Abstract
In the era of the Internet of Things (IoT), billions of smart devices connect, interact, and exchange data with each other. As “things” get connected together, intelligent systems and technologies have been developed to exploit the rich information in the collected data, perceive what is happening in the surroundings, and finally take actions to maximize their own utility. Thanks to the ubiquitous wireless signals and the prevalence of wireless devices, wireless sensing becomes more popular among the various approaches that have been adopted in the IoT to measure the surrounding environment. Because human activities interact with wireless signals and introduce distinct patterns to the propagation, analyzing how wireless channel state information (CSI) responds to human activities enables many IoT applications. Recently, radio analytics has been proposed as a promising technique that exploits multipath as virtual antennas, extracts various features from wireless signals, and reveals rich environmental information. As automobiles continue to play an important role nowadays, manufacturers have been seeking emerging techniques for IoT applications that support drivers and enhance safety. The interior of an automobile can be viewed as a special indoor environment where most of the multipath are restricted inside by the metal exterior. In this article, we introduce the concept of wireless artificial intelligence (AI) and demonstrate its concept in a smart car scenario where information about drivers and passengers is collected by commercial Wi-Fi devices deployed in the car. The proposed wireless AI system is capable of identifying authorized drivers based on radio biometric information. Vital signals of human introduce periodic patterns to the wireless CSI. By extracting the vital sign from wireless signals, the proposed wireless AI system can monitor the driver’s state, count the number of people in the car, and detect a child left in an unattended car.
Author Keywords
- Child presence detection,
- in-car monitoring,
- smart car,
- wireless artificial intelligent
IEEE Keywords
- Wireless communication,
- Wireless sensor networks,
- Automobiles,
- Communication system security,
- Sensors,
- Monitoring
Introduction
The Internet of Things (IoT) refers to the smart devices and sensors that are deployed in the environment and connected so that they can gather, share, and integrate information. Many emerging IoT technologies and systems have been designed to facilitate people understanding of human activities in surrounding environments. It has been envisioned that wireless sensing will become a prominent solution to the IoT applications due to the proliferation of wireless radio devices, ubiquitous wireless signals, and the rich information introduced into the wireless signals by human activities.
The feasibility of wireless sensing comes from the fact that environmental information is recorded in wireless signals. Nature provides numerous degrees of freedom that is delivered through wireless multipath propagation. Multipath propagation is the phenomenon that the received signal at the receiver side is a collection of signals traveling from the same source but through different paths. Due to a large number of multipath in a rich scattering indoor environment, information with a large degree of freedom can be captured by wireless signals. However, the performance of wireless sensing highly relies on the information richness we can decipher from the received wireless signal and it is determined by the transmission bandwidth. Nowadays, with advanced wireless communication technologies, more bandwidths become available and richer information can be revealed from wireless signals.
As originated from the time-reversal (TR) technique, radio analytics has been proposed as the technique that exploits the wireless signal, or more specifically the wireless channel state information (CSI), extracts various features, and then interprets the environmental information around us [1]. TR technique treats each indoor multipath as a distributed virtual antenna and generates a high-resolution spatial-temporal focusing effect, also known as the TR resonance effect [2]–[3][4]. The TR resonance effect is a result of the resonance of the electromagnetic (EM) field in response to the environment, a.k.a. the interaction between the wireless signal and its multipath propagation [5]. When the indoor environment changes, the multipath propagation varies accordingly and it results in a decrease in the TR resonance strength. Along with the TR technique, various radio analytic techniques have been developed to analyze radio signals, decipher the embedded environmental information, and support different IoT applications.
On one hand, human activities or moving objects introduce dynamics to the propagation of wireless signals. By deploying wireless sensors, extracting and analyzing various features implanted in wireless signals, one can infer macro changes in the indoor environment, such as indoor events detection [6]–[7][8][9], human activities recognition [10]–[11][12][13][14][15][16][17], indoor positioning [18]–[19][20][21][22][23][24][25][26][27], gait recognition [28]–[29][30] and tracking [31]–[32][33][34]. Moreover, one can also detect micro changes including hand gestures [35], [36], and vital signs [38]–[39][40][41] without requiring any wearable devices. Those IoT applications can be an ideal solution to home and office security systems, human activity recognition systems, and well-being monitoring systems. On the other hand, each human body will introduce unique perturbations to the wireless signals, through absorbing, reflecting, and scattering wireless signals [42], [43]. The static wireless propagation pattern interacted with a human body is defined as human radio biometrics, which is determined by individual biological characteristics. With the help of radio analytics, indoor human recognition now can be achieved through a non-vision based technique through radio biometrics [44].
