1. INTRODUCTION:

Artificial intelligence may be a branch of computing that concerned with building smart machines which will perform tasks that typically requires human intelligence. John McCarthy (father of AI) defined AI as “the science and engineering of making intelligent machine especially intelligent computer program”^1,2. By 2050, the world's population will have risen to 9.1 billion people, leaving only 4% of land available. During this covid19 pandemic, the only thing that can keep our bodies healthy is “immunity.” It is vital to eat healthy foods in order to preserve our body's immunity power. This review may be a study of – “how AI is playing a crucial role within the production of healthy food products”.

Food safety is a major concern of today’s Era lot of foods are wasted due to contamination, AI has a huge application in food industry. This technology has helped food industry to deal with the problems of human error^{3, 4}. Food processing waste is a major concern of today’s era as it contains many useful vitamins, minerals and many other nutrients, food waste come out throughout the food system, food processing, dispersal, retail and consumption. Food waste mainly occurs due to chemical contamination from environment, contaminants may be present within food in their raw stage and sources of this contamination is vehicle, exhaust of diesel and petrol, long distance transport. Heavy metals like mercury, lead, cadmium, zinc, and copper can float into the soil and become a part of the food chain to infect the raw food materials in field. Toxins and naturally existing contaminants cause the majority of food contamination, which occurs during food processing, packing, preparation, storage, and transportation. Many procedures must be completed before raw materials may be converted into a finished product, including sorting, grading, washing, processing, packing, and marketing. Not only that, but cleanliness must be maintained at the same time. Today, machine learning model are being developed to deal with the complexity and variety of data in food Industry². So that Artificial Intelligence techniques is use to make certain assured quality food product.

2. Sorting and Grading:

Sorting occur separation unit operation that is based on one single measurable property, on the other hand grading is overall assessment of quality based on multiple properties or multiple attributes. One of the important steps of food processing is sorting, a process of separation of food or raw materials on the basis of size, shape, weight, image and color. By utilizing AI, food Processing companies can accomplish significant automation for food cataloguing, using a combination of cameras, lasers and machine learning to enable food sorting with enhanced efficiency¹. Algorithm helps to turn a set of data into model to identify whether this algorithm is supervised, unsupervised, classification or it is regression etc. AI is used as a means to better calibrate machines in order to manage several product sizes and reduce waste and cost². Food manufacturers use it to determine which goods are fruits and vegetables, as well as to detect contaminants and anomalies. Sorting is done on the basis of image recognition. Weight sorting, size sorting, and shape sorting, and color sorting being done on the basis of image recognition. For preservation of these food items, it needs sorting and grading because raw material comes from the field may contain pesticide, herbicide and some disease also so these fruits and vegetables should be checked before processing otherwise shelf life of the food products will decrease. Sorting is a labor-intensive process and there is a high chance of human error, to reduce those errors automatic sorters are used by food industries⁴. Companies within the food industry, like TOMRA Sorting Food are among the few that cash in of AI to develop machines that significantly enhance the sorting of food. These technology-inclined systems are sensor-based and utilize features such as cameras and near-infrared sensors to see food products with human perception. The entire procedure of automatic sorting and grading is described further down⁴.

2.1 Image Capturing Method:

Image capturing method is an electronic technology, during this method object is targeted by a light-weight source. Absorption of that light by the thing is sensed by light weight instrument, and light-weight absorbing characteristics of the thing is converted to an electronic record on pixel basis number of the sensors like CCD (charged coupled device), CMOS (complementary metal oxide semiconductor) are utilized in camera for this purpose⁴.

2.1 Image Acquisition:

Image acquisition system Composed of a mini camera mounted perpendicularly to the Imaging stage on which fruits and vegetables are lay down and pictures of raw materials are casted. Digital image processing is employed for evaluating external features of the food Products like size, shape and colour image recognition name of the tools which are used for this purpose are camera, Magnetic Resonance Imaging (MRI), CT (CT), ultrasound Electrical tomography⁴.

2.2 Computer Vision System:

Computer vision system technology helps in automatic inspection of the food products it's usually done by capturing, processing and analysing images. Images are taken from physical sensors and software is employed to investigate the image in computer vision system colour of the raw materials are determined by the wavelength emitting from the surface out from fruits and vegetables. For quality checking purpose nowadays, this idea is widely utilized in food industries⁴.

2.3 Image Processing:

Image processing is typically done through number of stages like image pre-processing, segmentation, feature extraction and selection. Image pre-processing could be a method refers to the conversion of real images into grey scale image it helps in texture feature extraction using MATLAB, images captured by camera are further converted into a digital image which is read by the Computer within the variety of tiny dots (pixel) machine can identify the defects present within the fruits and vegetable⁴.

2.5 Segmentation:

Segmentation process is mostly accustomed recognize fruits and vegetable diseases and to notice the difficulty and challenges. Segmentation is often done by three different techniques i.e.

a) Thresholding

b) Edge segmentation

c) Region segmentation.

Thresholding is an efficient tool for separating the image from background, various factors like motion, noise, ambient illumination, gray level within the item act as a resistance in thresholding; during this method a threshold is chosen and a picture are splits into pixels, have values but the brink. Region segmentation method includes region growing, cleave and unite, histogram thresholding region growing could be a procedure that groups pixels or sub region into larger region. This method is a smaller amount tactful to noise and it's found to be a good technique for noisy images. Region splitting, region merging as the name indicates edge means boundaries; edge-based segmentation algorithm identifies the sting of the thing (pixel)⁴.

