FIELD OF THE DISCLOSURE

The present disclosure is directed generally to systems and methods for proactively determining whether real-time sensor signals are predictive or indicative of an onset of symptoms of infectious diseases in living beings and disinfecting the areas surrounding the living beings. More specifically, the present disclosure is directed to systems and methods for determining whether real-time sensor signals are predictive or indicative of an onset of symptoms of infectious diseases in living beings using lighting embedded sensors and/or additional sensors and disinfecting the areas using sources of disinfection.

BACKGROUND

The recent and pandemic outbreak of COVID-19 has exposed an urgent need to improve systems and methods for fighting infectious diseases, particularly those diseases that are transmitted from human-to-human by droplet transmission (z.e., infection spread through exposure to virus-containing respiratory droplets exhaled by an infectious person) and those diseases that are transmitted between humans and animals. Since these diseases are highly contagious and people may be unaware of their infection, it is critical to develop systems and methods for predicting symptoms, such as, coughing, sneezing, shortness of breath, and sore throat, quickly and accurately and disinfecting the surrounding surfaces and air as quickly as possible. Disinfection light, such as ultraviolet C (UVC) lighting, has been used to disinfect and reduce the spread of infectious diseases, such as COVID-19.

Sneezing or sternutation can spread respiratory diseases by producing 40,000 virus-containing droplets typically ranging from 0.5 to 5 pm in size. Plumes of droplets can travel up to 26 feet. A sneeze is a reflexive response that involves the face, throat, and chest muscles. Specifically, the mouth’s soft palate and palatine uvula are depressed and the back of the tongue moves up so that air from the lungs may be forced through the nose and mouth. Pressure typically builds up in the chest as the chest muscles contract the lungs, the diaphragm moves upward simultaneously, and the vocal cords close. When the vocal cords suddenly open again, air is driven up the respiratory tract and through the nose at a high speed. The eyes close involuntarily and the diaphragm moves upward as our chest muscles contract, releasing air from the lungs. For some individuals, the air that enters and exits the lungs disrupts the heart’s normal rhythm. The pressure built up in the chest can also slow blood flow to the heart. The inhalations can also increase the heart’s beats per minute in order to disperse inhaled oxygen. When the air is quickly released, the pressure around the heart drops, suddenly increasing blood flow. The heart’s beats per minute also decrease during exhalation. To minimize the spread of virus-containing droplets from sneezing, individuals can direct their nose and mouth into a forearm, the inside of an elbow, or a tissue or handkerchief. These effects on and movements of the human body, for example, can be exploited to predict when a sneeze is going to occur and detect when a sneeze has occurred and allow disinfection processes to begin quicker based on the prediction and/or the detection.

There is an urgent need in the art for improved systems and methods for quickly and accurately predicting and/or detecting the onset of symptoms of infectious diseases in individuals and/or animals and disinfecting the areas surrounding the individuals and/or animals.

SUMMARY OF THE INVENTION

The present disclosure is directed to inventive systems and methods for symptom onset prediction and detection and instantaneous disinfection. The symptom onset prediction and/or detection uses at least one of lighting embedded sensors to detect vital signs (e.g., breathing movement, heartbeat, etc.) and other metrics, such as, eye blinking, human gait, body posture and additional sensors to detect pressure build-up in the lungs. The instantaneous disinfection uses sources of disinfection light and/or sources of ionization. Generally, embodiments of the present disclosure are directed to improved systems and methods for detecting an onset of symptoms of infectious diseases in at least one living being in a space using lighting embedded sensors and pressure sensors in an internet of things (IoT) lighting system. Applicant has recognized and appreciated that lighting embedded sensors typically have a seamless coverage of a defined region, along with computational units. The systems and methods described herein exploit the redundancy in the overlapping fields-of- view of the lighting embedded sensors and distributed edge processing across the nodes. The real-time symptom onset detection based on the lighting embedded sensing system can be complemented by real-time symptom onset detection based on pressure sensors, such as, ultrasound sensors. At least one of the real-time symptom onset detection or prediction systems can be used to activate a disinfection rate using disinfection light. Information can be gleaned from the symptom detection or prediction systems after the symptom has occurred to improve the accuracy of the detection and/or prediction systems. In other words, a learning from the post symptom detection by either the lighting embedded sensors or the additional sensors, where a good detection accuracy can be achieved, can be fed back to train and calibrate the prediction algorithm to improve the accuracy. The systems and methods described herein advantageously reduce the spread of infections in workspaces or any other indoor spaces, thereby improving absenteeism, presentism, and the overall productivity of the workforce.

Generally, in one embodiment, a system for detecting an onset of one or more symptoms of an infectious disease in one or more living beings in a space is provided. The system includes a plurality of connected illumination devices arranged in the space, the plurality of connected illumination devices having one or more sensors configured to capture sensor signals related to one or more living beings in the space. The system further includes one or more sources of disinfection in the space, the one or more sources of disinfection configured to provide disinfection in the space and one or more processors in communication with the one or more sensors and the one or more sources of disinfection. The one or more processors are configured to receive training data for detecting vital signs or other metrics of the one or more living beings in the space; receive real-time sensor signals from the one or more sensors of the plurality of connected illumination devices; determine that the real-time sensor signals are predictive of an onset of one or more symptoms based on the received training data; and activate the one or more sources of disinfection for at least one period of time in response to determining that the real-time sensor signals are predictive of the onset of the one or more symptoms.

In embodiments, the one or more sensors of the system include one or more multi-pixel thermopile sensors.

