Next Article in Journal
A Non-Invasive Method for Measuring Bubble Column Hydrodynamics Based on an Image Analysis Technique
Previous Article in Journal
Optimization of a Green Extraction of Polyphenols from Sweet Cherry (Prunus avium L.) Pulp
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Processes
Volume 10
Issue 8
10.3390/pr10081658
processes-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

Prospects and Challenges of AI and Neural Network Algorithms in MEMS Microcantilever Biosensors

by
Jingjing Wang
*,
Baozheng Xu
,
Libo Shi
,
Longyang Zhu
and
Xi Wei
School of Electronic and Information Engineering, Tiangong University, Tianjin 300380, China
*
Author to whom correspondence should be addressed.
Processes 2022, 10(8), 1658; https://doi.org/10.3390/pr10081658
Submission received: 21 July 2022 / Revised: 19 August 2022 / Accepted: 19 August 2022 / Published: 21 August 2022
(This article belongs to the Section Biological Processes and Systems)
Browse Figures
Versions Notes

Abstract

:
This paper focuses on the use of AI in various MEMS (Micro-Electro-Mechanical System) biosensor types. Al increases the potential of Micro-Electro-Mechanical System biosensors and opens up new opportunities for automation, consumer electronics, industrial manufacturing, defense, medical equipment, etc. Micro-Electro-Mechanical System microcantilever biosensors are currently making their way into our daily lives and playing a significant role in the advancement of social technology. Micro-Electro-Mechanical System biosensors with microcantilever structures have a number of benefits over conventional biosensors, including small size, high sensitivity, mass production, simple arraying, integration, etc. These advantages have made them one of the development avenues for high-sensitivity sensors. The next generation of sensors will exhibit an intelligent development trajectory and aid people in interacting with other objects in a variety of scenario applications as a result of the active development of artificial intelligence (AI) and neural networks. As a result, this paper examines the fundamentals of the neural algorithm and goes into great detail on the fundamentals and uses of the principal component analysis approach. A neural algorithm application in Micro-Electro-Mechanical System microcantilever biosensors is anticipated through the associated application of the principal com-ponent analysis approach. Our investigation has more scientific study value, because there are currently no favorable reports on the market regarding the use of AI with Micro-Electro-Mechanical System microcantilever sensors. Focusing on AI and neural networks, this paper introduces Micro-Electro-Mechanical System biosensors using artificial intelligence, which greatly promotes the development of next-generation intelligent sensing systems, and the potential applications and prospects of neural networks in the field of microcantilever biosensors.

1. Introduction

Sensor technology is evolving as a result of advances in science technology and the popularization of information technology. Sensor development has gone through three generations thus far. Structural sensors make up the initial generation of sensors. By utilizing the pertinent sensor system variables, this kind of sensor can convert the signal and detect changes in the signal. A solid-state sensor is the second kind of sensor and is made of semiconductors, electrolytes, and magnetic components. In the 1970s, this kind of sensor started to evolve. This generation of sensors, which currently account for about 75% of the sensor industry, are often characterized by low cost, high accuracy, and outstanding performance. The smart sensor that this paper primarily introduces is the third-generation sensor. Miniaturization and intelligence are currently the two major requirements for sensor systems due to the growth of the Internet and the improvement in human demands. Microelectromechanical systems (MEMS) are integrated at the nanoscale and microscale. As a result, MEMS sensors differ from conventional sensors in that they are miniaturized, integrated with microelectronics, and manufactured in parallel with great precision. The potential use of MEMS and nanotechnology in the sensing sector is typically thought of due to their lower size, simpler integration into systems, better portability, and mobility.
Since the atomic force microscope in 1986 [1], its advantages of label-free, high sensitivity, portable, low cost, and fast response have attracted a large number of researchers to explore and study. Since then, MEMS-based biosensors have continued to develop; in the meantime, many types of MEMS biosensors such as optical acoustics have emerged [2,3,4,5]. Efficient, fast, and sensitive, it can quickly acquire and process information, just the same as the human body’s sensory organs; it can perceive the external environment and perceive important physical information, such as sound, light, pressure, and temperature. Due to these advantages, MEMS biosensors are widely used in automation, aerospace, consumer electronics, defense, industrial manufacturing, medical devices, life sciences, and telecommunications [6,7,8].
AI is being used increasingly for connecting and interacting with humans and computers. Users get a more immersive experience with this interactive system, which contains features of future sensors. It is utilized in a variety of application scenarios, including entertainment, medical rehabilitation, sports training simulation, and more (as depicted in Figure 1) [9].

2. Research State of AI Applications in Biosensors

Artificial intelligence has advanced quickly and is currently a popular field of study in technology. It uses densely connected networks to process information in a manner that mimics how the human brain processes information. It is capable of self-learning, parallel processing, and powerful information storage. The fields of application for artificial intelligence are growing as the field’s theory and technology mature. People are already able to see how artificial intelligence and MEMS sensors work together.

2.1. Gas Sensing Field

Gas monitoring systems are employed in a variety of settings, including commercial and residential settings, especially in the detection of dangerous gases. The tiny size and great sensitivity of semiconductor-type resistive gas sensors make them appealing. They are also inexpensive and simple to create. These benefits imply that semiconductor-based gas sensors are an excellent option for Internet of Things applications.
Suh published a fully integrated portable multi-gas sensor module for Internet of Things applications [10]. For Internet of Things (IoT) applications such as multiple gas sensor reading and data analysis, analog/digital signal processing, heater control, and wireless communication, Suh offers a portable gas sensing module with an ultra-compact MEMS gas sensor device. A microprocessor algorithm’s simplified schematic diagram is shown in Figure 2. (ESP32). The AFE circuit elements undergo a number of initializations when the system initially powers up, and a ramp voltage is generated to bring the heater power to its goal level (VDAC). The microprocessor can compute the power and maintain the desired power by modifying the VDAC for the heater control algorithm by keeping track of the current passing through the heater (Iheat). Rf ought to be automatically chosen in order to read the voltage in real time. Do not let the TIA output voltage become saturated (Vout). Select a lower RF when the voltage is almost zero volts. Select 2.1 V as the upper limit for RF change instead.
No intermediary hardware is needed, because the system fully incorporates RF, AFE, digital signal processing, and sensors, making it suitable for IoT application right now. The technology is portable and powerful, and it can be used to monitor the air quality in places like homes, cars, and manufacturing facilities, as shown in Figure 3.

2.2. Sound Detection Field

Speech recognition is the most user-friendly interface for two-way communication between people and smart devices; however, voice user interfaces (VUI) and biometric systems based on artificial intelligence (AI) and the Internet of Things (IoT) are also garnering a lot of attention. In terms of sound detection, Han et al. proposed a platform for speaker recognition utilizing machine learning-assisted approaches, as shown in Figure 4. The test data consisted of 40 individuals, and the machine learning speaker recognition algorithm used was based on the Gaussian Mixture Model (GMM). There are 2800 training data in it. They assert that, using the most and second-most sensitive data from the multi-channel output, Gaussian Mixture Models (GMMs) in machine learning obtain a speaker recognition rate of 97.5% and a 75% reduction in error when compared to a reference MEMS microphone [11].
Machine learning-based training on TIDIGITS speech data (40 people, 2800 speeches) was performed using the GMM algorithm, which has been modified for multi-signal processing. A randomly selected person’s speech is compared with the trained speech data set for speaker recognition.
In addition, as illustrated in Figure 5, Jung et al. reported a flexible piezoelectric acoustic sensor and machine learning for speech processing. Flexible piezoelectric acoustic sensors vibrate in response to the speaker’s voice to store electrical impulses, providing information for preprocessing. To train data and extract linguistic information from voices, use machine learning-based models. The transition of electronic systems from touch to voice operation will be assisted by this technique. They assert that new user interfaces for utilizing artificial intelligence (AI) services will be created by speech recognition systems built on cutting-edge sound sensors and optimized machine learning algorithms [12].
Due to its simplicity and two-way communication, voice user interface (VUI), the foundational technology of the Internet of Things (IoT) and Artificial Intelligence (AI), has garnered significant interest. Smart acoustic sensors can be applied to a variety of industries, including biometrics, smart home products, and speaker recognition. Speech recognition software transforms audio data into a binary digital format for machine learning algorithms. Recent developments in deep learning have considerably enhanced the voice processing task performance, outperforming that of traditional machine learning methods. However, these systems still have poor identification rates because of sensitive hardware problems and a lack of audio data. Future speech technologies should focus on the synergy between smart acoustic sensors and AI algorithms to overcome the fundamental weakness of speech recognition [13,14,15].