2.6 Feature Extraction:

After segmentation feature extraction is finished to acknowledge certain features of the image that may be detected and represented for further processing, it's wont to identify whether the fruit and vegetable is flawed or non-defective, colour feature is that the most generally used visual feature in image retrieval indexing to try and do this R Venkata Raman et al in 2012, images In RED, Green, Blue (RGB) color projection values of the Pixels are extracted using MATLAB programming. Ripeness and unripens also will be calculated by this system to work out the fault and full growth of the food products some properties like color feature, morphological feature and texture feature are used⁴.

3. Spectroscopic techniques and computing for Food and Beverage Analysis:

Spectroscopic techniques are potential tool to research the standard of food and beverages. Such techniques in addition to mathematical modelling and AI offer enhanced spectral data analysis experience. This Volume is handling spectral data analysis applying spectroscopic techniques equipped with computer science.

3.1 Laser Induced Breakdown Spectroscopy in Food Analysis:

Adulteration, internal control, food safety, and identifiable is severe issues in the food industry that are extremely important to buyers. In recent years, food analysis has focused on laser induced breakdown spectroscopy (LIBS) analysis by direct detection of the optical emission from laser-generated plasma, primarily because this technique offers a rapid and cost-effective method. The use of the LIBS approach in conjunction with mathematical modelling, namely neural Networks techniques, has opened up new possibilities, and is also covered. LIBS analyses a sample by directly measuring the atomic emission of the weather from a laser-induced plasma formed by ablation of the material, resulting in an instantaneous spectral fingerprint that is reflective of its elemental makeup⁵. LIBS provides several Advantages over conventional methods for elemental analysis by (a) Eliminating the sample preparation step for analysis; (b) Performing the analysis in any state of matter (solid, liquid, gas) (c) Providing a quick analysis during a few seconds; (d) Requiring a very bit of sample, within the order of micrograms, that's Vaporized from the surface of sample; and (e) Providing simultaneous detection of all elements disinterestedly , including those present in molecules (which are atomized during the process)⁶. Although there's a loss of molecular information in plasma, this system has provided excellent results for the identification of the many polymer organic compounds⁷ or bacterial samples⁵. The developed LIBS chemical analysis methods believe in conducting a quick identification of the sample by utilizing a unique property of LIBS, which is its capacity to obtain a spectral “fingerprint” of the sample from the emission spectra, such as the sample's character and composition. Thus, LIBS dispense a singular spectrum, illustrative of the sample beneath analysis, which may be analyzed by multivariate data analysis techniques or neural networks (NNs) Algorithms. employing a association procedure, the developed LIBS-NN system are often trained by supervised algorithms so as to acknowledge spectra of test sample from a group of various samples, evaluating the similarity of unknown test spectra against a Reference spectral library of classified samples, the selection of NNs as classification method has been made due to its significant identification capability with a comparatively Simple implementation⁸.

4. The utilization of FTIR Spectroscopy combined with statistical method in food Composition analysis:

IR spectroscopy is that the most vibrational spectroscopic techniques widely applied in Food analysis ⁹, which measures the vibrational energy levels during a compound¹⁰. IR spectroscopy is one among fingerprint analytical techniques, commonly applied in wide application in food science. Fourier Transform Infrared (FTIR) spectroscopy is a perfect technique for characterization and identification, confirmation, and quantitative chemical analysis of food components¹¹. There are two sorts of spectrometer, namely dispersive instrument and Fourier-Transformed spectrophotometer supported interferometer. FTIR spectroscopy offer some advantages in identification and quantitative analyses including fast spectral data acquisition, without or minimal sample preparation, non-destructive during which the analyzed samples by FTIR spectroscopy are often analyzed using other methods like chromatographic-based techniques, high-throughput, low cost, applicable for a good range of physical sample types (liquid, semi-solid and solid samples). Besides, IR spectroscopy are often used for analysis of multiple analytes, especially together with statistical method¹². FTIR spectroscopy are often utilized in the wide selection of wavenumbers region which give excellent resolution of spectra alongside the massive number of peaks, which may be correlated with the presence of certain analytes within the samples¹³. Due to its versatility with minimum use of solvents, FTIR spectroscopy is taken into account as green analytical techniques which are more environmentally friendly¹⁴.

4.1 Chemometrics:

Chemometrics also attribute to as multivariate data analysis (MDA), may be a branch of chemistry which apply mathematics and statistics sciences to treat chemical data either qualitative or quantitative data (pH, concentrations, weights, etc.). Some topics are covered in chemometrics, namely descriptive statistics, the experimental design, process optimization, detection and signal processing, multivariate calibration, classification modelling and analytical quality assurance¹⁵. Chemical data usually consists of the properties and values of numerous chemicals as determined by instrumental methods, with a variety of causes of variance. The Objectives of the Application of Combination FT-IR, 2D FT- IR and MVA for Food analysis:

a) Identification of raw RM; discrimination of the same RM, which was based on variants, geographical origins, harvested time and treatments.

b) Rapid identification of genuine and counterfeit products.

c) Quality control of the products.

d) Differentiate products from different manufacturers.

e) Stability evaluation of the RM and related products.

f) Performing qualitative and quantitative analysis of compounds or group of Compounds in RM and/or products.

g) Monitoring and analyzing the manufacturing and extraction processes.

h) Performing rapid qualitative identification of RM in various formulations of the merchandise.

