Search

Text classification is an essential advance in characteristic dialect processing. It very well may be performed utilizing different classification algorithms. Hadoop Map Reduce is widely utilized in text classification to perform classification on colossal measure of text data. However, Map Reduce required a ton of time to perform the tasks thereby increasing latency and since the data is distributed over the cluster it builds time and thus reducing processing speed. Also, Hadoop utilizes long queue of code. Motivated by this, we propose a basic yet compelling machine learning method which uses Naive Bayes classifier for text data. In Machine Learning approach, the classifier is built automatically by learning the properties of categories from a set of predefined training data. Hence, it can process complex furthermore, multi assortmentinformation in dynamic situations. Here we propose a naive bayes classifier which scales directly with number of indicators and data points which can be used for both binary and multi-class classification problems. We implemented the presented schemes using Machine Learning tool. The experimental results demonstrate the performance improvement in the classification technique.

Batteries are most widely used device to store the energy. The importance of the batteries is increasing especially to store the energy harnessed from renewable energy resources. The application of batteries in hybrid electric vehicles (HEV) is ever demanding and increasing. The batteries when employed in stack, individual cell parameters will be altered due to the effects of temperature gradients, ageing effects and charging and discharging cycles. Individual cells will have different SOC. If the stack is considered as a two terminal device and allowed to charge, the individual cells in the stack will not be charged uniformly. Few cells will be overcharged, few will be undercharged and few will be at the mid-range of its maximum value. Continued use of stack with this condition will degrade the life of the batteries and the efficiency of the entire system drops to unacceptable range. High-end battery users are aware of the uniformity to be achieved in the battery stack specially considering the valve regulated lead acid batteries. The paper aims at having the equalization for series connected lead acid batteries. The paper presents a simple and efficient active equalization scheme to equalize the batteries connected in series. The implemented model checks the voltage value across each battery and identifies the battery with the weakest voltage. The identified battery is allowed to charge without affecting the charging needs of other batteries in the stack. The paper is to have a firsthand experience in equalizing the series connected batteries.

The individual cells within a battery string differ due to manufacturing variations, temperature gradients, and aging effects. If the string is treated as a two-terminal device while being charged and discharged, the individual cells will have different states of charge (SOC). Some cells will be chronically overcharged, undercharged, or over discharged. Over many cycles, this tends toward capacity decrease for the cell and the pack. Sophisticated battery users are aware that SOC balance is necessary, particularly for valve-regulated lead-acid (VRLA) battery. The paper impact is to enhance the uniformity of the battery cells and hence to improve the life of the battery through active charge equalization process. A charge equalization circuit to equalize three lead acid batteries is developed and presented in this paper. To compensate for the differences in the capacities, and the variation in the rate of charging/discharging among different batteries in a stack, an active charge equalization topology has been developed to maintain all the batteries in the stack at the same voltage level. The implemented architecture monitors the voltage across each battery in the stack and then identifies the battery with lowest SOC in the stack. The main objective of this paper is to obtain a first-hand experience with the design of a battery equalization circuit.