JP2021509958A - Systems and methods for determining subject status based on volatile organic compounds - Google Patents

Abstract

Disclosed is a method for determining the state of a subject based on volatile organic compounds (VOCs) in the gas phase derived from the subject. This method comprises the step of receiving a set of sensor signals from one or more sensors in response to exposing one or more sensors to a sample of VOCs, and one from the set of sensor signals. Trained to classify VOCs samples based on the steps of extracting one or more feature values and one or more extracted feature values that correlate with one or more states of the subject. Based on the step of receiving the classification model and the step of associating one or more feature values received from the set of sensor signals with one or more classifications of the classification model, the condition of the subject is determined. It can include a step to determine. [Selection diagram] FIG. 1A

Description

The present invention generally relates to determining the condition of a subject based on biometric data. More specifically, the present invention is a system and method for determining the state of a subject based on biometric data collected from a sensor for sensing volatile organic compounds (VOCs) generated from the subject. Regarding.

Collecting biometric data of a subject includes widely used methods such as face image recognition (also known as face recognition), finger fingerprints, iris recognition, voice recognition, and the like. The methods listed detect all measured parameters and compare these parameters with the measured values of the parameters associated with a single subject stored in the database. Usually, a single measurement of the subject is sufficient to collect all the parameters needed to identify the subject. For example, a single image of the subject's face would be sufficient for face recognition, and a single speech recognition would be sufficient for speech recognition.

Using VOCs collected from a subject as a recognition method is even more complicated. Human and / or mammalian scents are affected by multiple parameters such as health, gender, diet, mental status, general health (eg fitness), and environmental status. Human and / or mammalian odors can change during the day from morning to evening due to changes in one or more parameters that affect the odor, such as the foods eaten. Humans and / or mammals produce many different VOCs (eg, odors) per second. VOCs can be derived from the subject's skin, subject's hair, urine, sweat, saliva, feces and virtually any substance derived from the subject's body. Humans can produce thousands of different compounds (VOCs) from the skin alone.

The human and / or mammalian nose is one of the most sensitive organs in the body, capable of distinguishing at least 10,000 different VOCs (eg, smells). Artificial VOCs sensors are very limited and are usually based on conductive elements coated / coated with organic ligands. Each type of organic ligand can be configured to react / connect to different types of VOCs or families of VOCs, but can also react / connect to other VOCs to some extent. Therefore, such sensors may be more sensitive to a particular list of VOCs or VOCs (eg, a family of VOCs). A list of known VOCs sensors includes chemical resistors, metal oxide sensors (MOS), catalytic near-infrared sensors, photoionization detectors (PIDs), UVdoas \ IR open path sensors, and portable gas chromatography mass spectrometers (GS-). MS), electrochemical and the like can be included.

However, the odor of the subject changes dramatically within a day and over a long period of time. In addition, there is no standard scale for measuring VOCs (eg, scents). Therefore, it is practically impossible to recognize a subject based on a single VOC measurement derived from the subject, as can be done by other biometric methods.

Therefore, in order to be included in the biometric recognition method, it is necessary to develop a system and a method that can utilize VOCs derived from the subject. Such biometrics can be used not only to identify an individual, but also to identify the individual's condition, such as a medical condition, mental condition, or even the general health of the individual.

Some aspects of the invention may relate to methods of determining the state of a subject based on the volatile organic compounds (VOCs) in the gas phase that are derived from the subject. In some embodiments, the method involves receiving a set of sensor signals from one or more sensors in response to exposing one or more sensors to a sample of VOCs, and the said sensor signals. To classify VOC samples based on extracting one or more feature values from the set and one or more extracted feature values that correlate with one or more states of the subject. Receiving a classification model trained in, and associating one or more extracted feature values received from the set of sensor signals with one or more classifications of the classification model, said association. It can include determining the condition of the subject based on.

In some embodiments, the condition can be at least one of the medical condition of the subject, the mental state of the subject, the identity of the subject, and the general health of the subject. In some embodiments, the method is based on receiving additional data, correlating the received additional data with one or more classifications of the classification model, and associating the additional data. , Determining the condition of the subject, and can be further included. In some embodiments, the additional data may include sample-related data. In some embodiments, the sample-related data can include at least one of humidity level, temperature, geographic location from which the sample was taken, and date and time. In some embodiments, the additional data can include subject data. In some embodiments, subject-related data can include at least one of gender, age, medical condition, ethnicity, culture, lifestyle, and diet. In some embodiments, the subject-related data can include data related to a particular sample taken from the subject.

In some embodiments, VOCs collect absorption materials attached to at least one subject, absorption materials attached to a device carried by at least one subject, and VOCs that evaporate from at least one subject. It can be collected in at least one of the containers for which it is used. In some embodiments, the at least one subject can be a mammal. In some embodiments, the VOCs can include VOCs contained in at least one of the subject's urine, the subject's sweat, and the subject's saliva.

In some embodiments, the subject is a human, and the method further comprises collecting VOCs samples and extracting VOCs from the samples when a human uses the toilet and using one or more sensors. Exposure to extracted VOCs can be included.

In some embodiments, the at least one subject is a female mammal and the condition is fertility. In some embodiments, VOCs can include VOCs contained in at least one of female mammal urine, sweat, saliva. In some embodiments, VOCs can include VOCs, which are found in at least one of the skin and hair of a female mammal. In some embodiments, at least one subject can include at least two humans, the condition of which is an opportunity for successful matching. In some embodiments, the classification model comprises a pair of feature values received from a pair of humans having at least one indication that the match was successful. In some embodiments, the at least one indication can include at least one of a period of time beyond a predetermined period, a long-lasting relationship, a number of children, a reported affection and a reported sexual attraction.

In some embodiments, the at least one subject is a human baby and the condition can be general health. In some embodiments, VOCs can include VOCs contained in at least one of urine and feces. In some embodiments, the at least one subject is a mammal and the condition is the identity of the mammal. In some embodiments, the method further uses the initial signal to receive one or more initial signals from one or more sensors, to associate the initial signal as an ambient background signal, and to use the initial signal. It can further include filtering background noise from the set of sensor signals.