Modified from PerkinElmer, Complete Solution for Traditional Medicine Research and Analysis¹⁶.

5. Spectrophotometric Methods and Electronic Spin Resonance for Evaluation of Antioxidant Capacity of Food:

“Antioxidant” could also be a well-liked term that bears on to bioactive compounds that are not necessarily nutrients but can deliver added value to food. Therefore, the determination of the antioxidant competence of foods has been of considerable interest for several decades. Free radicals are highly unstable molecules that contain unpaired electrons, generated in vivo during metabolic processes. However, environmental or behavioral Stressors (pollution, exposure to sunlight, smoking cigarettes, excessive alcohol Consumption, etc.) or just a malfunction of the assembly of endogenous antioxidants can cause excess free radicals, which results in oxidative stress. Oxidative Stress can damage lipids, proteins, enzymes, carbohydrates, and DNA, preventing the traditional functioning of the cell. These biochemical alterations build the molecular basis within the development of cancer, neurodegenerative and autoimmune disorders, cardiovascular diseases, and diabetes. Under such conditions, the exterior supply of Antioxidants is important to catch up on the harmful consequences of oxidative stress. Since antioxidants are naturally present in vegetables, a balanced diet helps the body prevent these diseases and deliver added value to plant products^17,18. Raw extracts of Phenolic compounds-rich fruits, herbs, vegetables, cereals, and other plant materials are gaining popularity in the food sector because they prevent lipid oxidation and thereby increase food quality and nutritional content^19,20. The antioxidants present in food, also called dietetics, perform important functions in food and/or in mammals by counteracting oxidation processes and preventing chronic diseases associated with oxidative stress. These compounds exert their activity through: (1) inhibition of free radicals, (2) inhibition of reactive oxygen/nitrogen Species (ROS/RNS), or (3) chelating metals that catalyze oxidative reactions. Different antioxidants of synthetic origin have been described that prevent rancidity in food caused by the oxidation of unsaturated fats. Likewise, naturally occurring antioxidants were discovered, isolated, and used for the same purpose²¹. Subsequently, synthetic antioxidants such as butylated hydroxytoluene (BHT), Butylated hydroxyanisole (BHA), propyl gallate (PG), and ethoxyquin (EQ) were developed. These compounds or their combinations are commonly used in various foods to retard rancidity^22,23. However, it's been reported that such antioxidants possibly increase health risks due to their toxicity and carcinogenicity, creating the necessity to spot natural sources that have antioxidant potential²⁴.

Table 1: Methods for determining Antioxidant capacity based on the mechanisms of Hydrogen atom transfer and Electron transfer.

Hydrogen atom transfer methods (HAT)	Electron transfer methods (ET)
Oxygen radical absorbance capacity (ORAC) method	Ferric reducing antioxidant power (FRAP)
Cellular antioxidant activity (CAA) assay	DPPH free radical scavenging assay
Scavenging of hydroxyl radical by ESR	Total phenols by Folin–Ciocalteu
ABTS radical scavenging method	Trolox equivalent antioxidant capacity (TEAC) decolorization
Lipid peroxidation inhibition capacity (LPIC) assay	Copper (II) reduction capacity
Total radical trapping antioxidant parameter (TRAP)	N, N-dimethyl-p-Phenylenediamine (DMPD) Assay
Inhibited oxygen uptake (IOC)
Crocin bleaching nitric oxide radical inhibition activity
Hydroxyl radical scavenging activity by p-NDA (p-butrisidunethyl aniline)
Scavenging of H2O2
Scavenging of super oxide radical formation by alkaline (SASA)

6. Thermoluminescence the tactic for the Detection of Irradiated Foodstuffs:

Irradiation, or cold irradiation, is a method of treating food with radiation. Pasteurization is one of the most effective ways of microbiological decontamination for reducing food-borne disease infection in potential consumers. From 1984 irradiation technique is approved and issued²⁵ by WHO/FAO Codex Commission and recommended for a standard use similarly to thermal Pasteurization or deep freezing. Thermoluminescence is one of the CEN-approved detection methods, which was published as European Standard EN 1788 in 1996²⁶. Improved by the modification of preparative step of thermoluminescence detection method supported European standard. The technique is now widely accepted as the most effective approach for detecting irradiated food, and it is used in the world's top food safety laboratories. The tactic's advantages include great sensitivity, dependability, and adaptability for controlling a variety of vegetal and seafood foods²⁷.

7. Food-Quality Monitoring and Smart Packaging with Chemical and Biological Sensors:

The increased interest in food quality and safety necessitates the development of sensitive and reliable research methodologies, as well as technology for food preservation and quality. Next-generation technologies such as smart sensors and labels so as may be applied to packaging can help monitor the status of the item. These are frequently used to detect freshness markers and offer a real-time “index of quality” for the products, as well as to monitor temperature fluctuations and detect the presence of dangerous components. We explain the current state of chemical and biological sensors for food quality and safety monitoring, which can be used to extend the time and estimation capabilities of food products²⁸.

