Intelligent Internet Of Things Research Articles

RFID tag-based mutual authentication protocol with improved security for TMIS

With the progressive and continuous development in micro-electro-mechanical technologies, intelligent internet of things (IoT), and the propagation of 5G communication technology, the security of resource-controlled IoT appliances like RFID-based TMIS applications has received predominant attention. Typically, wireless communication channel is utilised among tag, reader and back-end server, which is easily vulnerable to various intimidations such as spoofing, DoS, replay, and de-synchronisation. Therefore, the privacy and integrity of the communicated information cannot be guaranteed. Researchers proposed various symmetric and asymmetric encryptions, hash functions, key management, CRC, and ECC-based techniques for solving privacy and integrity issues of RFID authentication for TMIS systems. In the related work, we discussed up-to-date RFID-based authentication for TMIS systems. However, most do not solve formal, informal attacks; moreover, they suffer from communication and computational complexities. Thus, this manuscript describes an enhanced mutual authentication practice for RFID components with hash and random functions. We further demonstrate that the proposed scheme offers all the desired security requirements by verifying AVISPA, Scyther, and GNY logic.

Context-Aware Service Model of a Mobile Library Based on Internet of Things

Appropriate technology needs to be applied in libraries to provide users with more humanized, intelligent, and convenient services to improve service quality. Using theories from library science, management, and modeling, this paper examines library personalized service in the intelligent Internet of Things (IoT) environment using a literature review, comparative analysis, and UML modeling to analyze the influencing factors of mobile library users’ acceptance of personalized recommendation services. Based on the situational awareness framework, the experimental results of the effect of these personalized service recommendations show that the load factor is greater than 0.6, which indicates that the dimensions of a scalar can explain situational awareness. The P-value > 0.01 shows that the mobile library is linear and related to the user, mobile, resource, and service scenarios. Overall, based on this investigation and analysis, countermeasures, and suggestions, a personalized service system framework may be suitable for mobile libraries in the IoT environment.

6G Driven Fast Computational Networking Framework for Healthcare Applications

New Sixth-generation (6G) networks rely heavily on the Intelligence Internet of Things (IIoT) to store and process data more efficiently. 6G is desired to offer ultra-low latency, high bandwidth, and improvised quality of service that can effectively handle the communication among the nodes. All the healthcare facilities must be outfitted with cutting-edge technology to assist the individual with intelligent diagnosis, patient-centric treatment, and a range of other healthcare services both in the hospital and remotely. To make the system ready and adaptable to the technology and provide services to divergent applications ranging from robotic surgeries to remote monitoring of the patients through wearable technologies in an Ambient Assistive Living (AAL) environment over the intelligent networking platform. Various networking nodes and terminal devices provide the services for applications in the healthcare domain, which needs a backbone framework to deliberate the time-intensive services. This paper proposes a reference layered communication framework for the nodes and devices in real-time communication. The feature perspective aspects of 6G technology present the futuristic healthcare application for effective treatment and smart integration of services.

Communication Security Analysis of Intelligent Transportation System Using 5G Internet of Things From the Perspective of Big Data

The transportation system has entered the era of 5G intelligent Internet of things (IoT), which can realize the comprehensive monitoring, perception, and intelligent decision-making of people, vehicles, roads, and the environment. The purpose is to solve the problems in the communication security of intelligent transportation system (ITS) and improve the vulnerability of traditional distributed architecture. The security issues of the Internet of vehicles (IoV) in 5G environment are analyzed from the perspective of big data. An access control mechanism based on risk prediction is proposed aiming at the problems existing in the node access control process. A Wasserstein Distance-based Combined Generative Adversarial Network (WCGAN) is proposed. It modifies the loss function to solve the gradient disappearance problem, and a combination of multiple generators is designed to solve the pattern collapse. The simulation experiment is carried out on the dataset of the intrusion detection evaluation project. The WCGAN model has the smallest prediction error than the other models regarding the node packet transmission rate. Its loss value is close to 0 after 10 iterations, while the loss value of the BP neural network (BPNN) is about 0.28. The prediction accuracy of the WCGAN model can reach 86.3% when the training set is 5000, which is much higher than that of BPNN (77.8%). The reason is that the WCGAN model increases the number of generators according to GAN, which improves the low accuracy caused by pattern collapse. The IoT-based ITS can implement corresponding strategies according to the prediction results and control the access rights of nodes, thus ensuring the security of information resources effectively. The research content reduces the communication delay under ensuring the integrity and confidentiality of information in the process of data transmission, and provides a reference for ensuring the safe communication of IoV.