Some aspects of the invention may relate to systems for determining the state of a subject based on the volatile organic compounds (VOCs) in the gas phase derived from the subject, the system being at least one. One or more VOCs configured to detect VOCs derived from a subject and one or more sensors respond to exposure to a sample of VOCs by setting the set of sensor signals to 1. Received from one or more sensors, extracted one or more feature values from the sensor signals, and based on one or more extracted feature values correlated with one or more states of the subject. Receives a classification model trained to classify VOCs samples and correlates and correlates one or more extracted features received from a set of sensor signals with one or more classifications of the classification model. It can include a controller configured to determine the condition of the subject based on.

In some embodiments, the system can further include a chamber for holding one or more sensors and a gas circulation system for directing the VOC of the gas phase to one or more sensors. .. In some embodiments, the gas circulation system can include a fan, a pump, one or more gas monitoring sensors, and at least one of one or more valves. In some embodiments, the system can further include a replay device for replaying one or more sensors. In some embodiments, the regeneration device can include at least one of a heating element, a vacuum pump, and a gas stream.

In some embodiments, the system may further include one or more additional sensors for detecting the condition of at least one subject. In some embodiments, the system can further include a holder for holding an absorbent material carrying VOCs collected from at least one subject. In some embodiments, the absorbent material can include an absorbent material configured to absorb VOCs from the subject. In some embodiments, the sensor is one or more chemical resistors, metal oxide sensors (MOS), catalysts, including metal nanoparticles coated with organic ligands shells. Near infrared sensors, photoionization detectors (PIDs), IR open path sensors, portable gas chromatography mass spectrometers (GC-MS), electrochemical sensors and the like can be included.

In some embodiments, the controller can be configured to perform any one of the methods described above. Some aspects of the invention can be associated with methods of training a classification model to determine the condition of a subject. This method
a. Receiving a set of sensor signals from one or more sensors in response to exposing one or more sensors to a sample of VOCs from a subject.
b. Extracting one or more feature values from the sensor signal,
c. Tagging one or more feature values with a classification associated with at least one known condition of the subject,
d. Repeating steps (a)-(c) with different samples to train the classification model,
Can be included.

In some embodiments, the condition can be at least one of the medical condition of the subject, the mental state of the subject, the identity of the subject, and the general health of the subject. In some embodiments, the method can further include receiving additional data, tagging the additional data with a classification associated with a known state of the subject. In some embodiments, the additional data may include data associated with the sample. In some embodiments, the data associated with the sample can include at least one of humidity level, temperature, geographic location where the sample was taken, time, and date. In some embodiments, the additional data can include subject data. In some embodiments, the subject-related data can include at least one of gender, age, medical condition, ethnicity, culture, lifestyle, and diet. In some embodiments, the data associated with the subject can include data associated with a particular sample taken from the subject.

In some embodiments, VOCs collect absorption material attached to at least one subject, absorption material attached to a device carried by at least one subject, and VOCs evaporating from at least one subject. Can be collected by at least one of the containers for. In some embodiments, the method further comprises receiving one or more initial signals from one or more sensors, associating the initial signal as an ambient background signal, using the initial signal, and using the sensor. From a set of signals, filtering background noise can be included.

Some aspects of the invention can be associated with a system for training a classification model to determine the condition of a subject, such that the system detects VOCs from at least one subject. One or more VOCs, storage units, and
e. Receiving a set of sensor signals from one or more sensors in response to exposing one or more sensors to a sample of VOCs from the subject,
f. Extract one or more feature values from the sensor signal and
g. One or more feature values are tagged with a classification associated with at least one known condition of the subject.
h. Repeat steps (a)-(e) with different samples to train the classification model,
i. It can include a controller configured to store the trained classification model in a storage unit.

In some embodiments, the controller can be further configured to receive at least one known state of the subject per sample. In some embodiments, the system can further include a user interface, and the controller can be configured to receive at least one known state from the user interface. In some embodiments, the system may further include at least one additional sensor, and the controller is configured to receive at least one known state from the signal received from the additional sensor. In some embodiments, the additional signal can indicate at least one state. In some embodiments, the controller can be configured to perform any one of the methods described above. The subject matter considered to be the present invention is specifically pointed out and explicitly asserted in the conclusions of this specification. However, the present invention can be best understood with reference to the accompanying drawings and the following detailed description, both in terms of configuration and method of operation, along with its purpose, features and advantages. For the sake of simplicity and clarity, it should be understood that the elements shown in the figure are not necessarily drawn to a constant scale. For example, for clarity, the dimensions of some elements may be exaggerated relative to other elements. In addition, reference numbers may be repeated between figures to indicate corresponding or similar elements, where appropriate.

FIG. 5 is a diagram of a system for determining the state of a subject based on VOCs, according to some embodiments of the present invention. FIG. 6 is a block diagram of a computing device according to some embodiments of the present invention. FIG. 5 is a flowchart of a method of operating the system of FIG. 1A according to some embodiments of the present invention. FIG. 5 is a diagram of a sensor according to some embodiments of the present invention. FIG. 5 is a diagram of conductive nanoparticles coated with an organic ligand according to some embodiments of the present invention. FIG. 5 is a graph showing a signal received from the sensor of FIG. 2A as a function of time, according to some embodiments of the present invention. FIG. 5 is a diagram of a system for determining the condition of a subject based on VOCs according to some embodiments of the present invention. FIG. 5 is a diagram of a system for determining the state of a subject based on VOCs, according to some embodiments of the present invention. FIG. 5 is a diagram of a pad containing an absorbent material for collecting VOCs derived from cattle, according to some embodiments of the present invention. FIG. 5 is a diagram of a pad containing an absorbent material for collecting VOCs of human origin, according to some embodiments of the present invention. It is a flowchart of the method for determining the state of a subject based on VOCs according to some embodiments of the present invention. It is a flowchart of a method of training a classification model to determine the condition of a subject according to some embodiments of the present invention. Eight graphs showing the signal received from the sensor are shown according to some embodiments of the present invention.