7.1 Current Status of Active and Functional Packaging:

Traditional packing methods are employed not just to make products easier to handle, but also to keep their nutritional value, increase their shelf life, and prevent rotting. Efforts have recently been made to develop smart and active packaging solutions²⁹ that, in addition to preserving the goods, can perform additional services such as detection and communication to alert consumers when deterioration occurs³⁰. One example of active packaging is the use of absorbing or emitting sachets/pads as shown in Figure 2. Absorbing sachets could contain O2 scavengers to reduce fat oxidation, ethylene scavengers to reduce fruit and vegetable ripening, humidity absorbers, odor absorbers, and antimicrobial growth inhibitors. CO2 emitters restrict microbiological development in meat, antimicrobial preservative releasers to reduce spoiling due to bacterial growth, and antioxidant releasers to reduce oil and fat oxidation are all used in emitting pads²⁸.

Fig 1: Representation of the notion of smart and active packaging technology³¹.

The conceptualization is depicted in Fig 1. Existing systems include time temperature indicators (TTI), which permit a thermal history of the merchandise thought out time of storage, and distribution, allowing the buyer or the manufacturer to evaluate the product status³¹. For instance, MonitorMark™ a TTI sensor developed by 3M™ (3M™, Maplewood, MN, USA) was designed to watch thermal exposure for meat, fish, and dairy products in course of storage and transportation below 20°C³². Another example is the CoolVu indicator³³ expanded in Fresh point-Switzerland, which encompass a metal and a transparent label. Several systems enable remote monitoring via radio-frequency identification (RFID)³⁴. Flex Alert developed an RFID sensor for detecting Escherichia coli (E. coli) and Salmonella in packaged goods³⁵. RipeSense® (RipeSense, Auckland, New Zealand)³⁶was planned as a smart ripeness-indicator label, developed in New Zealand. The system can determine the ripeness of fruits without having to open the box; instead, it can detect the change in label color as it reacts with gases emitted by the fruit, which is put on the top of the package.

7.2. Food Freshness/Quality Monitoring:

Food freshness/Quality is the top “driver” during this portion, several developed and commercially obtainable freshness indicators are narrated for various sorts of food including fish, meat, and poultry, cereal grains, fruits, and vegetables.

7.2.1. Fish, Meat, and Poultry:

Different spoilage signs are typically observed when meat, fish, or poultry degrades, indicating lipid decay, protein breakdown, and ATP (ATP) decay. The pace of decomposition is determined by the type of product, storage temperature, feeding patterns, and harvesting techniques. Traditional methods for determining freshness rely on human perception; while important, they provide no quantitative data on ruined food. Methods that can quantitatively determine degradation signals through chemical or biological interactions can be used to assess the state and quality of food more precisely. Hypoxanthine, which is formed by the metabolic breakdown of ATP, is one of the most common freshness markers in fish products³⁷. Karube et al. (1984) amplified an equation for fish freshness judgement supported the content of inosine 5-phosphate, inosine, and hypoxanthine. Diverse enzymatic biosensors with colorimetric or electrochemical detection have been developed to quantify the level of hypoxanthine²⁸.

7.2.2 Cereal Grains:

One of the indications of grain spoilage during storehouse is that the emission of CO2 as results of insect infestations, and mold spoilage³⁸ bring about grain deterioration or the assembly of detrimental mycotoxins. Developing CO2 sensors for early spoilage detection has been announced and establish a sensor supported polyaniline boronic acid (PABA) managing polymer for measuring CO2 levels within the range of 380–2400 ppm in simulated grain bulk²⁸. Gluten is one more constitute of interest for grain analysis, as definite individuals can develop gluten bigotry which will bring out serious disorders of the gastrointestinal system³⁹. The most ordinary method for gluten analysis is by the traditional enzyme-linked immunosorbent assay (ELISA)⁴⁰. Recently, an antibody-based device has been reported to research the gluten content through a sort of food samples in just 3 min²⁸. Additional research into the toxicity of mycotoxin contamination in grains is of interest. Fungi produce mycotoxins like ochratoxin A (OTA), aflatoxins, trichothecenes, fumonisins, zearalenone, and ergot alkaloids⁴¹. Several types of biosensors for mycotoxin detection are described and discussed in detail. Electrochemical biosensors for OTA detection were developed using a competitive process that included OTA-specific aptamers and the peroxidase (HRP) enzyme⁴². Altogether, estimation of allergens and mycotoxins in cereals requires sample pre-treatments and extraction of the pick out component; thus, direct application of those sensing mechanisms in food packaging is challenging.

7.2.3. Fruits and Vegetables:

Fruits and vegetables are highly biodegradable and might therefore easily deteriorate before reaching the buyer. Technology for monitoring and preserving fruits and vegetables is main to decrease food loss during transportation and storage⁴³. Many fruits and vegetables produce ethylene due to environmental stress after being harvested. Ethylene are usually extracted by using ethylene absorbers or oxidizers (scavengers). Scavenging systems facilitate removal, thus lowering the loss of other products because of overproduced ethylene. To control produce freshness, ethylene sensors might be useful for recognize rapid ripening and stop fruit degradation²⁸.