Due to its on-demand transportation, mobility, independence, convenience, and comfortableness, automobiles have become a daily commodity with surging demand and prevalence. According to the report [45], [46], the number of worldwide automobiles on-the-road has reached 1.2 billion by 2017 and the U.S. vehicle ownership per household achieved 1.97 in 2016. In the past decade, automobile manufacturers and researchers have been working on innovative solutions that leverage emerging sensor technology to support the driver and enhance the safety, e.g., driver monitoring system to detect distraction and fatigue [47]–[48][49][50][51].
In contrast to most of the existing in-car techniques which require contact sensors and cameras [52], radio analytics that relies only on wireless signals is a promising solution to smart car monitoring. Nowadays, many car manufacturers are adding built-in Wi-Fi equipment to their new vehicles and internet providers are collaborating with them to provide cheap and fast Wi-Fi service. Secondly, superior to traditional sensors, Wi-Fi not only acts as an in-car sensor but also serves to connect passengers and drivers to the internet. On the other hand, what makes Wi-Fi an ideal solution for in-car sensing is that it can work under the circumstances of obstructions thanks to the multipath propagation, which is impossible for traditional sensors and cameras. The interior of a car can indeed be viewed as a special indoor environment where most of the multipath are confined inside the car because of the metal exterior. By deploying wireless radio devices in a car, radio analytics can enable many IoT applications specialized for automobile uses that have been envisioned for a long time but not been accomplished yet.
In this article, we will present the concept of wireless artificial intelligence (AI) which performs radio analytics, perceives the environment, and then takes optimal actions for different applications [53]. We demonstrate the capability of wireless AI through a smart car scenario. We first provide an overview of fundamental concepts of radio analytics and multipath harvesting. Then we define the smart car scenario and propose to use a single pair of commercial Wi-Fi devices to achieve 4 different IoT applications, including driver authentication, vital sign monitoring, passenger counting, and unattended child detection for parked cars.
To begin with, we first introduce the wireless AI driver authentication system that only allows an authorized driver to operate the car, guaranteeing the security and safety of automobiles. With a pair of commercial Wi-Fi devices deployed in the car, the biological information of the driver will be recorded by wireless signals. The proposed wireless AI smart car system extracts the radio biometric information of the driver and achieves accurate driver recognition and authentication. We further demonstrate how the proposed wireless AI system captures vital signs from the wireless signals to assist driver state monitoring, passenger counting, and unattended child detection. By analyzing the periodic pattern implanted in the wireless signal, the proposed wireless AI system can monitor the real-time breathing rate of the driver, which serves as an important indicator for health and fatigue in driver state monitoring. Moreover, by performing further analysis of the vital features recorded in the CSI, the proposed wireless AI system can count the number of people in the car. Inspired by the in-car vital monitoring, the proposed wireless AI system is also capable of detecting whether a child is left unattended in the car, which is extremely dangerous and even can be fatal [54]. Finally, we will survey and discuss recent related works.
Conclusion
Recent developments in wireless technologies and advancements in radio analytics empower many cutting-edge IoT applications that will dramatically change our lifestyle and assist people in understanding the who, what, when, where, and how of things happening around. Specifically, by leveraging the large degrees of freedom delivered via multipath propagation, one can retrieve the environmental information implanted in the CSI and thus perceive the surrounding world. With larger bandwidth becoming available in the next-generation communications, richer information can be revealed by the means of wireless sensing.
As the number of automobiles is proliferating and vehicles are becoming increasingly automated, it is important for the vehicle to be intelligent and provide driving assistance and safety guarantee. The inside of a car can be viewed as a special case of rich scattering indoor environments, where multipath propagation interacts with the driver and the passengers, meanwhile, recording their characteristics. Inspired by the techniques of radio analytics, we proposed the concept of wireless AI for smart cars, introducing smart IoT applications to the car. With the help of a pair of commercial Wi-Fi devices deployed in the car, the proposed wireless AI system can automatically identify the driver, monitor the driver’s state, count the number of people sitting in the car, and detect the presence of the unattended/left child. Unlike traditional approaches for smart car monitoring, the proposed wireless AI approach utilizes non-intrusive sensing, enjoys low complexity, works well under NLOS, and supports multiple IoT applications simultaneously, thus making it an ideal paradigm for the future smart car monitoring.
About KSRA
The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.
KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.
Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.
The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.
FULL Paper PDF file:
Wireless AI in Smart Car: How Smart a Car Can Be?Bibliography
author
Year
2020
Title
Wireless AI in Smart Car: How Smart a Car Can Be?,
Publish in
in IEEE Access, vol. 8, pp. 55091-55112, 2020,
Doi
10.1109/ACCESS.2020.2978531.
PDF reference and original file: Click here
Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.
Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.
Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.
