Description:APPARATUS AND SYSTEM FOR EVALUATING QUALITY OF MILK

FIELD OF THE PRESENT DISCLOSURE
[0001] The present disclosure generally relates to evaluating quality of milk. More particularly, the present disclosure pertains to a portable apparatus employing an electrochemical sensor, machine learning techniques, and data processing to detect adulterants in milk samples. Moreover, the present disclosure pertains to a system implementing the portable apparatus for providing historical data related to milk samples.

BACKGROUND
[0002] Milk is universally recognized as a vital source of nutrition for humans. For ages, it has been consumed in various forms, from raw milk to processed products like yogurt, cheese, and butter. Given its importance in daily diets, the consistent quality of milk is of paramount importance. Moreover, the dairy industry has evolved into a multi-billion-dollar sector, catering to the needs of millions worldwide. As the demand for milk and its derivatives has increased, so has the emphasis on ensuring its quality and purity. This emphasis has been necessitated by several factors, including the health implications of consuming adulterated milk and the economic repercussions for producers and consumers alike.
[0003] Milk adulteration has emerged as a pervasive challenge in the dairy industry. Unscrupulous individuals and entities introduce foreign substances into milk to increase its volume, enhance its appearance, or prolong its shelf life. These adulterants range from relatively harmless substances like water to potentially harmful adulterants such as urea, detergents, and even synthetic chemicals. Such adulteration not only compromises the nutritional value of milk but also poses serious health risks to consumers. For instance, the adulterants can lead to a host of health problems ranging from gastrointestinal issues to more severe complications. Furthermore, from an economic standpoint, adulteration undermines the trust of consumers, affecting the sales and reputation of genuine milk producers.
[0004] Considering the severity of the milk adulteration issue, the industry and regulatory bodies have explored various methods and technologies to detect and deter it. Traditional methods often involve chemical tests, where milk samples are subjected to specific reagents to ascertain their purity. For instance, the addition of certain chemicals can lead to a change in colour if specific adulterants are present. While these methods have their merits, they often require sophisticated laboratory setups, are time-consuming, and may not be foolproof against all types of adulterants.
[0005] To address the limitations of traditional methods, technological solutions have been sought. The advent of sensors and analytical devices has provided more sophisticated means of testing milk. These devices can quickly analyse milk samples and provide instant feedback. However, while these devices offer more accuracy than rudimentary chemical tests, they still have limitations. Many of these devices focus on specific adulterants, making them less versatile. Further, existing devices for milk quality evaluation often require bulky equipment, specialized training, and are time-consuming, making them less feasible for quick and on-site testing. Moreover, they often require frequent calibration and can be susceptible to errors, especially if not used correctly.
[0006] Furthermore, while technological solutions have made some advances in detecting adulteration, there is a broader challenge of tracking and managing the data associated with milk quality. Given the vast quantities of milk produced, tested, and consumed daily, there is an immense amount of data associated with milk quality. This data, if managed effectively, could provide invaluable insights into patterns of adulteration, supplier reliability, and even consumer preferences. However, traditional databases, while effective in storing data, do not offer the security, transparency, and traceability required for such sensitive data. There is a growing need for a robust data management system that can not only store but also analyse and secure milk quality data.
[0007] In light of the aforementioned challenges, there is a need for a comprehensive solution that not only detects adulteration easily and accurately but also manages the associated data securely and efficiently. Such a solution should leverage the latest in sensor technology, data analytics, and secure data storage. It should offer a holistic approach to milk quality assurance, ensuring that consumers receive pure, unadulterated milk and that genuine producers are rewarded for their commitment to quality. The present disclosure seeks to address this gap and provide a solution for evaluating the quality of milk, ensuring its purity, and managing the data associated therewith.

SUMMARY
[0008] In an aspect, the present disclosure provides a portable apparatus for evaluating quality of milk. The portable apparatus comprises a housing. The portable apparatus also comprises an electrochemical sensor located in the housing and adapted to be at least partially immersed in a milk sample. The portable apparatus further comprises a memory unit disposed within the housing and configured to store a machine learning model trained on reference waveforms corresponding to known adulterants mixed in milk. The portable apparatus further comprises a processing unit disposed within the housing, and in signal communication with the electrochemical sensor and the memory unit. Herein, the electrochemical sensor is configured to: generate one or more predefined waveforms to be transmitted in the milk sample; and capture one or more resultant waveforms corresponding to the one or more predefined waveforms from the milk sample. Further, the processing unit is configured to: implement the machine learning model to compare the one or more resultant waveforms with corresponding one or more of the reference waveforms; determine adulterants present in the milk sample based on the comparison; and output result of determination of adulterants.
[0009] In one or more embodiments, the electrochemical sensor is a potentiometer comprising two electrodes and configured to apply one or more predefined voltages to generate the one or more predefined waveforms, and measure resultant voltage shifts to capture the one or more resultant waveforms.
[0010] In one or more embodiments, the machine learning model is optimized utilizing TinyML framework for reduced memory and/or computational requirements, for implementation by the processing unit in the portable apparatus.