Fig. 2. Schematic representation of an ethylene chemo resistive sensor. Mixture of a Cu (I) complex and single-walled carbon nanotubes (SWNTs) were drop-cast between gold electrodes. When ethylene binds to the mixture, resistance changes³¹.

8. Biosensors in Food Analysis:

The necessity for straight forward, quick, and field-portable analytical methods has boosted. Development of biosensors for food analysis. The evolution of biosensors in this field is discussed, as well as biosensor examples for detecting pathogens, allergens, and other contaminants insecticides and mycotoxins are examples of toxicants²⁸.

8.1. Biosensors for Food-Allergen Detection:

As the prevalence of food allergies to even trace levels of allergens rises, allergens in foods such as milk, soybeans, crustaceans, eggs, gluten-containing cereals, peanuts, and nuts (e.g., almonds, Brazil nuts, cashews, walnuts) are becoming a greater safety concern. In industrialized countries, about 10% of preschool children suffer from clinical food allergies⁴⁴. A variety of DNA or immune-based biosensors have been succeeded for allergen detection, but in many cases sample preparation and purification are laborious and time-wasting²⁸. Employing antibody-based identification and magnetite beads, NIMA Company (San Francisco, CA, USA) has developed a sensor to identify peanut allergens in ppm ⁴⁵. The presence of gluten in food such as wheat, barley, and rye causes disorder for people who are unable to digest gluten. A label-free electrochemical immunological sensor for -lacto globulin, a milk allergy, was created. In another assay, allergy-causing proteins found in milk, such as casein and -lacto globulin (-LG), were identified utilizing an aptameric immobilized on a graphene-modified screen-printed electrode with Volta-metric detection²⁸.

8.2. Biosensors for Bacterial-Pathogen Detection:

In 2010, the Foodborne Disease Burden Epidemiology Reference Group (FERG) of the World Health Organization (WHO) predicted 600 million foodborne illnesses and 420,000 fatalities worldwide⁴⁶. The foremost causes of those diseases are pathogenic bacteria Escherichia coli and Salmonella causing most foodborne outbreaks within us⁴⁷. In food analysis, rapid identification of harmful bacteria is critical. Because of its portability and capacity to identify infections on-site, biosensors may be a viable alternative for pathogen detection. The most common biosensors for detecting bacterial pathogens are those based on immunological and DNA recognition, but these have need of lengthy preparation procedures, including labelling and numerous washing stages⁴⁸ and specialized facilities. A fluorescent DNAzyme probe that exclusively secures E. coli was recently developed and printed on a transparent cyclo-olefin polymer packaging. Biosensors might be designed to comprise materials with antimicrobial activity to compel smart packaging. A 3D-ZnO Nano rod-based electrochemical sensor was developed to both detect and kill bacteria showing the inactivation of fifty of bacteria²⁸.

8.3 Biosensors for Food Adulteration, Authenticity, and Toxicity Assessment

Food adulteration is predicated on the small change of food composition for the focus of monetary profit regardless safety recognition. Food adulteration might be a growing concern, which generates the need for reliable analysis methods. Adulteration of milk products with melamine detection was made possible through the development of an antibody-based optical biosensor⁴⁹. To detect melamine in milk, a label-free AgNP colorimetric sensor was created⁵⁰. However, biosensors are described to prove the claimed composition and concentration of food products. Ethanol content has been approximate in alcoholic beverages by electrochemical biosensors supported immobilized alcohol oxidase enzyme⁵¹. The resolution of polyphenol content in vegetable oils allows the estimation of the product’s antioxidant capacity. An HPR-based electrochemical biosensor was planned to gauge chromogenic acid content in oil⁵². The ability to distinguish within different types of vegetable oils (e.g., olive oil, sunflower-seed oil, and corn oil) was established using an electrochemical biosensor (e.g., extra virgin, virgin, etc.)⁵³. other adulterants in food are also of interest. L-glutamate is a natural amino acid, and it is usually added to improve food flavor and to add the umami taste to food. L-glutamate has been shown to boost food intake while posing minimal health hazards⁵⁴. L-glutamate, on the other hand, has been found to have neuro excitatory properties⁵⁵. Consequently, developing reliable methods to gauge glutamate content in food products is vital. Glutamate oxidase was immobilized on a Prussian Blue-modified electrode to create an aerometric biosensor⁵⁶ such biosensors are developed by AI which very helpful to give best quality food products.

9. How AI can save Food Industry:

Rarely features a crisis accelerated the adoption of a technology within the way that's occurring today with AI within the food industry. The business of selling food to consumers is being disrupted in ways that haven't been seen since the last pandemic, which occurred over a century ago. It's becoming increasingly clear that our food system was unprepared ('anti-fragile') for the Covid-19-caused crisis. With restaurants shuttered, a dramatic return to home cooking, a re-ignition in the meal-kit movement, shut-downs of meat factories and office refectory, and explosion of home delivery it's getting to seem as if the earth will never be the same again. Additionally of course will pass, yet instead of being a 6 month blip, the continued deconstruction and automation of the food supply process makes it clear that we are entering a replacement norm, which returning to the earth as we knew it won’t be possible. 8 digital technologies are convert the food business (Robots, AR, VR, 3 Printers, Sensors, Machine Vision, Drones, Block chain, IoT), but all of them have one thing in common, AI is that the cipher or sauce behind all of them⁵⁷.