In embodiments, the system includes an additional sensor that is separate from the plurality of connected illumination devices and the one or more sensors, wherein the additional sensor is configured to receive sensor signal data of the one or more living beings in the space, the received sensor signal data corresponding to normal healthy inhalation and/or exhalation patterns and abnormal inhalation and/or exhalation patterns.

In embodiments, the additional sensor includes an ultrasound sensor configured to detect a pressure build-up in lungs of the one or more living beings in the space based on the received sensor signal data corresponding to normal healthy inhalation and/or exhalation patterns and abnormal inhalation and/or exhalation patterns. In embodiments, the additional sensor is further configured to: detect when the received sensor signal data corresponds to abnormal inhalation and/or exhalation patterns; and in response to detecting when the received sensor signal data corresponds to abnormal inhalation and/or exhalation patterns, transmit one or more signals to the one or more processors for activating the one or more sources of disinfection for the at least one period of time.

In embodiments, the one or more processors are further configured to activate the one or more sources of disinfection for the at least one period of time in response to receiving the one or more signals from the additional sensor and determining that the real time sensor signals are predictive of the onset of the one or more symptoms of infection.

In embodiments, the system further includes an additional sensor that is separate from the plurality of connected illumination devices and the one or more sensors, wherein the additional sensor is configured to receive sensor signal data of the one or more living beings in the space, and the additional sensor is an on-body sensor configured to continuously measure vital signs of the one or more living beings.

In embodiments, the system further includes an additional sensor that is separate from the plurality of connected illumination devices and the one or more sensors, wherein the additional sensor is configured to receive sensor signal data of the one or more living beings in the space, and the additional sensor is an odor detector configured to measure odors from the one or more living beings.

Generally, in another embodiment, a method for detecting an onset of one or more symptoms of an infectious disease in one or more living beings in a space is provided. The method includes: providing a plurality of connected illumination devices in the space, the plurality of connected illumination devices including one or more sensors configured to capture sensor signals related to one or more living beings in the space; providing one or more sources of disinfection in the space, the one or more sources of disinfection configured to provide disinfection in the space; receiving, at one or more processors in communication with the one or more sensors and the one or more sources of disinfection, training data for detecting vital signs or other metrics of the one or more living beings in the space; receiving, at the one or more processors, real-time sensor signals from the one or more sensors of the plurality of connected illumination devices; determining, at the one or more processors, that the real-time sensor signals are predictive of an onset of one or more symptoms based on the received training data; and activating the one or more sources of disinfection for at least one period of time in response to determining that the real-time sensor signals are predictive of the onset of one or more symptoms.

In embodiments, the one or more sensors of the method include one or more multi-pixel thermopile sensors.

In embodiments, the method further includes providing an additional sensor that is separate from the plurality of connected illumination devices and the one or more image-based sensors; and receiving, at the additional sensor, sensor signal data of the one or more living beings in the space, the received sensor signal data corresponding to normal healthy inhalation and/or exhalation patterns or abnormal inhalation and/or exhalation patterns.

In embodiments, the additional sensor includes an ultrasound sensor configured to detect a pressure build-up in lungs of the one or more living beings in the space based on the received sensor signal data corresponding to normal healthy inhalation and/or exhalation patterns and abnormal inhalation and/or exhalation patterns.

In embodiments, the method further includes detecting, by the additional sensor, when the received sensor signal data corresponds to abnormal inhalation and/or exhalation patterns; transmitting, by the additional sensor, one or more signals to the one or more processors for activating the one or more sources of disinfection for the at least one period of time in response to detecting when the received sensor signal data corresponds to abnormal inhalation and/or exhalation patterns; and fusing, by the one or more processors, the received sensor signal data with the real-time sensor signals such that at least part of the signals from the one or more sensors complements at least part of the signals from the received sensor signal data from the additional sensor.

In embodiments, the method further includes activating, by the one or more processors, the one or more sources of disinfection for the at least one period of time based on the fused received sensor signal data and real-time sensor signals.

In embodiments, the method further includes detecting, by the additional sensor, when the received sensor signal data corresponds to normal inhalation and/or exhalation patterns; and providing feedback, by the one or more processors, to the additional sensor based on the real-time sensor signals from the one or more image-based sensors.

In various implementations, the one or more processors described herein may take any suitable form, such as, one or more processors or microcontrollers, circuitry, one or more controllers, a field programmable gate array (FGPA), or an application-specific integrated circuit (ASIC) configured to execute software instructions. Memory associated with the processor may take any suitable form or forms, including a volatile memory, such as random-access memory (RAM), static random-access memory (SRAM), or dynamic random- access memory (DRAM), or non-volatile memory such as read only memory (ROM), flash memory, a hard disk drive (HDD), a solid-state drive (SSD), or other non-transitory machine- readable storage media. The term “non-transitory” means excluding transitory signals but does not further limit the forms of possible storage. In some implementations, the storage media may be encoded with one or more programs that, when executed on one or more processors and/or controllers, perform at least some of the functions discussed herein. It will be apparent that, in embodiments where the processor implements one or more of the functions described herein in hardware, the software described as corresponding to such functionality in other embodiments may be omitted. Various storage media may be fixed within a processor or may be transportable, such that the one or more programs stored thereon can be loaded into the processor so as to implement various aspects as discussed herein. Data and software, such as the algorithms or software necessary to analyze the data collected by the tags and sensors, an operating system, firmware, or other application, may be installed in the memory.

It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein.

BRIEF DESCRIPTION OF THE DRAWINGS

In the drawings, like reference characters generally refer to the same parts throughout the different views. Also, the drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the present disclosure.