The use of deep learning and AIoT technology in loan word translation

The purpose is to translate loan words accurately, standardise their use, and better integrate with Chinese culture. The role of intelligent translation in loan words translation is studied based on deep learning and intelligent Internet of things. Moreover, a new neural translation mechanism of divide and conquer strategy is proposed based on the original Artificial Intelligence (AI) translation technology. Its translation quality is tested and compared with manual translation. The new neural translation mechanism can achieve the accuracy of human daily language. The accuracy rate of system Mobile Number Portability (MNP) identification is 74.67%, the recall rate is 71.42% and the F-value is 74.01%. Moreover, the average time is 0.01s/character. Therefore, the research results suggest that the constructed AI translation can more efficiently complete the translation task, save a lot of time cost and labour cost and produce a crucial reference for the intelligent development of the translation industry.

Firefly Optimization‐Based Cooperative Localization Algorithm for Intelligent IoT

To achieve effective connection between each node of the Internet of Things (IoT), there is a great demand of precise positioning. The traditional firefly localization algorithm only considers part of the ranging information, and the positioning effect is not good. Therefore, an improved algorithm is proposed to take advantage of the ranging information between unknown nodes to achieve cooperative location. First, all ranging information is considered to construct a new objective function. The firefly optimization approach is then utilized to discover the best solution based on the new goal function. The starting location created by the random technique has a significant impact on the new algorithm’s localization performance, thus the traditional firefly localization method’s initial position is employed to increase cooperative localization performance. The simulation results demonstrate that the novel approach outperforms the classic firefly technique in terms of placement accuracy.

A Distributed SDN Controller for Distributed IoT

Over the past decade, the Internet of Things (IoT) has undergone a paradigm shift away from centralized cloud computing towards edge computing. Hundreds of billions of things are estimated to be deployed in the rapidly advancing IoT paradigm, resulting in enormous amounts of data. Transmitting all these data to the cloud has recently proven to be a performance bottleneck, as it causes many network issues relating to latency, power consumption, security, privacy, etc. However, existing paradigms do not use edge devices for decision making. The use of distributed intelligence could strengthen the IoT in several ways by distributing decision-making tasks to edge devices within the network, rather than sending all data to a central server. In this approach, all computational tasks and data are shared among edge devices. To achieve efficient distribution of IoT intelligence and utilization of network resources, it is necessary to integrate the transport network control with distributed edge and cloud resources to provide dynamic and efficient IoT services. This challenge can be overcome by equipping an edge IoT gateway with the intelligence required to extract information from raw data and to decide whether to actuate itself or to outsource complex tasks to the cloud. Distributed intelligence refers to a collaboration between the cloud and the edge. In this context, we first introduce a distributed SDN-based architecture for IoT that enables IoT gateways to perform IoT processing dynamically at the edge of the network, based on the current state of network resources. Next, we propose an algorithm for selecting clients for the training process of Federated Learning Applications, based on the context information of the network. In the last step, we deploy Federated Learning Applications in our distributed SDN-based architecture, using the gateways to provide distributed intelligence at the edge of the network, and conduct a comprehensive and detailed evaluation of the system from several perspectives.