10. Applications of AI in Food Industry:

Artificial Intelligence (AI) refers to the gathering of knowledge from sensors and its conversion to comprehensible information. AI machines can mimic human cognitive functions like learning and problem solving, and interpret information more efficiently than humans, reducing their got to be involved, because it is being developed, it's clear that AI also can be self-learning, and progress beyond human abilities. The utilization of AI to advance food production is accelerating because the world progresses post-Covid and expectations of speed, efficiency also as sustainability are ever-increasing alongside the rapidly growing population. Here are six samples of actors within the food industry who have introduced AI, how this has accelerated their growth, or maybe changed the way during which they operate⁵⁷.

Fig.3. Applications of Artificial Intelligence (AI) in Food Industry.

11. Regulatory Issues:

The regulation of artificial intelligence is the development of public sector policies and laws for promoting and regulating AI. Regulation is now generally considered necessary to both encourage AI and manage associated risks. Public administration and policy considerations generally focus on the technical and economic implications and on trustworthy and human-cantered AI systems, although regulation of artificial super intelligences is also considered. The basic approach to regulation focuses on the risks and biases of AI’s underlying technology, i.e., machine-learning algorithms, at the level of the input data, algorithm testing, and the decision model, as well as whether explanations of biases in the code can be understandable for prospective recipients of the technology, and technically feasible for producers to convey. Every AI system falling within this definition will be regulated by the FDA, as provided by the Federal Food, Drug and Cosmetic Act. The FDA categorizes the AI tools into three classes, according to their uses and risks, and regulates them accordingly. The higher the risk, the Stricter control the category which includes the devices involving the greatest risk. The black box nature and the rapid growth of machine/deep learning applications will make it difficult for the FDA to approve in a timely fashion all the new l devices that are continuously being developed, given the volume and the Complex nature of testing and verification involved⁵⁸. As the market grows, the FDA will likely Promulgate new regulations with a greater degree of specificity than those currently in existence, particularly in the Realms of data security and privacy⁵⁹.

CONCLUSION AND OUTCOMES:

This review is all about the application of Artificial Intelligence in Food Industry. AI is at mean of new undertaking to raise computational models of intelligence. Automating the food processing can reduce human error and it will improve the assured Quality of food product. Here various methods, software and techniques are described which are used by food industry for inspection of food material at every stage to get best assured quality product. These systems can significantly bring down labor cost and reduce waste. It is making the food Industry more efficient and better promises to yield many more new changes in near future. Implementing such Artificial intelligence tools in Food Industry will be very beneficial. Various application of AI in Food Industry such as from Sorting and grading, Processing, Food safety and cleanliness, Analysis of food, Predicting trends, and also for designing better foods. Safety of food products need to assessed. AI improves food supply chains, Food safety monitoring and testing product at every step. In such way AI helps to give better results.

CONFLICT OF INTEREST:

The authors declare no conflict of interest.

REFERENCES:

1. Chindinma-Mary-Agbai, Application of Artificial Intelligence (AI) in food industry. GSC Biological and Pharmaceutical Sciences, 2020, 31(01), 171-178 13. 171 178.

2. Kurilyak, S. Artificial Intelligence (AI) in food industry. Available from http://www.produvia.com.

3. Sebastin, J. Atrificial intelligence: a real opportunity in food industry. Food Quality and Safety. 2018.

4. Bandyopadhyay, K., Ghosh, S., & Gope, R. K. Application of Artificial Intelligence in Food Industry—A Review

5. Marcos-Martinez D, Ayala JA, Izquierdo-Hornillos RC, de Villena FJM, Caceres JO (2011) Identification and discrimination of bacterial strains by laser induced breakdown spectroscopy and neural networks. Talanta 84(3):730–737

6. Moncayo S, Manzoor S, Rosales JD, Anzano J, Caceres JO (2017) Qualitative and quantitative analysis of milk for the detection of adulteration by Laser Induced Breakdown Spectroscopy (LIBS). Food Chem 232:322–328

7. Lasheras RJ, Bello-Gálvez C, Rodríguez-Celis EM, Anzano J (2011) Discrimination of organic solid materials by LIBS using methods of correlation and normalized coordinates. J Hazard Mater 192(2):704–713

8. Caceres JO, Moncayo S, Rosales JD, de Villena FJM, Alvira FC, Bilmes GM (2013) Application of laser-induced breakdown spectroscopy (LIBS) and neural networks to olive oils analysis. Appl Spectrosc 67(9):1064–1072

9. Cozzolino D (2014) an overview of the use of infrared spectroscopy and chemometrics in authenticity and traceability of cereals. Food Res Int 60:262–265. https://doi.org/10.1016/ j.foodres.2013.08.034

10. Teixeira AM, Sousa C (2019) A review on the application of vibrational spectroscopy to the chemistry of nuts. Food Chem 277:713–724 https://doi.org/10.1016/j.foodchem.2018.11.030

11. Tan HP, Ling SK, Chuah CH (2011) One- and two-dimensional Fourier transform infrared correlation spectroscopy of Phyllagathis rotundifolia. J Mol Struct 1006(1–3):297–302. https://doi.org/10.1016/j.molstruc.2011.09.023

12. Rohman A (2019) the employment of Fourier transform infrared spectroscopy coupled with chemometrics techniques for traceability and authentication of meat and meat products. J Adv Vet Anim Res 6(1):9–17

