Mathficast Software Services Limited

Mathfi-FoodAndDrink©
Classifier/Predictive AI

A next generation AI-powered service, helping your decision experts, food recommendations platforms or food or dietary scientists make binary and multi-class decisions by performing binary or multi-class predictions and classifications or sanity checking their existing predictions/classifications for example:

1. Help people predict how nutritious any food or recipe is for them: Having measured the key nutritional parameters of hundreds of past foods and recipes including energy level (calories), Lutein and Zeaxanthin, vitamin E, vitamin D, vitamin K, saturated fat, Monounsaturated Fat, Polyunsaturated Fat, Cholesterol, Weight, refuse percentage, Niacin, vitamin B6, Folate, Folic acid, Food folate, Folate DFE, Choline, vitamin B12, vitamin A, vitamin A RAE, Retinol, Alpha Carotene, Beta Carotene, Beta Cryptoxanthin, Lycopene and any other relevant data features and having correctly verified, labelled and classified those past samples of different recipes or foods at five levels in terms of being nutritious (Level 5 highly nutritious and Level 1 with the lowest nutritious value, the labels and targets of prediction), for a new food or recipe predict how nutritious it is (and with what certainty and probability).

2. Classify milk samples based on their quality: Having measured the quality parameters of hundreds of past milk samples including water (g), energy (cal.), protein (g), fat (g), lactose, minerals (g), total dry extract (% m/m), defatted dry extract (% m/m), Peroxidase, Phosphatase, acidity expressed as Lactose acid (% m/v), Cryoscopic index (°C), Crysocopic index (°H), Somatic Cell Count, levels of microorganisms and contaminants including Coliforms, Salmonella, Staphylococcus aureus, aerobic and anaerobic mesophilic bacteria, Lactobacillus fermenti, Lactobacillus lactic, Lactobacillus acidophilus, Streptococcus thermophilus, Aflatoxins, pH, temperature, taste score, odour score, turbidity and colour, and having correctly verified each past sample’s quality class and labelled as low, medium and high (the target of the classification), classify a new milk sample into the three quality levels (and provide probability and certainty of the classification), provided that all the data features (described above) are available for the new sample.

3. Decide whether a water sample is drinkable by human: Having the data features (characteristics) of hundreds of past water samples such as Nitrates and Nitrites , turbidity and total suspended solids (TSS), pH scale, water temperature, hardness of water, fecal indicator bacteria, flow of the water, total dissolved solids (TDS), total organic carbon (TOC), Polycyclic Aromatic, Hydrocarbons (PAH), Pesticides, Lead, Iron, Radionuclides, and some other potentially relevant data features, and having verified and labelled whether those past water samples were consumable by human or not, predict/decide whether a new water sample is also consumable by human or not (and with what probability and certainty).

4. Help people decide whether a food is suitable for their special dietary needs (for example a low carb diet, health conditions, etc.) or not: Having measured potential allergens such as milk, eggs, fish, Crustacean shellfish, tree nuts, peanuts, wheat, soybean, etc. and the levels of energy (calories), Lutein and Zeaxanthin, vitamin E, vitamin D, vitamin K, saturated fat, Monounsaturated fat, Polyunsaturated fat, Cholesterol, weight, refuse percentage, Niacin, vitamin B6, Folate, Folic acid, Food folate, Folate DFE, Choline, vitamin B12, vitamin A, vitamin A RAE, retinol, Alpha carotene, Beta Carotene, Beta Cryptoxanthin, Lycopene and having correctly verified and labelled those past samples of different recipes or foods as ”Good” or “Not Good” (binary labels and targets of prediction) for a specific type of diet (Low Carb for example) or a specific health condition (for example allergies), then for a new food or recipe, predict whether that food or recipe is also good for that specific diet or health condition or not (and with what certainty and probability).

5. Classify wine samples to different quality levels: Having the data features (characteristics) of past wine samples such as total acidity (g/L), alcohol (% vol.), volatile acidity (g/L), free SO2 (mg/L), total SO2 (mg/L), residual sugar mg/L), total sulphur dioxide, non-reducing extract (g/L), pH, acetic acid (g/L), soil type, and some other potentially relevant data features and verified and labelled those past wine samples in terms of quality is classified into which one of three quality levels of (5, 6, or 7), classify the quality of a new wine sample also into one of those three quality levels of (5, 6, or 7).

and any other binary or multi-class food or drink related binary and multi-class classification or prediction use cases.