FIG. 1 is an example schematic depiction of a flowchart showing instantaneous disinfection systems and methods based on symptom onset detection, according to aspects of the present disclosure;

FIG. 2 is an example schematic depiction of a lighting IoT system for detecting an onset of symptoms in a space and providing instantaneous disinfection, according to aspects of the present disclosure; FIG. 3 A shows an example process for activating one or more sources of disinfection to provide instantaneous disinfection, according to aspects of the present disclosure;

FIG. 3B shows another example process for activating one or more sources of disinfection to provide instantaneous disinfection, according to aspects of the present disclosure;

FIG. 4 shows an example process for using complementary real-time symptom onset detection systems for providing instantaneous disinfection, according to aspects of the present disclosure; and

FIG. 5 shows an example schematic depiction of an ultrasound-based sensor that can be used for activating one or more sources of disinfection to provide instantaneous disinfection, according to aspects of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS

The present disclosure describes various embodiments of systems and methods for symptom onset prediction and/or detection and disinfection by using sensors integrated in connected lighting systems and additional sensors. Applicant has recognized and appreciated that it would be beneficial to predict symptom onset using real-time detection systems and to provide disinfection based on the data from the real-time detection systems. Connected illumination devices can be provided in an indoor facility, with one or more connected illumination devices including embedded environment sensors. The environment sensors can include temperature-based sensors and/or image-based sensors configured to capture real time sensor signals related to vital signs or other metrics of living beings in the space. The term “living beings” as used herein is intended to refer to humans and/or animals. A neural network can be trained offline for recognition of the vital signs or other metrics and copies of the neural network can be provided across nodes of the connected lighting system to exploit field-of-view redundancy for inference. Additional sensors can be used to provide real-time symptom onset prediction or detection to complement the real-time sensor signals from the lighting embedded sensors. Sources of disinfection can be provided within the facility to provide disinfection in the space for one or more periods of time based on at least one of the data from the lighting embedded sensors and the data from the additional sensors.

The present disclosure describes various embodiments of systems and methods for providing a distributed network of symptom detection sensors by making use of illumination devices that may already be arranged in a multi-grid and connected architecture (e.g., a connected lighting infrastructure). Such existing infrastructures can be used as a backbone for the additional detection, disinfection, and feedback/calibration functionalities described herein. Signify’ s SlimBlend ^® suspended luminaire is one example of a suitable illumination device equipped with integrated IoT sensors such as microphones, cameras, and thermopile infrared sensors as described herein. In embodiments, the illumination device includes USB type connector slots for the receivers and sensors etc. Illumination devices including sensor ready interfaces are particularly well suited and already provide powering, digital addressable lighting interface (DALI) connectivity to the luminaire’s functionality and a standardized slot geometry. It should be appreciated that any illumination devices that are connected or connectable and sensor enabled including ceiling recessed or surface mounted luminaires, suspended luminaires, wall mounted luminaires, and free floor standing luminaires, etc. are contemplated. Suspended luminaires or free floor standing luminaires including thermopile infrared sensors may be advantageous because the sensors are arranged closer to humans and can detect higher temperatures of people. Additionally, the resolution of the thermopile sensor can be lower than for thermopile sensors mounted within a ceiling recessed or surface mounted luminaire mounted at approximately 3m ceiling height.

The term “luminaire” as used herein refers to an apparatus including one or more light sources of same or different types. A given luminaire may have any one of a variety of mounting arrangements for the light source(s), enclosure/housing arrangements and shapes, and/or electrical and mechanical connection configurations. Additionally, a given luminaire optionally may be associated with (e.g., include, be coupled to and/or packaged together with) various other components (e.g., control circuitry) relating to the operation of the light source(s). Also, it should be understood that light sources may be configured for a variety of applications, including, but not limited to, indication, display, and/or illumination.

Referring to FIG. 1, a schematic depiction of a flowchart pertaining to instantaneous disinfection systems and methods based on symptom onset detection is provided. The flowchart shows system 1 for detecting, in real-time, individuals or people P exhibiting one or more parameters of an occupant of a space 10 and/or onset symptoms of infectious diseases in a space 10. It should be appreciated that one or more parameters can include one or more symptoms of an infectious disease. Although people P are depicted in FIG. 1, it should be appreciated that the systems and methods disclosed herein can also be applied in areas with animals, such as, bams, stables, farms, etc. System 1 includes sensor signal and data capturing system 100, symptom onset prediction/detection system 120, disinfection system 140, and feedback system 160 as described herein. The sensor signal and data capturing system 100 includes a lighting embedded sensor symptom onset detection sub system and a complementary symptom onset prediction/detection sub-system as described herein. The lighting embedded sensor symptom onset detection sub-system of sensor signal and data capturing system 100 includes connected lighting system 101 having illumination devices 102 and on-board sensors 104. It should be appreciated that the on-board sensors can also include imaging sensors (e.g., cameras), microphone sensors, ZigBee transceivers, Bluetooth ^® radio, light sensors, and IR receivers.