13. Moros J, Garrigues S, De Guardia M (2010) Vibrational spectroscopy provides a green tool for multi-component analysis. Trends Anal Chem 29(7):578–591. https://doi.org/10.1016/ j.trac.2009.12.012

14. Gredilla A, De Vallejuelo SF, Elejoste N, De Diego A, Madariaga JM (2016) Trends in analytical chemistry non-destructive spectroscopy combined with chemometrics as a tool for green chemical analysis of environmental samples: a review. Trends Anal Chem 76:30–39. https://doi.org/10.1016/j.trac.2015.11.011

15. Daszykowski M, Walczak B (2006) Use and abuse of chemometrics in chromatography. TrAC-Trends Anal Chem 25(11):1081–1096

16. Indrayanto, G., & Rohman, A. (2020). The Use of FTIR Spectroscopy Combined with Multivariate Analysis. In Spectroscopic Techniques & Artificial Intelligence for Food and Beverage Analysis 9pp. 25-51). Springer, Singapore.

17. Amarowicz R, Pegg RB (2019) Natural antioxidants of plant origin. In: Advances in Food and Nutrition Research. Academic, Cambridge

18. Pérez-Cruz K, Moncada-Basualto M, Morales-Valenzuela J, Barriga-González G, Navarrete- Encina P, Núñez-Vergara L, Squella JA, Olea-Azar C (2018) Synthesis and antioxidant study of new polyphenolic hybrid-coumarins. Arab J Chem 11:525–537

19. Harnly J (2017) Antioxidant Methods. J Food Compos Anal 64:145–146

20. Al-Duais M, Müller L, Böhm V, Jetschke G (2009) Antioxidant capacity and total phenolics of Cyphostemma digitatum before and after processing: use of different assays. Eur Food Res Technol 228:813–821

21. Cömert ED, Gökmen V (2018) Evolution of food antioxidants as a core topic of food science for a century. Food Res Int 105:76–93

22. Kraybill HR, Dugan LR, Beadle BW, Vibrans FC, Swartz V, Rezabek H (1949) Butylated hydroxyanisole as an antioxidant for animal fats. J Am Oil Chem Soc 26:449–453

23. Kraybill HR, Dugan LR (1954) Antitoxidants, new developments for food use. J Agric Food Chem 2:81–84

24. Moncada-Basualto, M., & Olea-Azar, C. (2020). Spectrophotometric Methods and Electronic Spin Resonance for Evaluation of Antioxidant Capacity of Food. In Spectroscopic Techniques & Artificial Intelligence for Food and Beverage Analysis (pp. 53-75). Springer, Singapore.

25. Codex Alimentarius Commission. (1984). Codex general standard for irradiated foods and recommended international code of practice for the operation of radiation facilities used for the treatment of foods. CAC/VOL, XV, FAO, Rome.

26. PN-EN 1788:2002: Foodstuffs – Thermoluminescence detection of irradiated food from which silicate minerals can be isolated. European Committee for Standardisation, Brussels 2002. EN 1788 was published in 1996

27. Guzik, G. P., & Stachowicz, W. (2020). Thermoluminescence the Method for the Detection of Irradiated Foodstuffs. In Spectroscopic Techniques & Artificial Intelligence for Food and Beverage Analysis (pp. 77-93). Springer, Singapore.

28. Mustafa, F., & Andreescu, S. (2018). Chemical and Biological sensors for food-quality monitory and smart packaging. Food, 7(10), 168.

29. Rodriguez-Aguilera R., Oliveira J.C. Review of design engineering methods and applications of active and modified atmosphere packaging systems. Food Eng. Rev. 2009; 1:66–83.

30. Neethirajan S., Jayas D.S. Nanotechnology for the food and bioprocessing industries. Food Bioprocess Technol. 2011; 4:39–47.

31. Wang S., Liu X., Yang M., Zhang Y., Xiang K., Tang R. Review of time temperature indicators as quality monitors in food packaging. Packag. Technol. Sci. 2015;28:839– 867:

32. 3M™ MonitorMark™ Time Temperature Indicators. [Accessed on 21 August 2021]; Available online: https://www.3m.com/3M/en_US/company-us/all-3m-products/~/MONMARK-3M-MonitorMark-Time-Temperature-Indicators/?N=5002385+3293785721&rt=rud.

33. Time Temperature Indicators. [(accessed on 21 August 2021)]; Available online: http://freshpoint-tti.com/time-temperature-indicators/

34. Jones P., Clarke-Hill C., Hillier D., Comfort D. The benefits, challenges and impacts of radio frequency identification technology (RFID) for retailers in the UK. Mark. Intell. Plan. 2005; 23:395–402.

35. Biosensors. [Accessed on 21 August 2018]; Available online: http://www2.Flex-alert.Com/flexalert/applications/biosensors.

36. How Ripe Do You Like It. [(accessed on 21 August 2018)]; Available online: http://www.ripesense.co.nz/

37. Ashie I., Smith J., Simpson B., Haard N.F. Spoilage and shelf-life extension of fresh fish and shellfish. Crit. Rev. Food Sci. Nutr. 1996; 36:87–121.