2.3. Wearable Sensing Field

Smart wearables and IoT-based clothes have entered our field of view with the rise of the Internet of Things (IoT) and Artificial Intelligence (AI), and they are becoming more and more vital to us due to the unparalleled coordination and convenience, as well as the enjoyment given by fashion. Life has a profound effect. Today, seamless and widespread integration of sensors into textiles is made possible by the quick union of textiles and electronics. The Internet era of smart clothes has arrived with the development of smart fabrics that can communicate with smartphones to process physiological data like heart rate, temperature, respiration, pressure, movement, acceleration, and even hormone levels.
According to Tiago M., a garment must contain the fundamental subsystems depicted in Figure 6 in order to be a part of the future smart clothing Internet. Wireless technology or conductive fabrics can both be used for subsystem communication [16]. The first option often costs more in terms of technology and uses more energy, but it does away with the need to create and incorporate conductive yarn into smart clothes. New conductive fabrics and printed electronics will make it possible to seamlessly integrate sensors on a broad scale into textiles [17,18].
The architecture consists of the following main components:
  • Communication gateway, exchanging information with smart clothing in order to send information to cloud server or blockchain via internet or intranet [19].
  • Cloud servers that collect and store data and provide certain remote services for smart clothing and remote users.
  • A blockchain. It is not essential to the basic functions of the smart clothing system.
Additionally, the Internet of Things (IoT) and wearable technology, in conjunction with device-to-device communication (D2D) [20], virtual/augmented reality (VR/AR) [21,22], cyber-physical systems (CPS) [23], artificial intelligence (AI) [24], and smart textiles [25], as well as other developments in 5G communication networks, can enhance human-to-human and human-to-machine connections and interactions.

2.4. Body Sensor Field

Body sensors have drawn a lot of interest from scientists lately because of their useful uses in the area of smart medicine. Body sensors are now widely used in a variety of real-world settings, including entertainment, security, health, and healthcare. The ability of body sensors to protect and enhance people’s healthy lifestyles is a significant benefit of employing them to monitor individuals. Body sensor-based human motion detection yields insightful information about a person’s functioning and way of life. Figure 7 illustrates Uddin’s proposed body sensor-based behavior identification system, in which a person wears various body sensors on various body areas, including the wrist, ankle, and chest. Sensor data is acquired via wireless media and saved to a computer. The basic flow of the system is shown in Figure 8, which has two basic steps: training and testing [26].
The authors also employ the promising deep learning method known as the deep recurrent neural network (RNN), which is based on sequence data. Research interest in recurrent neural networks (RNNs) for evaluating rhythmic occurrences in time series applications is on the rise. Compared to other deep learning techniques currently used, it can offer stronger discrimination. As a result, various activities are trained and recognized using human sensor-based RNNs [27,28,29,30,31]. The following table is used to show the comparison of AI applied to different types of biosensors, as shown in Table 1.
Due to the complicated signal, it is impossible to manually measure the content information of each chemical, which is necessary for MEMS microcantilever biosensors to detect many substances simultaneously and more accurately. The issues with MEMS microcantilever biosensors can be efficiently fixed with AI, which also increases the detection precision.

3. Research Status of MEMS Microcantilever Biosensors

Micro-Electro-Mechanical Systems, sometimes known as MEMS, are electronic mechanical systems. It is a microelectromechanical system that incorporates interface circuits, signal processing and control circuits, microsensors, and microactuators. The microcantilever biosensor operates on the theory that, when the material being tested adheres to or remains on its surface, the mass of the microcantilever changes, which causes the micro-resonant cantilever’s frequency to change. The quality of the test object can be determined by measuring the size of the frequency offset.
The benefits of the miniaturization, integration, intelligence, low cost, and mass production of MEMS microcantilever biosensors have made them popular in a variety of industries, including wireless communication [32], biomedicine [33], military defense [34], consumer electronics [35], and many more. It may be claimed that MEMS microcantilever biosensors, to a certain extent, represent the future development of sensor technology, because these advantages are consistent with the path of future sensor development.
One of the MEMS components that is frequently utilized is the microcantilever sensor. Sensors based on microcantilevers have been employed in every part of life since Binning et al. created an improved atomic force microscope through a cantilever in 1986. Researchers now have a deeper knowledge of the microcantilever sensor thanks to extensive theoretical research and application exploration. In order to provide lateral stresses to the cells adhering to the material, Akiko [36], a researcher at the National Institute of Metal Science in Japan, assessed the separation force in the cell culture media, as shown in Figure 9 utilizing optical fiber sensors. A resolution of 0.25 nm and output voltage accuracy of 0.0005 m/mV can be reached when measuring the deviation value of the microcantilever beam, respectively. However, the optical fiber sensing in the liquid has some influence on the entire detecting process. It is difficult and inconvenient to use the equipment.
Using the optical lever readout method, as shown in Figure 10, to achieve a detection accuracy of 0.1 ng/mL, Wu [37], a researcher at the University of Berkeley in the United States, used the bending change of the microcantilever to perform prostate-specific antigen (prostate-specific antigen, PSA) bioassays and used the microcantilever to perform DNA hybridization, DNA–protein interactions, and protein–protein binding.
Numerous innovative micro-nano-biosensors have arisen in recent years as a result of the cross-integration of electronic information technology and biology, MEMS technology, and nanotechnology. Three groups can be made out of them, depending on the various conversion mechanisms: optical sensors, electrochemical sensors, and mass-sensitive sensors, as shown in Table 2.
In terms of the detection time, sensitivity, safety, in situ sensing, and real-time detection, optical biosensors have several advantages. Its widespread applicability is constrained by the high cost [38]. Electrochemical biosensors are advantageous due to their ability to be made smaller, cheaper, more sensitive, and unaffected by solution turbidity [40]. However, the sensor contains electrolytes, which have a low stability and are significantly impacted by external factors, including temperature, humidity, and pressure. It has some restrictions, because it needs to be calibrated separately for various application situations. Microelectromechanical systems (MEMS) typically use beams [41], discs [42], rings [43], interdigitated fingers [44], and other resonant structures to provide mass-sensitive sensors (as shown in Figure 11). The microbeam structure has the advantages of small size, a simple structure, high sensitivity, easy arraying, and integrationand has become the most potential device in the field of the simultaneous detection of multiple markers [45].
There are two operating modes for MEMS microcantilevers used as biosensors: static mode and dynamic mode. The object that needs to be detected is precisely adsorbed on the biofunctionalized microcantilever, which changes the microcantilever’s surface stress state and deflection of the amount of analyte on the microcantilever’s surface. The resonance mode is another name for the micro-dynamic cantilever’s operating mode. According to the detection concept, if the chemical being tested sticks to or remains on the microcantilever surface, it will change the mass of the device, which will change the resonance frequency. Using the frequency shift as a gauge, it might indicate how much analyte the microcantilever has adsorbed [46].
The initial report on the hybridization and detection of DNA molecular fragments by a static mode microbeam biosensor was made in the American Journal of Science by Fritz et al. of IBM Zurich Laboratory [47]. This research advances the static mode microbeam biosensor technology while demonstrating how the microbeam biosensor can be used to quickly align DNA. The static mode microbeam biosensor, which has some sensitivity restrictions, accomplishes the detection goal by deforming the cantilever beam through a change in the surface tension. The resonant microbeam biosensor has been employed extensively in recent years, because in the dynamic operating mode, the quality factor of the microbeam can approach 104 and beyond, and it can achieve trace detection in the order of 10−18 g [48], with extraordinarily high sensitivity and more and more focus. According to Lange et al., metal oxide microcantilevers can detect volatile organic chemical concentrations with an octane detection limit of 0.8 ppm and a mass resolution of roughly 2 pg [49]. The Caltech research team led by M. Roukes discovered that, in vacuum, the mass resolution of a nanometer-sized double-ended beam sensor can reach 4 kDa (1 Da =1.66 × 10−21 g) [50]. The dynamic mode microbeam sensor’s drawback, on the other hand, is that the environment has a significant impact on the resonant frequency and quality factor, and the high sensitivity of mass detection can only be demonstrated in a vacuum environment. The resonance frequency, quality factor, and detection sensitivity of the resonant beam sensor can all be significantly decreased by environmental damping, particularly damping caused by liquid environments. Additionally, the microbeam’s stiffness coefficient was altered, lowering its sensitivity. Based on this investigation, D. Ramos et al. of the Spanish National Microelectronics Center examined the resonance frequency change after printing the bacterial solution on the cantilever beam at various positions and discovered that the single-end clamped beam with only the free end printing the bacterial solution had the best quality and sensitivity to detection [51]. Nugaeva et al. of the University of Basel used single-end fixed beam arrays to explore the process of yeast and Aspergillus niger hyphae growth, as well as the method of the particular immobilization of fungi in the field of real-time monitoring of microbeam biosensors [52]. By monitoring the change of the dynamic resonance frequency of the microbeam, the concentration of fungi was detected in the range of 103–106 CFU/mL, realizing the real-time monitoring of the colony growth.
With the rapid advancement of microfluidic technology following the concept of the flow cell, polydimethylsiloxane material (PDMS) was used as the encapsulating shell of the microfluidic channel in the microbeam biosensors reported in recent years to replace the flow cell [53]. High binding efficiency and high sensitivity detection are successfully achieved through the creative combination of microcantilevers.