On-board sensors 104 can include temperature-based sensors 104, such as, multi-pixel thermopile sensors or any suitable alternative configured to measure temperature at a certain frequency. In embodiments, temperature-based sensors 104 are configured to measure heat flow of determined spectral characteristics and density in living beings and objects. The amount of heat that is absorbed in the thermopile sensors depends on the area and field-of-view of the sensors. The heat that is absorbed in the thermopile sensors passes through a series of thermocouples, each having a wire made of materials of different thermal activity, and a membrane structure. The heat flow in the sensor results in a temperature gradient that can be detected. The ends of the thermocouples have different temperatures. In embodiments, each sensing element of a multi-pixel thermopile sensor converts absorbed thermal energy to a proportional output signal. Those temperature signals can then be amplified, converted from analog to digital, and transmitted to a microprocessor via a suitable communication interface. The microprocessor can map the temperatures from the thermopile elements into a thermal representation of the entire field of view. A trained neural network can be used to classify the thermal representation as a symptom or otherwise as described herein.

On-board sensors 104 can also be embodied as image-based sensors, for example, 60GHz radar sensors, Wi-Fi Doppler imaging technologies, or any suitable sensor configured to generate a point cloud. For example, millimeter-wave (mmWave) sensors can be used to detect people P or other living beings in space 10. Such mmWave sensors can include a transmitting antenna, a receiving antenna, and a digital processing entity. The transmitting antenna can transmit radiofrequency (RF) signals into space 10 and the receiving antenna can receive the signals that are reflected by objects or living beings. The digital processing entity can analyze the reflected signals and generate a digital map or representation of the living beings or objects detected. A trained neural network can be used with the digital processing entity to classify such maps or representations as parameters, symptoms or otherwise as described herein. In embodiments using Wi-Fi Doppler imaging techniques, Doppler signatures can be obtained for moving living beings in space 10 using moveable beams and such Doppler signatures can be classified as parameters, symptoms or otherwise. Trained neural networks can be used to classify or label certain body positions or postures or other observable characteristics as one or more parameters, symptomatic or otherwise. Additionally or alternatively, a reflected signal can reveal subtle movement of the chest surface caused by heartbeats and respiration because the signal undergoes a phase shift due to the subtle movement.

On-board sensors 104 can also be used to detect acoustic events, such as when individuals speak or otherwise emit sounds that deviate from normal and healthy smooth vocal sounds. For example, when individuals have laryngitis or some other condition affecting the larynx or voice box, their voice exhibits a raspy, weak, or airy air quality that can be detected. Detection of a hoarse voice or other voice sound quality can be used to detect parameters of an occupant and/or symptoms of infectious diseases, such as, a sore throat.

The complementary symptom onset prediction/detection sub-system of sensor signal and data capturing system 100 includes an additional device configured to predict an onset of one or more parameters and/or symptoms of infectious diseases in people P or other living beings in space 10. In the embodiment depicted in FIG. 1, the additional device of the complementary symptom onset prediction/detection sub-system is wearable device 110. However, it should be appreciated that device 110 could also be embodied as an on-body sensor that can continuously monitor a living being’s vital signs (e.g., temperature, respiratory rate, and heart rate). In embodiments including an on-body sensor, continuous measurements of a living being’s vital signs can be analyzed to determine if there are statistical changes that are indicative of signs, parameters and symptoms of an infectious disease. Additionally, in alternate embodiments device 110 need not be wearable at all and could instead be embodied as a wall-mounted device, a ceiling-mounted device, and/or a suspended device. In embodiments, device 110 can be configured to capture odors that are emitted by individuals and/or animals in the space 10. The odor-capturing device can include a container or some equivalent for capturing and containing odors from individuals and/or animals in the space and an electronic scent reader. In embodiments, the odors can be tested from air exhaled from the individuals and/or animals. Device 110 is separate from the lighting embedded sensor symptom onset detection sub-system of sensor signal and data capturing system 100. It should be appreciated that the lighting IoT system 100 can be configured in a typical office setting, a hotel, a grocery store, an airport, or any suitable alternative.

Symptom onset prediction/detection system 120 is configured to analyze the sensor signals and data captured with system 100. Disinfection system 140 is configured to activate or trigger one or more sources of disinfection 106 in space 10. In embodiments, the one or more sources of disinfection 106 can be part of connected lighting system 101. One or more sources of disinfection 106 can be embodied as one or more sources configured to administer a luminaire-based disinfection means. Luminaire-based disinfection means can include light sources configured to emit ultraviolet C (UVC) lighting or any suitable alternative, and/or devices configured to accomplish disinfection via ionization. In embodiments, one or more illumination devices 102 can be configured to generate disinfection via light and/or ionization. Feedback system 160 is configured to improve the accuracy of the symptom onset prediction/detection system 120 using data from the lighting embedded sensor symptom onset detection sub-system or data from the complementary symptom onset detection sub-system. Additionally, feedback system 160 can be used to calibrate the sensors of sensor signal and data capturing system 100. These systems and methods are described in more detail below.

The lighting embedded sensor symptom onset detection sub-system of sensor signal and data capturing system 100 is embodied as a lighting IoT system for symptom onset detection in space 10. The system 100 includes one or more overhead connected lighting networks that are equipped with connected on-board sensors (e.g., advanced sensor bundles (ASBs)). The overhead connected lighting networks refer to any interconnection of two or more devices (including controllers or processors) that facilitates the transmission of information (e.g., for device control, data storage, data exchange, etc.) between the two or more devices coupled to the network. Any suitable network for interconnecting two or more devices is contemplated including any suitable topology and any suitable communication protocols. The sensing capabilities of the ASBs are used to accurately detect the one or more parameters and/or onset of symptoms in individuals and/or animals within space 10. The onset of parameters and/or symptoms can be gleaned, for example, by detecting when a living being raises his/her head and arm and his/her eyes close voluntarily. Such body movements can be correlated with sneezing. The onset of parameters and/or symptoms could also be gleaned, for example, by detecting when the heart’s normal rhythm is disrupted.