An Intelligent IoT Sensing System for Rail Vehicle Running States Based on TinyML

Real-time identification of the running state is one of the key technologies for a smart rail vehicle. However, it is a challenge to accurately real-time sense the complex running states of the rail vehicle on an Internet-of-Things (IoT) edge device. Traditional systems usually upload a large amount of real-time data from the vehicle to the cloud for identification, which is laborious and inefficient. In this paper, an intelligent identification method for rail vehicle running state is proposed based on Tiny Machine Learning (TinyML) technology, and an IoT system is developed with small size and low energy consumption. The system uses a Micro-Electro-Mechanical System (MEMS) sensor to collect acceleration data for machine learning training. A neural network model for recognizing the running state of rail vehicles is built and trained by defining a machine learning running state classification model. The trained recognition model is deployed to the IoT edge device at the vehicle side, and an offset time window method is utilized for real-time state sensing. In addition, the sensing results are uploaded to the IoT server for visualization. The experiments on the subway vehicle showed that the system could identify six complex running states in real-time with over 99% accuracy using only one IoT microcontroller. The model with three axes converges faster than the model with one. The model recognition accuracy remained above 98% and 95%, under different installation positions on the rail vehicle and the zero-drift phenomenon of the MEMS acceleration sensor, respectively. The presented method and system can also be extended to edge-aware applications of equipment such as automobiles and ships.

A Lossless Data-Hiding based IoT Data Authenticity Model in Edge-AI for Connected Living

Edge computing is an emerging technology for the acquisition of Internet-of-Things (IoT) data and provisioning different services in connected living. Artificial Intelligence (AI) powered edge devices (edge-AI) facilitate intelligent IoT data acquisition and services through data analytics. However, data in edge networks are prone to several security threats such as external and internal attacks and transmission errors. Attackers can inject false data during data acquisition or modify stored data in the edge data storage to hamper data analytics. Therefore, an edge-AI device must verify the authenticity of IoT data before using them in data analytics. This article presents an IoT data authenticity model in edge-AI for a connected living using data hiding techniques. Our proposed data authenticity model securely hides the data source’s identification number within IoT data before sending it to edge devices. Edge-AI devices extract hidden information for verifying data authenticity. Existing data hiding approaches for biosignal cannot reconstruct original IoT data after extracting the hidden message from it (i.e., lossy) and are not usable for IoT data authenticity. We propose the first lossless IoT data hiding technique in this article based on error-correcting codes (ECCs). We conduct several experiments to demonstrate the performance of our proposed method. Experimental results establish the lossless property of the proposed approach while maintaining other data hiding properties.

The Challenges and Emerging Technologies for Low-Power Artificial Intelligence IoT Systems

The Internet of Things (IoT) is an interface with the physical world that usually operates in random-sparse-event (RSE) scenarios. This article discusses main challenges of IoT chips: power consumption, power supply, artificial intelligence (AI), small-signal acquisition, and evaluation criteria. To overcome these challenges, many works recently aimed at IoT system design have emerged. This work reviews the architecture and circuit innovations that have contributed to IoT developments. This paper does not cover security of IoT. Event-driven architectures and nonuniform sampling ADCs significantly reduce the long-term average power. Besides, embedding AI engines in IoT nodes (AIoT) is one critical trend. The computing-in-memory technique improves the energy efficiency of the AI engine. Asynchronous spike neural networks (ASNNs) AI engines show low power potential. In addition to data processing, small-signal acquisition is also critical. The charge-domain analog-front-end (AFE) techniques such as floating inverter-based amplifiers improve energy efficiency. In addition to the above low power and high energy efficiency technologies, energy harvesting can also enhance the lifetime of AIoT devices. This article discusses recent ambient RF and natural energy harvesting approaches and high-efficiency DC-DC with a wide load range. Finally, novel evaluation criteria are introduced to establish benchmark standards for AIoT chips.