[0011] In one or more embodiments, the processing unit is further configured to pre-process the one or more resultant waveforms to enhance signal clarity, preceding the comparison, using at least one of: Standard Normal Variation (SNV) technique, Multiplicative Scatter Correction (MSC) technique, Savitzky-Golay Smoothing technique, Baseline Correction technique.
[0012] In one or more embodiments, the housing has a protruding portion, and wherein the electrochemical sensor has a probe located in the protruding portion of the housing and adapted to be immersed in the milk sample.
[0013] In another aspect, the present disclosure provides a system. The system comprises at least one portable apparatus. The portable apparatus comprises an electrochemical sensor adapted to be at least partially immersed in a milk sample. The portable apparatus further comprises a memory unit configured to store a machine learning model trained on reference waveforms corresponding to known adulterants mixed in milk. The portable apparatus further comprises a processing unit in signal communication with the electrochemical sensor and the memory unit. The portable apparatus further comprises a communication unit. Herein, the electrochemical sensor is configured to: generate one or more predefined waveforms to be transmitted in the milk sample; and capture one or more resultant waveforms corresponding to the one or more predefined waveforms from the milk sample. Further, the processing unit is configured to: implement the machine learning model to compare the one or more resultant waveforms with corresponding one or more of the reference waveforms; determine adulterants present in the milk sample based on the comparison; and output result of determination of adulterants. Further, the communication unit is configured to transmit the result of determination of adulterants. The system further comprises a database configured to receive the result of determination of adulterants from the at least one portable apparatus via the communication unit thereof, the database configured to store historical data related to milk samples, including at least one of their source, date of testing, and results of determination of adulterants. Herein, the system is configured to allow a computing device to connect with the database to access the historical data related to milk samples.
[0014] In one or more embodiments, the database is a blockchain database.
[0015] In one or more embodiments, the blockchain database implements at least one smart contract configured to be executed when one or more predefined conditions related to results of determination of adulterants for a specific milk sample are met.
[0016] In one or more embodiments, the system further comprises a user interface configured to at least one of: display the historical data related to milk samples, allow users to verify history and/or quality of specific milk samples by fetching relevant data thereof from the database.
[0017] In one or more embodiments, the system further comprises a server configured to generate analytical insights based on patterns in the historical data, wherein the analytical insights are related to one or more of: milk supplier evaluation, seasonal adulteration trends, regional adulteration trends.

BRIEF DESCRIPTION OF THE FIGURES
[0018] For a more complete understanding of example embodiments of the present disclosure, reference is now made to the following descriptions taken in connection with the accompanying drawings in which:
FIGS. 1A and 1B illustrate diagrammatic perspective views of a portable apparatus for evaluating quality of milk, in accordance with one or more embodiments of the present disclosure;
FIG. 1C illustrates a diagrammatic side view of the portable apparatus, in accordance with one or more embodiments of the present disclosure;
FIG. 1D illustrates a diagrammatic top view of the portable apparatus, in accordance with one or more embodiments of the present disclosure;
FIG. 1E illustrates a diagrammatic front view of the portable apparatus, in accordance with one or more embodiments of the present disclosure;
FIG. 1F illustrates a diagrammatic back view of the portable apparatus, in accordance with one or more embodiments of the present disclosure;
FIG. 2 illustrates a simplified block diagram of the portable apparatus depicting signal communication between components thereof, in accordance with one or more embodiments of the present disclosure; and
FIG. 3 illustrates a simplified block diagram of a system implementing the portable apparatus, in accordance with one or more embodiments of the present disclosure.

DETAILED DESCRIPTION
[0019] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. It will be apparent, however, to one skilled in the art that the present disclosure is not limited to these specific details.
[0020] Reference in this specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. The appearance of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Further, the terms “a” and “an” herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced items. Moreover, various features are described which may be exhibited by some embodiments and not by others. Similarly, various requirements are described which may be requirements for some embodiments but not for other embodiments.
[0021] Furthermore, in the following detailed description of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be understood that the present disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the present disclosure.
[0022] Embodiments described herein may be discussed in the general context of computer-executable instructions residing on some form of computer-readable storage medium, such as program modules, executed by one or more computers or other devices. By way of example, and not limitation, computer-readable storage media may comprise non-transitory computer-readable storage media and communication media; non-transitory computer-readable media include all computer-readable media except for a transitory, propagating signal. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or distributed as desired in various embodiments.
[0023] Some portions of the detailed description that follows are presented and discussed in terms of a process or method. Although steps and sequencing thereof are disclosed in figures herein describing the operations of this method, such steps and sequencing are exemplary. Embodiments are well suited to performing various other steps or variations of the steps recited in the flowchart of the figure herein, and in a sequence other than that depicted and described herein. Some portions of the detailed descriptions that follow are presented in terms of procedures, logic blocks, processing, and other symbolic representations of operations on data bits within a computer memory. These descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. In the present application, a procedure, logic block, process, or the like, is conceived to be a self-consistent sequence of steps or instructions leading to a desired result. The steps are those utilizing physical manipulations of physical quantities. Usually, although not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated in a computer system. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as transactions, bits, values, elements, symbols, characters, samples, pixels, or the like.
