allows collaborative training across multiple devices without raw data sharing, emerges as a potential solution to this problem. By integrating FL into causal problems, the discovery and inference of causal relationships across dispersed datasets can be achieved. On the other hand, causality can also enhance FL models in various dimensions, including model interpretability and explainability, generalizability, adversarial robustness, and fairness and bias mitigation. In this article, we provide a comprehensive review of the above two directions and summarize the interplays between causality and FL (short for Causal-FL ) by organizing our discussion around two key questions: (1) how FL enable decentralized causal analysis; and (2) how causality tackles FL challenges. The potential applications of these methods are also introduced, including healthcare, recommendation, economics, social equity, and so on. Moreover, we discuss promising future directions and future challenges to be explored.

Users often take notes for instructional videos to access key knowledge later without revisiting long videos.Automated note generation tools enable users to obtain informative notes efficiently.However, notes generated by existing research or off-the-shelf tools fail to preserve the information conveyed in the original videos comprehensively, nor can they satisfy users' expectations for diverse presentation formats and interactive features when using notes digitally.In this work, we present NoteIt, a system, which automatically converts instructional videos to interactable notes using a novel pipeline that faithfully extracts hierarchical structure and multimodal key information from videos.With NoteIt's interface, users can interact with the system to further customize the content and presentation formats of the notes according to their preferences.We conducted both a technical evaluation and a comparison user study (N=36).The solid performance in objective metrics and the positive user feedback demonstrated the effectiveness of the pipeline and the overall usability of NoteIt.

Leveraging blockchain in Federated Learning (FL) emerges as a new paradigm for secure collaborative learning on Massive Edge Networks (MENs). As the scale of MENs increases, it becomes more difficult to implement and manage a blockchain among edge devices due to complex communication topologies, heterogeneous computation capabilities, and limited storage capacities. Moreover, the lack of a standard metric for blockchain security becomes a significant issue. To address these challenges, we propose a lightweight blockchain for verifiable and scalable FL, namely LiteChain, to provide efficient and secure services in MENs. Specifically, we develop a distributed clustering algorithm to reorganize MENs into a two-level structure to improve communication and computing efficiency under security requirements. Moreover, we introduce a Comprehensive Byzantine Fault Tolerance (CBFT) consensus mechanism and a secure update mechanism to ensure the security of model transactions through LiteChain. Our experiments based on Hyperledger Fabric demonstrate that LiteChain presents the lowest end-to-end latency and on-chain storage overheads across various network scales, outperforming the other two benchmarks. In addition, LiteChain exhibits a high level of robustness against replay and data poisoning attacks.

Due to the revolution of communication technology, the rapidly increasing number of mobile devices in edge networks generates various real-time service requests, requiring a considerable volume of heterogeneous resources all the time. However, edge devices with limited resources cannot afford substantial learning cost, while migrating services requires heterogeneous resources, especially for dynamic networks. To address these issues, we first establish a cooperative service migration framework and formulate a bi-objective optimization problem to optimize service performance and cost. By analyzing the optimal migration ratio of service cooperative migration, we propose an offline expert policy based on global states to provide optimal expert demonstrations. To realize real-time service migration based on observable states, we design a lightweight online agent policy to imitate expert demonstrations and leverage meta update to accelerate the model transfer. Experimental results show that our algorithm is exceptional in training cost and accuracy, and has significant superiors in multiple metrics such as the service latency and payment under different workloads, compared to other representative algorithms.

The correlation between children's personal and family characteristics (e.g., demographics and socioeconomic status) and their physical and mental health status has been extensively studied across various research domains, such as public health, medicine, and data science. Such studies can provide insights into the underlying factors affecting children's health and aid in the development of targeted interventions to improve their health outcomes. However, with the availability of multiple data sources, including context data (i.e., the background information of children) and motion data (i.e., sensor data measuring activities of children), new challenges have arisen due to the large-scale, heterogeneous, and multimodal nature of the data. Existing statistical hypothesis-based and learning model-based approaches have been inadequate for comprehensively analyzing the complex correlation between multimodal features and multi-dimensional health outcomes due to the limited information revealed. In this work, we first distill a set of design requirements from multiple levels through conducting a literature review and iteratively interviewing 11 experts from multiple domains (e.g., public health and medicine). Then, we propose HealthPrism, an interactive visual and analytics system for assisting researchers in exploring the importance and influence of various context and motion features on children's health status from multi-levelperspectives. Within HealthPrism, a multimodal learning model with a gate mechanism is proposed for health profiling and cross-modality feature importance comparison. A set of visualization components is designed for experts to explore and understand multimodal data freely. We demonstrate the effectiveness and usability of HealthPrism through quantitative evaluation of the model performance, case studies, and expert interviews in associated domains.