Application of Mobile APP in Moral Education Course Teaching Based on Intelligent Internet of Things

Moral education is one of the important teaching goals of modern education. It is not a clear, specific, and microexamination teaching like knowledge and science but a political, ideological, and moral education in the form of curriculum teaching. In the information age, the Internet is filled with a huge amount of good and bad information. Facing the temptation and impact of bad information, moral education is very important. The main purpose of this research is to understand the current status of moral education curriculum teaching in China and propose a method of applying mobile APP to assist moral education curriculum teaching in accordance with the development difficulties faced by moral education curriculum teaching in the Internet era. This article uses the methods of literature research and questionnaire survey, by consulting the relevant literature and interviewing randomly selected teachers and students of moral education courses in secondary vocational colleges, from the basic conditions of students’ academic qualifications and age, moral education course learning situation, and moral education course teaching arrangements and conducts questionnaire surveys on mobile APP teaching applications. Finally, this article also uses statistical methods to analyze the difficulties and impacts of moral education curriculum teaching and tests the effectiveness of the application of mobile APP teaching methods in moral education teaching through the independent sample t-test method. Research shows that at the level of significance of α = 0.05 , the application of mobile APP does help to improve the learning efficiency and enthusiasm of students in the teaching of moral education courses and improve the teaching level of moral education courses.

Detecting security attacks in cyber-physical systems: a comparison of Mule and WSO2 intelligent IoT architectures.

The Internet of Things (IoT) paradigm keeps growing, and many different IoT devices, such as smartphones and smart appliances, are extensively used in smart industries and smart cities. The benefits of this paradigm are obvious, but these IoT environments have brought with them new challenges, such as detecting and combating cybersecurity attacks against cyber-physical systems. This paper addresses the real-time detection of security attacks in these IoT systems through the combined used of Machine Learning (ML) techniques and Complex Event Processing (CEP). In this regard, in the past we proposed an intelligent architecture that integrates ML with CEP, and which permits the definition of event patterns for the real-time detection of not only specific IoT security attacks, but also novel attacks that have not previously been defined. Our current concern, and the main objective of this paper, is to ensure that the architecture is not necessarily linked to specific vendor technologies and that it can be implemented with other vendor technologies while maintaining its correct functionality. We also set out to evaluate and compare the performance and benefits of alternative implementations. This is why the proposed architecture has been implemented by using technologies from different vendors: firstly, the Mule Enterprise Service Bus (ESB) together with the Esper CEP engine; and secondly, the WSO2 ESB with the Siddhi CEP engine. Both implementations have been tested in terms of performance and stress, and they are compared and discussed in this paper. The results obtained demonstrate that both implementations are suitable and effective, but also that there are notable differences between them: the Mule-based architecture is faster when the architecture makes use of two message broker topics and compares different types of events, while the WSO2-based one is faster when there is a single topic and one event type, and the system has a heavy workload.

Intelligent Application of Artificial Intelligence Internet of Things Technology in the Economic and Legal Fields

In today’s globalized situation, people on the one hand enjoy the great convenience brought by the Internet and artificial intelligence Internet of Things (IoT) technology, and, on the other hand, they are also inevitably subject to a series of harms brought by network technology. Internet economic crime is a new type of crime based on Internet technology. Criminals use Internet technology to conduct illegal visits and Trojan horse program attacks, steal user information, and defraud victims of money. This has resulted in the people’s personal and property safety and social harmony and stability. Strictly cracking down on cyber economic crimes in accordance with the law is of great significance to safeguarding the interests of the people and maintaining social stability. However, as the methods and forms of cyber economic crimes emerge endlessly, it is very important to collect intelligence information on such crimes. This paper proposes using the sensor technology, embedded system technology, radio frequency automatic identification technology, and cloud computing technology in artificial intelligence Internet of Things technology to design and build a data-mining-based network economic crime intelligent information aggregation collection system to realize network economic crime intelligence of aggregation and analyze and help combat cyber economic crimes. This article takes cyber economic crime cases in various cities in our province as an example, selects 9 cyber economic criminals’ intelligence information as sample data, and tests and applies the designed cyber economic crime intelligence information system. The final results show that the numbers of cyber economic crime cases in four cities A, B, C, and D in four provinces are roughly the same, but city A has the largest number; the minimum confidence of the 9 criminals is above 0.60, indicating that the economic crimes of cyber economic criminals are related to their academic background and family status and criminal history are related to a certain extent; illegal fund-raising fraud and online credit card fraud account for the largest proportion of the four cities and are currently the main forms of online economic crime.

