Git Product home page Git Product logo

Ramaswamy Iyer's Projects

a-simulation-and-optimization-of-the-hs2-line-from-london-to-birmingham icon a-simulation-and-optimization-of-the-hs2-line-from-london-to-birmingham

The main aim of this project is to create a simulation of a railway line and determine the optimal number of signalling blocks between LONDON and BIRMINGHAM and the number of trains every hour in this track line. This optimization takes into consideration the assumption of maximizing the throughput of passengers and minimizing the travel time of a passenger from the first station to the last. The assumption of two types of trains is given where a maximum of 420 or 630 passengers respectively in each type of train can travel.

a-statistical-analysis-of-synthetic-population-data-using-multiple-linear-regression-and-binary-logi icon a-statistical-analysis-of-synthetic-population-data-using-multiple-linear-regression-and-binary-logi

The primary objective of this research is to focus on the use of Multiple Linear Regression and Binary Logistic Regression. Using data from the Pew research center website, we will analyze the use of these regression techniques for predicting continuous as well as dichotomous variables and discuss on the statistical findings thereof. The dataset being used for the research is from a “2016 Online Opt-In Comparison Study” . It contains two data files, from which we will be studying the synthetic population data set. The underlying research performed has been as per the below analysis – a. Considering personal factors like Age, Gender, Ethnicity, Education, Marital Status, Children, US Citizenship, Income class and Worker class to analyze the hours of work put in by a person every week. b. Considering political, interpersonal, geographical and cultural factors like Military Service, Ownership of home, Area, Tenure (more than 1 year or not), trust in neighbor, supporting political party, religion and political ideology to analyze the ownership of a gun in the house.

comparison-of-hybrid-neural-network-methodologies-for-sentiment-emotion-analysis icon comparison-of-hybrid-neural-network-methodologies-for-sentiment-emotion-analysis

Twitter tweets play an important role in every organisation. This project is based on analysing the English tweets and categorizing the tweets based on the sentiment and emotions of the user. The literature survey conducted showed promising results of using hybrid methodologies for sentiment and emotion analysis. Four different hybrid methodologies have been used for analysing the tweets belonging to various categories. A combination of classification and regression approaches using different deep learning models such as Bidirectional LSTM, LSTM and Convolutional neural network (CNN) are implemented to perform sentiment and behaviour analysis of the tweets. A novel approach of combining Vader and NRC lexicon is used to generate the sentiment and emotion polarity and categories. The evaluation metrics such as accuracy, mean absolute error and mean square error are used to test the performance of the model. The business use cases for the models applied here can be to understand the opinion of customers towards their business to improve their service. Contradictory to the suggestions of Google’s S/W ratio method, LSTM models performed better than using CNN models for categorical as well as regression problems.

evaluation-of-factors-that-affect-and-predict-a-game-s-popularity-considering-its-sales-and-ratings icon evaluation-of-factors-that-affect-and-predict-a-game-s-popularity-considering-its-sales-and-ratings

This research paper aims to apply five machine learning algorithms to three different data sets from the Gaming and Entertainment industry to evaluate the various factors that possibly affect their popularity. These three data sets have been acquired from Kaggle and are based on the Games on Steam, Board Games, Apple App Store Strategy Games. Using the C5.0 Decision Tree and RIPPER Rule on Steam Games, Multiple Linear Regression and Model Tree M5-Prime on Board Games and Binary Logistic Regression on the Apple App Store Strategy Games data set, the popularity of these games has been predicted and various significant factors have been found. The number of owners and the average ratings of these games have been taken into consideration for predicting their popularity. Apart from applying these five machine learning algorithms on these three data sets a comparison was also considered between the two machine learning algorithms applied on each of the data sets except the Apple App Store Strategy Games. A very interesting observation in the Board Games data set was that as per Lantz B., the M5-Prime should perform better than a Multiple Linear Regression model but we found the complete opposite\cite{b1}. Also, the C5.0 Decision tree applied on the Steam games data set grew to a size of 176 branches but the RIPPER Rule only had 37 rules for the same dependent and independent variables. We will look deep into all these factors in the research paper using the KDD methodology of data mining to find answers.

