A Wearable Veterinary Sensor
We're proud to inform you that we've received our product classification trademark (TM) from the United States Patent and Trademark Office (USPTO ). With the approval of the USPTO, we are now CLASS10 device manufacturers. Generally, the CLASS 10 classification is reserved to medical apparatuses such as surgical, medical, dental and veterinary apparatuses and instruments; artificial limbs, eyes, and teeth; orthopedic articles; suture materials. Specifically, we have been assigned "Class 10: Wearable veterinary sensor for use in capturing a cow’s vital signs, providing data to the farmer to monitor the cow’s milk productivity, and improving its overall health".

Waterproof Sensor Enclosure
Our field analysis revealed that having a waterproof sensor enclosure enables a long lasting, smooth function of IoT sensors; as such, dairy management does not need to change any existing day to day activities or process.

Edge Module
The Sensor Edge Module enables the delivery of real-time actionable insights to dairy management. We have designed the Sensor Edge Module for low and intermittent network connections so that our analytics provide the most accurate and meaningful insights to the dairy industry.

Milk Fever
Milk fever is a disorder that often affects dairy cows close to calving. It is a metabolic disease caused by a low blood calcium level (hypocalcaemia). Between 3 to 10% of cows in dairy districts are affected each year, with much higher percentages occurring on some properties.

• Patented algorithms based on accelerometer & cattle movement activity
• Identification of halts, or stillness, in activity

Ketosis
Ketosis is a metabolic disorder that occurs in cattle when energy demands-- for example, the increased production of milk-- exceed energy intake, thus resulting in a collective lower, or “negative” energy.

• Patented edge analytics that monitor the onset of increased activity.
• Identification of Yield changes
• Production
• Feeding

Rumination
Rumination, in cattle, is the regurgitation of fibrous matter from the rumen to the mouth, and the return back to the rumen; the process of rumination is also a window to cattle health. This biological process is natural within cattle and other animals classified as ruminants. Rumination is not only a requirement for healthy cows; it can be a very early indicator of stress or illness. Although both dietary factors-- the fiber content in a forage, dietary fiber form, digestibility-- and internal rumen function impact the process of rumination, on any given diet, a cow will control rumination in response to external stressors. Stress can be assessed by means of deviation from the herd’s or the individual cow’s baseline rumination time, 48 hours prior to any other indicators being evident. By monitoring decreases in rumination times, management changes can be made to alleviate stressful situations, or to begin treating a sick cow. Our sensors enable farmers to specify & capture rumination threshold counts, allowing them to identify possible deviations in rumination patterns, and thus treat cattle accordingly.

Lameness
Lameness causes stress in cattle, which debilitates them and reduces productivity. The financial impact of lameness includes losses from decreased production, cost of treatment, prolonged calving interval, and possibly nursing labor. Loss of milk of 1.7–3 L/day for up to 1 month before and 1 month after treatment due to pain, and milk discarded because of antibiotic therapy must also be considered. Our sensors identify lameness symptoms, and enable farmers to address them accordingly. Our Sensors identify Lameness (proactive) Symptoms:

• Built-in Machine Learning Algorithms that Detect Lameness Symptoms
• Cloud Enabled In-Memory Grids that Compare Behavior vs. Health

Healthy vs. Sick Cattle Detection
Our Sensors identify healthy-vs.-sick cattle:

• Patented Algorithms based on accelerometer & cattle moment activity
• Behavior Change

Forecasting commodity prices plays an important role in terms of decision making regarding forecasted planted/harvested acreage of crops and the financial well being of small farmers. Expected agricultural commodity prices can influence the production decisions of farmers and ranchers on a planted/harvested acreage of crops or inventory of livestock and, thus, affect the supply of agricultural commodities.

Changes in commodity prices also affect a farm’s financial wellbeing. For example, sustained periods of low commodity prices reduce farm revenues and prompt farmers to rely increasingly on credit, making them vulnerable to higher interest rates and other changes in economic conditions. Sustained periods of high commodity prices can contribute to an increase in farm revenues as well as an increase in resilience to changes in economic conditions. Changes to commodity prices also have implications on food security: sustained low prices increase a consumers' ability to purchase adequate quantities of food, while sustained high prices decrease their food security, particularly in developing countries.

The behavior of agricultural product prices is sufficiently unusual and requires special treatment. Agricultural Commodity Markets are sensitive to macroeconomic environment, oil prices, demand/supply, consumer tastes/preferences, adverse climatic conditions, biofuels, stock to use ratios, dollar exchange rates, speculation, food storage, speculative activity, financial markets, fertilizers, trade restrictions, wealth of nations, and other economic conditions.