A 148-nW Reconfigurable Event-Driven Intelligent Wake-Up System for AIoT Nodes Using an Asynchronous Pulse-Based Feature Extractor and a Convolutional Neural Network

This article presents a 148-nW always-on wake-up system that drastically reduces the system power consumption of Internet of Things (IoT) sensor nodes while oftentimes operating in random-sparse-event (RSE) scenarios. To significantly reduce the long-term average (LTA) power consumption and realize multiapplication and intelligent event detection, three techniques are proposed: 1) In a three-stage pipelined event-driven architecture, a frame generator and a convolutional neural network intelligent inference engine (CNN IIE) in stage III are event-driven by the preliminary detectors in stage II, and the detectors are triggered by a level-crossing (LC) analog-to-digital converter (ADC), i.e., stage I, dramatically reducing the overall power consumption. 2) The clock-free pulse-based instant rate of change (IROC) feature extractor directly processes the asynchronous pulses of the LC-ADC outputs in the temporal domain instead of utilizing a conventional power-hungry frequency-domain method. 3) A reconfigurable IROC, the frame generator, and the CNN IIE provide adaptive intelligence for various IoT events, enhancing the accuracy of multipurpose detection with ultralow power. We demonstrate two artificial intelligence IoT (AIoT) applications at 0.6-V V_DD. For electrocardiogram (ECG) recognition, one example works at a typical event rate (ER) of &#x007E;4800/h, with an active power of 1.68 <inline-formula> <tex-math notation="LaTeX">$\mu \text{W}$ </tex-math></inline-formula> and a precision of up to 99&#x0025;; the other is used for keyword spotting (KWS), where the chip achieves 378 nW at &#x007E;720/h ER and 94&#x0025; accuracy. The LTA power is bounded to 148 nW, while the event-driven chip is on call and waiting for events; this chip dominates the AIoT device battery life in RSE scenarios.

Design Guidelines for Cooperative UAV-supported Services and Applications

Internet of Things (IoT) systems have advanced greatly in the past few years, especially with the support of Machine Learning (ML) and Artificial Intelligence (AI) solutions. Numerous AI-supported IoT devices are playing a significant role in providing complex and user-specific smart city services. Given the multitude of heterogeneous wireless networks, the plethora of computer and storage architectures and paradigms, and the abundance of mobile and vehicular IoT devices, true smart city experiences are only attainable through a cooperative intelligent and secure IoT framework. This article provides an extensive study on different cooperative systems and envisions a cooperative solution that supports the integration and collaboration among both centralized and distributed systems, in which intelligent AI-supported IoT devices such as smart UAVs provide support in the data collection, processing and service provisioning process. Moreover, secure and collaborative decentralized solutions such as Blockchain are considered in the service provisioning process to enable enhanced privacy and authentication features for IoT applications. As such, user-specific complex services and applications within smart city environments will be delivered and made available in a timely, secure, and efficient manner.