38. Maier D., Channaiah L., Martinez-Kawas A., Lawrence J., Chaves E., Coradi P., Fromme G. Monitoring carbon dioxide concentration for early detection of spoilage in stored grain. Julius-Kühn-Archiv. 2010; 425:505.

39. Malvano F., Albanese D., Pilloton R., Di Matteo M. A new label-free impedimetric aptasensor for gluten detection. Food Control. 2017; 79:200–206.

40. Nassef H.M., Bermudo Redondo M.C., Ciclitira P.J., Ellis H.J., Fragoso A., O’Sullivan C.K. Electrochemical immunosensor for detection of celiac disease toxic gliadin in foodstuff. Anal. Chem. 2008; 80:9265–9271.

41. Zain M. E. Impact of Mytotoxins on humans and animals. J. Saudi Chem. Soc. 2011; 15:129-144.

42. Bonel L., Vidal J.C., Duato P., Castillo J.R. An electrochemical competitive biosensor for ochratoxin a based on a DNA biotinylated aptamer. Biosens. Bioelectron. 2011; 26:3254–3259.

43. Buzby J.C., Wells H.F., Axtman B., Mickey J. Supermarket loss estimates for fresh fruit, vegetables, meat, poultry, and seafood and their use in the ERS loss-adjusted food availability data. Econ. Inf. Bull.-USDA Econ. Res. Serv. 2009; 44:26.

44. Prescott S.L., Pawankar R., Allen K.J., Campbell D.E., Sinn J.K., Fiocchi A., Ebisawa M., Sampson H.A., Beyer K., Lee B.-W. A global survey of changing patterns of food allergy burden in children. World Allergy Organ. J. 2013; 6:1.

45. Test Your Food for Peanuts: anytime, Anywhere. [(accessed on 21 August 2018)]; Available online: https://nimasensor.Com/peanut/

46. Centers for Disease Control and Prevention (CDC) Foodborne Illness: Frequently Asked Questions. CDC; Atlanta, GA, USA: 2018.

47. Centers for Disease Control and Prevention Surveillance for foodborne disease outbreaks-united states, 2009–2010. MMWR Morb. Mortal. Wkly. Rep. 2013; 62:41.

48. Beumer R.R., Brinkman E. Detection of Listeria spp. With a monoclonal antibody-based enzyme-linked immunosorbent assay (ELISA) Food Microbiol. 1989;6:171–177

49. Gossner C.M.-E., Schlundt J., Embarek P.B., Hird S., Lo-Fo-Wong D., Beltran J.J.O., Teoh K.N., Tritscher A. The melamine incident: Implications for international food and feed safety. Environ. Health Perspect. 2009; 117:1803.

50. Ping H., Zhang M., Li H., Li S., Chen Q., Sun C., Zhang T. Visual detection of melamine in raw milk by label-free silver nanoparticles. Food Control. 2012; 23:191– 197.

51. Boujtita M., Hart J.P., Pittson R. Development of a disposable ethanol biosensor based on a chemically modified screen-printed electrode coated with alcohol oxidase for the analysis of beer. Biosens. Bioelectron. 2000; 15:257–263.

52. Mello L.D., Sotomayor M.D.P.T., Kubota L.T. HRP-based amperometric biosensor for the polyphenols determination in vegetables extract. Sens. Actuators B Chem. 2003; 96:636–645.

53. Apetrei C., Rodriguez-Mendez M., De Saja J. Modified carbon paste electrodes for discrimination of vegetable oils. Sens. Actuators B Chem. 2005; 111:403–409.

54. Jinap S., Hajeb P. Glutamate. Its applications in food and contribution to health. Appetite. 2010; 55:1–10.

55. Choi D.W. Glutamate neurotoxicity and diseases of the nervous system. Neuron. 1988; 1:623–634.

56. Karyakin A.A., Karyakina E.E., Gorton L. Amperometric biosensor for glutamate using prussian blue-based “artificial peroxidase” as a transducer for hydrogen peroxide. Anal. Chem. 2000; 72:1720–1723.

57. https://www.linkedin.com/pulse/can-artificial-intelligence-save-food-industry-aidan-connolly.

58. Pesapane, F., Volonté, C., Codari, M., and Sardanelli, F. (2018). Artificial intelligence as a medical device in radiology: ethical and regulatory issues in Europe and the United States. Insights into imaging, 9(5), 745-753.

59. Harvey, H. B., & Gowda, V. (2020). How the FDA regulates AI. Academic radiology, 27(1), 58-61.

60. Rathod S, Mali S, Shinde N, Aloorkar N. Cosmeceuticals and Beauty Care Products: Current trends with future prospects. Research Journal of Topical and Cosmetic Sciences. 2020;11(1):45-51.

61. Kale N, Rathod S, More S, Shinde N. Phyto-Pharmacological Profile of Wrightia tinctoria. Asian Journal of Research in Pharmaceutical Sciences. 2021 Nov 26;11(4):301-8.

62. Sanket Rathod, Ketaki Shinde, Namdeo Shinde, Nagesh Aloorkar. Cosmeceuticals and Nanotechnology in Beauty Care Products. Research Journal of Topical and Cosmetic Sciences. 2021; 12(2):93-1.

Received on 09.12.2021 Modified on 03.03.2022

Asian J. Pharm. Tech. 2022; 12(3):242-250.

DOI: 10.52711/2231-5713.2022.00040