Climate change has had a dramatic impact on many agrarian developing nations. For example, in 2009, the delay of the monsoon rains by a month in India affected several macroeconomic factors including food price increases, a stock market slump, agricultural product export restrictions, and an array of agricultural subsidies. Over the past decade, there has been a growing trend in the number of farmer suicide deaths throughout the country due to a combination of economic, social, and environmental factors. On one hand, the fraction of arable land has decreased over the years due to soil erosion factors, excessive use of pesticides, and land encroachment from urban dwellers (buying land in rural areas).On the other hand, agriculture as an occupation has becomeless profitable due to a combination of poor yield (due to poor water availability, monsoon unpredictability, and soil erosion) and an increase in the cost of living. Many of these factors hint at a pending agrarian catastrophe. From a technology perspective, what can we do to help agrarian communities in India and elsewhere? While we are not experts in economic and social factors, we do believe that technology can aid in addressing some of the environmental problems faced by such agrarian societies, even if it is in some limited manner that complements other efforts.
A fire detector that can tell the difference between burning toast and a burning building could save money, annoyance, and possibly even lives, by cutting down on false alarms. German company Siemens will start selling the detector in the UK to commercial users by January 2006, and the technology could eventually make its way into homes, says the firm's fire safety manager, Andrew Morgan. The detector uses four sensors and a neural network to determine if the smoke and heat it's detecting are from a fire or are just part of the normal room environment. In the UK more than half of the 872,000 fire call-outs in 2004 were bogus, and 285,000 of those false alarms were due to fire detectors. Responding to false alarms costs money, and in the home annoying false alarms encourage people to disable their alarms.
RFID tags are being explored as possible low-cost sensors which could monitor and improve human health. Radio-frequency identification tags (RFID) are simple, electronic labels outfitted with a tiny chip and antenna. These labels are used to track and monitor everything from payments to products in a supply chain, but it is hoped that their use can go far beyond the tracking of physical items. The Auto-ID Lab at the Massachusetts Institute of Technology (MIT) believes that the chip's functionality can be transformed with a new feature: sensors. To demonstrate the idea, the team has created an ultra-high-frequency (UHF) RFID configuration which "senses spikes in glucose and wirelessly transmits this information."
The crucial component making smart technologies possible – from something as small as a ring to as large as an entire city – is the IoT. Although there are varying definitions, the term IoT is mainly used for previously'dumb' devices that didn't have an Internet connection, but that now communicate with the network independently of human action. For this reason, a smartphone isn't explicitly defined as an IoT device – although it's crammed with sensors. A connected refrigerator or microwave oven however is. Nowadays, these smart technology devices devices include billions of objects of all shapes and sizes – coffee machines, lightbulbs, driver-less trucks, wearable fitness devices, jet engines and children's smart toys – all equipped with sensors and communicating data through the Internet.
At its core, machine learning studies the construction of algorithms and learns from them to make predictions on data by building models from sample inputs. If we further break it down, machine learning borrows heavily from computational statistics (prediction modeling using computers) and mathematical optimization, which provides methods, theory and application data to those models. In essence, it creates its own data models based on algorithms and then uses them to predict defined patterns within a range of data sets. Machine-learning algorithms can be broken down into five types: supervised, unsupervised, semi-supervised, active, and reinforcement, all of which act just like they sound. Supervised algorithms are programmed and implemented by humans to provide both input and output as well as furnishing feedback on predictive accuracy during training.