Pub. Date | : April, 2021 |
---|---|
Product Name | : The IUP Journal of Computer Sciences |
Product Type | : Article |
Product Code | : IJCS20421 |
Author Name | : Neethu Behanan, Rakshita Ramesh and Vijayalakshmi A |
Availability | : YES |
Subject/Domain | : Management |
Download Format | : PDF Format |
No. of Pages | : 6 |
Weather predictions have conventionally been performed using complex models with satellite data and readings from weather stations. In recent times, modern technology has replaced these conventional techniques. However, obtaining accurate and precise weather predictions continues to remain extremely challenging. The paper proposes an architecture to enable weather forecasting using a combination of two modern technologies - Machine Learning (ML) and Internet of Things (IoT). By making use of the concept of crowd sensing and Collaborative Internet of Things (C-IoT), the paper proposes how a large amount of useful information can be collected and then processed using ML algorithms to arrive at meaningful results that aid in weather prediction. This can in turn help the IoT devices become more efficient in terms of energy consumption.
The Internet of Things (IoT) has become one of the most integral parts of modern technology. IoT-enabled system can collect vast amounts of data using low-cost embedded sensors and devices. This, along with its increasing applications, has contributed to areas like home automation, smart cities, aviation, health monitoring systems etc. If combined with other modern technologies such as Artificial Intelligence (AI), Machine Learning (ML) or Data Science, IoT can not only replace conventional systems being used for a particular task, but can also provide higher accuracy results. The paper proposes a system where IoT and ML are combined for weather forecasting. The system aims for effective prediction and better accuracy when compared to conventional weather forecasting systems. Since the accuracy of results can be increased with greater amounts of data, the aim is to collect as much data as possible from sensors embedded in various devices or objects, such as mobile phones, roads, vehicles, plants, roof tops, gardens and so on. This data is then compiled and fed into a ML model which is trained for weather prediction. This in turn can be used in smart cities for prediction of atmospheric temperature, humidity, visibility, wind speed
Embedded system, Internet of Things (IoT), Machine Learning (ML), Weather prediction