The lighting IoT system 100 includes illumination devices 102 that may include one or more light-emitting diodes (LEDs). The LEDs are configured to be driven to emit light of a particular character (i.e., color intensity and color temperature) by one or more light source drivers. The LEDs may be active (i.e., turned on); inactive (i.e., turned off); or dimmed by a factor d, where 0 < d < 1. The value d = 0 means that the LED is turned off whereas d = 1 represents an LED that is at its maximum illumination. The illumination devices 102 may be arranged in a symmetric grid or, e.g., in a linear, rectangular, triangular, or circular pattern. Alternatively, the illumination devices 102 may be arranged in any irregular geometry. The illumination devices 102 are arranged to provide one or more lighting effects that are visible to individuals and/or animals or persons P present in space 10. In embodiments, illumination devices 102 are also arranged to provide one or more lighting effects that may or may not be visible to individuals and/or animals or persons P present in space 10, but that provide disinfection. Illumination devices 102, and any suitable lighting characteristic that can be generated by illumination devices 102, can be controlled by a central controller 200 as shown in FIG. 2.

It should be appreciated that the overhead connected lighting networks can include, in addition to illumination devices 102, occupancy sensors, people-counting sensors, ambient/daylight level sensors, humidity sensors, noise sensors, and temperatures sensors that can obtain readings at desk level even though the bundle of sensors are at or near the ceiling. The overhead connected lighting networks can include additional or alternative sensors as well. Since the ASBs are arranged within overhead lighting fixtures, they can provide a sufficiently dense sensor network to cover a whole building indoor space. Although in some embodiments the illumination devices 102 and on-board sensors 104 are integrated together and configured to communicate within a single device via wired or wireless connections, in other embodiments the on-board sensors 104 can be separate from the illumination devices 102 and in communication with the illumination devices 102 via a wired or wireless connection.

Referring to FIG. 2, controller 200 includes a network interface 210, a memory 220, and one or more processors 230. Network interface 210 can be embodied as a wireless transceiver or any other device that enables the connected luminaires to communicate wirelessly with each other within the connected lighting system 101 as well as other devices including mobile devices utilizing the same wireless protocol standard and/or to otherwise monitor network activity and enables the controller 200 to receive data from the connected sensors 104 and the one or more sources of disinfection 106. In embodiments, the network interface 210 may use wired communication links. The on-board sensors 104 and/or the sources of disinfection 106 are configured to transmit data to one or more processors 230 via any suitable wired/wireless network communication channels. In embodiments, the data can be transmitted directly to one or more processors 230 without passing through a network. The data can be stored in memory 230 via the wired/wireless communication channels. The memory 220 and one or more processors 230 may take any suitable form in the art for controlling, monitoring, and/or otherwise assisting in the operation of illumination devices 102, on-board sensors 104, and one or more sources of disinfection 106 and performing other functions of controller 200 as described herein. The one or more processors 230 are also capable of executing instructions stored in memory 220 or otherwise processing data to, for example, perform one or more steps of the methods described herein. One or more processors 230 may include one or more modules, such as, a data capturing module of system 100, a symptom onset prediction module and a symptom onset detection module of system 120, a disinfection module of system 140, a feedback module of system 160, and training and redundancy modules as described further below.

As shown in FIGS. 1 and 2, the lighting embedded on-board sensors 104 are configured to detect sensor signals from person P or other living beings. For embodiments including on-board thermopile sensors, such sensors can capture sequences of images showing temperature-sensitive radiation from individuals and/or animals in the space 10. In embodiments, image frames can be collected at 1 Hz, i.e., one frame of image is produced every second. Additional sensors can be used as well or instead. For example, one or more forward-looking infrared (FLIR) thermal cameras can be used to measure the body temperature of person P or other living beings. Since the illumination devices 102 and on board sensors 104 are arranged at specific fixed locations within space 10, position information of their fixed locations can be stored locally and/or at memory 220.

As described further below, training data for detecting vitals and/or other metrics of individuals and/or animals in space 10 can be stored in memory 220. One or more processors 230 can be configured to analyze real-time sensor signals received from the on board sensors 104 based on training data stored in memory 220. Processors 230 can also be configured to determine that the real-time sensor signals are predictive or indicative of an one or more parameters and/or onset of symptoms of infection. Processors can also be configured to activate one or more sources of disinfection 106 in the space 10 for one or more periods of time in response to determining that the real-time sensor signals are predictive or indicative of the onset of one or more parameters and/or symptoms.

Processors can also be configured to provide one or more notifications to the people in the space when an onset of parameters and/or symptoms is detected and/or predicted. In example embodiments, one or more illumination devices of the connected illumination devices can be illuminated in such a way that conveys when an onset of parameters and/or symptoms is detected and/or predicted. For example, one or more illumination devices can emit red light that is visible to people in the space to signal to the people that the risk of infection has increased. Of course, it should be appreciated that the illumination devices can emit any color light or any other suitable light effect regardless of color to signal to people in the space that the risk of infection has increased. Based on the light, the people can take additional preventative measures, such as, wearing a mask even though they are indoors and socially distanced from other people. In other embodiments, the processors can additionally or alternatively be configured to provide signals to one or more electronic displays in the space when an onset of parameters and/or symptoms is detected and/or predicted. For example, based on such signals, the one or more electronic displays in the space can be configured to present visible indicia to signal to the people that the risk of infection has increased. In other embodiments, the processors can additionally or alternatively be configured to provide signals to one or more sound emitting devices in the space when an onset of parameters and/or symptoms is detected and/or predicted. For example, based on such signals, the one or more sound emitting devices in the space can be configured to produce one or more sounds to signal to the people that the risk of infection has increased. Based on the visual indicia and/or the sounds, the people in the space can take additional preventative measures to protect themselves from an increased risk of infection. It should be appreciated that the illumination devices, the electronic displays, and/or the sound emitting devices can also be configured to provide notifications when the risk of infection has decreased. In such scenarios, the individuals in the space can resume their normal routine without the additional preventative safety measures in place when an increased risk of infection exists. It should further be appreciated that other suitable devices and/or systems can be provided to generate the types of notifications disclosed herein.