4. The Application Prospect of Neural Network in MEMS Microcantilever Biosensor

A type of sensor with significant current development potential is the MEMS microcantilever biosensor. Due to its benefits in miniaturization, integration, intelligence, low cost, and mass production, it has been extensively employed in wireless communication, biomedicine, military defense, consumer electronics, and other disciplines. It is now possible to use high tech in microcantilever biosensors and spur their development in the present world, where computer science and technology are advancing one after the other.
Neural networks have advanced significantly in models, learning techniques, and ap plications in recent years. Due to its traits of self-adaptation, generalization, nonlinear mapping, and extremely parallel processing, it has been widely used in the field of smart sensors. The application increases the sensor’s intelligence and raises its level of intelligence.
A neural network is a network made up of certain basic (often adaptive) components and their massively parallel connections that are hierarchically organized and have a high capacity for nonlinear description. The neural network continually trains the network in practical applications based on the input and output data of the object and accomplishes nonlinear mapping from the input parameters to the output parameters in order to learn adaptively. Neural networks come in a variety of forms, each with unique advantages, and they are frequently employed in conjunction with sensors in nonlinear correction, classification, diagnosis, identification, and other applications.

4.1. Nonlinear Self-Calibration

The majority of a sensor’s input and output properties are now nonlinear. It can be challenging to adjust for some nonlinear sensor systems using hardware or standard software. Due to their advantages in parallel processing, fault tolerance, self-adaptation, and powerful self-learning, neural networks are frequently utilized in the nonlinear self-correction of sensor systems. Currently, neural networks are gradually being employed in new domains, including micromechanical systems, in addition to large-scale mechanical control fields. Steele created a new sensor system with a closed-loop topology with the goal of simplifying the design and fabrication while addressing the unique nonlinear and sophisticated electrical circuits of micromechanical sensors [54,55]. Two different types of neural networks are used in this sensor system to build the mathematical model of the micro-sensing system. A compensation neural network completes the input’s static mapping, while a feedback neural network is utilized to demodulate and linearize the feedback signal. The simulation results demonstrate the system’s excellent linearity, wide dynamic range, and strong vibration resistance. The closed-loop detection system of the microcantilever beam sensor can use the data model created by the compensation neural network and feedback neural network. Since the system uses FPGA for logic architecture, as indicated in the picture, it is incredibly dependable, compact, and affordable. At the same time, it addresses the issues with the analog phase-locked loop’s zero drift and the ease with which changes in the power supply and outside temperature have an impact on the phase-locking performance, as shown in Figure 12.
Environmental factors affect sensor properties in a nonlinear way. The system’s microcantilever biosensors can function in a variety of conditions, including those with varying pressures, humidity levels, magnetic fields, and temperatures. In this instance, the sensor’s reaction is dependent nonlinearly on both the environmental conditions and the measured value, depending on the materials and manufacturing processes utilized to create the sensor. As a result, getting accurate sensor readings under various environmental circumstances is a challenging problem. There have been a number of digital and analog interface circuits described in the past to account for nonlinear response characteristics and achieve correct readings [56,57]. Environmental factors affect sensor properties in a nonlinear way. The system’s microcantilever biosensors can function in a variety of conditions, including those with varying pressures, humidity levels, magnetic fields, and temperatures. In this instance, the sensor’s reaction is dependent nonlinearly on both the environmental conditions and the measured values, depending on the materials and manufacturing processes utilized to create the sensor. As a result, getting accurate sensor readings under various environmental circumstances is a challenging problem. There have been a number of digital and analog interface circuits described in the past to account for nonlinear response characteristics and achieve correct readings [57,58]. Iterative and noniterative algorithms are among these methods. Patra suggested a neural network among them that automatically corrects for the nonlinear impacts of the surrounding temperature [58], as shown in Figure 13. With temperatures ranging from 0 to 250 °C, this method is used to model capacitive pressure sensors that operate under challenging conditions. The usefulness of the model in predicting the nonlinear effects of various types of ambient temperatures on the properties of the pressure sensor is confirmed by computer simulation trials. Iterative and noniterative algorithms are among these methods. Patra suggested a neural network among them that automatically corrects for the nonlinear impacts of the surrounding temperature. With temperatures ranging from 0 to 250 °C, this method is used to model capacitive pressure sensors that operate under challenging conditions. The usefulness of the model in predicting the nonlinear effects of various types of ambient temperatures on the properties of the pressure sensor is confirmed by computer simulation trials.
Artificial neural networks have become a potent learning method for carrying out difficult tasks in changing contexts. The effects of these methods on this complicated problem are constrained under the supposition that environmental parameter fluctuation is modest and that the environmental parameter influence on sensor characteristics is not linearly significant.
To actualize the sensor characteristics, the linear equation of the linear segment is produced using the best fitting approach, and the inverse function of the nonlinear segment of the sensor characteristics is mapped using an upgraded BP neural network as a corrective link. The simulation test results for linearization suggest that this method may almost ten times more effectively minimize the sensor’s nonlinear error [59,60,61]. The majority of these techniques transfer the inverse function of the sensing properties as a correction link in order to accomplish linearization. To correct the sensor’s nonlinear error, Zhang employed a single-input, single-output cerebellar neural network (SISO-CMAC) inverse operation. He also examined and demonstrated the SISO-CMAC algorithm’s convergence using the incremental learning approach [62], as shown in Figure 14.
The measurement and control system’s performance are directly impacted by the sensor’s error, which is mostly a nonlinear error. As a result, contemporary research has begun to focus heavily on the linearization of the microcantilever biosensor’s properties.

4.2. Fault Self-Diagnosis

The neural network has excellent nonlinear fitting capabilities and does not require the mathematical model of the known system; rather, it simply adapts to the properties of the targeted item for defect diagnostics in which the model is elusive. As a result, neural networks have gradually been used in recent years in study areas including defect detection and monitoring. Reference [63] used a multi-layer forward feedback neural network structure based on the B-P method to monitor and categorize the operational state of the processing equipment after guiding the network’s training. The model trained with the frequency domain signal is found to be more effective than the model trained with the time domain signal, according to the simulation results in this study, which demonstrate that this strategy can produce optimal results. Neural networks are used to identify the chemical and gas components of substances, in addition to gas sensor fault detection. The literature suggests using neural network models to enhance the optical sensors based on the idea that two-color mixes on triacyl cellulose sheets have fixed features. The findings demonstrate that utilizing a neural network model to process the detection value increases the sensor’s measuring range while simultaneously increasing the precision and accuracy, with an error rate of no more than 2%.
The learning object of the neural network model is chosen to be a typical sensor with good performance, and the sensor output signal data is fed into the neural network model for learning. The neural network’s weight is initially set to a random value. A signal output estimate is created when the test data from the gas sensor enters the neural network. The update method of the weights uses the difference between this estimate and the actual output signal of the gas sensor. The neural network method will continually update the connection weight of the learning network as long as the output data from the gas sensor continues to enter the network for the operation.
w i j ( n + 1 ) = w i j ( n ) + η δ j Z j
where w i j is the neuron weight, Z j   is the neuron output, η is the learning coefficient, and δ j is the neuron difference.
The learning process can be stopped when the mean square error (MSE) achieves a minimal value. Such learning is carried out by several regression processes. The artificial neural network model has now finished learning and evolved into the nonlinear output model of the gas sensor at the same time as the network weight reaches a stable coefficient. As can be seen, the correctness of the dynamic nonlinear model of the gas sensor may be ensured as long as sufficient numbers of accurate training samples are given.
The fault diagnosis of the gas sensor can be done online thanks to the precise dynamic output model of the gas sensor, as shown in Figure 15.
The graphic shows that, when the gas sensor operates normally, the actual output of the sensor and the anticipated output of the neural network are both consistent. The actual sensor output varies from what the neural network predicts when the gas sensor malfunctions. The estimated value is compared with the predetermined threshold value by measurements in the detection method, making it simple to diagnose sensor faults.
The use of artificial neural networks provides greater benefits than conventional techniques for the dynamic nonlinear modeling of gas sensors to perform online fault testing. The implementation of artificial neural networks in microcantilever biosensors is made possible by the fact that they are appropriate for the modeling and fault diagnostics of other dynamic nonlinear systems.
According to the actual system and the output residuals of the neural network observer, Reference [64] developed a fault-tolerant control system and a neural network state observer that can diagnose sensor defects. A neural network time series predictor-based sensor defect diagnosis method was shown in Reference [65]. The difference between the sensor output value and the actual sensor output is predicted using a neural network prediction model, which is first utilized to create a prediction model for the sensor output sequence and whether the sensor will be faulty. The method of the sensor fault diagnosis combines the optimization (HPSO) algorithm and neural network, using the HPSO algorithm to optimize the parameters of the neural network model, and establishes a prediction model for sensor fault diagnosis.