[0024] In some implementations, any suitable computer usable or computer readable medium (or media) may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-usable, or computer-readable, storage medium (including a storage device associated with a computing device) may be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable medium may include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fibre, a portable compact disc read-only memory (CD-ROM), an optical storage device, a digital versatile disk (DVD), a static random access memory (SRAM), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, a media such as those supporting the internet or an intranet, or a magnetic storage device. Note that the computer-usable or computer-readable medium could even be a suitable medium upon which the program is stored, scanned, compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory. In the context of the present disclosure, a computer-usable or computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with the instruction execution system, apparatus, or device.
[0025] In some implementations, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. In some implementations, such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. In some implementations, the computer readable program code may be transmitted using any appropriate medium, including but not limited to the internet, wireline, optical fibre cable, RF, etc. In some implementations, a computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
[0026] In some implementations, computer program code for carrying out operations of the present disclosure may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like. Java and all Java-based trademarks and logos are trademarks or registered trademarks of Oracle and/or its affiliates. However, the computer program code for carrying out operations of the present disclosure may also be written in conventional procedural programming languages, such as the “C” programming language, PASCAL, or similar programming languages, as well as in scripting languages such as JavaScript, PERL, or Python. In present implementations, the used language for training may be one of Python, Tensorflow, Bazel, C, C++. Further, decoder in user device (as will be discussed) may use C, C++ or any processor specific ISA. Furthermore, assembly code inside C/C++ may be utilized for specific operation. Also, entire user system can be run in embedded Linux (any distribution), Android, iOS, Windows, or the like, without any limitations. The program code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the later, the remote computer may be connected to the user’s computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the internet using an Internet Service Provider). In some implementations, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs) or other hardware accelerators, micro-controller units (MCUs), or programmable logic arrays (PLAs) may execute the computer readable program instructions/code by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.
[0027] In some implementations, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus (systems), methods and computer program products according to various implementations of the present disclosure. Each block in the flowchart and/or block diagrams, and combinations of blocks in the flowchart and/or block diagrams, may represent a module, segment, or portion of code, which comprises one or more executable computer program instructions for implementing the specified logical function(s)/act(s). These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program instructions, which may execute via the processor of the computer or other programmable data processing apparatus, create the ability to implement one or more of the functions/acts specified in the flowchart and/or block diagram block or blocks or combinations thereof. It should be noted that, in some implementations, the functions noted in the block(s) may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
[0028] In some implementations, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks or combinations thereof.
[0029] In some implementations, the computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed (not necessarily in a particular order) on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts (not necessarily in a particular order) specified in the flowchart and/or block diagram block or blocks or combinations thereof.
[0030] Referring to FIGS. 1A-1F, illustrated are different views of a portable apparatus (as represented by reference numeral 100) for evaluating quality of milk, in accordance with one or more embodiments of the present disclosure. The portable apparatus 100 (hereinafter, simply referred to as “apparatus 100”) is tailored specifically to cater to application of milk quality evaluation. For portability purposes, the apparatus 100 may have an in-built power unit, such as a battery (not shown), to power its components. Herein, the apparatus 100 is further designed to have integrated processing capabilities (as discussed later in the description) for direct, on-site applications. The apparatus 100 is generally designed to address the challenges in swiftly and accurately evaluating milk quality. FIGS. 1A-1F detail exterior structure of the apparatus 100 without showing inner components. Referring to FIG. 2, illustrated is a block diagram of the apparatus 100 showing inner components and connections therebetween. Further description regarding the apparatus 100 has been provided in consideration of combination of FIGS. 1A-1F and FIG. 2, without any limitations.
[0031] As illustrated, the apparatus 100 includes a housing 102 designed to protect and contain the internal components. The housing 102 is designed to facilitate user-friendly interaction of the apparatus 100, making it accessible to individuals with varying levels of expertise. In some configurations, as depicted in FIG. 1F, the housing 102 may also provide a port 103 to allow for connecting a power source to provide power to its internal electrical components and/or to charge a battery located inside thereof. This port 103 may also be utilized as a connection port for transfer of data from the apparatus 100, as may be required for given applications. In general, the housing 102 may be constructed from hard materials to provide a sturdy exterior that shields the internal components from potential physical harm, such as drops or impacts. The design considerations for the housing 102 also account for environmental factors. Given that milk quality evaluation may need to be conducted in diverse environments, including farms, dairies, or even retail outlets, the housing 102 is potentially resistant to moisture, temperature fluctuations, and contaminants. Further, the shape and structure of the housing 102 are devised to ensure comfortable handling and operation. Given the nature of the task, the housing 102 may feature grip-enhancing surfaces or contours, facilitating steady immersion without inadvertent slips or tilts. It may be appreciated that the design of the housing 102 may vary from illustrated embodiments, but its primary function remains to provide a robust enclosure, ensuring the durability and portability of the apparatus 100.