In embodiments where the one or more sources of disinfection 106 comprise disinfection light, UV disinfection light, such as, UVC disinfection light can be quantified by inactivation rates or log reduction values (LRV). Log reduction refers to the relative number of live microbes eliminated by disinfection light. In embodiments where the sources of disinfection light 106 are UVC LEDs, the processors 230 can be configured to select one or more UV doses to eliminate live microbes in the air or on surfaces in the space 10 by disinfection light. The UV dose is the amount of UV radiation a microbe is exposed to and depends on the intensity of UV radiation and exposure time. In embodiments, the memory 220 can store a plurality of widely accepted typical UV dose requirements for most common target microbes in disinfection. For example, to achieve a 3 log reduction (i.e., 99.9 percent) of B. Subtillus (ATCC 6633) a 60 mJ/cm ² dose is required.

FIG. 3A depicts an example process 300A for activating one or more sources of disinfection 106 to provide instantaneous disinfection. At step 302A, connected lighting system 101 including illumination devices 102 and on-board sensors 104 can be provided in space 10. The on-board sensors 104 can include temperature-based or image-based sensors that are configured to capture sensor signals related to at least one living being in the space 10. In embodiments, the sensor signals are related to vital signs, other metrics, or gestures of individuals and/or animals in the space 10. The on-board sensors 104 can be embodied as multi-pixel thermopile sensors which are configured to capture sequences of images showing temperature-sensitive radiation from individuals and/or animals in the space 10. In embodiments, image frames can be collected at 1 Hz, i.e., one frame of image is produced every second. However, the frames can be produced at any time interval. Additional sensors can be used in lieu of or in addition to the multi-pixel thermopile sensors as described herein. For example, forward-looking infrared (FLIR) thermal cameras can be used to measure the body temperature of individuals and/or animals in the space. Since the on-board sensors 104 are arranged at specific locations within the space, position information of their fixed locations can be stored locally and/or at memory 220.

At step 304A, one or more sources of disinfection 106 can be provided in the space 10. The sources of disinfection 106 can include any suitable sources configured to generate UV light, such as UV LEDs, UVC LEDs, or mercury lamps, sources configured to generate infrared light, or sources configured to generate 405nm purple light disinfection light which is visible. The sources of disinfection 106 can alternatively or additionally include any suitable sources configured to provide disinfection via ionization. Any other suitable alternatives or additions are contemplated as well for the sources of disinfection 106.

At step 306 A, training data for detecting vital signs or other metrics of individuals and/or animals in the space 10 can be received. In embodiments, an artificial recurrent neural network (RNN) can be trained offline to detect vital signs or other metrics, such as sneezing gestures, produced by individuals and/or animals or persons in the space 10. In embodiments directed to detecting sneezing gestures, the artificial RNN can be trained to detect typical head motions and hand gestures performed during sneezing. The artificial RNN can be embodied in any suitable architecture that is capable of processing sequences of images obtained from image-based sensors 104. In RNNs, connections between nodes are in a temporal sequence, which allow it to exhibit temporal dynamic behaviors. In embodiments, the artificial neural network can include a long short-term memory (LSTM) neural network. The neural network using long short-term memory units can be trained in a supervised fashion, on sets of training sequences, using an optimization algorithm. In embodiments, sets of training image sequences from the image-based sensors 104 showing sneezing gestures can be sequentially labeled and those labeled images can be input to a LSTM neural network. Feature extraction can be performed on the sequences of labeled images over time and those features can be assigned to different gesture identifiers or one or more identifiers indicating the presence of a gesture.

At step 308 A, real-time sensor signals from the on-board sensors 104 can be received and analyzed based on the received training data. In embodiments with a long short term memory (LSTM) artificial recurrent neural network architecture that is trained offline, such a trained architecture can be copied and distributed across multiple lighting nodes in the connected lighting system 101. To minimize latency, each of the multiple lighting nodes in the connected lighting system 101 that have copies of the trained LSTM architecture can be configured to operate on local copies of data, which can be thermopile images. Since adjacent sensors have overlapping fields-of-view, there can be redundancy across the images collected by the thermopile sensors. In embodiments, the multiple lighting nodes in the connected lighting system 101 can use local communication between the nodes to distribute the computation of the forward pass of the LSTM, and exploit the overlapping thermopile images.

At step 310A, the analysis of the real-time sensor signals can be used to determine whether the real-time sensor signals are predictive or indicative of an onset of one or more parameters and/or one or more symptoms of infectious diseases.

At step 312A, one or more sources of disinfection 106 in the space 10 can be activated for at least one period of time in response to determining that the real-time sensor signals are predictive or indicative of the onset of one or more parameters and/or one or more symptoms of infectious diseases.