The following detailed description provides many specific details to provide a complete understanding of the present invention. However, it will be appreciated by those skilled in the art that the present invention may be practiced without these particular details. In other examples, well-known methods, procedures, and components, modules, units, and / or circuits are not described in detail so as not to obscure the invention. Some features or elements described for one embodiment can be combined with features or elements described for other embodiments. For clarity, descriptions of the same or similar features or elements may not be repeated. Embodiments of the present invention are not limited in this respect, but for example, "processing", "computing", "calculating", "determination", "establishment", "analysis", "check", etc. As the amount of physical (eg, electronic) in a computer, computing platform, computing system, or computer's registers and / or memory that manipulates and / or transforms data represented as physical (eg, electronic). The represented data is similarly represented as physical quantities in other information non-temporary storage media that can store computer registers and / or memory or operations and / or instructions for executing processes. It may also refer to the behavior and / or process of other electronic computing devices that manipulate and / or convert to other data. Embodiments of the present invention are not limited in this regard, but the terms "plurality" and "plurality" as used herein may include, for example, "plurality" or "plurality". The term "plurality" or "plurality" may be used throughout the specification to describe two or more components, devices, elements, units, parameters, and the like. The term set can include one or more items when used herein. Unless explicitly stated, embodiments of the methods described herein are not constrained to any particular order or sequence. Moreover, some of the embodiments or elements of the described method can occur or be performed at the same time, at the same time, or at the same time.

Systems and methods according to some embodiments of the present invention can allow the use of artificial scent sensors to detect changes in the condition of a subject or even the identity of a subject. Such sensors may be configured to detect VOCs in the gas phase. The system can use the signals generated by these sensors to determine the state. The odor of a subject (eg, human or mammal) is very sensitive to changes in the condition of the subject, and a single measurement obtained from the subject, even within a day, is any recognition / diagnosis. It cannot be the basis of systems and methods. In addition, there are standard methods for measuring VOCs, which are highly dependent on the type and number of VOC sensors used. Therefore, systems and methods according to some embodiments are artificial intelligence (AI) for further use to train a classification model and further use to classify or tag new samples taken from one subject or another. ) And machine learning (ML) techniques can be used to study and analyze signals received from multiple samples taken from each subject or group of subjects. The classification model can be used to determine the condition of the subject.

As used herein, the term "subject" can include any organism that produces odors (eg, VOCs). Subjects can include humans, mammals (eg, livestock) or any other animal. As used herein, the term "state" can refer to any condition, state, or parameter associated with an organism, eg, the medical condition of a subject, of a subject. It is associated with the evaporation of VOCs from an organism, such as mental state, subject identity, successful matching between two subjects, and general health of the subject.

As used herein, the term "volatile organic compound (VOC)" may include any organic compound that can evaporate from or be caused by the subject. VOCs can be derived from the skin or hair of a subject, such as from urine, feces, saliva, etc. (eg, evaporate by sweat).

See FIG. 1A, which is a diagram of a system 10 for determining the state of a subject based on VOCs in the gas phase resulting from the subject, according to some embodiments of the present invention. In some embodiments, the system 10 may be for training a classification model (eg, classification model 128 shown in FIG. 1B) to determine the condition of the subject. System 10 includes one or more VOC sensors 50 configured to detect VOCs emitted by at least one subject and controller 105 of computing device 100 (illustrated and discussed in FIG. 1B). And can be included. One or more sensors 50 may include any sensor configured to generate a signal (eg, an electrical signal) when exposed to VOCs in the gas phase. For example, one or more sensors 50 can include one or more chemical resistors, including metal nanoparticles coated with an organic ligand shell, as discussed in detail with respect to FIGS. 2A-2C. In another example, the one or more VOCs sensors 50 are a metal oxide sensor (MOS), a catalytic near infrared sensor, a photoionization detector (PID), an IR open path sensor, a portable gas chromatography mass spectrometer (GC-). MS), at least one such as an electrochemical sensor can be included.

In some embodiments, the system 10 may further include a chamber 40 for holding one or more sensors 50. The chamber 40 can be configured to hold the VOCs 42 in the gas phase while exposing one or more sensors 50 of the VOCs 42. The chamber 40 may further include one or more additional sensors 60 for sensing the environment and gas flow within the chamber 40, such as a thermometer, barometer, humidity sensor, flow meter, etc. In some embodiments, the chamber 40 can further include a regeneration device 70 for one or more sensors 50. The regenerator 70 can include a heating element for heating one or more sensors 50, thus evaporating VOCs captured by one or more sensors 50. In some embodiments, the regenerator 70 may include a vacuum pump to cause evaporation of VOCs by quasi-atmospheric pressure. In some embodiments, the regenerator 70 has a gas stream (eg, clean air or a controlled amount of VOC) to cause flashing of VOCs from the surface of one or more sensors 50. It may contain any other gas).

In some embodiments, the system 10 may further include a gas circulation system 30 for directing the VOC of the gas phase to one or more sensors 50 contained in the chamber 40. The gas circulation system 30 can include a fan 33, a pump 33, one or more gas monitoring sensors 60, one or more valves 34 and 35, a filter 31, a manifold 32, a pipe 37, and the like. The components of the gas circulation system 30 shown in FIG. 1A are provided by way of example only, indicating that the gas circulation system 30 according to an embodiment of the present invention may include some, all or more of the components shown. Those skilled in the art should understand.

In some embodiments, the system 10 holds at least one holder (not shown) for holding an absorbent material carrying VOCs collected from at least one subject, as described with respect to FIGS. 5 and 6. ) Can be included or fluid connected.

It is a schematic block diagram of an example of a computing device according to some embodiments of the present invention. See FIG. 1B. The computing device 100 is a controller or processor 105 (eg, central processing unit processor (CPU), graphics processing unit (GPU), chip, cloud-based computing service or any suitable computing or computing device), operating. Communicate with remote devices via a communication network such as system 115, memory 120, executable code 125, storage 130, input device 135 (eg keyboard or touch screen), and output device 140 (eg display), eg the Internet. Communication unit 145 for the purpose (eg, cellular transmitter or modem, Wi-Fi communication unit, etc.) can be included. The controller 105 can be configured to execute program code for performing the operations described herein. The system described herein can include one or more computing devices (s) 100.

The operating system 115 schedules the coordination, scheduling, arbitration, monitoring, control, or other management of the operation of the computing device 100, such as the execution of a software program, so that the software program or other modules or units can communicate. It may be, or may include, any code segment (eg, similar to the executable code 125 described herein) that is designed and / or configured to perform tasks that include doing so.

The memory 120 includes, for example, a random access memory (RAM), a read-only memory (ROM), a dynamic RAM (DRAM), a synchronous DRAM (SD-RAM), a double data rate (DDR) memory chip, a flash memory, and a volatile memory. It can be or include non-volatile memory, cache memory, buffers, short-term memory units, long-term memory units, or other suitable memory units, or storage units. The memory 120 may be a plurality of, and in some cases different memory units, or may include them. The memory 120 can be a non-transitory readable medium of a computer or processor, or a non-temporary storage medium of a computer such as RAM.