[0032] The apparatus 100 further includes an electrochemical sensor 104 located in the housing 102. Herein, the electrochemical sensor 104 is adapted to be at least partially immersed in a milk sample. In particular, the electrochemical sensor 104 has a probe 105 adapted to be immersed in the milk sample, and thus serves as a primary interface between the milk sample and the apparatus 100. In some embodiments, the housing 102 may have a unique design feature in the form of a protruding portion 106. The protruding portion 106 is designed to accommodate the probe 105 of the electrochemical sensor 104. This alignment ensures that when a user wishes to test a milk sample, only the probe 105 needs to be immersed into the milk sample. This design consideration minimizes the risk of the housing 102 coming into contact with the milk or any potential contaminants, thus preserving the integrity of the internal components and prolonging the lifespan of the apparatus 100. Furthermore, the protruding portion 106, by its design, offers users a clear indication of how to interact with the apparatus 100. The protruding portion 106 acts as a guide, ensuring that the immersion process is intuitive and user-friendly. This design aspect highlights user-centric design of the apparatus 100, ensuring that milk testing is not only accurate but also convenient.
[0033] In the present apparatus 100, the electrochemical sensor 104 performs dual functions when partially immersed in a milk sample. Herein, the electrochemical sensor 104 is configured to generate one or more predefined waveforms to be transmitted in the milk sample. That is, the electrochemical sensor 104 generates the one or more predefined waveforms that are transmitted into the milk sample. These waveforms interact with constituents of the milk sample, and any adulterants present, producing specific responses. Further, the electrochemical sensor 104 is configured to capture one or more resultant waveforms corresponding to the one or more predefined waveforms from the milk sample. These resultant waveforms, which correspond to the predefined waveforms, carry information about composition of the milk sample. The differences, shifts, or alterations in these waveforms, can indicate the presence of adulterants (as discussed later in more detail).
[0034] The electrochemical sensor 104, as employed in the apparatus 100, operates based on the principle of potentiometry, a well-established electrochemical technique. Potentiometry measures the voltage differential between two electrodes in an electrochemical cell and is ubiquitously utilized in various analytical and scientific applications. For this purpose, the electrochemical sensor 104 may be embodied as a potentiometer. This configuration comprises two electrodes (not shown). The potentiometer setup ensures accurate generation and capture of waveforms. By applying one or more predefined voltages to the electrodes, specific waveforms are generated. Simultaneously, resultant voltage shifts between the electrodes which arise due to the interaction of the waveforms with the milk sample are measured. These voltage shifts serve as the resultant waveforms, which are then used for further analysis. As may be contemplated, in other examples, instead of voltages, current pulses or frequency signals may be utilized without departing from the scope and the spirit of the present disclosure.
[0035] In the context of the present disclosure, when the electrochemical sensor 104 generates and transmits the one or more predefined waveforms into the milk sample, these waveforms interact with inherent constituents of the milk sample and any potential adulterants present therein. As a result of these interactions and influenced by the availability of various chemicals in the milk sample, there is a shift in ions within such system. Such shifts lead to alterations in the predefined waveforms, thereby providing the resultant waveforms as captured by the electrochemical sensor 104. These resultant waveforms, corresponding to the initially transmitted predefined waveforms, provide information regarding composition of the milk sample. Specifically, any deviations, shifts, or modifications in these waveforms can be indicative of the presence of adulterants. The choice of the electrochemical sensor 104, and more specifically a potentiometer configuration, ensures that the apparatus 100 can detect even minute traces of adulterants. This sensitivity is important, given that certain adulterants, even in small quantities, can significantly compromise milk quality.
[0036] Now, to extract and analyse this information, the apparatus 100 includes a memory unit 108 and a processing unit 110. The processing unit 110 may be coupled for communication with the memory unit 108. The processing unit 110 may execute instructions and/or code stored in the memory unit 108. A variety of computer-readable storage media may be stored in and accessed from the memory unit 108. Generally, as used herein, the memory unit 108 may be a non-volatile memory. The memory unit 108 may include any suitable elements for storing data and machine-readable instructions, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, a hard drive, a removable media drive for handling compact disks, digital video disks, diskettes, magnetic tape cartridges, memory cards, and the like. Herein, the processing unit 110 refers to a computational element that is operable to respond to and processes instructions that drive the apparatus 100. Optionally, the processing unit includes, but is not limited to, a microprocessor, a microcontroller, a complex instruction set computing (CISC) microprocessor, a reduced instruction set (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or any other type of processing circuit. Furthermore, the processing unit 110 may include one or more individual processors, processing devices and various elements associated with a processing device that may be shared by other processing devices. Additionally, the one or more individual processors, processing devices and elements are arranged in various architectures for responding to and processing the instructions that drive the apparatus 100.
