The fusion of edge computing and artificial intelligence (AI) technology is a key enabler for the smart Internet of Things (IoT). However, these two emerging paradigms face many issues for their integration, such as data storage structure, model generation algorithms and cloud-edge collaboration mechanisms. Moreover, edge computing is not ready for supporting AI and can be enabled to support AI via some basic network functions related to quality of experience (QoE), such as passive computation offloading and content caching. In this paper, we present an intelligent cooperative edge (ICE) computing in IoT networks to achieve a complementary integration of AI and edge computing. The AI-related modules of edge computing are redesigned for distributing AI’s core functions from the cloud to the edge. IoT-generated data are differentiated as user-private data preserved locally in IoT devices, edge-private data isolated on the edge and public data uploaded to the cloud. Therefore, a cloud-scale machine learning model can be generated, followed by privacy-preserving transfer learning running on each edge, which also has data updated more frequently that enables the model’s incremental learning. The model distribution is accomplished through lightweight deployment pipelines consisting of cloud compression and edge reconstruction. Conversely, some key issues of edge computing, such as the computation offloading and content caching, achieve a better solution using the localized AI. We perform prototype-based evaluation, which indicate that the ICE computing architecture enables a benign combination of AI and edge computing.

Smart city (SC) technologies can provide appropriate services according to citizens’ demands. One of the key enablers in a SC is the Internet of Things (IoT) technology, which enables a massive number of devices to connect with each other. However, these devices usually come from different manufacturers with different product standards, which confront interactive control problems. Moreover, these devices will produce large amounts of data, and efficiently analyzing these data for intelligent services. In this paper, we propose a novel artificial intelligence-based semantic IoT (AI-SIoT) hybrid service architecture to integrate heterogeneous IoT devices to support intelligent services. In particular, the proposed architecture is empowered by semantic and AI technologies, which enable flexible connections among heterogeneous devices. The AI technology can support very implement efficient data analysis and make accurate decisions on service provisions in various kinds. Furthermore, we also present several practical use cases of the proposed AI-SIoT architecture and the opportunities and challenges to implement the proposed AI-SIoT for future SCs are also discussed.

In this paper, a scheme to detect both clone and Sybil attacks by using channel-based machine learning is proposed. To identify malicious attacks, channel responses between sensor peers have been explored as a form of fingerprints with spatial and temporal uniqueness. Moreover, the machine learning based method is applied to provide a more accurate authentication rate. Specifically, by combining with edge devices, we apply a threshold detection method based on channel differences to provide offline training sample sets with labels for the machine learning algorithm, which avoids manually generating labels. Therefore, our proposed scheme is lightweight for resource constrained industrial wireless devices, since only an online-decision making is required. Extensive simulations and experiments were conducted in real industrial environments. Both results show that the authentication accuracy rate of our strategy with an appropriate threshold can achieve 84% without manual labeling.

Insufficient system bandwidth and chromatic dispersion (CD) of fiber are major limitations for high-speed four-level pulse amplitude modulation (PAM4) direct detection systems. In this paper, we investigate C-band 112-Gb/s PAM4 optical transport systems over 10-km and 20-km standard single-mode fiber (SSMF) transmission, which suffers from both bandwidth limitation and CD-induced power fading. Advanced digital signal processing techniques are proposed to handle those channel distortions. At the transmitter, a low-complexity 1 + αZ $^-1$ finite impulse response (FIR) filter coarsely pre-compensates system bandwidth without a preliminary channel estimation. At the receiver, a modified feed-forward equalizer and decision feedback equalizer (FFE-DFE) is employed to compensate residual insufficient bandwidth and CD-induced power fading. Moreover, a novel multi-symbols joint decision is proposed for receiver-side FFE-DFE to mitigate symbol error propagation and correct possible previous error symbols. Experimental results show that the proposed pre-equalization technique exhibits a better transmission performance, which reduces bit error ratio (BER) from 3.3e-3 to 5.5e-4 for optical back to back transmission. As for 10-km transmission case, FFE-DFE with 5-symbols joint decision achieves a BER of 7.3e-5, which is better than the BER of 1.6e-4 with ideal error propagation-free FFE-DFE (EPF-FFE-DFE). Furthermore, for 20-km transmission scenario, FFE-DFE with 8-symbols joint decision achieves a BER of 6e-4, which is also a superior result than the BER of 9.1e-4 with EPF-FFE-DFE.

Sharded blockchain offers scalability, decentralization, immutability, and linear improvement, making it a promising solution for addressing the trust problem in large-scale collaborative IoT. However, a high proportion of cross-shard transactions (CSTs) can severely limit the performance of decentralized blockchain. Furthermore, the dynamic assemblage characteristic of collaborative sensing in sharded blockchain is often ignored. To overcome these limitations, we propose HMMDShard, a dynamic blockchain sharding scheme based on the hidden Markov model (HMM). HMMDShard leverages fine-grained blockchain sharding and fully embraces the dynamic assemblage characteristic of IoT collaborative sensing. By integrating the HMM, we achieve adaptive dynamic incremental updating of blockchain shards, effectively reducing CSTs across all shards. We conduct a comprehensive analysis of the security issues and properties of HMMDShard, and evaluate its performance through the implementation of a system prototype. The results demonstrate that HMMDShard significantly reduces the proportion of CSTs and outperforms other baselines in terms of system throughput and transaction confirmation latency.

With the advent of the Internet of Things (IoT), crowdsensing, as a new emerging application of the IoT that employs ubiquitous mobile users with smartphones for data collection and processing, has further deepened our knowledge. However, the problems of the current crowdsensing systems regarding system security, user privacy, and user payment (UP) raise serious privacy and security concerns, which affect participants’ adoption of the system. The Blockchain technology allows for nondeterministic multiple parties to interact with each other anonymously in a network that is not fully trusted. In this article, we propose a new decentralized crowdsensing system, called CrowdHB . Unlike other blockchain-based crowdsensing systems, CrowdHB adopts a hybrid blockchain architecture and uses smart contracts to achieve location privacy preservation and ensure data quality while improving the system performance. Furthermore, to optimize task assignments to mobile users, we propose a location privacy-preserving optimization mechanism (LPPOM) and the approach of consistency optimization (ACO) to achieve a tradeoff between user privacy and system performance. The extensive experimental results show that the proposed CrowdHB outperforms the other crowdsensing systems in terms of task success rate and performance for a large number of mobile users and tasks.