Execution code 125 can be any executable code, such as an application, program, process, task or script. Execution code 125 can be executed by controller 105 under the control of operating system 115. For example, executable code 125 may be a software application that performs a method as further described herein, eg, a method of determining a subject's condition based on the VOC of the gas phase derived from the subject. .. In yet another example, code 125 may include a software application that implements a method of training classification model 128 according to some embodiments of the invention. For clarity, a single item of executable code 125 is shown in FIG. 1B, but a system according to an embodiment of the invention can be stored in memory 120 and is described in Controller 105. It may include a plurality of executable code segments similar to the executable code 125 that causes the method described in the document to be performed.

The memory 120 may further include a classification model 128 used in determining the condition of the subject according to some embodiments of the present invention. A method of training classification model 128 is disclosed with respect to the flowchart of FIG.

The storage 130 can be or can be, for example, a hard disk drive, a universal serial bus (USB) device, or other suitable removable and / or fixed storage unit. In some embodiments, the storage 10 can be a cloud-based storing service that communicates with the system 10 over the Internet. In some embodiments, some of the components shown in FIG. 1B can be omitted. For example, the memory 120 can be a non-volatile memory having the storage capacity of the storage 130. Thus, although illustrated as a separate component, the storage 130 can be embedded or included in the memory 120.

The input device 135 can be or include a keyboard, touch screen or pad, one or more sensors, or any other or additional suitable input device. Any suitable number of input devices 135 can be operably connected to the computing device 100. The output device 140 can include one or more displays or monitors and / or any other suitable output device. Any suitable number of devices 140 can be operably connected to the computing device 100. Any applicable input / output (I / O) device can be connected to the computing device 100 as shown in blocks 135 and 140. For example, a wired or wireless network interface card (NIC), a universal serial bus (USB) device or an external hard drive can be included in the input device 135 and / or the output device 140.

Embodiments of the invention, for example, encode, include, or store instructions that execute the methods disclosed herein, eg, computer-executable instructions, when executed by a processor or controller, of a computer or processor. It may include non-transitory readable media or articles such as non-temporary storage media of a computer or processor, such as a memory, disk drive, or USB flash memory. For example, the article can include a storage medium such as memory 120, computer executable instructions such as executable code 125, and a controller such as controller 105. Such non-transitory computer-readable media, eg, when executed by a processor or controller, encode, contain, or store computer-executable instructions that perform the methods disclosed herein, eg, memory. It can be a disk drive or a USB flash memory. Storage media are, but are not limited to, read-only memory (ROM) and / or random access memory (RAM), flash memory, electrically erasable programmable read-only memory (EEPROMs), or programmable storage. It can include any type of disk, including semiconductor devices such as media containing any type of medium suitable for storing electronic instructions, including devices. For example, in some embodiments, the memory 120 is a non-temporary machine-readable medium.

Systems according to embodiments of the present invention are limited to, but are not limited to, a plurality of central processing units (CPUs), graphics processing units (GPUs), or any other suitable, versatile or specific processor or controller (eg, for example. A controller similar to the controller 105), a plurality of input units, a plurality of output units, a plurality of memory units, and a plurality of storage units can be included. The system further includes other suitable hardware and / or software components.

In some embodiments, the system may be, or may include, for example, a personal computer, desktop computer, laptop computer, workstation, server computer, network device, or any other suitable computing device. it can. In some embodiments, at least some of the components of the computing device 100 can be assembled on a printed circuit board (PCB) assembled into a system such as system 10. In some embodiments, the system 10 further includes a power supply 101 (shown in FIG. 1A) that powers at least some of the components of the system 10, such as the computing device 100, the sensor 50, the sensor 60, and the like. be able to. In some embodiments, the power supply 101 can be assembled on a PCB.

A flowchart showing an example for operating various components of the system 10 is shown in FIG. 1C. Samples of VOCs can be introduced into the system 10 to receive signals from one or more sensors 50, so the sampling cycle can be started in box 150. In some embodiments, the controller 105 can control the fan 33 to generate an air flow capable of carrying VOCs samples. VOCs samples can be received directly from the air near the system 10 or collected from an absorbent material (eg, in the form of a ped) placed in a holder near the entrance to the filler 31. it can. The airflow generated by the fan 33 filters the sampled VOC-containing air through the filter 31 from particles and dust that can impair measurements made by one or more sensors 50. can do. The airflow can then be introduced into the manifold 23. In order to introduce the air carrying the VOC into the chamber 40, the valve 34 is closed (box 151), the valve 35 is opened, and the chamber 40 is operated while pumping air from the chamber 40 (box 153) by operating the pump 36. In addition, a vacuum can be formed. By closing the valve 35 and the pump 36 and opening the valve 34, the air carrying the VOCs sample can be introduced into the chamber 40 following the closing of the valve 34 (box 154).

In some embodiments, before introducing air carrying VOCs samples, a heating system such as that included in the regeneration system 70 is operated to create a controlled environment (in box 160) and / or sensor 50. Can be washed. In some embodiments, the one or more sensors 50 can be exposed to VOCs in the air for a predetermined time and one or more signals can be received by the controller 105 (box 155). Following detection, valve 35 (box 156) and pump 36 (box 157) can be reactivated to pump up and clean chamber 40 (box 158). In some embodiments, pumping air from the chamber 40 can also regenerate one or more sensors 50 that are washed from the previous VOC before introducing additional VOC samples (box 159). ..

In some embodiments, the system 10 can be used to apply different operating methods. For example, a sensor signal can be generated by a sensor 50 that is exposed to the flow of VOCs, leaving both valves 34 and 35 open. In such an operating method, both the fan 33 and the pump 37 can constantly supply the air flow carrying the VOCs to the chamber 40.

In some embodiments, the system 10 can be housed in a housing 20. Examples of different housing structures are illustrated in FIGS. 3 and 4. In some embodiments, the housing 20 may include an inlet (eg, in the form of a mouthpiece) that is inserted into the mouth of the subject or configured to receive a breath of air from the subject. it can. The intake can be arranged in front of the filter 31. In some embodiments, air breathing can include VOCs from the subject's mouth and digestive system.

