Self-cleansing Urban Drainage

A moderate rainfall event can lead to harsh flash floods in most of the compact cities. Present urbanization happening in these cities create an imbalance between generated urban runoff volume and effective drainage capacity. For the survival of these, it is vital in enhancing the efficiency of an urban drainage system. However, it is a complicated task due to the accumulation of solid waste in drainage channels. These drainage systems are super sensitive to some external factors caused by their immediate surroundings. This study found out the impact of the urban form, population agglomeration, floating population, imminent prone areas of urban sprawl and waste disposing patterns of settlers can be highly influenced to the efficiency of a storm drainage system. Hence, Geographical Information System based computational techniques and weighted fussy sets are being used to track the attention need areas of the system. These particular zones to be treated through the design of "Smart Storm Drainage Unit". By this, it is expected to maintain a clear drainage channel for transportation of surface runoff all the time. Thus, by Smart Storm Drainage will be fixed into the breakdown areas or highly sensitive areas of a drainage system. This paper discusses the impact of surrounding urban area to the breakdown of the drainage system and fixates the problem by bypassing “Smart Storm Drainage Unit”.

Social media applications such as twitter, face book, blogs etc are used by the people extensively to give their opinions on everything. Study on these opinions is the major research trend and this research will help to understand the people views and this study will help to take further decisions. For the study of exploring the opinion, NLP and ML is used to classify the different emotions such as positive, negative and neutral opinions. It is very complex task to examine the input text data given by the user in social media applications. Here proposed a novel bounded logistic regression with the demonetization data sets taken from different cities of India. Results of the approached technique give the good accuracy. INTRODUCTION With the extensive use of social applications for communications, people across the globe create tons of text data every day. An interaction usually happens through a public domain, and making all this data available to everyone. Analysis of emotions is the process to extract the opinions from social media applications. Location wise data is collected and opinions of users are analyzed to find out the location wise impact of any product or any scheme. Result analyses are helpful for taking optimal decisions in future. Here, Data is collected from different locations based on the demonetization scheme and used the bounded logistic regression method and categorize the opinions of the people. Twitter Data set on demonetization took from different locations of India and explored the sentiments from that data set. In this paper, exploring the emotions and analysis of those location inference system that works with dataset from Twitter , which restricts the posts to 200 characters, and taken recent tweets only and extracting the information and process of identifying the emotions that the people express in the form textual reviews later categorized as positive, negative or neutral. Analysis of emotions is very complex and crucial in the growth of the company. This process will provide the useful information about the reviews. Demonetization scheme was launched in the year of 2016 November 8 and decision took by the Indian government. Twitter application is majorly used by the people to interact and express their feelings in the form of text. Share the post with someone is known as tweeting. Users are very curious to find out the tweets of their interest [1]. This manuscript is defined as follows: section II is about the earlier work and proposed method, section III is about the implementation and results from the proposed technique, section IV is conclusion and future work.