A Review of Embedding Artificial Intelligence in Internet of Things and Building Information Modelling for Healthcare Facility Maintenance Management

Latest innovations in Internet of Things (IoT) technologies as well as the new paradigms in Artificial Intelligence systems are opening up opportunities to create smart computing infrastructures for the Healthcare Facility Management. However, the current scenario of hospital buildings maintenance management is strongly characterized by slow, redundant, and not integrated processes, which lead to loss of money, resources, and time. On the other hand, lack of data and information in as-built digital models considerably limits the potential of Building Information Modelling in Facility Maintenance Management. Consequently, optimization of data collection process and management is required. In this light, this paper presents a review of embedding AI (Artificial Intelligence) in BIM-IoT integration for the process of healthcare Facility Maintenance Management (FMM) in order to conquer the current challenges. The first challenge in front of integrating IoT&amp;ndash; BIM, is the lack of information; the second challenge is BIM&amp;rsquo;s sematic information that has not been able to display indoor conditions&amp;rsquo; elements which should be reconsidered; and the third challenge is the data size which is stored in systems as well as the eligibility of individuals to apply the related data. Additionally, some emerging trends in IoT are reviewed such as the combination of Machine Learning and Artificial Intelligence in order to exploit their advantages and complement their limitations, which enable new promising IoT applications.

Automotive Intelligence Embedded in Electric Connected Autonomous and Shared Vehicles Technology for Sustainable Green Mobility

The automotive sector digitalization accelerates the technology convergence of perception, computing processing, connectivity, propulsion, and data fusion for electric connected autonomous and shared (ECAS) vehicles. This brings cutting-edge computing paradigms with embedded cognitive capabilities into vehicle domains and data infrastructure to provide holistic intrinsic and extrinsic intelligence for new mobility applications. Digital technologies are a significant enabler in achieving the sustainability goals of the green transformation of the mobility and transportation sectors. Innovation occurs predominantly in ECAS vehicles’ architecture, operations, intelligent functions, and automotive digital infrastructure. The traditional ownership model is moving toward multimodal and shared mobility services. The ECAS vehicle’s technology allows for the development of virtual automotive functions that run on shared hardware platforms with data unlocking value, and for introducing new, shared computing-based automotive features. Facilitating vehicle automation, vehicle electrification, vehicle-to-everything (V2X) communication is accomplished by the convergence of artificial intelligence (AI), cellular/wireless connectivity, edge computing, the Internet of things (IoT), the Internet of intelligent things (IoIT), digital twins (DTs), virtual/augmented reality (VR/AR) and distributed ledger technologies (DLTs). Vehicles become more intelligent, connected, functioning as edge micro servers on wheels, powered by sensors/actuators, hardware (HW), software (SW) and smart virtual functions that are integrated into the digital infrastructure. Electrification, automation, connectivity, digitalization, decarbonization, decentralization, and standardization are the main drivers that unlock intelligent vehicles' potential for sustainable green mobility applications. ECAS vehicles act as autonomous agents using swarm intelligence to communicate and exchange information, either directly or indirectly, with each other and the infrastructure, accessing independent services such as energy, high-definition maps, routes, infrastructure information, traffic lights, tolls, parking (micropayments), and finding emergent/intelligent solutions. The article gives an overview of the advances in AI technologies and applications to realize intelligent functions and optimize vehicle performance, control, and decision-making for future ECAS vehicles to support the acceleration of deployment in various mobility scenarios. ECAS vehicles, systems, sub-systems, and components are subjected to stringent regulatory frameworks, which set rigorous requirements for autonomous vehicles. An in-depth assessment of existing standards, regulations, and laws, including a thorough gap analysis, is required. Global guidelines must be provided on how to fulfill the requirements. ECAS vehicle technology trustworthiness, including AI-based HW/SW and algorithms, is necessary for developing ECAS systems across the entire automotive ecosystem. The safety and transparency of AI-based technology and the explainability of the purpose, use, benefits, and limitations of AI systems are critical for fulfilling trustworthiness requirements. The article presents ECAS vehicles’ evolution toward domain controller, zonal vehicle, and federated vehicle/edge/cloud-centric based on distributed intelligence in the vehicle and infrastructure level architectures and the role of AI techniques and methods to implement the different autonomous driving and optimization functions for sustainable green mobility.