Next, reference is made to FIG. 2A, which is a diagram of an example of a chemical sensor 50 according to some embodiments of the present invention. The chemical sensor 50 can be a resistor that can change its resistance when exposed to chemicals in general, especially VOCs in the gas phase. The chemical resistor is made of a sensing element 52 made of metal nanoparticles coated with an organic ligand shell (shown in FIG. 2B) and connecting the element 52 to the outside world (eg, made of Au or Pt). It may include metal electrodes. The detection element 52 and the metal electrode may be arranged on a substrate 54 such as a semiconductor wafer having a separation layer made of glass, plastic or the like.

The detection element 52 is a metal or alloy such as Au, Pt, Pd, Ag, Ni, Co, Cu, Al, Au / Ag, Au / Cu, Au / Ag / Cu, Au / Pt, Au / Pd, Au. It may include metal nanoparticle cores made from / Ag / Cu / Pd, Pt / Rh, Ni / Co, and / or Pt / Ni / Fe. The metal nanoparticle core can be coated with an organic ligand. Different organic ligands can be selected to detect different VOCs or families of VOCs. For example, the shell of an organic ligand is an alkyl thiol with a C3-C24 chain, a co-functionalized alkanethiolate, an allenthiolate, a (g-mercaptopropyl) trimethyloxysilane, a dialkyldisulfide, a xanthate, an oligonucleotide, a polynucleotide. , Peptides, proteins, enzymes, polysaccharides, phospholipids, etc., can be composed of thiol (sulfide) -bonded groups (to the metal core).

In some embodiments, the system 10 can include an array (eg, plural) of sensors 50. For example, such an array (because some organic ligands can detect multiple types of VOCs (eg, families of VOCs)), for a particular type of VOC, or for a particular type of VOC. It may include various sensors 50, each (or some) of which may be designed to be more sensitive than other VOCs (eg, by choosing the type of organic ligand). Therefore, the array 50 of sensors can be configured to detect a plurality of VOCs.

Here, refer to the graph shown in FIG. 2C, which shows an example of signals received from sensors such as the sensor 50 at different stages of operation of the system 10. Such sensor signals are generated by the sensor 50 and sent to the controller 105 for further analysis. First, when the system is in ambient conditions, there is a small amount of VOCs (eg, there is always an amount of VOCs in the air) in chamber 50 (eg, compared to the amount being detected) (1). , Almost no signal (eg resistance (ohm)) can be detected. When air carrying VOCs from the sample is introduced into the chamber 40 and exposed to the sensor 50, the resistance can change (eg, increase, illustration, decrease, alternation, etc.) (2). At the end of the detection / exposure time (3) the air carrying the VOC is expelled from the chamber 50 (4) and the signal is reduced to a minimum (5) when the system returns to ambient conditions.

Here, refer to FIG. 3, which is a diagram of a system 10 for determining the condition of a subject based on a VOC configured to be assembled in a toilet. In some embodiments, the subject may be a human and VOCs can be collected when the human uses the toilet. Such a system 10 can be configured to detect the presence of a human being in the toilet, for example, received from an external sensor such as a motion detector. When a human enters the toilet, a detection sequence (eg, box 151-159 in FIG. 1C) can be triggered. In some embodiments, the detection sequence may be triggered at a predetermined time after the human leaves the toilet or after the human enters the toilet. Evaporated VOC42 from urine and / or human-derived feces enters column 25, is pumped, and flows towards a sensor array containing two or more sensors 50. The housing 20 is attached to a commercial toilet and is configured to allow VOC collection from near the system 10.

Next, refer to FIG. 4, which is a diagram of a system 10 for determining the state of a subject based on VOCs, which is assembled or configured to be contained in a garbage bag 5. The garbage bag 5 may be configured to collect, for example, one or more dippers, sanitary pads, and the like. The floss 20 can be configured to be airtightly inserted into the hole of the garbage bag 5. Upon closing the bag 5, the user can start or trigger the detection sequence (eg, box 151-159 in FIG. 1C). In some embodiments, in the configuration shown in FIG. 4, the array of sensors 50 is located in a portion of the system 10 inserted inside the plastic bag 5, and the gas circulation system (not shown) is the bag 5. It is arranged in a part of the system 10 which is arranged on the outside.

Next, refer to FIG. 5, which is a diagram of a pad 16 made of absorbent material 15 for collecting VOCs from mammals, such as livestock such as cows, horses, and ships. In some embodiments, the absorbent material can be included in a pad 16 attached to the mammal by attachment means 17 (eg, belt, sticker, etc.). In some embodiments, the pad 15 is placed in various locations, such as on the back (under the tail as shown), on the back, near the briskets or vagina (of female mammals), on the forehead, and the like. It can be configured to be attached to a mammal. The absorbent material 15 can be any material configured to absorb VOCs, such as cotton, polymeric sponge, polymeric rubber, or any other suitable material. The absorbent material 15 can be further configured to release VOCs when exposed to airflow, for example at the inlet to the system 10 (eg near the filter 31). According to some embodiments, the pad 16 may be located near the air intake of the system 10 so that the VOCs absorbed by the absorbent material can be released and during the operation of the fan 33 and / or the pump 37. , Enter the chamber 40.

Next, with reference to FIG. 6, an absorbent material 15 contained in the pad for collecting VOCs from humans is shown. In some embodiments, the absorbent material 15 may be included in a human-worn bracelet 18 as illustrated. In some embodiments, the absorbent material 15 may be integrated into a wearable device (eg, watch) or garment (eg, hat, scarf, sweatband, etc.). According to some embodiments, the absorbent material 15 may be attached to a human by any other method, such as using a sticker. According to some embodiments, the absorbent material 15 may be attached to a device or accessory that is regularly carried by a human, such as a mobile phone, tablet computer, or the like.

In some embodiments, the system 10 may include a holder (not shown) for holding the absorbent material 15 at the inlet to the system 10 (eg, in front of the filter 31). Therefore, as disclosed with respect to FIGS. 1A-1C, when the gas circulation system 30 circulates air through the filter 31, the VOCs captured by the absorbent material 15 are disclosed with respect to FIGS. 3 and 4. It evaporates into the system 10 (eg, via the filter 31 and manifold 32) and is exposed to the sensor 50. As will be appreciated by those skilled in the art, the configurations shown in FIGS. 3-6 are merely exemplary and the present invention is not limited to these examples.