Existing methods for adapting Neural Radiance Fields (NeRFs) to scene changes require extensive data capture and model retraining, which is both time-consuming and labor-intensive. In this paper, we tackle the challenge of efficiently adapting NeRFs to real-world scene changes over time using a few new images while retaining the memory of unaltered areas, focusing on the continual learning aspect of NeRFs. To this end, we propose CL-NeRF, which consists of two key components: a lightweight expert adaptor for adapting to new changes and evolving scene representations and a conflict-aware knowledge distillation learning objective for memorizing unchanged parts. We also present a new benchmark for evaluating Continual Learning of NeRFs with comprehensive metrics. Our extensive experiments demonstrate that CL-NeRF can synthesize high-quality novel views of both changed and unchanged regions with high training efficiency, surpassing existing methods in terms of reducing forgetting and adapting to changes. Code and benchmark will be made available.

The development of the content-centric Internet of Things (C2IoT) enriches the services provided by the IoT devices, which diversifies the provided contents. However, system resources are terribly wasted by repeated delivering the same content. Efficiently utilizing caching resources can reduce the link load caused by delivering and forwarding contents, further improving the users’ quality of experience (QoE). However, the collaboration among independent decision nodes is insufficient, which consumes substantial energy redundantly. To solve the mentioned issue, we propose a genetic-algorithm-based collaborative caching scheme integrating on-path strategy and off-path strategy, named cost-oriented caching scheme (CCS), to minimize the energy consumption of requesting contents. First, based on the analysis of content popularity, users’ historical requests, and transmission delay, an optimization problem is formulated to minimize the communication delay of obtaining content. Then, we formulate a submodular function optimization problem to optimize energy consumption, and an improved genetic algorithm is proposed to solve the mentioned problem. Performance evaluations demonstrate that the proposed CCS is superior to other existing caching schemes.

In the Internet of Vehicles (IoVs), task offloading is necessary to ensure the low-response delay due to the limitation of vehicular computational capacity. Task offloading involving social behavior can improve the utilization of computational resources in IoVs. To offload tasks effectively, the connected vehicles (CVs) need to upload context information, such as speed and location to road side unit (RSU) and base station (BS), which brings dramatic threat and risk for CVs’ privacy security. To solve the above-mentioned issue, we propose a privacy-preserving vehicular edge computing (PP-VEC) system architecture in this article. In the PP-VEC, the vehicular tasks can be offloaded to RSUs and adjacent CVs with adequate computing resources. Privacy mechanism disturbs the context information of CVs based on differential privacy technology before uploading it to the BS for offloading decisions to protect the CVs’ privacy. This article adopts the local differential privacy algorithm based on histogram algorithm and proposes a K-neighbor joint optimization of task offloading and resource allocation algorithm (K-NJTA) to optimize the global delay of task execution. We demonstrate the effectiveness of the proposed methods by simulation experiments. The results demonstrate K-NJTA on task execution delay and our local differential privacy algorithm can protect CVs’ privacy while has less effect on the task offloading algorithm due to the context information distribution.

Network virtualization techniques are promising to overcome the obstacle of applying and expanding costly traditional networks in the industrial Internet of things (IIoT). Artificial intelligence (AI)-enhanced distributed resource management in edge networks has aroused researchers’ widespread attention. However, dynamically arrived service requests and limited edge resources complicate the service scheduling issue. In this article, we establish a dynamic network virtualization technique enabled service function chain (SFC) orchestration framework in IIoT, formulate the joint optimization problem to maximize total utility and decompose it into two subproblems, i.e., SFC selection and dynamic SFC orchestration. A dynamic orchestration of SFC (DOS) scheme, consisting of resource-aware matching algorithm and averaged multistep double deep q-network algorithm, is designed to embed SFC requests distributedly on the optimal virtualized network function chains. At last, we validate the superiority of our proposed DOS scheme by experimental results.