Solar energy is one of the fastest growing energy industries around the world. One of the main problems faced by PV installations is the diversity of solar energy supply during the day. To increase the efficiency of providing this energy, use solar tracking - A solar tracking system is a specific device intended to move the PV modules in such a way that they continuously face the sun with the aim of maximizing the irradiation received by the PV array. The use of such a solution always increases efficiency, regardless of location. This is crucial in the case of India, which increased its energy production from solar panels by 8 times in 4 years. In this article we present the results of joint work of students from Poland and India. Based on the work, they designed and constructed a solar tracking system based uniquely on image processing. Instead of the most common photoresistors, to determine the position of the sun in the sky, the image from the camera was used, which was then subjected to appropriate filtration to quickly and efficiently determine the brightest point of the image - assuming that this is the position of the sun. Then, based on the coordinates of the brightest point, servo motors position the panel at the right angle, perpendicular to the sun, on the vertical and horizontal axis. The control unit is Raspberry Pi Zero, to which both the servos and the camera are connected. Research in laboratory conditions, under artificial light, confirmed the correct operation of the system. The system should be able to follow the sun also under various weather conditions which are occurring in Nagpur where system is located. It can be used in practical application and operate in real time.
There is huge amount of information accessible within the healthcare systems. But there do not exist enough analysis tools to mine uncovered, unusual but useful patterns in data. Data mining has been used successfully in various fields to discover hidden patterns and trends, alerting about the hidden anomalies in the data or simply helping in the decision making process. This paper how classification techniques in data mining can be applied for heart disease prediction. To predict and alert about any future coronary ailment in the patients techniques like Naïve Bayes, and Decision tree are applied and efficiency of these algorithms is compared. The dataset taken is Cleveland dataset with 14 attributes.
This paper presents an overview of the current state-of-the-art in mobile data stream mining and its applications. The paper presents the strategies and techniques for adaptation that are essential in order to perform real-time, continuous data mining on mobile devices. We present an overview of adaptation strategies for data stream mining and in particular for memory conservation with Algorithm Output Granularity. For mining purpose, we uses k-means clustering algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.