Next, refer to FIG. 7, which is a flowchart of a method for determining the state of the subject based on the VOC in the gas phase generated from the subject according to some embodiments of the present invention. The method of FIG. 7 can be performed by a controller such as controller 105 of system 10 or by any other suitable controller. In step 710, a set of sensor signals can be received from one or more sensors in response to exposing one or more sensors to a sample of VOCs. For example, a sample containing VOCs from one or more subjects (eg, humans or mammals) may be introduced into the circulation system 30 of system 10. For example, the sample may include air collected from near the system 10 assembled in the toilet, as shown in FIG. In another example, VOCs may be collected from a garbage bag 5 holding a dipper, as shown in FIG. In yet another example, VOCs can be collected from the absorbent material 15 described herein with respect to FIGS. 5 and 6.

The VOCs contained in the sample are introduced into chamber 40 (eg, VOC42) and detected by one or more sensors 50 as described herein with respect to FIGS. 1C and 2A-2C. In some embodiments, after exposure, a series of sensor signals may be received by controller 105. Such a set may include one or more sensor signals. An example of a set of eight sensor signals from the eight sensors 50 is shown in FIG. In the example shown in FIG. 9, each signal was received from a different type of VOC-sensitive sensor 50.

In some embodiments, the VOC measurement cannot be scaled, so the sensor signal itself may not be sufficient to classify the sample. Therefore, it is possible to analyze one or more sensor signals in the set. In step 720, one or more feature values may be extracted from the set of sensor signals. For example, each sensor signal can be analyzed and one or more feature values can be extracted. As used herein, feature values are any mathematical value that can be derived from the analysis of the signal, such as mean, maximum, minimum, first-order differential, second-order differential, signal-to-noise ratio, gradient. It can be defined as a gradient, a decreasing gradient, a rising time, an overshoot value with respect to a steady state value, vibration damping in time, a vibration frequency, and the like. Therefore, each signal can be associated with one or more feature values that are further evaluated by controller 105.

In step 730, a classification model (eg, classification model 128) can be received, which is based on one or more extracted feature values that correlate with one or more states of the subject. Can be trained to classify samples. The classification model 128 is stored in storage 130 or memory 120 and can be received from there. Methods for training and creating such classification models are disclosed and discussed with respect to FIG.

In step 740, one or more extracted features received from the set of sensor signals may be associated with one or more classes of the classification model. In some embodiments, each class may be associated with the condition of one or more subjects, and thus by identifying the classes to which one or more extracted features may be associated. The state of the specimen can be determined in step 750.

In some embodiments, the condition includes at least one such as the medical condition of the subject, the mental condition of the subject, the identity of the subject, the general health condition of the subject, and the like. For example, the subject can be a human using a toilet that includes system 10, as shown in FIG. The VOCs collected when a human uses the toilet can be detected by one or more sensors 50, and the set of signals can be analyzed by the controller 105. For example, controller 105 has at least one feature or feature value extracted into a class that correlates with human medical conditions such as diabetes, cystitis, dehydration, vitamin deficiency, influenza, unbalanced diet, constipation diarrhea, internal intake of foreign bodies, etc. Groups can be associated. In some embodiments, the subject may be a female human and the condition may include fertility that can be sensed by VOCs derived from the female human urine.

In another example, one or more subjects can include any female mammal and the condition can be fertility. VOCs may be collected using absorbent materials such as the absorbent material 15 shown in FIGS. 5 and 6. In some embodiments, when the female mammal is ovulating, the VOCs in the urine of the female mammal are altered. These VOCs can be detected using the disclosed methods and can be used to determine the hormonal cycle of female mammals.

In yet another example, one or more subjects can include at least two humans, and the condition may be a chance for successful matching. For example, VOC samples taken from a couple (shown in Figure 6) or one person can be used to see if a couple or two individuals in a group are likely to succeed in matching. it can. Successful matching between couples can be defined as matching or pairing of people who have at least one positive sign that the relationship is well established. In some embodiments, the classification model 128 can include one or more pairs of feature values received from a pair of humans having at least one indication that the match was successful. In some embodiments, the at least one indication can include at least one of a relationship that lasts longer than a predetermined period of time, the number of children, the reported affection and the reported sexual attraction.

In some embodiments, additional data may be included in the classification model 128 and may be associated with the class of the model. For example, if additional data matching is successful: Gender, age, sexual orientation, ethnicity, culture, lifestyle, diet, etc. when classifying pairs that are likely to be successful: Can be considered. This type of data may include data related to the subject, which may improve the accuracy of the determination of the likelihood of successful matching. In some embodiments, additional subject-related data such as medical condition, mental state and general health may be further included and associated with one or more classes of the classification model. In some embodiments, subject-related data may be received from a user (eg, subject, caregiver, etc.) using a user interface, eg, input device 135. In some embodiments, the subject-related data uses an application that runs on a mobile device that communicates with the computing device 100, for example, the data can be uploaded to the controller 105 (eg, via the Internet). It can then be provided to the system 10 by a caregiver (eg, a parent).

In some embodiments, the subject-related data may include data related to a particular sample taken from the subject. For example, if the subject was a baby and the sample was taken from the baby's dipper, as illustrated and described with respect to FIG. 4, the data associated with the subject wore the baby's dipper. It can include time, time to sleep with a dipper, and so on. Such data may be provided to the system 10 by a caregiver (eg, a parent), for example, using an application running on a mobile device that can upload the data to the controller 105.

In some embodiments, the additional data may include sample-related data. Such sample-related data can include environmental conditions from which the sample was taken, eg, received from one or more sensors 70. For example, sample-related data may include the humidity level within chamber 40, the temperature or ambient temperature within chamber 40, the geographical location where the sample was taken, the date and time when the sample was taken, and the like.

In some embodiments, parameters such as geographic location and date and time can affect the type and amount of VOCs generated from the subject. For example, VOCs may contain VOCs derived from sweat because warm places sweat more often than cold places. Similarly, dates (such as the season and the exact weather for the day) and time can also affect VOCs. In some embodiments, the method can further comprise receiving one or more initial signals from one or more sensors 50 when the sensors are not exposed to VOC samples. The initial signal can be associated as an ambient background signal that can be used to filter background noise from a set of sensor signals using the initial signal.

In some embodiments, the method of FIG. 7 may be used to identify an object. Therefore, the condition may be the identity of the subject. In some embodiments, the classification model 128 can be trained to identify features typical of a particular subject, regardless of changes in subject location, diet, medical condition, and the like. Such a training method will be described below with respect to the method of FIG.

