The sixth generation (6G) wireless communication networks are envisioned to revolutionize customer services and applications via the Internet of Things (IoT) towards a future of fully intelligent and autonomous systems. In this article, we explore the emerging opportunities brought by 6G technologies in IoT networks and applications, by conducting a holistic survey on the convergence of 6G and IoT. We first shed light on some of the most fundamental 6G technologies that are expected to empower future IoT networks, including edge intelligence, reconfigurable intelligent surfaces, space-air-ground-underwater communications, Terahertz communications, massive ultra-reliable and low-latency communications, and blockchain. Particularly, compared to the other related survey papers, we provide an in-depth discussion of the roles of 6G in a wide range of prospective IoT applications via five key domains, namely Healthcare Internet of Things, Vehicular Internet of Things and Autonomous Driving, Unmanned Aerial Vehicles, Satellite Internet of Things, and Industrial Internet of Things. Finally, we highlight interesting research challenges and point out potential directions to spur further research in this promising area.

6G Internet of Things: A Comprehensive Survey

The sixth-generation (6G) wireless communication networks are envisioned to revolutionize customer services and applications via the Internet of Things (IoT) toward a future of fully intelligent and autonomous systems. In this article, we explore the emerging opportunities brought by 6G technologies in IoT networks and applications, by conducting a holistic survey on the convergence of 6G and IoT. We first shed light on some of the most fundamental 6G technologies that are expected to empower future IoT networks, including edge intelligence, reconfigurable intelligent surfaces, space–air–ground–underwater communications, Terahertz communications, massive ultrareliable and low-latency communications, and blockchain. Particularly, compared to the other related survey papers, we provide an in-depth discussion of the roles of 6G in a wide range of prospective IoT applications via five key domains, namely, healthcare IoTs, Vehicular IoTs and Autonomous Driving, Unmanned Aerial Vehicles, Satellite IoTs, and Industrial IoTs. Finally, we highlight interesting research challenges and point out potential directions to spur further research in this promising area. 

/pdf/6g-internet-of-things-a-comprehensive-survey-1ryvmcag.pdf

Image fusion meets deep learning: A survey and perspective

In recent years, the internet of things (IoT) has been progressing rapidly with the integration of technologies in various fields. At this stage, triboelectric nanogenerator (TENG) technology based on the...

Human body IoT systems based on triboelectrification effect: energy harvesting, sensing, interfacing and communication

With the in-depth application of the Internet of Things, many emerging technologies are changing the global industry landscape on an unprecedented scale. At the same time, they also provide an opportunity for the development of intelligent management to break through the bottleneck. The proposal and evolution of the concept of intelligent management makes the development of management technology more advanced. Therefore, the introduction of the Internet of Things technology into intelligent management has very important research significance and value. First, conduct research on the origin and current situation of the Internet of Things technology at home and abroad and understand the relevant theories and cutting-edge technologies of the Internet of Things technology. Second, take the enterprise as an example to study the process flow and existing problems in the logistics link in the factory, combine the management concept of the Internet of Things, and integrate IC card identification technology, RFID radio frequency identification technology, barriers and ground sensing technology, and OPC/PLC. Third, combined with PLC/OPC technology, the design and integration of the software system and hardware system are realized. The experimental results show that the system modules have been tested to provide company information management, employee multifactor predictive analysis, and efficient batch efficiency evaluation, which has a certain value for company data management and data analysis and mining, and improve company efficiency by more than 30%.

/pdf/application-and-research-of-the-intelligent-management-3iboacgt0i.pdf

Application and Research of the Intelligent Management System Based on Internet of Things Technology in the Era of Big Data

Deep learning technology has been extensively explored in pattern recognition and image processing areas. A multi-mode medical image fusion with deep learning will be proposed, according to the characters of multi-modal medical image, medical diagnostic technology and practical implementation, according to the practical needs for medical diagnosis. It cannot be only made up for the deficiencies of MRI, CT and SPECT image fusion, but also can be implemented in different types of multi-modal medical image fusion problems in batch processing mode, and can be effectively overcome the limitation of only one-page processing. The proposed method can greatly improve the fusion effect, image detail clarity and time efficiency. The experiments on multi-modal medical images are implemented to analyze performance, algorithm stability and so on. The experimental results prove the superiority of our proposed method in terms of visual quality and a variety of quantitative evaluation criteria.

