ABSTRACT Unlike traditional machine learning techniques, few‐shot learning (FSL) represents a paradigm aimed at acquiring new tasks from just a handful of labeled examples. The challenge in FSL lies in its requirement for models to generalize effectively from a small dataset to previously unseen examples. Various approaches have been developed for FSL, encompassing techniques such as metric learning, meta‐learning, and hybrid methods, among others. These approaches have found success in numerous computer vision tasks, including image and video classification, object detection, object segmentation, robotics, natural language processing, and various real‐world applications such as medical diagnosis and self‐driving cars. This comprehensive survey offers an in‐depth exploration of recent advancements and the current state‐of‐the‐art in FSL. The study presents a thorough examination of different FSL approaches, categorizing them primarily into meta‐learning and non‐meta‐learning methods. It also delves into benchmark datasets for FSL, highlights existing research challenges, and explores the diverse applications of FSL. Furthermore, the survey identifies and discusses open research challenges within the field of FSL.

Summary Smart devices are concerned about the processing and computation of tasks due to their tiny nature. They prefer to offload their tasks to the cloud for processing and computation. Due to the huge amount of data being generated by smart devices, the cloud becomes inefficient in terms of huge delay. Thus, Processing tasks in the cloud can add latency and finally needs to be addressed. Thus, fog computing is an alternative to the latency issue. The tasks are offloaded to fog instead of the cloud. In this paper, e‐TOALB (enhanced task offloading and load balancing), a modified and enhanced nature‐inspired and meta‐heuristic ant colony optimization is used to offload tasks in a fog environment. The results obtained by the proposed method are compared with Particle swarm optimization (PSO), round robin (RR), and ant colony optimization. The numerical results clearly show an improvement in average response time and load sharing among all fog nodes. The results of the proposed model produce low response time, low average service time, and low standard deviation. The proposed scheme aims to find the best possible decision for offloading tasks to nearby fog devices and to find an optimal route for offloading with the least communication cost and average service time.

Pervasive Computing has become more personal with the widespread adoption of the Internet of Things(IoT) in our day-to-day lives. The emerging domain that encompasses devices, sensors, storage, and computing of personal use and surroundings leads to Personal IoT(PIoT). PIoT offers users high levels of personalization, automation, and convenience. This proliferation of PIoT technology has extended into society, social engagement, and the interconnectivity of PIoT objects, resulting in the emergence of the Social Internet of Things (SIoT). The combination of PIoT and SIoT has spurred the need for autonomous learning, comprehension, and understanding of both the physical and social worlds. Current research on PIoT is dedicated to enabling seamless communication among devices, striking a balance between observation, sensing, and perceiving the extended physical and social environment, and facilitating information exchange. Furthermore, the virtualization of independent learning from the social environment has given rise to Artificial Social Intelligence (ASI) in PIoT systems. However, autonomous data communication between different nodes within a social setup presents various resource management challenges that require careful consideration. This paper provides a comprehensive review of the evolving domains of PIoT, SIoT, and ASI. Moreover, the paper offers insightful modeling and a case study exploring the role of PIoT in post-COVID scenarios. This study contributes to a deeper understanding of the intricacies of PIoT and its various dimensions, paving the way for further advancements in this transformative field.

Spider Monkey optimization (SMO) is a quite popular and recent swarm intelligence algorithm for numerical optimization. SMO is Fission-Fusion social structure based algorithm inspired by spider monkey’s behavior. The algorithm proves to be very efficient in solving various constrained and unconstrained optimization problems. This paper presents the application of SMO in fog computing. We propose a heuristic initialization based spider monkey optimization algorithm for resource allocation and scheduling in a fog computing network. The algorithm minimizes the total cost (service time and monetary cost) of tasks by choosing the optimal fog nodes. LJFP (longest job fastest processor), SJFP (shortest job fastest processor), and MCT (minimum completion time) based initialization of SMO are proposed and compared with each other. The performance is compared based on the parameters of average cost, average service time, average monetary cost, and the average cost per schedule. The results demonstrate the efficacy of MCT-SMO as compared to other heuristic initialization based SMO algorithms and PSO (Particle Swarm Optimization).

There is an exponential increase in the number of smart devices, generating helpful information and posing a serious challenge while processing this huge data. The processing is either done at fog level or cloud level depending on the size and nature of the task. Offloading data to fog or cloud adds latency, which is less in fog and more in the cloud. The methods of processing data and tasks at fog level or cloud are mostly machine learning based. In this paper, we will discuss all three levels in terms of architecture, starting from the internet of things to fog and fog to cloud. Specifically, we will describe machine learning-based offloading from the internet of things to fog and fog to cloud. Finally, we will come up with current research directions, issues, and challenges in the IoT–fog–cloud environment.