[0037] The processing unit 110 may include one or more processing cores with each core configured to perform independently. A multi-core processor enables multiprocessing within a single physical package. Examples of a multi-core processor include two, four, eight, or greater numbers of processing cores. Alternatively, or in addition, the processing unit 110 may include one or more microprocessors configured in tandem to enable independent execution of instructions, pipelining, and multithreading. The processing unit 110 may also be accompanied with one or more specialized components to perform certain processing functions and tasks such as one or more digital signal processors (DSP), and/or one or more application-specific integrated circuits (ASIC). Other specialized components to aid in performing the inventive functions described herein include one or more field programmable gate arrays (FPGA) (not shown), one or more controllers (not shown), or one or more other special-purpose computer chips.
[0038] In the present configuration, the memory unit 108 and the processing unit 110 are disposed within the housing 102, to provide the integrated apparatus 100. The memory unit 108 is configured to store a machine learning model 112 trained on reference waveforms corresponding to known adulterants mixed in milk. The choice of utilizing the machine learning model for this application is not arbitrary. Given the vast array of potential adulterants and their varying concentrations, traditional deterministic models may not suffice. Machine learning models can adapt, learn, and predict based on patterns in the data, making them exceptionally suited for this application. The machine learning model 112, once trained on a comprehensive dataset of reference waveforms, can detect even subtle indications of adulteration in milk samples.
[0039] Given the portable nature of the apparatus 100 and the potential constraints in terms of computational power and memory, the machine learning model 112 is refined using specific frameworks designed for resource-constrained environments. In an embodiment, the machine learning model 112 is optimized utilizing TinyML framework for reduced memory and/or computational requirements, for implementation by the processing unit 110 in the apparatus 100. This framework allows for the development and deployment of machine learning models that are both compact and efficient. Such optimization ensures that the apparatus 100, despite its compact form factor, can execute the machine learning model 112 efficiently and accurately, providing users with real-time feedback on milk quality.
[0040] Further, in the apparatus 100, the processing unit 110 is disposed in signal communication with the electrochemical sensor 104 to receive the resultant waveforms. Upon receiving the resultant waveforms from the electrochemical sensor 104, the processing unit 110 executes on a series of computational tasks. The processing unit 110 first retrieves the machine learning model 112 from the memory unit 108. The processing unit 110 implements the machine learning model 112 to compare the one or more resultant waveforms with corresponding one or more of the reference waveforms. That is, the machine learning model 112, trained on reference waveforms, serves as the benchmark against which the resultant waveforms are compared. The processing unit 110, leveraging the algorithms embedded within the machine learning model 112, undertakes a detailed comparison of the resultant waveforms against these reference waveforms. It may be appreciated that this is not just a superficial juxtaposition; but a comparison for identifying shifts and patterns within the waveforms, to determine correlations or deviations that may hint at the presence of adulterants.
[0041] In some embodiments, the processing unit 110 preprocesses the resultant waveforms to enhance their clarity. Given the potential for noise or other extraneous signals, preprocessing techniques such as Standard Normal Variation (SNV) technique, Multiplicative Scatter Correction (MSC) technique, Savitzky-Golay Smoothing technique, and Baseline Correction technique are employed. The SNV technique, for instance, normalizes the data, ensuring that variances in magnitude do not skew the analysis. The MSC technique corrects scatter effects in the data, ensuring that the waveforms are consistent and devoid of anomalies. The Savitzky-Golay Smoothing technique, on the other hand, smoothens the data, filtering out minor fluctuations that may not be representative of quality of the milk sample. Further, the Baseline Correction technique adjusts the waveform baseline, ensuring that it is consistent and facilitates accurate comparison. These techniques refine the waveform data, ensuring that the subsequent comparison with the reference waveforms is both accurate and reliable.
[0042] Once the waveforms are pre-processed, the processing unit 110 implements the machine learning model 112 to perform the comparison (as discussed above). Through advanced algorithms, the processing unit 110 evaluates the differences, shifts, or alterations in the resultant waveforms against the reference waveforms. These reference waveforms correspond to known adulterants mixed in milk, having been derived from extensive prior testing and research. Based on this comparison, the processing unit 110 may then determine the presence and potentially the concentration of adulterants in the milk sample. Further, in some examples, through intricate algorithms, the processing unit 110 can not only detect the presence of an adulterant but may also estimate its concentration, providing a comprehensive assessment of quality of the milk sample. Herein, the magnitude or extent of these deviations can provide insights into the concentration of the adulterants. For instance, a minor deviation may indicate a lower concentration, while a significant deviation could signify a higher concentration of the adulterant.
[0043] Further, the processing unit 110 outputs result of determination of adulterants. That is, after comparing the resultant waveforms with the reference waveforms, identifying the deviations, and applying the machine learning model 112, the processing unit 110 arrives at a conclusion regarding the purity of the milk sample. This conclusion is not merely a binary output of ‘adulterated’ or ‘pure’. Instead, the result provides specific details, such as the type of adulterant detected, and possibly its estimated concentration. For example, the result may indicate the presence of urea, detergents, or other synthetic chemicals, each of which has distinct waveform deviations when introduced to the milk sample. The output result from the processing unit 110 may provide immediate feedback to the user, allowing for an immediate action. The detailed nature of the result also aids in traceability. By identifying specific adulterants and their concentrations, dairy professionals can trace back to potential points of contamination in the supply chain, be it a specific supplier, a batch, or even a specific production process. This traceability can lead to corrective and preventive actions, ensuring that such adulteration incidents are minimized in the future.