An efficient and improved model for power theft detection in Pakistan

This paper describes an improved model for the monitoring of power used by a party such as household users and different industries in Pakistan. The power theft detection was done using the intelligent internet of things (IoT) service system for calculating the user's power simultaneously. The power meter catches a theft detection device that is instantly transmitted to the central system which compares both the data by means of microcontroller and if there is any difference found, it informs the power utility about the hooking, meter relief or theft activities happen. Information of the theft detection through the global mobile communications system is transmitted and notified theft is displayed on the terminal monitor or won. As a result, although consumers continue to use excess fuel, the customer's power supply is cut in the electricity boards segment. The general radio package module system sends central circuit and meter data via an internet protocol address to a web server. GSM's IoT based perception is used to monitor the power supply and billing information calculated with a microcontroller continuously with the determination of the electricity table area. With this unit, the duplicate user can be located at the rear of the electricity office with the power meter status.

Highway 4.0: Digitalization of highways for vulnerable road safety development with intelligent IoT sensors and machine learning

According to United Nations (UN) 2030 agenda, the transportation system needs to be enhanced for the establishment of access to safe, affordable, accessible, and sustainable transport systems along with enhanced road safety. The highway road transport system is one of the transport systems that enables to transits goods and humans from one location to another location. The agenda of UN 2030 for the transport system will be accomplished with the assistance of digital technologies like the internet of things (IoT) and artificial intelligence (AI). The implementation of these digital technologies on highways empowers to provide reliable, smarter, intelligent, and renewable energy sources experience to the users travelling along the highways. This study discusses the significance of the digitalization of highways that supporting and realizing a sustainable environment on the highways. To discuss the significance of digitalization, the study has categorized digitalization into five subcomponents namely smart highway lighting system, smart traffic and emergency management system, renewable energy sources on highways, smart display and AI in highways. An architecture-for smart highway lighting, smart traffic, and emergency management are proposed and discussed in the study. The significance of implementing smart display boards and renewable sources with real-time applications is also addressed in this study. Moreover, the integration of AI in highways is addressed with the perspective of enhancing road safety. The integration of deep learning (DL) in the edge-based vision node for predicting the patterns of traffic flow, highway road safety, and maintenance of quality roads have been addressed in the discussion section. Embedding the deep learning techniques in the vison node at the traffic junction and the highway lighting controller is able to deliver an intelligent system that provides sustained experience and management of the highways. Smart reflectors, adoption of renewable energy, developing vehicle-to-vehicle communication in vehicles, and smart lamppost are the few recommendations for the implementation of digitalizing highways.

Deep Learning Data Privacy Protection Based on Homomorphic Encryption in AIoT

With the rapid development of 5G technology, its high bandwidth, high reliability, low delay, and large connection characteristics have opened up a broader application field of IoT. Moreover, AIoT (Artificial Intelligence Internet of Things) has become the new development direction of IoT. Through deep learning of real-time data provided by the Internet of Things, AI can judge user habits more accurately, make devices behave in line with user expectations, and become more intelligent, thus improving product user experience. However, in the process, there is a lot of data interaction between the edge and the cloud. Given that the shared data contain a large amount of private information, preserving information security on the shared data is an important issue that cannot be neglected. In this paper, we combine deep learning with homomorphic encryption algorithm and design a deep learning network model based on secure multiparty computing (MPC). In the whole process, we realize that the cloud only owns the encryption samples of users, and users do not own any parameters or structural information related to the model. In the experimental part, we input the encrypted Mnist and Cifar-10 datasets into the model for testing, and the results show that the classification accuracy rate of the encrypted Mnist can reach 99.21%, which is very close to the result under plaintext. The classification accuracy rate of encrypted Cifar-10 can reach 91.35%, slightly lower than the test result in plaintext and better than the existing deep learning network model that can realize data privacy protection.