In some embodiments, the controller 105 may also be configured to display to the subject or user in relation to the commercial data of the subject associated with the determined state. For example, the controller 105 can be configured to upload data related to dippers, baby-related commercials, to a parent's mobile device. In another example, controller 105 can display commercial data related to a romantic hotel or restaurant to two individuals after successfully matching the two individuals.

Next, refer to FIG. 8, which is a flowchart of a method of training the classification model 128 according to some embodiments of the present invention. The method of FIG. 8 may be performed by a controller such as controller 105 of system 10 or by any other suitable controller. Steps 810 and 820 can be substantially the same as steps 710 and 720 of the method of FIG. In step 830, one or more feature values can be tagged with a class associated with at least one known condition of the subject. In some embodiments, known conditions are performed from the user or multiple users via a user interface, eg, on an input device 135, or a mobile device associated with the user and communicating with the computing device 100. Can be received from the application. For example, a subject known to have an abnormal medical condition, such as diabetes, can be provided with a sample that is tested and sensed by System 10. Therefore, one or more feature values extracted from the provided sample can be tagged with the class "have diabetes".

In some embodiments, additional data related to the subject is also received and tagged with one or more feature values, such as age, gender, lifestyle, weight, height, ethnicity, diet, geographic location, etc. Can be done. For example, a class tagged with a sample provided from a diabetic subject may further include the following tagging: male, normal BMI, Asian, US resident, 60-70 years old, smoking, physical activity. Not performed. In step 840, steps 810-830 may be repeated with new samples.

In some embodiments, subject-related data can be received from additional sensors, such as sensors that can directly measure the chemical composition of urine samples. Such a sensor can provide, for example, the level of fertilizing hormone in the urine and can provide a direct indicator of the fertility of a woman who provides a urine sample. Additional sensors may include a thermometer, an oxygen saturation sensor, a blood pressure sensor, a heart rate sensor, etc. for measuring the body temperature of the subject. In some embodiments, the relevant data may include the subject's healthcare record provided by the subject's healthcare provider. The medical record can be received by the controller 105 via the Internet by forming an external database related to the medical provider.

In some embodiments, additional data associated with the sample, or the state in which the sample is perceived, is also formed from a sensor, such as the sensor 70, as disclosed herein above, for example with respect to the method of FIG. obtain. All data collected is associated with and tagged with a class in the classification model. For example, the class may include a human female aged 30-40 who has problems with overweight and infertility.

In some embodiments, the controller 105 may be configured to receive feature values extracted from a sample taken from a "control group". In some embodiments, classification model 128 has similar characteristics, but an additional group of subjects who do not have a known condition, eg, overweight 30-40 years old without fertility issues. It may further include samples received from human females. In some embodiments, the controller 105 sets the feature values extracted from the additional target group with the classified target group in order to eliminate similar feature values in both groups due to similar characteristics. By comparison, only the class can leave characteristic values due to known medical conditions.

Examples of training taxonomy model 128 to identify subjects were taken from specific subjects in different conditions, such as different geographic locations, different dates and times, after diet changes, after changes in medical condition, and so on. It can include extracting multiple features from the set of signals associated with each sample. In some embodiments, the classification model may be trained to look for feature values that may be found in most of the samples taken from the subject, regardless of the different conditions in which the samples were taken. These feature values may be tagged with the identity of the subject or may be further used to identify the subject.

In another example, classification model 128 can be trained to determine the likelihood of successful matching between two humans. The training process may collect samples from couples identified as having at least one indicator of successful matching. For example, samples may be collected from couples who have been in a relationship for more than 15 years, couples who have at least two children, couples who report mutual affection, and couples who report mutual attractiveness. Couples are further tagged with additional tags such as heterosexual couples, lesbian couples, homosexual couples, etc., depending on age group, ethnicity, place of residence, and so on. In some embodiments, the classification model 128 may be trained to look for similar features extracted from the signals received from the samples provided by the couple, which may indicate "successful matching". These features are identifiable in all "successfully matched" couples or subgroups. For example, classification model 128 has a relationship that lasts at least 10 years, has two children, is 20-40 years old, and has similar characteristics in signals received from a lesbian couple living in Italy. Can be identified.

In yet another example, the classification model 128 can be trained to determine the general health of the baby based on the sample received from the dipper (as described above with respect to FIG. 4). In some embodiments, the classification model 128 can receive information about the general health of the baby providing the dipper from the caregiver via an application running on a mobile device. For example, each sample from a dipper can be tagged with how many hours the baby sleeps uninterrupted at night, whether it has teeth, and whether the baby suffers from gas, age, gender, diet, etc. .. In some embodiments, classification model 128 identifies similar features of the signal received from a sample given from a 4-7 month old baby so that it grows teeth and sleeps continuously for less than 3 hours. Can be trained. In step 840, the classification model 128 can be stored in memory 120 and / or storage unit 130.

Although the present invention has been illustrated and described here with certain features, those skilled in the art are capable of producing many modifications, substitutions, modifications and equivalents. Therefore, it should be understood that the appended claims are intended to cover all such modifications and modifications contained in the true spirit of the invention.

Various embodiments have been presented. Each of these embodiments can, of course, include features from other embodiments presented, and embodiments not specifically described can include various features described herein.

Claims (48)