FIG. 3B depicts another example process 300B for activating one or more sources of disinfection 106 to provide instantaneous disinfection. At step 302B, connected illumination devices 102 of a connected lighting system 101 are provided in a space 10 along with one or more sources of disinfection 106 that are configured to disinfect air and/or surfaces within the space 10. At step 304B, reflected sensor signal data is received at a sensor of a sensing device that is separate from but in communication with the connected illumination devices 102. The sensing device can be embodied as wearable device 110 as described above. In embodiments, the sensing device can be a device that can be worn over a person’s clothing to detect inhalation and/or exhalation patterns and the reflected sensor signal data can correspond to inhalation and/or exhalation patterns of an individual in the space 10. The reflected sensor signal data can be obtained with an ultrasound-based sensor as discussed below with reference to FIGS. 4 and 5, for example. In other embodiments, the sensing device can be embodied as an on-body sensor that can continuously monitor a living being’s vital signs. The sensing device can also be embodied as a stand-alone, wall-mounted, ceiling- mounted, or suspended device as described herein. In embodiments, the sensing device can be embodied as an odor-capturing device.

At step 306B, the received reflected sensor signal data is analyzed at the sensing device using a classifier to predict whether the vital signs or other metrics of the living being are indicative of an onset of one or more parameters and/or one or more symptoms of one or more infectious diseases.

At step 308B, the sensing device transmits activation signals to the connected illumination devices to prepare at least one source of disinfection 106 to generate disinfection via light and/or ionization in response to determining that an onset of one or more parameters and/or one or more symptoms of infection is predicted.

At step 310B, at least one on-board sensor of the connected illumination devices detects real-time sensor signals of the living being in the space 10 and a determination is made, based on the real-time sensor signals, that an onset of one or more parameters and/or one or more symptoms of at least one infectious disease has occurred. The real-time sensor signals can comprise at least one image frame from a multi-pixel thermopile sensor, by way of one example.

At step 312B, the prediction from the sensing device is fused with the detection at the at least one on-board sensor. If the prediction predicts a symptom of an infectious disease and the detection detects the symptom of infectious disease, then at least one source of disinfection is activated or triggered to generate a flash of disinfection light and/or ionization for at least one period of time. The at least one source of disinfection that is activated or triggered can be selected based on proximity to the living being exhibiting the symptom of the infectious disease in the space. In this way, the symptom detection at the at least one on-board sensor can complement the symptom prediction from the sensing device.

FIG. 4 depicts an example process 400 for using complementary real-time symptom onset detection and/or prediction systems for instantaneous disinfection. At step 402, a neural network is trained offline for recognition of vital signs or other metrics and distributed among lighting embedded sensors 104 in a space 10. As described herein, a connected lighting system 101 can be equipped with its own on-board sensors and the on board sensors can include image-based sensors or multi-pixel thermopile sensors as described herein. Since the symptom onset detection is in real-time (i.e., an example use case being latency-critical), a long short-term memory artificial neural network can be trained offline to detect symptomatic vital signs, gestures, or other metrics produced by individuals and/or animals in the space 10. The symptomatic gestures can be typical head motions and/or hand gestures performed during sneezing. At step 404, copies of the trained neural network are distributed and deployed across multiple lighting nodes of the connected lighting system 101. The on-board sensors 104 receive real-time sensor signals and the nodes determine whether the real-time sensor signals are predictive or indicative of an onset of one or more one or more parameters and/or one or more symptoms based on the local training data. Steps 402 and 404 are part of lighting embedded sensor symptom onset detection system 405.

At step 406, a sensor that is separate from the on-board sensors 104 and the connected illumination devices 102 receives real-time sensor signal data relating to individuals and/or animals in the space 10. In embodiments, the received sensor signal data can correspond to inhalation and/or exhalation patterns of the individuals and/or animals in the space 10. For example, the sensor that is separate from the image-based sensors 104 and the connected illumination devices 102 can be embodied as a sensor within device 110 as described above and as shown in FIG. 1. The sensor within device 110 can include an ultrasound-based sensor as shown in FIG. 5. Such an ultrasound-based sensor can be worn over clothes or as an on-body sensor. The ultrasound-based sensor 500 in FIG. 5 includes a transducer 502 and sensors 504 and 506. It should be appreciated that embodiments need not include sensor 506 as further explained below. Transducer 502 is configured to emit ultrasound waves, such as wave W, into the pulmonary cavity in the chest region of person P from side 508 of pulmonary cavity. Sensor 506 can receive the emitted ultrasound waves on the other side 510 of the pulmonary cavity of person P or any other living being. Thus, some embodiments of ultrasound-based sensor 500 can include sensors arranged on opposite sides of person P or any other living being. In other words, embodiments of sensor 500 can include a first sensor 504 configured to be placed on or near side 508 of a pulmonary cavity of a person P when worn and a second sensor 510 configured to be placed on or near side 510 of the pulmonary cavity of the person P when worn. In other embodiments, ultrasound-based sensor 500 includes only a single sensor 504 that is arranged on the same side of the pulmonary cavity as transducer 502 when worn. Sensor 504 is configured to receive a first reflected signal SI as the ultrasound wave passes through the sensor housing. The first reflected signal SI is due to internal reflection within device 110. Sensor 504 is also configured to receive a second reflected signal S2 as the ultrasound wave passes through the body and is reflected from the various surfaces. The second reflected signal S2 is due to the wave reflecting through the body of the person from the other side, i.e., side 510 of pulmonary cavity. Patterns in the received second reflected signal S2 can correspond to healthy or normal inhalation and/or exhalation patterns or abnormal inhalation and/or exhalation patterns. Such patterns can be analyzed and classified as described herein.