4.3. Data Fusion

The precision of the measurement and control system can be significantly increased by using multi-sensor information fusion to provide rich and comprehensive information about the system. It represents a significant step in the direction of microcantilever biosensor development. The microcantilever biosensor’s many beams collect information, which is analyzed and combined by multi-sensor information fusion technology to create a thorough and full description of the information about the measured object. Neural network technology’s nonlinear capability has developed into a useful tool for fusing data from several sensors effectively and quickly. To increase the precision and accuracy of multi-sensor data processing, References [66,67] made use of rough sets and backpropagation networks. Reference [68] suggested a multi-sensor data fusion approach based on belief entropy and belief-based divergence measures. It resolves the issue where combining extremely incongruent data could lead to outcomes that are contrary to conventional wisdom. To reduce the uncertainty of sensor data, Reference [69] used fuzzy sets to combine data from several sensors. Reference [70] was based on the continuous Markov model. The motion control and somatosensory sensor data fusion algorithm was created. The outcomes of the experiments demonstrated that the algorithm may successfully lower the degree of uncertainty in sensor data. A framework for sign language recognition was suggested on the basis of this. Random finite sets were used in Reference [71], so the subsequent sensor data was anticipated, as well as fused with the initial sensor data. The single data fusion techniques can only partially accomplish the goal of fusion due to their weak resilience and inaccurate and unstable fusion outputs.
In the traditional sense, the realization of neural network multi-sensor integration and fusion can be divided into three important steps:
(1) According to the requirements of the intelligent system and the form of sensor integration and fusion, the topology of the neural network is selected.
(2) Comprehensively process the input information of each sensor into an overall input function and define this function mapping as the mapping function of the relevant unit, which reflects the statistical law of the environment to the network itself through the interaction between the neural network and the environment. in the structure.
(3) Learn and understand the sensor output information to determine the distribution of the values, and complete the knowledge acquisition and information fusion.
Due to traditional multi-sensor information fusion, Chen Ying improved the data preprocessing and fusion process of the fusion method, as shown in Figure 16. The fusion process steps of the improved fusion method are as follows:
(1) Preprocess the data collected by the sensor through the Laida criterion, including data cleaning, replacing outliers, etc.
(2) Denoising the preprocessed data by using the wavelet threshold of the high-frequency coefficients after the layers are subjected to threshold processing and the obtained low-frequency coefficients are optimized by the neural network.
(3) Neural network optimization is performed on the transformed and reduced data.
(4) Data fusion is performed through the reliability of the sensor, and the final fusion result is obtained.
A large-scale, continuously adapting, nonlinear information processing system is a neural network. It uses a vast network of extensive connections of a significant number of neurons for information processing and simulates the information processing function of the human brain. It offers powerful parallel processing, information storage, and self-learning capabilities. When a neural network is used to combine data from several sensors, it is first important to choose an appropriate neural network model based on the system’s needs and the sensor’s properties. To learn it, set the weight distribution and finish the network training so that the trained neural network may take part in the actual fusion process; the system decisions and existing sensor data are employed.

5. Application of Principal Component Analysis in Biosensors

The principal component analysis (PCA) has been employed for a long time as a fault detection technique to extract pertinent data from multivariate sensors. The PCA has been used to analyze multivariate data for a number of multivariate data analysis technologies, including sensor process monitoring, quality control, and problem diagnosis. The multi-scale principal component analysis (MSPCA) method, which combines the principal component analysis with wavelet analysis, was first proposed by Bakshi in 1998 [72]. In Reference [73], the authors described a method for identifying sensor failures that uses an MSPCA model to track the statistical variable T2 in the principal component space, squared prediction error (SPE) to identify the sensor drift error, and SPE contributions from each sensor to identify the faulty sensors [74]. Secondly, the principal component analysis, as an effective tool for multi-sensor modeling, is often used in sensor data reconstruction [75,76,77,78]. The PCA is a modeling method that is independent of the knowledge of the mathematical model of the system, and the output of the sensor can build a statistical model for sensor fault diagnosis [79]. Under normal circumstances, the sensor database   X m × n is collected, where m is the number of samples and n is the number of sensors. Then, it is standardized to remove the effects of different units of the variables:
X ¯ = D σ − 1 [ X − E ( x ) ]
where X = [ x 1 , x 2 , ⋯ , x n ] T ∈ ℜ n is the data vector of the specified point in X m × n , E(X) = [μ1, μ2, μ3, μn] T is the average vector of X m × n . D σ = diag ( σ 1 , σ 2 , ⋯ , σ n ) , where σ i = E ( x i − μ i ) 2 is the ith standard deviation of X ¯ m × n . In this way, the standard database X ¯ m × n is realized. Calculate the correlation matrix with X ¯ m × n and then perform singular decomposition. Finally, project X ¯ m × n into the principal component space X ^ and the residual space X ^ , namely:
X → m × n = X ^ + X ˜ = C ^ X ¯ m × n + C ˜ X ¯ m × n
where the projection matrix C ^ = P P T . To detect sensor failures, statistical variables in the subspace need to be specified. Reference [80] presented a comparison between some statistical variables, proving that the SPE in the residual space can better reflect the correlation changes between sensor outputs than the T2 in the principal component space. Therefore, SPE can detect sensor failures in real time. The definition of SPE is as follows:
SPE = ∥ C ˜ x ¯ ∥ 2 ⩽ δ SPE 2
where δ SPE is the threshold of SPE, which can be calculated from the sample distribution of SPE [81].
Anurag placed detection samples in a 1650 × 6 matrix in the form of datasets, where the rows represent the data vectors in the microcantilever sensor space. It is frequently impossible to discriminate between raw data vectors linked to distinct vapor classes because of overlap or ambiguity in the chemical interactions between water vapor and polymers. According to the mutually orthogonal directions with the greatest variance, the principal component analysis (PCA) can convert the data into a six-dimensional principle component space. The primary components are listed in decreasing order of variance, with the variance serving as a measure of the information content (as shown in Figure 17).
The principal component distribution maps of four sensor arrays constructed utilizing static and dynamic mode sensing, as well as FCM and FSC polymer options, respectively, are shown in the principal component analysis of the response of the MEMS cantilever sensor array on respiratory volatiles. Microcantilever sensors have the potential for mass production, they have the benefits of convenience, cheap cost, and high sensitivity, and they have the possibility to add more features.
In the future, PCA will be required to integrate microcantilever sensors with high tech, since it improves the characteristics of data extraction from these sensors.

6. Challenges and Prospects of AI Applied to Microcantilever Sensors

The development and use of monitoring, optimization, and control technologies have recently been aided by artificial intelligence, data-driven technologies, cyber–physical systems, cloud computing, and cognitive computing [82]. Nonlinear algorithms, for instance, can be used to monitor dynamic systems and provide observer gains [83].
In the progress of the optimization of microcantilever biosensor systems, the lack of a significant application field for human–computer interactions has prevented a trend of full integration between microcantilever sensors and high-tech systems such as the Internet of Things, as shown in Figure 18. As illustrated in the image, there are adaptable applications and user-friendly human–machine interface applications in various sensor areas, including wearable sensor fields and human body sensor fields.
In addition, there are also some restrictions with the artificial neural algorithm and microcantilever combo. The study of artificial neural networks is a cutting-edge field that has advanced significantly in recent decades. It can get over the current bottleneck and conduct in-depth research on nonlinear phenomena because of its capacity for large-scale parallel processing, high-fault tolerance, high self-organization, adaptability, and ability to approximate any nonlinear function. However, the artificial neural network still encounters some challenges when the training samples are excessively vast and great precision is needed. The classic backpropagation (BP) neural network, as shown in Figure 19 for instance, has drawbacks, such as a high output mean square error and poor diagnostic precision. Artificial intelligence algorithms used in the sensor industry have this same issue.
Future MEMS microcantilever biosensors should be able to connect to the Internet and engage in a larger variety of human–computer interactions and interconnections. The application of AI in biosensors can benefit from deep-level data processing, such as data processing and data fusion with the aid of neural algorithms. Today, with the booming development of the Internet, cases of biosensors for human–computer interaction, such as smart bracelets, are seen everywhere. We can envision MEMS microcantilever biosensors based on neural algorithms and artificial intelligence technologies being used in a range of applications in the near future, including medical treatments, industrial production, environmental protection, and others.