Medical image fusion method by deep learning

The purposes are to enable large-scale Internet of Things (IoT) devices to analyze data more effectively and provide high-efficiency, low-energy, and wide-coverage technical services for terminals The channel model and energy loss model analyze the devices’ access performance, data transmission path delay, energy consumption in the IoT, and large-scale devices’ access in the cellular narrowband IoT (NB-IoT) based on big data analysis technology are also discussed The results show that in the access success rate analysis, the access success rate is the highest with an access time ( ${T}$ ) of 5 s and a preamble resource number ( ${K}$ ) of 25 The restriction factor is inversely proportional to the access success rate In the node utilization analysis, different transmission node priorities result in different node utilization, and priority 2’s node utilization is better than that of priority 1 Moreover, local data makes data analysis and transmission faster The search time is prolonged, and the corresponding energy consumption is also higher without local data In the energy consumption analysis, with the 6-generation (6G) technology, different interference thresholds lead to the different energy efficiency of data transmission The larger the interference threshold, the higher the energy efficiency Therefore, the 6G-based big data analysis technology can significantly improve large-scale IoT devices’ access success rate and enable the system to meet the requirements of low energy consumption and high access success rate, significant for research on more devices’ access data analysis

Big Data Analytics for 6G-Enabled Massive Internet of Things

In order to explore the application value of deep learning denoising autoencoder (DAE) in Internet-of-Things (IoT) fusion security, in this study, a hierarchical intrusion security detection model stacked DAE supporting vector machine (SDAE-SVM) is constructed based on the three-layer neural network of self-encoder. The sample data after dimension reduction are obtained by layer by layer pretraining and fine-tuning. The traditional deep learning algorithms [stacked noise autoencoder (SNAE), stacked autoencoder (SAE), stacked contractive autoencoder (SCAE), stacked sparse autoencoder (SSAE), deep belief network (DBN)] are introduced to carry out the comparative simulation with the model in this study. The results show that when the encoder in the model is a 4-layer network structure, the accuracy rate (Ac) of the model is the highest (97.83%), the false-negative rate (Fn) (1.27%) and the false-positive rate (Fp) (3.21%) are the lowest. When the number of nodes in the first hidden layer is about 110, the model accuracy is about 98%. When comparing the model designed in this study with the common feature dimension reduction methods, the Ac, Fn, and Fp of this model are the best, which are 98.12%, 3.21%, and 1.27%, respectively. When compared with other deep learning algorithms of the same type, the recognition rate, Ac, error rate, and rejection rate show good results. In multiple data sets, the recognition rate, Ac, error rate, and rejection rate of the model in this study are always better than the traditional deep learning algorithms. In conclusion, when deep learning SDAE is applied to IoT convergence-based intrusion security detection, the detection load can be reduced, the detection effect can be improved, and the operation is more secure and stable.

Deep-Learning-Enabled Security Issues in the Internet of Things

With increasingly complex network structure, requirements for heterogeneous 5G are also growing. The aim of this study is to meet the network security performance under the existing high-capacity and highly reliable transmission. In this context, deep learning technology is adopted to solve the security problem of the 5G heterogeneous network. First, the security problems existing in 5G heterogeneous networks are presented, mainly from two aspects of the physical layer security problems and application prospects of deep learning in communication technology. Then the combination of deep learning and 5G heterogeneous networks is analyzed. The combination of deep learning technology, modulation information recognition, and beam formation is introduced. The application of deep learning in communications technology is analyzed, and the modulation information recognition and beamforming based on deep learning are introduced. Finally, the challenges of solving security problems in 5G heterogeneous networks by deep learning are explored. The results show that the deep learning model can solve the modulation recognition problem well, and the modulation mode of the convolutional neural network can well identify the modulation signals involved in the experiment. Therefore, deep learning has a good advantage in solving modulation recognition. In addition, compared to the traditional algorithm, the unsupervised beamforming algorithm based on deep learning proposed in this research can effectively reduce the computational complexity under different numbers of transmitting antennas, which verifies the superiority of the unsupervised beamforming algorithm based on deep learning proposed in this research. Therefore, the present work provides a good idea for solving the security problem of 5G heterogeneous networks.

Deep Learning for Security Problems in 5G Heterogeneous Networks

3D face similarity is a critical issue in computer vision, computer graphics and face recognition and so on. Since Frechet distance is an effective metric for measuring curve similarity, a novel 3D face similarity measure method based on Frechet distances of geodesics is proposed in this paper. In our method, the surface similarity between two 3D faces is measured by the similarity between two sets of 3D curves on them. Due to the intrinsic property of geodesics, we select geodesics as the comparison curves. Firstly, the geodesics on each 3D facial model emanating from the nose tip point are extracted in the same initial direction with equal angular increment. Secondly, the Frechet distances between the two sets of geodesics on the two compared facial models are computed. At last, the similarity between the two facial models is computed based on the Frechet distances of the geodesics obtained in the second step. We verify our method both theoretically and practically. In theory, we prove that the similarity of our method satisfies three properties: reflexivity, symmetry, and triangle inequality. And in practice, experiments are conducted on the open 3D face database GavaDB, Texas 3D Face Recognition database, and our 3D face database. After the comparison with iso-geodesic and Hausdorff distance method, the results illustrate that our method has good discrimination ability and can not only identify the facial models of the same person, but also distinguish the facial models of any two different persons.

Jinhua Li

Papers

Medical image fusion method by deep learning

Big Data Analytics for 6G-Enabled Massive Internet of Things

Deep-Learning-Enabled Security Issues in the Internet of Things

Deep Learning for Security Problems in 5G Heterogeneous Networks

3D Face Similarity Measure by Fréchet Distances of Geodesics