Referring back to FIG. 4, the received real-time sensor signal data can be analyzed within the device 110 that houses the sensor 500. For example, device 110 can also include one or more processors. In embodiments, the processor of the device 110 can comprise a lightweight classifier, such as a decision tree, and such classifier can be used to detect the onset of one or more parameters and/or one or more symptoms by analyzing the inhalation and/or exhalation patterns or other vital signs or other metrics. In embodiments, temporal features of the received real-time sensor signal data can be extracted at step 408 using a trained feature extraction module of the one or more processors. Temporal features can include inter-peak latency and/or shape similarity and any other suitable temporal features. At step 410, the extracted temporal features can be classified as an onset of one or more parameters and/or one or more symptoms or otherwise using the classifier. Steps 406, 408, and 410 are part of complementary symptom onset prediction system 411 using sensor 500 or any suitable alternative.

At step 412, data from lighting embedded sensor symptom onset detection system 405 and data from complementary symptom onset prediction system 411 are fused together at one or more processors 230 to determine whether the respective outputs agree.

The output from complementary symptom onset prediction system 411 can be transmitted from or otherwise obtained or accessed from sensor 500 via any suitable means. If both systems agree (i.e., detect/predict the onset of one or more parameters and/or one or more symptoms), then, at step 414A, one or more flashes of disinfection light and/or ionization can be triggered from the sources of disinfection 106 in the space 10. On the other hand, if the lighting embedded sensor symptom onset detection system 405 detects a symptom but the complementary symptom onset prediction system 411 does not predict a symptom, then remedial actions (i.e., feedback) can be provided to the sensor 500 for further calibration at step 414B. Post symptom calibration can further improve the prediction accuracy of the complementary symptom onset detection system 411 since, in embodiments, the lighting embedded sensor symptom onset detection system 405 can achieve greater than 80% accuracy using, for example, acoustic event detection with microphone sensors, other sensors, or any other suitable detection techniques. In embodiments, when the complementary symptom onset prediction system 411 detects a symptom, but the lighting embedded sensor symptom onset detection system 405 does not, then no action is taken.

Advantageously, the systems and methods described herein provide for improved instantaneous disinfection. Although the embodiments described above pertain to predicting and/or detecting one or more parameters and/or one or more symptoms of infectious diseases, the disclosure is not to be limited to such applications. The embodiments described herein can also be used to predict and/or detect when individuals and/or animals in a space are about to engage in any activities or actions that can spread virus-containing droplets in the space 10. For example, the lighting embedded sensor symptom onset detection system 405 and/or the complementary symptom onset prediction system 411 can be configured to measure movements or other vital signs in individuals that are indicative of precursors of speaking activities. In embodiments, the sub-systems 405 and/or 411 can be configured to detect when individuals remove facemasks or other face coverings. Sub systems 405 and/or 411 can also be configured to detect when a person is preparing for an audio phone call using a wearable device, such as, a headset or in-ear devices. In still other embodiments, sub-systems 405 and/or 411 can be configured to detect when a person or a baby is about to cry, sing, or speak, etc.

It should also be understood that, unless clearly indicated to the contrary, in any methods claimed herein that include more than one step or act, the order of the steps or acts of the method is not necessarily limited to the order in which the steps or acts of the method are recited.

All definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and/or ordinary meanings of the defined terms. The indefinite articles “a” and “an,” as used herein in the specification and in the claims, unless clearly indicated to the contrary, should be understood to mean “at least one.”

The phrase “and/or,” as used herein in the specification and in the claims, should be understood to mean “either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with “and/or” should be construed in the same fashion, i.e., “one or more” of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the “and/or” clause, whether related or unrelated to those elements specifically identified.

As used herein in the specification and in the claims, “or” should be understood to have the same meaning as “and/or” as defined above. For example, when separating items in a list, “or” or “and/or” shall be interpreted as being inclusive, i.e., the inclusion of at least one, but also including more than one, of a number or list of elements, and, optionally, additional unlisted items. Only terms clearly indicated to the contrary, such as “only one of’ or “exactly one of,” or, when used in the claims, “consisting of,” will refer to the inclusion of exactly one element of a number or list of elements. In general, the term “or” as used herein shall only be interpreted as indicating exclusive alternatives (i.e. “one or the other but not both”) when preceded by terms of exclusivity, such as “either,” “one of,” “only one of,” or “exactly one of.”

As used herein in the specification and in the claims, the phrase “at least one,” in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed within the list of elements and not excluding any combinations of elements in the list of elements. This definition also allows that elements may optionally be present other than the elements specifically identified within the list of elements to which the phrase “at least one” refers, whether related or unrelated to those elements specifically identified.

In the claims, as well as in the specification above, all transitional phrases such as “comprising,” “including,” “carrying,” “having,” “containing,” “involving,” “holding,” “composed of,” and the like are to be understood to be open-ended, i.e., to mean including but not limited to. Only the transitional phrases “consisting of’ and “consisting essentially of’ shall be closed or semi-closed transitional phrases, respectively. While several inventive embodiments have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and/or structures for performing the function and/or obtaining the results and/or one or more of the advantages described herein, and each of such variations and/or modifications is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and/or configurations will depend upon the specific application or applications for which the inventive teachings is/are used. Those skilled in the art will recognize or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. It is, therefore, to be understood that the foregoing embodiments are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, inventive embodiments may be practiced otherwise than as specifically described and claimed. Inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and/or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and/or methods, if such features, systems, articles, materials, kits, and/or methods are not mutually inconsistent, is included within the inventive scope of the present disclosure.