In a method of determining the state of a subject based on a volatile organic compound (VOC) in the vapor phase derived from the subject.
A step of receiving a set of sensor signals from the one or more sensors in response to exposing the one or more sensors to a sample of the VOC.
A step of receiving one or more sensors from the set of sensor signals.
A step of receiving a classification model trained to classify a sample of the extracted features correlated with one or more of the subjects.
A step of associating the one or more extracted features received from the set of sensor signals with one or more classifications of the classification model.
A step of determining the state of the subject based on the association,
A method equipped with. The method of claim 1, wherein the condition is at least one of the medical information of the subject, the mental state of the subject, the identity of the subject, and the general health of the subject. Steps to receive additional data and
With the step of associating the received additional data with one or more classifications of the classification model.
The method of claim 1 or 2, further comprising the step of determining the state of the subject based on the association of the additional data. The method of claim 3, wherein the additional data comprises sample-related data. The method of claim 4, wherein the sample-related data comprises at least one of humidity level, temperature, geographical location where the subject was taken, time and date. The method of claim 3, wherein the additional data comprises subject data. The method of claim 6, wherein the subject-related data comprises at least one of gender, age, medical condition, ethnicity, culture, lifestyle and diet. The method according to claim 6, wherein the subject-related data includes data related to a specific sample collected from the subject. The VOCs are an absorbent material attached to the at least one subject, an absorbent material attached to a device carried by the at least one subject, and a container for collecting VOCs evaporating from the at least one subject. The method according to any one of claims 1 to 8, which is collected by at least one of the above. The method according to any one of claims 1 to 9, wherein the at least one subject is a mammal. The method according to claim 10, wherein the VOCs include VOCs contained in at least one of a subject's urine, a subject's sweat, and a subject's saliva. The subject is a human, and the method further comprises
The step of collecting VOCs when the human uses the toilet, and
The method according to any one of claims 1 to 7, further comprising a step of extracting the VOCs from the sample and exposing the one or more sensors to the extracted VOCs. The method of any one of claims 1-9, wherein the at least one subject is a female mammal and the condition is fertility. 13. The method of claim 13, wherein the VOCs comprise VOCs contained in at least one of the female mammal's urine, sweat, and saliva. 13. The method of claim 13, wherein the VOCs comprise VOCs contained in at least one of the skin and hair contained in the female mammal. The method of any one of claims 1-9, wherein the at least one subject comprises at least two humans, wherein the condition is an opportunity for successful matching. 16. The method of claim 16, wherein the classification model comprises one or more pairs of feature values received from a pair of humans having at least one indication with successful matching. 17. The method of claim 17, wherein the at least one indication comprises at least one of a relationship, a number of children, a reported affection, and a reported sexual attraction that lasts for a period of time or longer. The method of any one of claims 1-9, wherein the at least one subject is a human baby and the condition is general health. 19. The method of claim 19, wherein the VOCs comprise VOCs contained in at least one of urine and stool. The method of any one of claims 1-9, wherein the at least one subject is a mammal and the condition is the identity of the mammal. The step of receiving one or more initial signals from the one or more sensors,
With the step of associating the initial signal with the surrounding background signal,
A step of filtering background noise from the set of sensor signals using the initial signal,
The method according to any one of claims 1 to 21, further comprising. In a system that determines the state of a subject based on volatile organic compounds (VOCs) in the gas phase
With one or more VOCs configured to detect VOCs derived from at least one subject,
In response to exposing the one or more sensors to a sample of the VOCs, a set of sensor signals is received from the one or more sensors.
One or more feature values are extracted from the sensor signal,
Received a classification model trained to classify VOCs samples based on the extracted feature values correlated with one or more states of the subject.
The one or more extracted features received from the set of sensor signals are associated with one or more classifications of the classification model.
The state of the subject is determined based on the association.
With a controller configured to
A system equipped with. A chamber holding the one or more sensors,
A gas circulation system for directing VOCs in the gas phase to the one or more sensors.
23. The system according to claim 23. 24. The system of claim 24, wherein the gas circulation system comprises at least one of a fan, a pump, one or more gas monitoring sensors, and one or more valves. The system according to any one of claims 23 to 25, further comprising a reproduction device for reproducing the one or more sensors. 26. The system of claim 26, wherein the regeneration device comprises at least one of a superheating element, a vacuum pump and a gas stream. The system according to any one of claims 23 to 27, further comprising one or more additional sensors for detecting the condition of at least one subject. The system according to any one of claims 23 to 28, further comprising a holder for holding an absorbent material carrying the VOCs collected from the at least one subject. 29. The system of claim 29, wherein the absorbing material comprises an absorbing material configured to absorb VOCs from the subject. The one or more sensors are one or more chemical resistors containing metal nanoparticles coated with an organic ligand shell, a metal oxide sensor (MOS), a catalytic near-infrared sensor, a photoionization detector (PID), IR. The system according to any one of claims 23 to 30, comprising an open path sensor, a portable gas chromatography mass spectrometer (GCV-MS) and an electrochemical sensor. The system according to any one of claims 23 to 31, wherein the controller is configured to perform any one of the methods of claims 1 to 19. In a method of training a classification model to determine the condition of a subject,
a. A step of receiving a set of sensor signals from one or more sensors in response to exposing the one or more sensors to a sample of VOCs derived from the subject.
b. A step of extracting one or more feature values from the sensor signal, and
c. A step of tagging the one or more feature values with a classification associated with at least one known condition of the subject.
d. Steps (a) to (c) are repeated to train the classification model.
Method with. 33. The method of claim 33, wherein the condition is at least one of the medical condition of the subject, the mental state of the subject, the identity of the subject, and the general health of the subject. Steps to receive additional data and
The step of tagging the additional data with the classification associated with the known state of the subject.
33 or 34. 35. The method of claim 35, wherein the additional data comprises sample-related data. The method of claim 30, wherein the sample collection data comprises at least one of humidity level, temperature, geographic location where the sample was taken, time and date. 35. The method of claim 35, wherein the additional data comprises subject-related data. 38. The method of claim 38, wherein the subject-related data comprises at least one of gender, age, medical condition, ethnicity, and diet. 38. The method of claim 38, wherein the subject-related data comprises data associated with a particular sample taken from the subject. The VOCs are of an absorbent material attached to the at least one subject, an absorbent material attached to a device carried by the at least one subject, and a container for collecting VOCs evaporated from the at least one subject. The method according to any one of claims 33 to 40, which is collected by at least one. The step of receiving one or more initial signals from the one or more sensors,
With the step of associating the initial signal with the surrounding background signal,
A step of filtering background noise from the set of sensor signals using the initial signal,
The method according to any one of claims 33 to 41, further comprising. In a system for training a classification model to determine the condition of a subject,
With one or more VOCs configured to detect VOCs derived from at least one subject,
Storage unit and
a. In response to exposing the one or more sensors to the sample VOCs derived from the subject, a set of sensor signals is received from the one or more sensors.
b. One or more feature values are extracted from the sensor signal and
c. The one or more feature values are tagged with the classification associated with at least one known condition of the subject.
d. Steps (a) to (c) are repeated with different models to train the classification model.
e. A controller configured to store the trained classification model in the storage unit.
System with. 43. The system of claim 43, wherein the controller is further configured to receive at least one known state of the subject for each sample. 44. The system of claim 44, further comprising a user interface, wherein the controller is configured to receive at least one known state from the user interface. 44. The system of claim 44, further comprising at least one additional sensor, wherein the controller is configured to receive at least one known state from a signal received from the additional sensor. 46. The system of claim 46, wherein the additional signal indicates at least one of the states. The system of any one of claims 43-47, wherein the controller is configured to perform the method of any one of claims 33-42.

Images