7. Conclusions

Future sensors and microelectromechanical systems (MEMS) will play an increasingly significant part in our daily lives as we enter the new era of intelligence and experience the rapid growth of technology. As a result, MEMS sensor systems integrate neural networks and artificial intelligence (AI), and the following iteration of sensors will have a distinct development trajectory. This essay explores the possibility of fusing MEMS microcantilever biosensors with neural algorithms, as well as the specific case of fusing AI with MEMS biosensors. As a sensor type with several benefits, including portability, affordability, and high sensitivity, its integration with the Internet should go beyond the use of neural networks and instead help people interact with other objects in a variety of scenario applications.

Author Contributions

Conceptualization, J.W. and B.X.; methodology, B.X.; software, B.X.; validation, B.X.; formal analysis, J.W. and B.X.; investigation, J.W.; resources, B.X.; data curation, B.X.; writing—original draft preparation B.X.; writing—review and editing, J.W., B.X., L.S., L.Z. and X.W.; visualization, J.W. and B.X.; supervision, J.W., project administration, J.W.; funding acquisition, J.W. All authors have read and agreed to the published version of the manuscript.

Funding

This research was funded by [the National Science Foundation of China and Tianjin Municipal Science and Technology Bureau], grant number [(61804107) and (20JCQNJC00180)]. And the APC was funded by [the National Science Foundation of China (61804107) and Tianjin Municipal Science and Technology Bureau (20JCQNJC00180)].

