The rapid advancement of artificial intelligence (AI) technologies has led to an increasing deployment of AI models on edge and terminal devices, driven by the proliferation of the Internet of Things (IoT) and the need for real-time data processing. This survey comprehensively explores the current state, technical challenges, and future trends of on-device AI models. We define on-device AI models as those designed to perform local data processing and inference, emphasizing their characteristics such as real-time performance, resource constraints, and enhanced data privacy. The survey is structured around key themes, including the fundamental concepts of AI models, application scenarios across various domains, and technical challenges faced in edge environments. We also discuss optimization and implementation strategies, such as data preprocessing, model compression, and hardware acceleration, which are essential for effective deployment. Furthermore, we examine the impact of emerging technologies, including edge computing and foundation models, on the evolution of on-device AI models. By providing a structured overview of the challenges, solutions, and future directions, this survey aims to facilitate further research and application of on-device AI, ultimately contributing to the advancement of intelligent systems in everyday life.

As one of the cyber–physical–social systems that plays a key role in people's daily activities, a smart city is producing a considerable amount of industrial data associated with transportation, healthcare, business, social activities, and so on. Effectively and efficiently fusing and mining such data from multiple sources can contribute much to the development and improvements of various smart city applications. However, the industrial data collected from the smart city are often sensitive and contain partial user privacy such as spatial–temporal context information. Therefore, it is becoming a necessity to secure user privacy hidden in the smart city data before these data are integrated together for further mining, analyses, and prediction. However, due to the inherent tradeoff between data privacy and data availability, it is often a challenging task to protect users’ context privacy while guaranteeing accurate data analysis and prediction results after data fusion. Considering this challenge, a novel privacy-aware data fusion and prediction approach for the smart city industrial environment is put forward in this article, which is based on the classic locality-sensitive hashing technique. At last, our proposal is evaluated by a set of experiments based on a real-world dataset. Experimental results show better prediction performances of our approach compared to other competitive ones.

The IoT-Cloud combines the Internet of Things (IoT) and cloud computing, which not only enhances the IoT’s capability but also expands the scope of its applications. However, it exhibits significant security and efficiency problems that must be solved. Internal attacks account for a large fraction of the associated security problems, however traditional security strategies are not capable of addressing these attacks effectively. Moreover, as repeated/similar service requirements become greater in number, the efficiency of IoT-Cloud services is seriously affected. In this paper, a novel architecture that integrates a trust evaluation mechanism and service template with a balance dynamics based on cloud and edge computing is proposed to overcome these problems. In this architecture, the edge network and the edge platform are designed in such a way as to reduce resource consumption and ensure the extensibility of trust evaluation mechanism, respectively. To improve the efficiency of IoT-Cloud services, the service parameter template is established in the cloud and the service parsing template is established in the edge platform. Moreover, the edge network can assist the edge platform in establishing service parsing templates based on the trust evaluation mechanism and meet special service requirements. The experimental results illustrate that this edge-based architecture can improve both the security and efficiency of IoT-Cloud systems.

With the advent of 5G, the Industrial Internet of Things (IIoT) has developed rapidly. The industrial Sensor-Cloud System (SCS) has also received widespread attention. In the future, a large number of integrated sensors that simultaneously collect multi-feature data will be added to industrial SCS. However, the collected big data is not trustworthy due to the harsh environment of the sensor. If the data collected at the bottom networks is directly uploaded to the cloud for processing, the query and data mining results will be inaccurate, which will seriously affect the judgment and feedback of the cloud. The traditional method of relying on sensor nodes for data cleaning is insufficient to deal with big data, while edge computing provides a good solution. In this paper, a new data cleaning method is proposed based on the mobile edge node during data collection. An angle-based outlier detection method is applied at the edge node to obtain the training data of the cleaning model, which is then established through support vector machine (SVM). Besides, online learning is adopted for model optimization. Experimental results show that multi-dimensional data cleaning based on mobile edge nodes improves the efficiency of data cleaning while maintaining data reliability and integrity, and greatly reduces the bandwidth and energy consumption of the industrial SCS.

Sensor-cloud originates from extensive recent applications of wireless sensor networks and cloud computing. To draw a roadmap of the current research activities of the sensor-cloud community, we first investigate the state-of-the-art sensor-cloud literature reviews published since the late 2010s and discovered that these surveys have primarily studied the sensor-cloud in specific aspects, security-enabled solutions, efficient management mechanisms, and architectural challenges. While the existing surveys have reviewed the sensor-cloud from various perspectives, they are inadequate for the three key issues that require urgent attention in the sensor-cloud: reliability , energy , and heterogeneity . To fill this gap, we perform a thorough survey by examining the origins of the sensor-cloud and providing an in-depth and comprehensive discussion of these three key challenges. We summarize initial designs of the new edge-based schemes to address these challenges and identify several open issues and promising future research directions.

Both academia and industry have directed tremendous interest toward the combination of Cyber Physical Systems and Cloud Computing, which enables a new breed of applications and services. However, due to the relative long distance between remote cloud and end nodes, Cloud Computing cannot provide effective and direct management for end nodes, which leads to security vulnerabilities. In this article, we first propose a novel trust evaluation mechanism using crowdsourcing and Intelligent Mobile Edge Computing. The mobile edge users with relatively strong computation and storage ability are exploited to provide direct management for end nodes. Through close access to end nodes, mobile edge users can obtain various information of the end nodes and determine whether the node is trustworthy. Then, two incentive mechanisms, i.e., Trustworthy Incentive and Quality-Aware Trustworthy Incentive Mechanisms, are proposed for motivating mobile edge users to conduct trust evaluation. The first one aims to motivate edge users to upload their real information about their capability and costs. The purpose of the second one is to motivate edge users to make trustworthy effort to conduct tasks and report results. Detailed theoretical analysis demonstrates the validity of Quality-Aware Trustworthy Incentive Mechanism from data trustfulness, effort trustfulness, and quality trustfulness, respectively. Extensive experiments are carried out to validate the proposed trust evaluation and incentive mechanisms. The results corroborate that the proposed mechanisms can efficiently stimulate mobile edge users to perform evaluation task and improve the accuracy of trust evaluation.