New Generation Alternative Sensors for IoT

Euclides Lourenço Chuma
September 15, 2020

 

The Internet of things (IoT) is a system of interrelated computing devices and mechanical and digital machines provided with unique identifiers (UIDs) and the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction. Many types of sensors are used in IoT for various applications, such as measuring temperature, humidity, pressure, acceleration, proximity, etc. However, a new generation of alternative sensors is being developed, which can be connected to IoT so that they are used in the creation of autonomous vehicles, in health monitoring, and other research areas.

This new generation of sensors together with artificial intelligence gathers more data and accurate information to be used in IoT systems that will make them more powerful, bringing benefits to mankind.

Microwave and mmWave Radar Sensors

Microwave and mmWave radar sensors can be used in the applications for detecting, positioning, and tracking of humans, animals, or generally moving objects without compromising their privacies. Microwave and mmWave radar facilitate the rapid detection of the position of nearby objects with high sensitivity and high accuracy even when there are environments interferences.

Microwave and mmWave radars have some unique features and they work within a particular range, i.e., operate in the range of few centimeters to a few hundred meters without a direct line of sight (for example, through drywall or plywood). Further, they are also highly adaptable to environmental conditions such as darkness, sunshine, smoke, fog, or haze [1].

Technology companies like Infineon and Vayyar are manufacturing mmWave radar sensors that use frequencies above 60 GHz and are sensitive enough to sense even a heartbeat [2-3]. Therefore, it is possible to use this type of sensor to gather a lot of data and information.

Therefore, these types of sensors can replace traditional cameras in many situations with so many advantages. The main advantage is that people’s privacy is protected during its operation and its ability to operate efficiently in environments where there are light and sound interferences as well as adverse atmospheres.

Figure 1: Some applications of mmWave radar sensors.

Figure 1: Some applications of mmWave radar sensors.

 

Light Detection and Ranging

Light detection and ranging (LiDAR) is a device that combines pulse of light (laser) and sensors of light (photodetector) to make digital 3-D representations of the target or surrounding environment. The LiDAR compute distances (ranging) by illuminating the targets with laser light and measuring the reflection with a sensor. Targets made up of different materials at different distances will generate different laser return times and wavelengths and these data can then be used to make 3-D representations of the target [4-6].

LiDAR is commonly used in many applications to generate high-resolution 3-D maps, such as in surveying, geography, geology, seismology, forestry, atmospheric physics, laser guidance, and airborne laser swath mapping.

Multispectral and Hyperspectral Imaging

It is known that the human eye can view or see the color of visible light mostly in three wavelength bands (red, green, and blue). But it is possible to obtain and view images in the bands that are beyond the visible region using new technologies. Multispectral and hyperspectral imaging divide the spectrum into many more wavelength bands., The recorded spectra in hyperspectral imaging have fine wavelength resolution and cover a wide range of wavelengths (Bands), while multispectral imaging measures spaced spectral bands.

Hyperspectral sensors detect objects using a wide band of the electromagnetic spectrum and as a result, objects leave unique “fingerprints” in the electromagnetic spectrum, which are known as spectral signatures. These “fingerprints” enable identifying the materials a scanned object or target is made of. Therefore, it is possible to know and obtain the chemical composition of the material at distance with a hyperspectral camera [7-8].

AI, Sensors, and IoT

The new generation of sensors as demonstrated earlier generate a huge amount of data requiring intelligent processing systems. Two systems are used for processing these huge amounts of information using artificial intelligence: cloud and edge [9-11].

Companies like Xilinx and Nvidia are developing solutions for both systems. When processing is carried out in the cloud, special cards are installed on the servers to speed up the deep learning processing method. When processing is performed on the edge, close to the sensor, processors specialized in deep learning with low energy consumption is used. In both cases, IoT solutions can accelerate the artificial intelligence process of the system thereby improving data quality.

Figure 2: AI Cloud vs AI Edge.Figure 2: AI Cloud vs AI Edge.

 

Final Remarks

Sensor fusion is the combination of sensory data received or data derived from disparate sources such that the resulting information has less uncertainty than that would be possible when these sources were used individually. It is important to know that several categories or levels of sensor fusion are commonly used. The sensor fusion level can also be defined based on the type of information used to feed the fusion algorithm [11-12].

Apart from the traditional sensor fusion model, currently, there are many modern methods based on artificial intelligence that can simultaneously process sensor data in many channels (such as the hyperspectral image with hundreds of bands) and merge relevant information to produce classification results.

In summary, the most important thing is to know that many innovative technologies are emerging that can be applied to IoT systems so that a more robust and effective system can be built to serve mankind.

References

  1. Z. Zhao, et al., “Point Cloud Features-Based Kernel SVM for Human-Vehicle Classification in Millimeter Wave Radar”, IEEE Access, 2020, v.8
  2. S. Dong, et al., “Doppler Cardiogram: A Remote Detection of Human Heart Activities”, IEEE Transactions on Microwave Theory and Techniques, 2020, v.68, i.3
  3. T. Lauteslager, et al., “Coherent UWB Radar-on-Chip for In-Body Measurement of Cardiovascular Dynamics”, IEEE Transactions on Biomedical Circuits and Systems, 2019, v.13, i.5
  4. J. Shaw, “Lidar Instruments and Applications”, IEEE Conference on Lasers and Electro-Optics (CLEO), 2017
  5. A. M. Wallace, A. Halimi, G. S. Buller, “Full Waveform LiDAR for Adverse Weather Conditions”, IEEE Transactions on Vehicular Technology, 2020, v.69, i.7, pp.7064-7077
  6. T. Sang, S. Tsai, T. Yu, “Mitigating Effects of Uniform Fog on SPAD LiDAR”, IEEE Sensors Letters, 2020
  7. W. Sun, Q. Du, “Hyperspectral Band Selection: A Review”, IEEE Geoscience and Remote Sensing Magazine, 2019, v.7, i.2
  8. M. Parente, J. Kerekes, R. Heylen, “A Special Issue on Hyperspectral Imaging”, IEEE Geoscience and Remote Sensing Magazine, 2019, v.7, i.2
  9. A. M. Ghosh, K. Grolinger “Deep Learning: Edge-Cloud Data Analytics for IoT”, IEEE Canadian Conference of Electrical and Computer Engineering (CCECE), 2019
  10. D. Liu, et al., “HierTrain: Fast Hierarchical Edge AI Learning With Hybrid Parallelism in Mobile-Edge-Cloud Computing”, IEEE Open Journal of the Communications Society, 2020, v.1, pp.634-645
  11. M. Chiang, T. Zhang, “Fog and IoT: An Overview of Research Opportunities”, IEEE Internet of Things Journal, 2016, v.3, i.6
  12. M. A. Al-Jarrah, et al., “Decision Fusion for IoT-Based Wireless Sensor Networks”, IEEE Internet of Things Journal, 2020, v.7, i.2
  13. P. Ferrer-Cid, et al., “Multisensor Data Fusion Calibration in IoT Air Pollution Platforms”, IEEE Internet of Things Journal, 2020, v.7, i.4

 

Euclides Lourenco ChumaEuclides Lourenço Chuma earned a degree in Mathematics (2003) from the University of Campinas (UNICAMP), a graduate degree in network and telecommunications Systems (2015) at INATEL, and MSc in electrical engineering (2017) at UNICAMP, and a PhD in electrical engineering (2019) at UNICAMP, SP-Brazil. His research interests are microwave, millimeter-wave, photonics, bioengineering, sensors, wireless power transfer, and telecommunications.