major-and-minor-severity-accidents-a-study-of-environmental-factors-using-deep-neural-networks-and- icon major-and-minor-severity-accidents-a-study-of-environmental-factors-using-deep-neural-networks-and-

Owing to the increase in number of vehicles and infrastructure, the need for severity analysis in road accidents has gained a fundamental importance. This research aims to create a severity detection system for major and minor accidents depending on the length of the road. In order to achieve this, the environmental factors of weather, road demographics, accident situation factors and nearby landmarks has been taken into consideration. The literature survey shows that the implementation of feature importance on a per class basis along with the model as a whole has not been widely explored. The implemented Stratified K-Fold Deep Neural Network performs better than traditional ensemble models with an accuracy of more than 89% for both, Major and Minor accidents. Along with this, to gain more information from the neural network and how it predicts, SHAP (Shapely Additive Explanations) has been applied to gain overall importance. These feature importance scores have been further explored on a per class basis using the data itself and extraction of SHAP scores for each class. The findings from this research can be used by the main four stakeholders in an accident - transportation safety planners, hospitals, medical agencies and insurance companies for proactive action and purposes.

mumbai-dabbawalas-a-case-study-on-application-of-business-intelligence-and-analytics icon mumbai-dabbawalas-a-case-study-on-application-of-business-intelligence-and-analytics

The Mumbai Tiffin Box Supplier's Association, commonly known as the Mumbai Dabbawalas, is a well-known organization which supplies lunch boxes to office and college going people. Founded in the year 1890 with a mere 100 dabbawalas, the organization has grown to a size of 5000 dabbawalas has continued to provide delivery services to almost 200,000 Mumbaikars. The end to end delivery process of dabba delivery has three teams. First team has around 20-25 dabbawalas who pick up dabba from the resident address. Second team segregates the dabbas as per the destination and the third team delivers the dabbas to the destination address. The same process is followed in a reverse fashion to deliver the empty dabba to the original pick-up address. The dabbas are coded using a special nomenclature, known by all the dabbawalas in the organization, which makes it easier for delivering the lunch boxes with precision. Realizing the need of the hour and current competition in the food delivery industry, the dabbawalas have adopted technology to maintain their position in the food delivery industry. This project involves the end to end creation of a BI and Analytics system for the Mumbai dabbawalas which includes a database, its various components (tables, data, triggers, etc.) and visulaizations using the data in Power BI.

prediction-of-box-office-profit-of-movies-using-hierarchical-clustering-random-forest-ensemble icon prediction-of-box-office-profit-of-movies-using-hierarchical-clustering-random-forest-ensemble

This research paper aims to predict the box office profit of a movie using a clustering and random forest based ensemble technique. The motivation behind this comes from the need of better predictive techniques in the movie industry owing to its unpredictable nature. The literature survey found meta data and social data to be important factors in predicting a movies box-office success. The use of clustering and random forest ensemble provided an accuracy of 78 percent on the training data and 62 percent on unseen or test data with a correlation of 78 percent between actual and predicted values. The variable importance chart showcased the budget, budget year ratio, release month, run time, genre, collection and review sentiment score to be influential in the profitability of a movie. The business use cases for this model and data considered is mainly for on-demand video service providers and television service companies.

visualizing-the-various-trends-among-popular-movies-tv-shows-and-a-sentiment-analysis-of-their-revi icon visualizing-the-various-trends-among-popular-movies-tv-shows-and-a-sentiment-analysis-of-their-revi

The aim of this research is to analyze the various trends and distributions among popular movies and tv shows along with a sentiment analysis of the reviews for them. Considering the number of movies and tv shows spread throughout the years along with their popularity, ratings, genres and various other intrinsic factors, we have created visualizations for better understanding of what the current trends have been. Along with this, a sentiment analysis of the various reviews were considered which was divided into positive and negative reviews and a visual study was conducted to find comparisons between these two modes of entertainment. A notable finding was that there is no correlation of the ratings and the popularity of movies as well as tv shows along with the fact that movies and tv shows released very recently have more popularity than others. In terms of the sentiment analysis of reviews for these popular movies and tv shows, the most number of popular tv shows is in the Drama genre, but it also has the most number of negative reviews.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.