Informed Consent Statement

Written informed consent has been obtained from the patients to publish this paper.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Binnig, G.; Quate, C.F.; Gerber, C. Atomic Force Microscope. J. Mater. Eng. 1986, 56, 930–933. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  2. Marauska, S.; Claus, M.; Lisec, T.; Wagner, B. Low temperature transient liquid phase bonding of Au/Sn and Cu/Sn electroplated material systems for MEMS wafer-level packaging. Microsyst. Technol. 2013, 19, 1119–1130. [Google Scholar] [CrossRef]
  3. Xie, J.; Lee, C.; Wang, M.; Liu, Y.; Feng, H. Characterization of heavily doped polysilicon films forCMOS-MEMS thermoelectric power generators. J. Micromech. Microeng. 2009, 19, 125029. [Google Scholar] [CrossRef] [Green Version]
  4. Yang, B.; Lee, C.; Kotlanka, R.; Xie, J.; Lim, S. A MEMS rotary comb mechanism for harvesting kinetic energyof planar vibrations. J. Micromech. Microeng. 2010, 20, 065017. [Google Scholar] [CrossRef] [Green Version]
  5. Lee, C.; Yu, A.; Yan, L.; Wang, H.; He, J.; Zhang, Q.; Lau, J. Characterization of intermediate In/Ag layers of low temperature fluxless solder based wafer bonding for MEMS packaging. Sens. Actuators A Phys. 2009, 154, 85–91. [Google Scholar] [CrossRef]
  6. Lee, C.; Lim, Y.; Yang, B.; Kotlanka, R.; Heng, C.; He, J.; Tang, M.; Xie, J.; Feng, H. Theoretical comparison of theenergy harvesting capability among various electrostatic mechanisms from structure aspect. Sens. Actuators A Phys. 2009, 156, 208–216. [Google Scholar] [CrossRef]
  7. Koh, K.; Lee, C.; Kobayashi, T. A piezoelectric-driven three-dimensional MEMS VOA using attenuation mechanism with combination of rotational and translation Effects. IEEE/ASME J. Microelectromech. Syst. 2010, 19, 1370–1379. [Google Scholar] [CrossRef]
  8. Wang, N.; Tsai, J.; Hsiao, F.; Soon, B.; Kwong, D.; Palaniapan, M.; Lee, C. Experimental investigation of a cavity-mode resonator using a micromachined two-dimensional silicon phononic crystal in a square lattice. IEEE Electron Device Lett. 2011, 32, 821–823. [Google Scholar] [CrossRef] [Green Version]
  9. Zhu, J.; Liu, X.; Shi, Q.; He, T.; Sun, Z.; Guo, X.; Liu, W.; Sulaiman, O.B.; Dong, B.; Lee, C. Development Trends and Perspectives of Future Sensors and MEMS/NEMS. Micromachines 2019, 11, 7. [Google Scholar] [CrossRef] [Green Version]
  10. Suh, J.-H.; Cho, I.; Kang, K.; Kweon, S.-J.; Lee, M.; Yoo, H.-J.; Park, I. Fully integrated and portable semiconductor-type multi-gas sensing module for IoT applications. Sens. Actuators B Chem. 2018, 265, 660–667. [Google Scholar] [CrossRef]
  11. Han, J.H.; Bae, K.M.; Hong, S.K.; Park, H.; Kwak, J.-H.; Wang, H.S.; Joe, D.J.; Park, J.H.; Jung, Y.H.; Hur, S.; et al. Machine learning-based self-powered acoustic sensor for speaker recognition. Nano Energy 2018, 53, 658–665. [Google Scholar] [CrossRef]
  12. Jung, Y.; Hong, S.K.; Wang, H.S.; Han, J.H.; Pham, T.X.; Park, H.; Kim, J.; Kang, S.; Yoo, C.D.; Lee, K.J. Flexible Piezoelectric Acoustic Sensors and Machine Learning for Speech Processing. Adv. Mater. 2020, 32, 35. [Google Scholar] [CrossRef] [PubMed]
  13. Wang, X.; Gu, Y.; Xiong, Z.; Cui, Z.; Zhang, T. Silk-molded flexible, ultrasensitive, and highly stable electronic skin for monitoring human physiological signals. Adv. Mater. 2014, 26, 1336–1342. [Google Scholar] [CrossRef] [PubMed]
  14. Park, J.; Lee, Y.; Hong, J.; Lee, Y.; Ha, M.; Jung, Y.; Lim, H.; Kim, S.Y.; Ko, H. Tactile-direction-sensitive and stretchable electronic skins based on human-skin-inspired interlocked microstructures. ACS Nano 2014, 8, 12020–12029. [Google Scholar] [CrossRef]
  15. Jian, M.; Xia, K.; Wang, Q.; Yin, Z.; Wang, H.; Wang, C.; Wang, H.; Xie, M.; Zhang, Y. Flexible and highly sensitive pressure sensors based on bionic hierarchical structures. Adv. Funct. Mater. 2017, 27, 1606066. [Google Scholar] [CrossRef]
  16. Fernández-Caramés, T.M.; Fraga-Lamas, P. Electronics towards the internet of smart clothing: A review on iot wearables and garments for creating intelligent connected e-textiles. Electronics 2019, 7, 405. [Google Scholar] [CrossRef] [Green Version]
  17. Yang, T.; Xie, D.; Li, Z.; Zhu, H. Recent advances in wearable tactile sensors: Materials, sensing mechanisms, and device performance. Mater. Sci. Eng. R Rep. 2017, 115, 1–37. [Google Scholar] [CrossRef]
  18. Allison, L.; Hoxie, S.; Andrew, T.L. Towards seamlessly integrated textile electronics: Methods to coat fabrics and fibers with conducting polymers for electronic applications. Chem. Commun. 2017, 53, 7182–7193. [Google Scholar] [CrossRef]
  19. Fernández-Caramés, T.M.; Fraga-Lamas, P. A Review on the Use of Blockchain for the Internet of Things. IEEE Access 2018, 6, 32979–33001. [Google Scholar] [CrossRef]
  20. Akpakwu, G.A.; Silva, B.J.; Hancke, G.P.; Abu-Mahfouz, A.M. A Survey on 5G Networks for the Internet of Things: Communication Technologies and Challenges. IEEE Access 2018, 6, 3619–3647. [Google Scholar] [CrossRef]
  21. Blanco-Novoa, Ó.; Fernández-Caramés, T.M.; Fraga-Lamas, P.; Vilar-Montesinos, M.A. A Practical Evaluation of Commercial Industrial Augmented Reality Systems in an Industry 4.0 Shipyard. IEEE Access 2018, 6, 8201–8218. [Google Scholar] [CrossRef]
  22. Fraga-Lamas, P.; Fernández-Caramés, T.M.; Blanco-Novoa, Ó.; Vilar-Montesinos, M.A. A Review on Industrial Augmented Reality Systems for the Industry 4.0 Shipyard. IEEE Access 2018, 6, 13358–13375. [Google Scholar] [CrossRef]
  23. Fraga-Lamas, P. Enabling Technologies and Cyber-Physical Systems for Mission-Critical Scenarios. Ph.D. Thesis, University of A Coruña, A Coruña, Spain, 2017. [Google Scholar]
  24. Javaid, N.; Sher, A.; Nasir, H.; Guizani, N. Intelligence in IoT-Based 5G Networks: Opportunities and Challenges. IEEE Commun. Mag. 2018, 56, 94–100. [Google Scholar] [CrossRef]
  25. Loss, C.; Gonçalves, R.; Lopes, C.; Pinho, P.; Salvado, R. Smart Coat with a Fully Embedded Textile Antenna for IoT Applications. Sensors 2016, 16, 938. [Google Scholar] [CrossRef]
  26. Mzu, A.; Mmhb, C.; Aa, B.; Savaglio, C. A body sensor data fusion and deep recurrent neural network-based behavior recognition approach for robust healthcare-ScienceDirect. Inf. Fusion 2020, 55, 105–115. [Google Scholar]
  27. Sak, H.; Senior, A.; Beaufays, F. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. Interspeech 2014, 338–342. [Google Scholar] [CrossRef]
  28. Williams, R.J.; Peng, J. An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories. Neural Comput. 1990, 2, 490–501. [Google Scholar] [CrossRef]
  29. Fortino, G.; Galzarano, S.; Gravina, R.; Li, W. A framework for collaborative computing and multi-sensor data fusion in body sensor networks. Inf. Fusion 2015, 22, 50–70. [Google Scholar] [CrossRef]
  30. Fortino, G.; Guerrieri, A.; Bellifemine, F.L.; Giannantonio, R. SPINE2: Developing BSN Applications on Heterogeneous Sensor Nodes. In Proceedings of the 2009 IEEE International Symposium on Industrial Embedded Systems, Lausanne, Switzerland, 8–10 July 2009; IEEE: Torino, Italy; pp. 128–131. [Google Scholar]
  31. Gravina, R.; Fortino, G. Automatic methods for the detection of accelerative cardiac defense response. IEEE Trans. Affect. Comput. 2016, 7, 286–298. [Google Scholar] [CrossRef]
  32. Rebeiz, G.M. RF MEMS: Theory, Design and Technology; John Wiley & Sons: Hoboken, NJ, USA, 2004; pp. 87–120. [Google Scholar]
  33. Kim, Y.J.; Hwang, E.S.; Kim, Y.H. MEMS-Based Biosensor; Springer: New York, NY, USA, 2008. [Google Scholar]
  34. You, Z.; Li, B.; Yu, S. Applications of MEMS devices in nanosatellite. In Proceedings of the 2nd International Conference on Recent Advances in Space Technologies, Istanbul, Turkey, 9–11 June 2005; pp. 240–243. [Google Scholar]
  35. Brigante, C.M.N.; Abbate, N.; Basile, A.; Faulisi, A.C.; Sessa, S. Towards Miniaturization of a MEMS-Based Wearable Motion Capture System. IEEE Trans. Ind. Electron. 2011, 58, 3234–3241. [Google Scholar] [CrossRef]
  36. Akiko, Y. A new technique for direct measurement of the shear force necessary to detach a cell from a material. Biomaterials 1998, 19, 871–879. [Google Scholar]
  37. Wu, G. Bioassay of prostate-specific antigen (PSA) using microcantilevers. Nat. Biotechnol. 2001, 19, 856–860. [Google Scholar] [CrossRef] [PubMed]
  38. Mehrotra, P. Biosensors and their applications-A review. J. Oral Biol. Craniofacial Res. 2016, 6, 153. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  39. Zhao, C.; Thuo, M.M.; Liu, X. A microfluidic paper-based electrochemical biosensor array for multiplexed detection of metabolic biomarkers. Sci. Technol. Adv. Mater. 2013, 14, 4402. [Google Scholar] [CrossRef] [PubMed]
  40. Boisen, A.; Dohn, S.; Keller, S.S.; Schmid, S.; Tenje, M. Cantilever-like micromechanical sensors. Rep. Prog. Phys. 2011, 74, 036101. [Google Scholar] [CrossRef]
  41. Okan, M.; Duman, M. Functional polymeric nanoparticle decorated microcantilever sensor for specific detection of erythromycin. Sens. Actuators B-Chem. 2018, 256, 325–333. [Google Scholar] [CrossRef]
  42. Malmir, K.; Habibiyan, H.; Ghafoorifard, H. An ultrasensitive optical label-free polymeric biosensor based on concentric triple microring resonators with a central microdisk resonator. Opt. Commun. 2016, 365, 150–156. [Google Scholar] [CrossRef]
