WO2021232150A1

WO2021232150A1 - A multi-channel and agnostic hardware-software interface and database architecture for predictive and prescriptive materials discovery

Info

Publication number: WO2021232150A1
Application number: PCT/CA2021/050674
Authority: WO
Inventors: Kourosh MALEK; Qianpu WANG
Original assignee: National Research Council Of Canada
Priority date: 2020-05-19
Filing date: 2021-05-18
Publication date: 2021-11-25

Abstract

A data logging device comprising: a microprocessor; an input/output interface for connecting at least one sensor, wherein the at least one sensor senses an absolute value or a change in a physical quantity and generates a corresponding signal; an analog to digital converter for sampling the corresponding signal to generate sensor data; a memory for storing the corresponding signal or sensor data; a sensor identification module having instructions stored in the memory, said instructions executable by the microprocessor to determine an identity of the at least one sensor connected to the input/output interface.

Description

A MULTI-CHANNEL AND AGNOSTIC HARDWARE-SOFTWARE INTERFACE AND DATABASE ARCHITECTURE FOR PREDICTIVE AND PRESCRIPTIVE MATERIALS DISCOVERY

FIELD

[0001] Aspects of the disclosure relate to a method and system for aggregating and analyzing data from IoT-enabled equipment and other external data sources. BACKGROUND

[0002] In this digital economy, data has now become of the most valuable assets that an organization can possess. This is particularly true for scientific data, which is the accumulation of many hours of parallel investment in resources, such as time and equipment. Collecting and gaining insight from scientific data sets is a necessary task for improving workflows, ensuring quality records and troubleshooting issues with reproducibility.

[0003] At present, in laboratory settings most equipment is standalone and any data generated from such non-networked equipment is typically saved locally and is only available for use by individual users. Generally, this data is most-often aggregated in a non-standardized format in user-owned databases, and sharing of this user-owned data is done at an individual or project / program scope basis via customized user interfaces, spreadsheet or in some other proprietary format. Working with unstructured data lacking a standardized format makes it challenging to conduct deep and meaningful data analysis, thereby making the results sub- optimal for use by researchers and enterprises. In addition, there are also significant time delays ranging from days to months, from the moment the data is generated to when it is filtered, integrated and analyzed by various potential beneficiaries.

[0004] Furthermore, in the field of materials research, there are significant barriers to energy materials discovery, e.g. limitation on data producers who desire to disseminate results, availability of validated data for analysis, traceability of data to establish quality assurance, cross utilization of data from different scientific fields and provision of data to researchers and enterprises to enable accelerated discovery. The drawbacks may be categorized into three broad categories: (i) access of data, (ii) advanced analysis for energy materials context, and (iii) dissemination of data to benefit enterprise users. In the first category, at present data sources are largely resided in user owned databases generated from non-networked equipment utilizing a combination of non-standard operating procedure (SOP) and standardized SOPs. A limited number of datasets are aggregated in 3^rd party databases which charge premium fees for access with no advanced analytics and AI-driven design capability. In the second category, in-depth analysis of results leading to meaningful trends and analytics is limited since data from various sources is non-standardized and since there is a general lack of traceability; and lastly in the third category, data access by enterprises and researchers is limited, lacking full traceability and ability to utilize for quality assurance.

[0005] It is an object of the present disclosure to mitigate or obviate at least one of the above-mentioned disadvantages.

SUMMARY

[0006] In one of its aspects, there is provided a data logging device comprising: a microprocessor; an input/output interface for connecting at least one sensor, wherein the at least one sensor senses an absolute value or a change in a physical quantity and generates a corresponding signal; an analog to digital converter for sampling the corresponding signal to generate sensor data; a memory for storing the corresponding signal or sensor data; a sensor identification module having instructions stored in the memory, the instructions executable by the microprocessor to determine an identity of the at least one sensor connected to the input/output interface.

[0007] In another of its aspects, there is provided a computer-implemented platform for aggregating data, the platform comprising: at least one data logging device for receiving unstructured input data from at least one sensor associated with at least one equipment; a computing device comprising a processor and a computer readable medium having instructions executable by the processor to at least: receive the unstructured input data from the at least one data logging device; convert the unstructured input data into structured data; categorize the structured data based on an identity of the at least one sensor; generate output data comprising connections and relationships between the structured data; and output a visual representation of the connections and relationships between the structured data via a user interface.

[0008] In another of its aspects, there is provided a computer-implemented method for aggregating data comprising a computing device comprising a processor and a computer readable medium having instructions executable by the processor to at least: receive the unstructured input data from at least one data logging device configured to receive unstructured input data acquired by at least one sensor associated with at least one equipment; convert the unstructured input data into structured data; categorize the structured data based on an identity of the at least one sensor; generate output data comprising connections and relationships between the structured data; and output a visual representation of the connections and relationships between the structured data via a user interface.

[0009] Advantageously, one aspect of the disclosure teaches a way to seamlessly integrate data sources (equipment, user databases and 3^rd party data center) through a combination of interfaces (IoT, user interfaces and application programming interface (API)) to form standardized energy materials data in real-time and utilize the best of Information and Communication (ICT) technologies with advanced filtering, machine learning and blockchain functionalities to accelerate secure communication of output data for enterprise applications (Al-driven design of energy materials, traceability and quality assurance) to substantially shorten discovery and time to commercialization.

[0010] In addition, one aspect of the disclosure teaches the architecture and underpinning technologies for such a system, with a strong emphasis on the hardware-software equipment integration via an Internet of Things (IoT) device to a database, coupled with an advanced analytics platform to transform the measurement data as well as data from various user generated or 3^rd party databases to enable enterprise application solutions.

BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Several exemplary embodiments of the present disclosure will now be described, by way of example only, with reference to the appended drawings in which:

[0012] Figure 1 shows a top-level component architecture diagram for implementing a platform based for aggregating data;

[0013] Figure 2 shows a diagram of a data logging device; and

[0014] Figure 3 shows exemplary steps for converting unstructured and heterogeneous data outputs from different equipment into a standard format. DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS [0015] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar elements. While embodiments of the disclosure may be described, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, or modifications may be made to the elements illustrated in the drawings, and the methods described herein may be modified by substituting, reordering, or adding stages to the disclosed methods. Accordingly, the following detailed description does not limit the disclosure. Instead, the proper scope of the disclosure is defined by the appended claims.

[0016] Moreover, it should be appreciated that the particular implementations shown and described herein are illustrative of the invention and are not intended to otherwise limit the scope of the present invention in any way. Indeed, for the sake of brevity, certain sub-components of the individual operating components, conventional data networking, application development and other functional aspects of the systems may not be described in detail herein. Furthermore, the connecting lines shown in the various figures contained herein are intended to represent exemplary functional relationships and/or physical couplings between the various elements. It should be noted that many alternative or additional functional relationships or physical connections may be present in a practical system.

[0017] Referring to Figure 1, there is shown a top-level component architecture diagram for implementing a platform for aggregating data, generally indicated by numeral 10. System 10 comprises equipment 12a-c with a plurality of sensing elements, or sensors, 14, 16, 18 associated therewith. Generally, sensing elements 14, 16, 18 are physical devices that sense the absolute value or a change in a physical quantity and generate a corresponding signal or data. Examples of a physical quantity include, but are not limited to, voltage, temperature, current, humidity, density, luminosity, salinity, conductivity, acoustic vibrations, pressure, level precipitation, flow rate, pH, coefficient of friction, intensity of light, intensity of sound, intensity of radio waves, barometric air pressure, wind speed and wind direction, environmental parameters, and the like. As an example, sensor data from sensors 14, 16, 18 can include data measured at a particular frequency (e.g., at every 500 millisecond interval).

[0018] Data logging device 20 receive inputs from a plurality of sensing elements 14, 16, 18 associated with equipment 12a-c, such as laboratory equipment, instrument, machinery, machines, machine components, actuators, and so forth. Accordingly, sensing elements 14, 16, 18 transfer the corresponding signal or data to data logging devices 20. In turn, sensed data is transmitted to computing device 22 or server computer via communication network 24 for analysis. User devices 26, 28 and other external data sources 30, 32 may also communicatively coupled to server computer 22 via communication network 24.

[0019] In more detail, data logging device 20 comprises microprocessor 40 with one or more processing elements (programmable or hardwired), computer-readable medium 42 which may include memory cache, non-volatile memory (NVM), read- only memory (ROM), and/or random access memory (RAM), static RAM. Memory 42 stores program code and data and microprocessor 40 executes the program code and processes the data. In one exemplary implementation, a non-volatile memory may be used for persistent storage and a volatile memory may be used for execution of the program code and data at runtime. Moreover, memory 42 may be integrated within microprocessor 40 or may be coupled to microprocessor 40 via a bus or communication fabric, such a system bus for fast memory access, and a peripheral bus for reduced complexity and low-power consumption.

[0020] The program code may include application program code defining an application-specific set of functions to be performed by data logging device 20 and library code comprising a set of predefined building blocks which may be utilized by the application developer of data logging device 20. In addition, the library code also contains a list of generic data formats and conversion functions thereof trained and matched over time by ad-hoc embedded artificial intelligence (AI) algorithms. In one exemplary implementation, the library code comprises a set of basic functions required to implement data logging device 20 such as a communication protocol stack for enabling communication between each data logging device 20 and computer server 22, or an Intemet-of-Things (IoT) hub associated with computer server 22. Data logging device 20 comprises other peripheral devices such as multiple physical hardware interfaces (PHYs) 43 for radio transceivers compatible with UMTS/HSPA, CDMA/CDMA2000, GSM/EDGE, GPRS, EVDO, other 3G/2G, legacy TDD, or other air interfaces used for mobile telephony. In some implementations, the base stations described herein may support Wi-Fi air interfaces, which may include one or more of IEEE 802.11a/b/g/n/ac or IEEE 802.16 (WiMAX) ZigBee, Bluetooth, or other radio frequency protocols, or other air interfaces. Other interfaces include RS-232 interface, USB interface 46 or GPIO interface 48. Other peripherals may include system logic 50, timers 52, ADC/DAC 54, I²C interface 56 and SPI interface used to communicate with sensing elements 14, 16, 18.

[0021] Looking at Figure 3, there is shown flowchart 60 comprising exemplary steps for converting unstructured and heterogeneous data outputs from different equipment into a standard format. In step 62, unstructured data from data logging device 20 is received by server computer 22, and the data is cleaned (step 64) and provided as input training data into an artificial intelligence (AI) engine. Accordingly, a training dataset is built and a training model for benchmark is generated and stored for use in the next steps (step 66). The AI engine categorizes the received data and learns from the datasets. Next, additional data is collected and cleaned (step 68) and the collected new data is compared the previous dataset using K-means algorithm or other suitable unsupervised machine learning algorithms (step 70). Next, in step 72, a visualization of the collected data is generated and combined with new data such that the process returns to step 66, as part of an iterative learning process. Finally, a visualization of the data is displayed on a frontend user interface. [0022] In one exemplary implementation, data logging device 20 is integrated with equipment 12b, such as laboratory equipment, such that sensed data from sensing elements 14, 16, 18 and equipment-generated data is gathered and transmitted to server computer 22. This approach of data integration via data logging device 20 represents at least 2-3 orders of magnitude lower cost of entry than upgrading each laboratory device 12b for network connectivity. For example, this hardware/software integration establishes a communication standard for various energy materials' physicochemical properties (i.e. morphology, strength, conductivity, pore size distribution, etc.), within a framework of technological requirements from an enterprise target application. The IoT- enabled equipment 12a, b streams large datasets in real time to server computer 22 for the data storage, and analysis, enabling users to rapidly gain real-time insight into data as the data is received from the field. In another implementation, data logging device 20 is communicatively coupled to user device 21 running a software application for data acquisition, instrument control, and industrial automation, such as LabVIEW™ from National Instruments Corp., U.S.A.

[0023] In one exemplary implementation, data logging device 20 is controlled by host equipment 12a-c or server computer 22. For example, data logging device 20 may receive control data from host equipment 12a-c or server computer 22. Control data may indicate an operating mode of multiple operating modes of data logging device 20. In one operating mode, data logging device 20 may receive the log data from sensing elements 14, 16, 18 and store the log data at the memory 42 of data logging device 20. In another operating mode, data logging device 20 may transmit the log data from the memory of data logging device 20 to server computer 22. In a third operating mode, data logging device 20 may receive the log data from sensing elements 14, 16, 18 and transmit the log data to the remote device in real time or near real-time. In some implementations of the third operating mode, data logging device 20 may also store a copy of the log data on the memory of data logging device 20.

[0024] Server computer 22 may be configured to wirelessly control data logging device 20 to receive log data acquired by sensing elements 14, 16, 18 and/or to wirelessly transmit the log data to data logging device 20 via a wireless interface. The wireless interface may be coupled to the microprocessor 40, and the wireless interface may be configured include one or more wireless transceivers 45 that communicate with one or more user devices associated with the user using any one or a combination of the wireless protocols described herein (including, but not limited to, 2.4 GHz or 5 GHz WiFi, Bluetooth, ZigBee, etc.) for wireless communication interface functionality; or via a 5G cellular connection.

[0025] In some implementations, data logger device 20 may optionally include a power source, such as a battery, coupled to microprocessor 40. In some implementations, the battery (or other power source) may be configured to be charged via a power supply received via a suitable connector.

[0026] In one exemplary implementation, a plurality of sensing elements 14, 16, 18, such as an array of sensors, may be connected to an indeterminate amount of data loggers 20 communicatively coupled to server computer 22.

[0027] Generally, data logging device 20 receives information from sensing elements 14, 16, 18 in an unstructured data format, and therefore provides the widest compatibility with legacy, non-network connected laboratory equipment 12b. In one exemplary implementation, data logging device 20 packages the unstructured data into a structured data format, such as a universal key/value archive format, before being sent to server computer 22 for analysis. For example, data logging device 20 packages the sensed raw data input as a CSV fde, or other format, for input into server computer 22. This structured format allows data logging device 20 to convey information from any type of equipment 12a-c to server computer 22 in a consistent manner.

[0028] Server computer 22 comprises computing system 80 comprising at least one processor such as processor 82, at least one memory 84, input/output (I/O) module 86 and communication interface 88. Although computing system 80 is depicted to include only one processor 82, computing system 80 may include any number of processors therein. In an embodiment, memory 84 is capable of storing instructions. Further, the processor 82 is capable of executing instructions.

[0029] In one exemplary implementation, processor 82 may be embodied as a multi-core processor, a single core processor, or a combination of one or more multi-core processors and one or more single core processors. For example, processor 82 may be embodied as one or more of various processing devices, such as a coprocessor, a microprocessor, a controller, a digital signal processor (DSP), a processing circuitry with or without an accompanying DSP, or various other processing devices including integrated circuits such as, for example, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a microcontroller unit (MCU), a hardware accelerator, a special-purpose computer chip, Application-Specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), Graphics Processing Units (GPUs), and the like. For example, some or all of the device functionality or method sequences may be performed by one or more hardware logic components. [0030] Memory 84 may be embodied as one or more volatile memory devices, one or more non-volatile memory devices, and/or a combination of one or more volatile memory devices and non-volatile memory devices. For example, memory 84 may be embodied as magnetic storage devices (such as hard disk drives, floppy disks, magnetic tapes, etc.), optical magnetic storage devices (e.g., magneto-optical disks), CD-ROM (compact disc read only memory), CD-R (compact disc recordable), CD-R/W (compact disc rewritable), DVD (Digital Versatile Disc), BD (BLU-RAY™ Disc), and semiconductor memories (such as mask ROM, PROM (programmable ROM), EPROM (erasable PROM), flash ROM, RAM (random access memory), etc.). [0031] I/O module 86 is configured to facilitate provisioning of an output to a user of computing system 80 and/or for receiving an input from the user of computing system 80. I/O module 86 is configured to be in communication with processor 82 and memory 84. Examples of the I/O module 86 include, but are not limited to, an input interface and/or an output interface. Some examples of the input interface may include, but are not limited to, a keyboard, a mouse, a joystick, a keypad, a touch screen, soft keys, a microphone, and the like. Some examples of the output interface may include, but are not limited to, a microphone, a speaker, a light emitting diode display, a thin-film transistor (TFT) display, a liquid crystal display, an active-matrix organic light-emitting diode (AMOLED) display, and the like. In an example embodiment, processor 82 may include I/O circuitry configured to control at least some functions of one or more elements of I/O module 86, such as, for example, a speaker, a microphone, a display, and/or the like. Processor 82 and/or the I/O circuitry may be configured to control one or more functions of the one or more elements of I/O module 86 through computer program instructions, for example, software and/or firmware, stored on a memory, for example, the memory 84, and/or the like, accessible to the processor 82.

[0032] Communication interface 88 enables server computer 22 to communicate with other entities over various types of wired, wireless or combinations of wired and wireless networks, such as for example, the Internet. In at least one example embodiment, the communication interface 88 includes transceiver circuitry configured to enable transmission and reception of data signals over the various types of communication networks. In some embodiments, communication interface 88 may include appropriate data compression and encoding mechanisms for securely transmitting and receiving data over the communication networks. Communication interface 88 facilitates communication between computing system 80 and I/O peripherals.

[0033] In one exemplary embodiment, various components of computing system 80, such as processor 82, memory 84, I/O module 86 and communication interface 88 may be configured to communicate with each other via or through a centralized circuit system 90. Centralized circuit system 90 may be various devices configured to, among other things, provide or enable communication between the components (82-88) of computing system 80. In certain embodiments, centralized circuit system 90 may be a central printed circuit board (PCB) such as a motherboard, a main board, a system board, or a logic board. Centralized circuit system 90 may also, or alternatively, include other printed circuit assemblies (PCAs) or communication channel media.

[0034] In one exemplary implementation, processor 82 may be configured to execute hard-coded functionality. In an embodiment, processor 82 may be embodied as an executor of software instructions, wherein the software instructions may specifically configure processor 82 to perform algorithms and/or operations described herein. Server computer 22 comprises various modules, such as data categorization module and learning module 100, search engine 102, and visualization module 104. Coupled to server computer 22 is database arrangement 110 which includes any data storage software and systems, such as, for example, a relational database like IBM DB2, Oracle 9, MySQL, and SQLite, or relational databases, NoSQL databases, and any suitable database associated with other database architectures. Database 110, including database schemas, may be designed to maximize the storage space available for the data to be stored, which may account for both the quality and quantity of data. Database 110 may also be optimized for rapid data retrieval. The database schema may provide a description of a structure of database 110, such as definitions of the tables, fields in each table and relationships between the fields and tables. Queries to database 110 to retrieve or otherwise access the data, as stored in database 110, may be designed based on the database schema. The database schema may include a plurality of data sources 20, 30, 32, each data source including one or more fields for storing data, and metadata defining relationships amongst the fields. A schema parser may determine one or more datasets of the data from the database schema, wherein a dataset includes one or more fields from a data source of the database schema and represents the data corresponding to the one or more fields.

[0035] Unstructured data from data logging device 20 is received by server computer 22, and data categorization and learning module 100 uses artificial intelligence (AI), such as machine learning (ML) and deep learning (DL) techniques to analyze the properties of the input data for the purposes of categorization for storage in database 110. Accordingly, data categorization and learning module 100 learns how to organize the data over time, with minimal user input. For example, data categorization and learning module 100 “learns” the types of equipment 12a-c supplying the data, and learns how to record and display the data collected from equipment 12a-c and determines a suitable, efficient and useful way to display the data on front end user interface 112 of user device 26, 28. Data categorization and learning module 100 allows for a seamless experience going from data acquisition by machine 12a-c to the front end user interface 112.

[0036] Data categorization and learning module 100 curates the data collected from the sensing elements 14, 16, 18 by the data logging device 20, employs learning methods comprising algorithms executable by processors to determines several properties and actions to be taken regarding the data, such as: efficient storage format of the data, the preferred method of displaying the data visually, number of stored significant figures, type of recorded data (e.g. voltage, current, temperature, humidity, density etc.), how many data points must be stored in short term storage, how many data points must be stored in long term storage, the time interval in-between sampling, possible comparisons and correlations to other recorded data and possible visual representations that would display them. The algorithms may include deep learning models, such as machine learning models. Generally, machine learning provides server 22 with the ability to learn without being explicitly programmed, that is, the algorithms are able to learn from and make predictions on the sensed data. Accordingly, such algorithms overcome following strictly static program instructions by making data driven predictions or decisions, through building a model from sample inputs from sensed data. Data categorization and learning module 100 may comprise machine learning models in any one of the following categories: (1) supervised learning, (2) unsupervised learning, or (3) reinforcement learning. Deep learning employs a statistical learning method that uses multi-layered artificial neural networks to automatically learn, extract extracts features or attributes from raw data sets, and translate features from the data sets with high accuracy, without introducing traditional hand-coded code or rules.

[0037] Server computer 22 also comprises search engine 102 which performs algorithmic searches. For example, in material research algorithmic search engine 102 combines user-weighted desirability of materials' properties for the specified application, potential substitute materials with similar properties, and user search history. Visualization module 104 automatically selects and generates the most suitable type of visualization to highlight similarities and differences between the selected materials. As such, platform 10 use the tool to visually trade-off between materials, export the results for further comprehensive analysis.

[0038] The data may be displayed on front end user interface 112 automatically, or upon user request. The data may be displayed in a way that is categorized by the AI/ML algorithm specific to the type of data that was requested. For example, the data may be represented visually as a graph (bar, scatter, pie, etc.) or via trends (percentage difference between previous data points, etc.)

[0039] Additionally, system 10 comprises involves user interface 112 which is integrated with data categorization and learning module 100 to access or interact with the output from data categorization and learning module 100. For example, a user can request access to various data points stored within database 110 via front end user interface 112. Server computer 22 comprises a Web server framework for browser-based applications utilizing an application server. As an example, the Web server framework comprises access ports and receives HTTP requests from a user's browser, and users with valid credentials can access the aggregated data using a desktop computer, a laptop, a tablet, smart phone, or any other device that can access communication network 24. Via user interface 112, a user may build a structured query to run against database 110.

[0040] In one exemplary implementation, data categorization and learning module 100 provides predictive equipment calibration based on the received data from host equipment 12a-c, or detected host equipment 12a-c. Accordingly, data categorization and learning module 100 recommends or implements an appropriate calibration of host equipment 12a-c in order to maintain the integrity of output data from host equipment 12a-c, and better prepare the data for generation of training models for data categorization and learning module 100.

[0041] In one exemplary implementation, system 10 aggregates data from multiple different sources 30, 32 in a cloud-based environment, including but not limited to machine data via data logging device 20, manually input data via computer terminal, data from an outside source (e.g. partner company). In addition to the types of data described above, the data may include biological data like DNA samples/lab test results, or medical data, such as, heart rate/blood pressure/sugar levels. The aggregate data is stored in database 110, and is accessible by users.

[0042] In one exemplary implementation, data logging device 20 receives signals or data from different sensor sets to accommodate different environments and machinery and the desired data. Data logging device 20 can determine the type of sensors 18 atached thereto, via a sensor identification module with instructions executable by microprocessor 40 to determine an identity of sensors 14, 16 or 18 connected to the input/output interface. Accordingly, data logging device 20 may assist data categorization and learning module 100 in determining the best method to store and display the recorded data from each individual sensor 14, 16 or 18.

[0043] In one exemplary implementation, data logging device 20 collects both equipment data and metadata (including calibration, QC data and sample results) automatically, and relays the data and metadata to server computer 22. Data categorization and learning module 100 is able to track contextual variables, such as temperature, humidity, air pressure and light, in the research lab or monitor critical equipment performance e.g. freezers, refrigerators, ovens, and incubators, for easy access to performance data, as well as alerts when readings are out of range. A dashboard presented on front end user interface 112 allows for user access which is time and location independent.

[0044] Advantageously, gathering and synthesizing environmental data into actionable information, elemental machines provides critical insights that improve transparency, repeatability and outcomes, and save customers time and money.

[0045] In one exemplary implementation, gathering data signals from data logging device 20, generating data from the sensed signals and transforming the data to useful information for energy materials applications involves the following critical functionalities; (a) predictive discovery protocols from materials characterization to back end web application in real time, (b) prescriptive knowledge generated via open communication with data logging device 20, and (c) data analytics including utilizing aggregated database 110.

[0046] In another implementation, system 10 connects data sources 30, 32 to aggregated database 110 utilizing intelligent filtering, machine learning through advanced analytics and blockchain functionality to enable traceability and quality assurance. System 10 accelerates output data for enterprise applications e.g. AI- driven design of energy materials, and substantially shortens discovery and time to commercialization.

[0047] In another implementation, platform 10 is employed for research on materials and their properties. Advantageously, platform 10 identifies trends in material properties and predicts combinations that meet specific user requirements. Visualization module 108 creates a rich visual representation of connections and relationships between data via user interface 112. For example, the data may be represented visually as a graph (bar, scatter, pie, etc.) or via trends (percentage difference between previous data points, etc.). Users may use this information to guide research decisions. Built-in tools allow further data analysis, comparison, and export. The database provides two interfaces: user data entry and data acquisition. [0048] In one exemplary implementation, a schema-less protocol for data acquisition is employed. Generally, storing schema-less (unstructured) data in relational databases is challenging, as this type of data tends to be sparse and generally requires a large number of tables/columns for storage. However, metadata may be used to infer the best way to organize the input into database 110. Schema less data representations include, for example, key/value databases (e.g., CouchDB). [0049] In one exemplary implementation, a research branch of company A is conducting some tests on a certain set of materials. In order to ensure that the data company A collects during this test is stored properly for future reference, data logging devices 20 are coupled to sensor array 14, 16, and 18 to collect the data. Server computer 22 executes AI/ML/DL algorithm of data categorization and learning module 100 to analyze and convert the format of the sensed data into a standard format, and automatically stores the data in long-term storage on server computer 22. The research company is able to access this data in the future to compare data points from years past for long term correlations and meta-analysis. [0050] In one exemplary implementation, in a routine medical checkup, a doctor examines a patient associated with a unique identifier. The patient’s blood pressure cuff features data logging device 20 connected to machine 12c. Once testing is complete the patient’s blood pressure is displayed locally to the doctor and immediately uploaded to computer server 22 where the data is saved as a time- stamped data point on database 110, and associated with the previous tests. In one example, the AI/ML/DL algorithm of data categorization and learning module 100 determines the characteristics and any trends associated with the patients’ blood pressure. Upon request visualization module 104 displays the change between the most recent reading and previous data points both as a scatter plot and as percentage change from day to day, or any other format.

[0051] It is noted that various example embodiments as described herein may be implemented in a wide variety of devices, network configurations and applications. [0052] Those of skill in the art will appreciate that other embodiments of the disclosure may be practiced in network computing environments with many types of computer system configurations, including personal computers, hand-held devices, multi-processor systems, microprocessor-based or programmable consumer electronics, network PCs, server computers, minicomputers, mainframe computers, and the like. Accordingly, system 10 may be coupled to these external devices via the communication, such that system 10 is controllable remotely. Embodiments may also be practiced in distributed computing environments where tasks are performed by local and remote processing devices that are linked (either by hardwired links, wireless links, or by a combination thereof) through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0053] In another implementation, system 10 follows a cloud computing model, by providing an on-demand network access to a shared pool of configurable computing resources (e.g., servers, storage, applications, and/or services) that can be rapidly provisioned and released with minimal or nor resource management effort, including interaction with a service provider, by a user (operator of a thin client). [0054] The descriptions of the various embodiments of the present disclosure have been presented for purposes of illustration, but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

[0055] Embodiments are described above with reference to block diagrams and/or operational illustrations of methods, systems, and computer program products. The operations/acts noted in the blocks may be skipped or occur out of the order as shown in any flow diagram. For example, two or more blocks shown in succession may be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. While the specification includes examples, the disclosure's scope is indicated by the following claims. Furthermore, while the specification has been described in language specific to structural features and/or methodological acts, the claims are not limited to the features or acts described above. Rather, the specific features and acts described above are disclosed as example for embodiments.

Claims

CLAIMS:

1. A data logging device comprising: a microprocessor; an input/output interface for connecting at least one sensor, wherein the at least one sensor senses an absolute value or a change in a physical quantity and generates a corresponding signal; an analog to digital converter for sampling the corresponding signal to generate sensor data; a memory for storing the corresponding signal or sensor data; and a sensor identification module having instructions stored in the memory, said instructions executable by the microprocessor to determine an identity of the at least one sensor connected to the input/output interface.

2. The data logging device of claim 1, wherein the sensor data from the at least one sensor comprises an unstructured data format.

3. The data logging device of claim 2, further comprising a data packeting module comprising instructions executable by the microprocessor to convert the sensor data from each of the at least one sensor comprising the unique unstructured data format into a common structured data format.

4. The data logging device of claim 3, wherein the sensed data in the common structured data format is transmitted to a computing device.

5. The data logging device of claim 4, wherein the data logging device is integrated with an equipment associated with the at least one sensor.

6. The data logging device of claim 4, wherein the sensed data in the common structured data format is transmitted to the computing device via a communication network in real-time.

7. A computer-implemented platform for aggregating data, the platform comprising: at least one data logging device for receiving unstructured input data from at least one sensor associated with at least one equipment; a computing device comprising a processor and a computer readable medium having instructions executable by the processor to at least: receive the unstructured input data from the at least one data logging device; convert the unstructured input data into structured data; categorize the structured data based on an identity of the at least one sensor; generate output data comprising connections and relationships between the structured data; and output a visual representation of the connections and relationships between the structured data via a user interface.

8. The computer-implemented platform of claim 7, wherein the computing device comprises a data categorization and learning module having instructions executable by the processor to curate the structured data received from the at least one data logging device to iteratively learn characteristics of the structured data and determine actions to be taken regarding the structured data.

9. The computer-implemented platform of claim 8, wherein newly received unstructured input data is compared a previous dataset to re-categorize and re classify output data using at least one machine learning algorithm.

10. The computer-implemented platform of claim 9, wherein the computing device comprises a visualization module having instructions executable by the processor to generate a visual display of the structured data.

11. The computer-implemented platform of claim 10, wherein the actions comprise at least one of efficient storage format of the data, comparisons and correlations to other recorded data and method of displaying the structured data visually.

12. The computer-implemented platform of claim 11, wherein the method of displaying the structured data comprises at least one of a graph or a representation of a trend.

13. The computer-implemented platform of claim 10, wherein the characteristics of the structured data comprise at least one of a number of stored significant figures, a type of recorded data, a number of data points for storage in short term memory, a number of data points for storage in long term storage, and a time interval in-between sampling.

14. The computer-implemented platform of claim 7, wherein the data logging device comprises a microprocessor, a memory having instructions stored thereon, an input/output interface, the instructions executable by the microprocessor to determine an identity of the at least one sensor connected to the input/output interface.

15. The computer-implemented platform of claim 14, wherein the data categorization and learning module provides predictive equipment calibration for the at least one equipment based on the received unstructured input data.

16. The computer-implemented platform of claim 11, user queries to the computing device are input via the user interface and visual representation of the data is displayed on the user interface.

17. The computer-implemented platform of claim 15, wherein the computing device receives external data from other external data sources.

18. The computer-implemented platform of claim 17, wherein the unstructured data originating from the at least one sensor comprises at least one of machine parameters, biological data, medical data and environmental parameters.

19. The computer-implemented platform of claim 17, wherein the data from the at least one data logging device is transmitted to the computing device via a communication network in real-time.

20. The computer-implemented platform of claim 19, wherein the data from the at least one data logging device is transmitted to the computing device via a wireless communication medium.

21. A computer-implemented method for aggregating data comprising a computing device comprising a processor and a computer readable medium having instructions executable by the processor to at least: receive the unstructured input data from at least one data logging device configured to receive unstructured input data acquired by at least one sensor associated with at least one equipment; convert the unstructured input data into structured data; categorize the structured data based on an identity of the at least one sensor; generate output data comprising connections and relationships between the structured data; and output a visual representation of the connections and relationships between the structured data via a user interface.

22. The computer-implemented method of claim 21, wherein the steps of categorizing the structured data, generating and outputting the visual representation are performed by at least one machine learning algorithm.