[0044] In the present embodiments, the apparatus 100 further includes a communication unit 114. The communication unit 114 is configured to transmit the determined results regarding milk quality and potential adulteration. The inclusion of the communication unit 114 in the apparatus 100 substantially broadens its scope and utility. Given the importance of ensuring milk quality, it is often necessary to not merely analyse and determine the purity of milk but also to communicate these findings to relevant stakeholders or systems. The communication unit 114 serves this purpose. The communication unit 114 may establish connections with various external systems over wired protocols or wireless mediums, depending on its configuration. The communication unit 114 may utilize standard communication protocols and interfaces, ensuring seamless integration with a wide range of external systems. This could include, but is not limited to, systems such as databases, quality control dashboards, supply chain management systems, or even consumer-facing applications that inform customers about the quality of the milk they consume.
[0045] The present apparatus 100 offers numerous advantages over existing solutions. The design of the apparatus 100, with the housing 102 and the strategically positioned electrochemical sensor 104, ensures durability and ease of use, making it a user-friendly solution for individuals without specialized training. The integration of the electrochemical sensor 104 with the machine learning model 112 ensures quick and accurate detection of adulterants, eliminating the need for bulky laboratory equipment and extensive manual labour. Moreover, the optimization of the machine learning model 112 ensures that the apparatus 100 remains compact and power-efficient, providing an edge solution ideal for on-site testing in various environments. Moreover, the preprocessing techniques employed further enhance the accuracy of adulterant detection, ensuring that the results are reliable and actionable. Thus, the apparatus 100 provides advanced technologies with a practical approach, offering a state-of-the-art solution for milk quality evaluation.
[0046] The utility of the portable apparatus 100 extends beyond a mere laboratory setting. Given its compact design and rapid testing capabilities, the apparatus 100 finds relevance in diverse areas. For instance, household consumers can utilize the apparatus 100 because of its user-friendly and cost-effective approach for milk testing. Dairy farmers can deploy the apparatus 100 to test milk at source. This proactive approach ensures that any contamination or adulteration is identified at the earliest stage, preventing potential distribution of compromised milk to consumers. In many regions, milk from multiple farmers is aggregated at collection centers before being dispatched to processing units. Here, the apparatus 100 can serve as a quality control tool, ensuring that the aggregated milk batch meets requisite quality standards. In a retail setting, the apparatus 100 can empower both retailers and consumers. Retailers can validate the quality of milk they receive from suppliers, while consumers, equipped with the portable apparatus 100, can verify the quality of milk before purchase, ensuring they get the best value for their money. Further, food safety regulators can deploy the apparatus 100 for surprise checks and audits. Given its rapid testing capabilities, large batches of milk can be tested in short timeframes, ensuring widespread compliance with food safety standards.
[0047] Referring now to FIG. 3, illustrated is a block diagram of a system 300 implementing the apparatus 100 of the present disclosure, which has been discussed in the preceding paragraphs. The system 300 seeks to leverage the capabilities of the apparatus 100 and augment it with additional functionalities and integrations, ensuring a comprehensive solution for milk quality assessment and data management. Considering the vastness and variability of the milk supply chain, the system 300 is configured to manage data from multiple apparatuses 100. Each of these apparatuses 100, though functioning independently, can be geographically distributed, serving distinct segments of the supply chain or different regions. The collective data they generate, when fed into the system 300, provides information that reflects the quality of milk across various regions and over time.
[0048] It may be appreciated that the system 300 described herein may be implemented in various forms of hardware, software, firmware, special purpose processors, or a combination thereof. One or more of the present embodiments may take a form of a computer program product comprising program modules accessible from computer-usable or computer-readable medium storing program code for use by or in connection with one or more computers, processors, or instruction execution systems. For the purpose of this description, a computer-usable or computer-readable medium may be any apparatus that may contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium may be electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation mediums in and of themselves as signal carriers are not included in the definition of physical computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, random access memory (RAM), a read only memory (ROM), a rigid magnetic disk and optical disk such as compact disk read-only memory (CD-ROM), compact disk read/write, and digital versatile disc (DVD). Both processors and program code for implementing each aspect of the technology may be centralized or distributed (or a combination thereof) as known to those skilled in the art. In an example, the system 300 may be embodied as a computer-program product programmed for milk quality evaluation. The system 300 may be incorporated in one or more physical packages (e.g., chips). By way of example, a physical package includes an arrangement of one or more materials, components, and/or wires on a structural assembly (e.g., a baseboard) to provide one or more characteristics such as physical strength, conservation of size, and/or limitation of electrical interaction. It is contemplated that in certain embodiments the computing device may be implemented in a single chip.
[0049] The system 300 includes a database 302 designed to serve as a repository for the vast amounts of data generated by the apparatuses 100 and potentially other similar devices. As the apparatus 100 evaluates milk samples and determines the presence of adulterants, it generates detailed results that includes not only the type and concentration of adulterants but also potentially other metadata such as, but not limited to, time of testing, location of testing, and specific apparatus identifier. The communication unit 114 of the apparatus 100 interfaces directly with the database 302, ensuring that post-evaluation, the results are transmitted and stored. This transmission may involve protocols that ensure data integrity, security, and accuracy. Upon receiving this data, the database 302 categorizes and stores it, maintaining a structured record that can be accessed, analysed, or retrieved later. By continuously aggregating data from diverse sources, the system 300 can construct a comprehensive historical data of milk quality stored in the database 302. This historical data may include details about the source of the milk sample, the exact date and time of testing, the specific apparatus (if multiple are in operation) that conducted the test, and the results of the determination of adulterants. Such a comprehensive record ensures that over time, the system 300 accumulates a vast knowledge concerning milk quality, offering insights into patterns, trends, and anomalies.
[0050] In the present embodiments, the system 300 is architected to be open and accessible. Herein, the system 300 is configured to allow external computing devices to establish connections with the database 302. Thereby, the system 300 provides the necessary interfaces for various stakeholders, such as quality control personnel seeking to analyse recent results, supply chain managers aiming to trace the origin of a contaminated batch, or even researchers studying broader trends in milk quality, to access the data they require. This accessibility is achieved while ensuring data security and integrity. Proper authentication and authorization protocols are implemented, ensuring that while the data is accessible, it remains protected from unauthorized access or tampering.
[0051] In an embodiment, the database 302 is a blockchain database. Blockchain, at its core, is a decentralized ledger of all transactions across a network. When applied in the context of the system 300, the blockchain database 302 provides an immutable, transparent, and verifiable record of all milk quality evaluations conducted by the apparatus 100. The decentralized nature of blockchain ensures that the data is not stored in a single centralized server but across a network of nodes, enhancing data security and reducing single points of failure. This decentralization also ensures that any alterations to the data are virtually impossible without the consensus of the majority of the network. For given applications where trust and authenticity are vital, this feature of blockchain provides confidence to the stakeholders. Moreover, the data stored in the blockchain database 302 is timestamped, ensuring traceability and accountability. Such a feature is invaluable in scenarios where one needs to trace back a quality issue to its origin or verify the authenticity of a particular evaluation.
[0052] In some embodiments, the system 300 incorporates the concept of smart contracts, as implemented by the blockchain database 302. A smart contract, in essence, is a self-executing contract where the terms of the agreement or conditions are written directly into lines of code. In the present system 300, these smart contracts are activated based on predefined conditions related to the results of determination of adulterants for specific milk samples. For instance, a smart contract could be configured such that if a particular milk sample evaluation detects a specific adulterant beyond a permissible limit, the smart contract automatically triggers a series of actions. These could range from notifying quality control teams, alerting supply chain managers, or even automatically flagging the particular batch for further checks. The smart contracts execute these actions without human intervention, ensuring timely responses to potential quality issues.
[0053] The system 300 further includes a user interface 304. The user interface 304 is designed to cater to various stakeholders, from quality control personnel and supply chain managers to researchers and end consumers. In an implementation, the user interface 304 is configured to display the historical data related to milk samples. This historical data may provide a chronological view of milk samples tested, the results of these tests, the presence and concentration of any detected adulterants, and the like. For instance, a dairy farmer could utilize this feature to track the quality of milk produced in their farm over a period, identifying any patterns or anomalies that may warrant attention. In some examples, the user interface 304 offers functionalities that allow users to not only view and display the historical data related to milk samples but also delve deeper into specific data points. In another implementation, the user interface 304 is configured to allow users to verify history and/or quality of specific milk samples by fetching relevant data thereof from the database 302. For instance, users can employ search and filter functionalities to narrow down specific batches of milk, specific time frames, or specific adulterants. Such capabilities empower users with information, ensuring transparency and traceability in the milk supply chain.
[0054] The system 300 further includes a server 306. The server 306, equipped with advanced analytical tools and algorithms, is configured to analyse the historical data, identifying patterns, correlations, and trends. The server 306 performs this analysis to generate actionable insights that can impact decision-making related to milk supply chain or the like. Herein, the actionable insights are related to one or more of: milk supplier evaluation, seasonal adulteration trends, regional adulteration trends. That is, for instance, the server 306 may generate insights related to milk supplier evaluations. By analysing data over time, the server 306 may rank suppliers based on consistent quality, identify suppliers who may have recurrent quality issues, or even highlight suppliers who have shown marked improvement in quality over time. Such insights can inform procurement decisions, negotiate supplier contracts, or design targeted quality improvement initiatives. Further, by analysing data across seasons or specific months, the server 306 may identify if there are recurrent adulteration issues during certain times of the year. Such insights can guide targeted quality checks, inform consumer advisories, or even define procurement strategies. Furthermore, by segmenting data based on geographical origins, the server 306 may generate insights into regional adulteration trends. This could identify specific regions with consistent quality issues or even identify regions that produce premium quality milk consistently.