  43. Camli, B.; Kusakci, E.; Lafci, B.; Salman, S.; Torun, H.; Yalcinkaya, A.D. Cost-effective, Microstrip Antenna Driven Ring Resonator Microwave Biosensor for Biospecific Detection of Glucose. IEEE J. Sel. Top. Quantum Electron. 2017, 23, 6900706. [Google Scholar] [CrossRef]
  44. Partel, S.; Kasemann, S.; Matylitskaya, V.; Thanner, C.; Dincer, C.; Urban, G. A simple fabrication process for disposable interdigitated electrode arrays with nanogaps for lab-on-a-chip applications. Microelectron. Eng. 2017, 173, 27–32. [Google Scholar] [CrossRef]
  45. Leahy, S.; Lai, Y. A cantilever biosensor exploiting electrokinetic capture to detect Escherichia coli in real time. Sens. Actuators B Chem. 2017, 238, 292–297. [Google Scholar] [CrossRef]
  46. Hansen, K.M.; Thundat, T. Microcantilever biosensors. Methods 2005, 37, 57–64. [Google Scholar] [CrossRef] [PubMed]
  47. Dammer, U.; Hegner, M.; Anselmetti, D.; Wagner, P.; Dreier, M.; Huber, W.; Güntherodt, H.J. Specific antigen/antibody interactions measured by force microscopy. Biophys. J. 1996, 70, 2437–2441. [Google Scholar] [CrossRef] [Green Version]
  48. Fritz, J.; Baller, M.K.; Lang, H.P.; Rothuizen, H.; Vettiger, P.; Meyer, E.; Ntherodttch, G.; Gerberand, J.; Gimzewski, K. Translating Biomolecular Recognition into Nanomechanics. Science 2000, 288, 316–318. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  49. Wang, D.F.; Du, X.; Wang, X.; Ikehara, T.; Maeda, R. Improving picogram mass sensitivity via frequency doubling in coupled silicon microcantilevers. J. Micromech. Microeng. 2016, 26, 015006. [Google Scholar] [CrossRef]
  50. Thundat, T.; Wachter, E.A.; Sharp, S.L.; Warmack, R.J. Detection of mercury vapor using resonating microcantilevers. Appl. Phys. Lett. 1995, 66, 1695–1697. [Google Scholar] [CrossRef]
  51. Ramos, D.; Tamayo, J.; Mertens, J.; Calleja, M.; Zaballos, A. Origin of the response of nanomechanical resonators to bacteria adsorption. J. Appl. Phys. 2006, 100, 061101. [Google Scholar] [CrossRef] [Green Version]
  52. Nugaeva, N.; Gfeller, K.Y.; Backmann, N.; Lang, H.P.; Düggelin, M.; Hegner, M. Micromechanical cantilever array sensors for selective fungal immobilization and fast growth detection. Biosens. Bioelectron. 2005, 21, 849–856. [Google Scholar] [CrossRef]
  53. Moudgil, A.; Singh, K.K.; Swaminathan, S. MEMS based design and analysis of a biosensor for detection of hepatitis virus. In Proceedings of the IEEE International Conference on Nanotechnology, Rome, Italy, 27–30 July 2015; pp. 805–808. [Google Scholar]
  54. Kartanas, T.; Ostanin, V.; Challa, P.K.; Daly, R.; Charmet, J.; Knowles, T.P.J. Enhanced Quality Factor Label-free Biosensing with Microcantilevers Integrated into Microfluidic Systems. Anal. Chem. 2017, 89, 11929–11936. [Google Scholar] [CrossRef] [Green Version]
  55. Fortino, G.; Giannantonio, R.; Gravina, R.; Kuryloski, P.; Jafari, R. Enabling Effective Programming and Flexible Management of Efficient Body Sensor Network Applications. IEEE Trans. Hum. Mach. Syst. 2013, 43, 115–133. [Google Scholar] [CrossRef]
  56. Patra, J.C.; Kot, A.C.; Panda, G. An intelligent pressure sensor using neural networks. IEEE Trans. Instrum. Meas. 2000, 49, 829–834. [Google Scholar] [CrossRef]
  57. Patra, J.C.; van den Bos, A. Auto-calibration and -compensation of a capacitive pressure sensor using multilayer perceptrons. ISA Trans. 2000, 39, 175–190. [Google Scholar] [CrossRef]
  58. Patra, J.C.; Ang, E.L.; Das, A.; Chaudhari, N.S. Auto-compensation of nonlinear influence of environmental parameters on the sensor characteristics using neural networks. ISA Trans. 2005, 44, 165–176. [Google Scholar] [CrossRef]
  59. Daponte, P.; Grimaldi, D. Artificial neural networks in measurements. Measurement 1998, 23, 93–115. [Google Scholar] [CrossRef]
  60. Dias Pereira, J.M.; Silva Girao, P.M.B.; Postolache, O. Fitting transducer characteristics to measured data. IEEE Instrum. Meas. Mag. 2001, 4, 26–39. [Google Scholar] [CrossRef]
  61. Dias Pereira, J.M.; Postolache, O.; Silva Girao, P.M.B. A temperature compensated system for magnetic field measurements based on artificial neural networks. IEEE Trans. Instrum. Meas. 1998, 47, 494–498. [Google Scholar] [CrossRef]
  62. Zhang, X.; Liu, Q. Sensor Nonlinear Error Compensation Based on Neural Network Inverse operation. J. Nanjing Norm. Univ. Nat. Sci. Ed. 2010, 33, 5. [Google Scholar]
  63. Zhuang. Fault Diagnosis of Gas Sensor based on Neural Network. Ind. Instrum. Autom. 2002, 60, 54–55. [Google Scholar]
  64. Shan, F.; Luo, J.; Wu, W.; Shen, X. Optimal Wireless Power Transfer Scheduling for Delay Minimization. In Proceedings of the IEEE INFOCOM, San Francisco, CA, USA, 10–14 April 2016. [Google Scholar]
  65. Kim, M.U.; Yang, H.J. Min-SINR Maximization with DL SWIPT and UL WPCN in Multicell Multi-Antenna Networks. IEEE Wirel. Commun. Lett. 2017, 6, 318–321. [Google Scholar] [CrossRef]
  66. Li, K.; Wang, Q. Study on signal recognition and diagnosis for spacecraft based on deep learning method. In Proceedings of the Prognostics and System Health Management Conference (PHM), Beijing, China, 21–23 October 2015; IEEE: Piscataway, NJ, USA, 2015; pp. 1–5. [Google Scholar]
  67. Guo, L.; Gao, H.; Huang, H.; He, X.; Li, S. Multifeatures Fusion and Nonlinear Dimension Reduction for Intelligent Bearing Condition Monitoring. Shock Vib. 2016, 2016, 1–10. [Google Scholar] [CrossRef] [Green Version]
  68. Verma, N.K.; Gupta, V.K.; Sharma, M.; Sevakula, R.K. Intelligent Condition Based Monitoring of Rotating Machines Using Sparse Auto-Encoders. In Proceedings of the 2013 IEEE Conference on Prognostics and Health Management (PHM), Gaithersburg, MD, USA, 24–27 June 2013; pp. 1–7. [Google Scholar]
  69. Sohaib, M.; Kim, C.-H.; Kim, J.-M. A hybrid feature model and deep-learning-based bearing fault diagnosis. Sensors 2017, 17, 2876. [Google Scholar] [CrossRef] [Green Version]
  70. Cheng, F.; Wang, J.; Qu, L.; Qiao, W. Rotor current-based fault diagnosis for DFIG wind turbine drivetrain gearboxes using frequency analysis and a deep classifier. IEEE Trans. Ind. Appl. 2017, 54, 1062–1071. [Google Scholar] [CrossRef]
  71. Chen, R.; Chen, S.; He, M.; He, D.; Tang, B. Rolling bearing fault severity identification using deep sparse auto-encoder network with noise added sample expansion. Proc. Inst. Mech. Eng. Part O J. Risk Reliab. 2017, 231, 666–679. [Google Scholar] [CrossRef]
  72. Bakshi, R.B. Multiscale PCA with application to multivariate statistical process monitoring. AKE J. 1998, 44, 1596–1610. [Google Scholar] [CrossRef]
  73. Luo, R.; Misra, M.; Himmelblau, D.M. Sensor Fault Detection via Multiscale Analysis and Dynamic PCA. Ind. Eng. Chem. Res. 1999, 38, 1489–1495. [Google Scholar] [CrossRef]
  74. Hui, D.; Liu, J.H.; Shen, Z. Drift reduction of gas sensor by wavelet and principal component analysis. Sens. Actuators 2003, 96, 354–363. [Google Scholar] [CrossRef]
  75. Mallat, S. A theory for multiresolution signal decomposition: The wavelet representation. IIPEE Trans. Pattern Anal. Mach. Intell. 1989, 11, 674–693. [Google Scholar] [CrossRef] [Green Version]
  76. Dunia, R.; Qin, S.J.; Edgar, T.F.; McAvoy, T.J. Identification of faulty sensors using principal component analysis. AKlhE J. 1996, 42, 2797–2812. [Google Scholar] [CrossRef]
  77. Barker, M.; Hengst, M.; Schmid, J.; Buers, H.-J.; Mittermaier, B.; Klemp, D.; Koppmann, R. Volatile organic compounds in the exhaled breath of young patients with cystic fibrosis. Eur. Respir. J. 2006, 27, 929–936. [Google Scholar] [CrossRef]
  78. Buszewski, B.; Ligor, T.; Jezierski, T.; W-Piesik, A.; Walczak, M.; Rudnicka, J. Identification of volatile lung cancer markers by gas chromatography–mass spectrometry: Comparison with discrimination by canines Analytical and Bioanalytical Chemistry. Anal. Bioanal. Chem. 2012, 404, 141–146. [Google Scholar] [CrossRef] [Green Version]
  79. Buszewski, B.; Kesy, M.; Ligor, T.; Amann, A. Human exhaled air analytics: Biomarkers of diseases. Biomed. Chromatogr. 2007, 21, 553–566. [Google Scholar] [CrossRef]
  80. Amann, A.; Miekisch, W.; Schubert, J.; Buszewski, B.; Ligor, T.; Jezierski, T.; Pleil, J.; Risby, T. Analysis of Exhaled Breath for Disease Detection. Annu. Rev. Anal. Chem. 2014, 7, 455–482. [Google Scholar] [CrossRef] [PubMed]
  81. Dunia, R.; Qin, S.J.; Edgar, T.F.; McAvoy, T.J. Use of principal component analysis for sensor fault identification. Comput. Chem. 1996, 20, S713–S718. [Google Scholar] [CrossRef]
  82. Gao, Z.; Chen, M.Z.Q.; Zhang, D. Special Issue on “Advances in Condition Monitoring, Optimization and Control for Complex Industrial Processes”. Processes 2021, 9, 664. [Google Scholar] [CrossRef]
  83. Pen, C.-L.; Chang, W.-J.; Lin, Y.-H. Development of Fuzzy Observer Gain Design Algorithm for Ship Path Estimation Based on AIS Data. Processes 2022, 10, 33. [Google Scholar] [CrossRef]
Processes 10 01658 g001 550
Figure 1. The development trend of future biosensors.
Figure 1. The development trend of future biosensors.
Processes 10 01658 g001
Processes 10 01658 g002 550
Figure 2. Schematic diagram of the algorithm programmed on the ESP32 microprocessor. The first procedure generates a ramp voltage to initialize the circuit components in the AFE and set each heating power to the target value (VDAC). By monitoring Iheat and subsequently changing VDAC, the heater control keeps the heating power at the desired level. In order to prevent the TIA output from becoming saturated, the proper Rf is automatically chosen for the Rsens readout control.