Analytics platform consists of two core engines: Machine Learning and Recommendation Engine

The goal of our ML and rule processing is simple: provide actionable insights to dairy farmers. Technologically, ML and rule processing are performed at both a dairy sensor level (closer to cattle in dairy farms) and in the Hanumayamma Dairy Cloud.

Pattern Detection: As a part of the Dairy Analytics platform, we have developed several supervised and unsupervised machine learning algorithms. We have analyzed several real-time dairy streams and developed industry standard decision trees that can apply the most appropriate proprietary machine learning algorithms ( USPTO - Patent Pending ). Using Machine Learning and Pattern detection, we can correlate the relation between several dairy optimization factors, such as the impact of medication, vitamin intake, output, and seasonal influencing factors on the health and milk output of dairy cattle.

Historical Analysis: Historical analysis includes the influence of seasonal factors such as heat Stress(HS), and pneumonia on dairy cattle milk output. Moreover, our architecture ties the weather forecast-- i.e. weather patterns in coming weeks-- to the historical observed behavior of dairy cattle. For instance, if a dairy cattle shows illness related symptoms due to sudden temperature changes, our architecture provides actionable insights to dairy personnel by looking into any sudden, or prospective, weather changes and immediately alerting them of any such events.

Our recommendation system helps dairy management such that food optimization, medication suggestions, optimal dairy settings per cattle, and disease management are assured. We have developed a dairy recommendation engine by integrating several data sources that take into consideration both dairy contextual details and location details ( USPTO - Patent Pending ).

We apply both content and collaborative recommendation systems. The main idea of the collaborative recommendation approach is to generate network synergies in terms of cattle disease analysis, medication, and milk productivity.

Smary Notifications: Another important feature of our recommendation system is to prioritize the notifications that dairy management and operation personnel receive and present the notifications in a way that reduces alert fatigue. We have observed various dairy farms-- small and large-- where systems such as milk production, weather, temperature, health, and location generate several notifications per day; if not handled properly, this can interrupt dairy operations, and thus reduce overall productivity.

Social presence Analytics: Our recommendation system applies location based social presence analytics to provide the most relevant information to dairy management. By applying social presence analytics to dairy management, cattle disease management drastically improves, and, at the same time, dairy farms can actively collaborate with the local community.

Farming is an expensive process that consists of both internal and external expenses; feed, fertilizers, human labor, equipment, finance, operations, security, and transportation are some of these expenses. Fertilizer is a significant expense for most grain farms, although its percentage as a crop expense varies across continents and countries. For example, fertilizer is the leading cause of major debt faced by small farms in India. Additionally, the cost of agricultural fertilizers has a huge influence on the overall yield and production of maize in Malawi.

Predicting the cost of fertilizer would have a multiplier effect on developing economies, and thus a live-saving impact on them as well. To elaborate, fertilizer price prediction would reduce the debt of farmers. A 2018 study conducted by the National Bank for Agriculture and Rural Development in India showed that 52.5 percent of all agricultural households were indebted, in accordance with prevailing banking rules that do not allow farmers who have running loans to borrow more credit. Hence, indebted families in need of credit often push female farmers to take loans, further perpetuating the vicious debt cycle that is now so common across the western Indian region, as well as in many developing countries where farms have plunged into cyclic debt due to the cost of fertilizers and low crop yields. Data released earlier this year showed that India had 93 million microfinance accounts, most of whom were women in self-help groups; a rise of 22 percent from the previous year. Microfinance lending rates are much lesser than those quoted by private money lenders, who thrive in these areas.

Particularly, risks related to the effects of climate change & weather events on agriculture play an important role in every industry and service sector of the economy. It would be prudent to say that macroeconomic indicators and Gross Domestic Product (GDP) has weather event signatures written all-over. To elaborate, the direct impact of weather events can be witnessed in construction, retail, agriculture, oil & gas, entertainment, travel, and public health. The project cost estimation, schedule, delivery, and productivity of business-related activities of the above-mentioned industries depend on the weather. Adaptive analytics is key to understanding and planning for the impacts of weather events on agriculture.

The interplay of commodity models and weather model events coupled with the infusion of ensemble machine learning models serve as the best signal harvesters; they can predict crop yield and provide information regarding the lineage of weather events to mitigate small farmer risk.