[0055] Thus, the system 300 provides a holistic solution for milk quality management. From the quality evaluations carried out by the apparatus 100 to the vast data management and analytical capabilities, the system 300 serves as a comprehensive tool ensuring transparency, quality, and informed decision-making in the milk supply chain. The incorporation of the blockchain database 302 provides data integrity, transparency, and security. Traditional databases may be susceptible to tampering or unauthorized access. In contrast, the present blockchain database 302, with its decentralized and encrypted nature, ensures that the stored data remains unaltered and authentic.
[0056] In conclusion, the apparatus 100 and the system 300 of the present disclosure represent a significant improvement in the domain of milk quality evaluation and data-driven decision-making. The apparatus 100, with the electrochemical sensor 104 and the machine learning model 112, offers an efficient and accurate means to detect and determine adulterants in milk samples. The portability of the apparatus 100 ensures that quality evaluation can occur at any point in the milk supply chain, from the farm to the end consumer. On the other hand, the system 300 increases the value derived from the apparatus 100. By collating, storing, and making accessible the historical data related to milk samples, the system 300 helps stakeholders across the dairy industry. The integration of modern technologies, including the blockchain database 302 and the user interface 304, further helps in ensuring milk quality and for fostering transparency.
[0057] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the present disclosure.
, Claims:WE CLAIM:
1. A portable apparatus for evaluating quality of milk, the portable apparatus comprising:
a housing;
an electrochemical sensor located in the housing and adapted to be at least partially immersed in a milk sample;
a memory unit disposed within the housing and configured to store a machine learning model trained on reference waveforms corresponding to known adulterants mixed in milk; and
a processing unit disposed within the housing, and in signal communication with the electrochemical sensor and the memory unit,
wherein the electrochemical sensor is configured to:
generate one or more predefined waveforms to be transmitted in the milk sample; and
capture one or more resultant waveforms corresponding to the one or more predefined waveforms from the milk sample,
wherein the processing unit is configured to:
implement the machine learning model to compare the one or more resultant waveforms with corresponding one or more of the reference waveforms;
determine adulterants present in the milk sample based on the comparison; and
output result of determination of adulterants.

2. The portable apparatus as claimed in claim 1, wherein the electrochemical sensor is a potentiometer comprising two electrodes and configured to apply one or more predefined voltages to generate the one or more predefined waveforms, and measure resultant voltage shifts to capture the one or more resultant waveforms.

3. The portable apparatus as claimed in claim 1, wherein the machine learning model is optimized utilizing TinyML framework for reduced memory and/or computational requirements, for implementation by the processing unit in the portable apparatus.

4. The portable apparatus as claimed in claim 1, wherein the processing unit is further configured to pre-process the one or more resultant waveforms to enhance signal clarity, preceding the comparison, using at least one of: Standard Normal Variation (SNV) technique, Multiplicative Scatter Correction (MSC) technique, Savitzky-Golay Smoothing technique, Baseline Correction technique.

5. The portable apparatus as claimed in claim 1, wherein the housing has a protruding portion, and wherein the electrochemical sensor has a probe located in the protruding portion of the housing and adapted to be immersed in the milk sample.

6. A system comprising:
at least one portable apparatus comprising:
an electrochemical sensor adapted to be at least partially immersed in a milk sample;
a memory unit configured to store a machine learning model trained on reference waveforms corresponding to known adulterants mixed in milk;
a processing unit in signal communication with the electrochemical sensor and the memory unit; and
a communication unit,
wherein the electrochemical sensor is configured to:
generate one or more predefined waveforms to be transmitted in the milk sample; and
capture one or more resultant waveforms corresponding to the one or more predefined waveforms from the milk sample,
wherein the processing unit is configured to:
implement the machine learning model to compare the one or more resultant waveforms with the reference waveforms;
determine adulterants present in the milk sample based on the comparison; and
output result of determination of adulterants,
wherein the communication unit is configured to transmit the result of determination of adulterants; and
a database configured to receive the result of determination of adulterants from the at least one portable apparatus via the communication unit thereof, the database configured to store historical data related to milk samples, including at least one of their source, date of testing, and results of determination of adulterants,
wherein the system is configured to allow a computing device to connect with the database to access the historical data related to milk samples.

7. The system as claimed in claim 6, wherein the database is a blockchain database.

8. The system as claimed in claim 7, wherein the blockchain database implements at least one smart contract configured to be executed when one or more predefined conditions related to results of determination of adulterants for a specific milk sample are met.

9. The system as claimed in claim 6 further comprising a user interface configured to at least one of: display the historical data related to milk samples, allow users to verify history and/or quality of specific milk samples by fetching relevant data thereof from the database.

10. The system as claimed in claim 6 further comprising a server configured to generate analytical insights based on patterns in the historical data, wherein the analytical insights are related to one or more of: milk supplier evaluation, seasonal adulteration trends, regional adulteration trends.