Figure 2. Schematic diagram of the algorithm programmed on the ESP32 microprocessor. The first procedure generates a ramp voltage to initialize the circuit components in the AFE and set each heating power to the target value (VDAC). By monitoring Iheat and subsequently changing VDAC, the heater control keeps the heating power at the desired level. In order to prevent the TIA output from becoming saturated, the proper Rf is automatically chosen for the Rsens readout control.
Processes 10 01658 g002
Processes 10 01658 g003 550
Figure 3. Data transmission by transmitting raw data from multiple sensors over Wi-Fi. (a) Data transfer over a Wi-Fi access point that is connected to the Internet. In this instance, the sensor data is recorded in a Google Spreadsheet file and displayed as graphs. (b) Data transmission via a BLE to an Android application that creates graphs of the sensor data in real-time.
Figure 3. Data transmission by transmitting raw data from multiple sensors over Wi-Fi. (a) Data transfer over a Wi-Fi access point that is connected to the Internet. In this instance, the sensor data is recorded in a Google Spreadsheet file and displayed as graphs. (b) Data transmission via a BLE to an Android application that creates graphs of the sensor data in real-time.
Processes 10 01658 g003
Processes 10 01658 g004 550
Figure 4. A platform for speaker recognition using machine learning-assisted methods. (a) Speaker testing and training utilizing the common TIDIGITS dataset and the GMM algorithm (20 men and 20 female speakers, 77 speeches per each speaker, and a total of 3080 voice data). Ninety percent of the TIDIGITS dataset is utilized for training purposes, and ten percent is used for testing purposes. (b) The trained STFT features from 2800 training data from 40 individuals are shown in an t-SNE plot. The t-SNE graphic integrates similar objects’ high-dimensional data into a low-dimensional space associated with probability distribution. (c) In the event that a 12th speaker is discovered, the majority voting approach is used to test the speaker recognition mechanism throughout the frames.
Figure 4. A platform for speaker recognition using machine learning-assisted methods. (a) Speaker testing and training utilizing the common TIDIGITS dataset and the GMM algorithm (20 men and 20 female speakers, 77 speeches per each speaker, and a total of 3080 voice data). Ninety percent of the TIDIGITS dataset is utilized for training purposes, and ten percent is used for testing purposes. (b) The trained STFT features from 2800 training data from 40 individuals are shown in an t-SNE plot. The t-SNE graphic integrates similar objects’ high-dimensional data into a low-dimensional space associated with probability distribution. (c) In the event that a 12th speaker is discovered, the majority voting approach is used to test the speaker recognition mechanism throughout the frames.
Processes 10 01658 g004
Processes 10 01658 g005 550
Figure 5. Schematic diagram of the application prospect of the voice user interface platform. By vibrating in response to the speaker’s voice, flexible piezoelectric acoustic sensors convert utterances to electrical multi-signals, which can give digitalized data for preprocessing. Language information is collected from the voice once the data are trained using a machine learning-based model. This procedure will aid in the transition of touch-operated devices to sound-operated ones.
Figure 5. Schematic diagram of the application prospect of the voice user interface platform. By vibrating in response to the speaker’s voice, flexible piezoelectric acoustic sensors convert utterances to electrical multi-signals, which can give digitalized data for preprocessing. Language information is collected from the voice once the data are trained using a machine learning-based model. This procedure will aid in the transition of touch-operated devices to sound-operated ones.
Processes 10 01658 g005
Processes 10 01658 g006 550
Figure 6. General architecture of IoT smart clothing system.
Figure 6. General architecture of IoT smart clothing system.
Processes 10 01658 g006
Processes 10 01658 g007 550
Figure 7. A schematic device of a human activity prediction system based on human sensors.
Figure 7. A schematic device of a human activity prediction system based on human sensors.
Processes 10 01658 g007
Processes 10 01658 g008 550
Figure 8. The basic flow of the proposed body sensor-based physical activity recognition system.
Figure 8. The basic flow of the proposed body sensor-based physical activity recognition system.
Processes 10 01658 g008
Processes 10 01658 g009 550
Figure 9. Reading out the deviation value of the microcantilever through the optical fiber.
Figure 9. Reading out the deviation value of the microcantilever through the optical fiber.
Processes 10 01658 g009
Processes 10 01658 g010 550
Figure 10. Microcantilever sensor optical lever readout detection system.
Figure 10. Microcantilever sensor optical lever readout detection system.
Processes 10 01658 g010
Processes 10 01658 g011 550
Figure 11. Mass sensing MEMS biosensors with different structures.
Figure 11. Mass sensing MEMS biosensors with different structures.
Processes 10 01658 g011
Processes 10 01658 g012 550
Figure 12. The closed-loop detection circuit of the microcantilever sensor.
Figure 12. The closed-loop detection circuit of the microcantilever sensor.
Processes 10 01658 g012
Processes 10 01658 g013 550
Figure 13. Linear and nonlinear relationship between true pressure and pressure estimated by the neural network model at different temperature values.
Figure 13. Linear and nonlinear relationship between true pressure and pressure estimated by the neural network model at different temperature values.
Processes 10 01658 g013
Processes 10 01658 g014 550
Figure 14. SISO-CMAC structure.
Figure 14. SISO-CMAC structure.
Processes 10 01658 g014
Processes 10 01658 g015 550
Figure 15. Neural network prediction output and output of a faulty gas sensor.
Figure 15. Neural network prediction output and output of a faulty gas sensor.
Processes 10 01658 g015
Processes 10 01658 g016 550
Figure 16. The data preprocessing and fusion processes of the improved fusion method.
Figure 16. The data preprocessing and fusion processes of the improved fusion method.
Processes 10 01658 g016
Processes 10 01658 g017 550
Figure 17. Distribution of the principal components.
Figure 17. Distribution of the principal components.
Processes 10 01658 g017
Processes 10 01658 g018 550
Figure 18. Human–computer interaction applications of wearable sensors.
Figure 18. Human–computer interaction applications of wearable sensors.
Processes 10 01658 g018
Processes 10 01658 g019 550
Figure 19. BP neural network algorithm flow.
Figure 19. BP neural network algorithm flow.
Processes 10 01658 g019
Table
Table 1. The comparison of AI applied to different types of biosensors.
Table 1. The comparison of AI applied to different types of biosensors.
TypeSchematicApplicationAdvantages
Gas Sensor Processes 10 01658 i001Multi-sensor data reading and analysis,
Analog/Digital
Signal Processing,
Wireless Communication		small size,
powerfulWidely
Acoustic Sensor Processes 10 01658 i002Speech Recognition
Algorithm Improvement
Multiple Signal Processing		Convenient
Bidirectional
Widely
Wearable Sensor Processes 10 01658 i003Human-computer interaction
Remote Service
Wireless communication		Improve Connection and Interaction
Great Business Value
Health Check
Convenient
Body Sensor Processes 10 01658 i004Identify activities
body detection
Signal transmission		Health Check
Body Protection
Convenient storage
Table
Table 2. Three types of micro-nano-biosensors.
Table 2. Three types of micro-nano-biosensors.
Detection typeSchematicDetection
Principle		Advantages and Disadvantages
Optical sensor
(such as surface plasmon resonance SPR [38])		 Processes 10 01658 i005Optical properties such as light absorption and reflectionhigh sensitivity,
real-time
complex
bulky device
Electrochemical sensors (such as microelectrodes [39]) Processes 10 01658 i006Redox Reaction
chemical reaction
Dielectric change
between electrodes		high sensitivity,
easy to array.
Unstable
Mass-sensitive sensors (such as microcantilevers [40]) Processes 10 01658 i007After adsorption of the biological sample to be detected, the resistance, voltage, and frequency of the sensing unit changehigh sensitivity,
mature
easy to array
Easy to integrate with IC;
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Share and Cite

MDPI and ACS Style

Wang, J.; Xu, B.; Shi, L.; Zhu, L.; Wei, X. Prospects and Challenges of AI and Neural Network Algorithms in MEMS Microcantilever Biosensors. Processes 2022, 10, 1658. https://doi.org/10.3390/pr10081658

AMA Style

Wang J, Xu B, Shi L, Zhu L, Wei X. Prospects and Challenges of AI and Neural Network Algorithms in MEMS Microcantilever Biosensors. Processes. 2022; 10(8):1658. https://doi.org/10.3390/pr10081658

Chicago/Turabian Style

Wang, Jingjing, Baozheng Xu, Libo Shi, Longyang Zhu, and Xi Wei. 2022. "Prospects and Challenges of AI and Neural Network Algorithms in MEMS Microcantilever Biosensors" Processes 10, no. 8: 1658. https://doi.org/10.3390/pr10081658

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop