Suneetha Manne

Bio: Suneetha Manne is an academic researcher from Velagapudi Ramakrishna Siddhartha Engineering College. The author has contributed to research in topics: Automatic summarization & Ranking (information retrieval). The author has an hindex of 5, co-authored 16 publications receiving 64 citations.

Effective Comparison of LDA with LSA for Topic Modelling

Abstract: The process of converting unstructured data into a structured readable format is becoming hard day by day Till day every organization consists of more than 80% of its operational data in an unreadable format The proposed method helps in converting unreadable data to a readable structured format with the help of Machine learning were classification, and clustering plays a crucial role in converting the operational data into data models and visualize the processed information to the end-user As organizations have specific requirements, considering them, we are going to implement latent dirichlet allocation (LDA) and latent semantic analysis (LSA), which were able to handle discrete data Also, a comparison is made to test divergence, throughput, quality, and response time, as both of them can classify the data based on the content and by giving labels to each category The algorithm with better divergence is implemented that can handle the organizational requirements by presenting the top areas that need to improve/concentrate depending on the analytics made by the algorithm on the available discrete data, and by implementing visualization techniques, the results will be even displayed in graphical format

An intelligent energy management and traffic predictive model for autonomous vehicle systems

Abstract: In recent times, the utilization of autonomous vehicles (AVs) has been significantly increased over the globe. It is because of the tremendous rise in familiarity and the usage of artificial intelligence approaches in distinct application areas. Though AVs offer several benefits like congestion control, accident prevention, and so on, energy management and traffic flow prediction (TFP) remain a challenging issue. This paper concentrates on the design of intelligent energy management and TFP (IEMTFP) technique for AVs using multi-objective reinforced whale optimization algorithm (RWOA) and deep learning (DL). The proposed model involves an energy management module using fuzzy logic system to reach the specified engine torque with respect to different measures. For optimal tuning of the variables involved in the fuzzy logic membership functions (MFs), RWOA is employed to further reduce the energy utilization. Besides, the proposed model uses a DL-based bidirectional long short-term memory (Bi-LSTM) technique to perform TFP. For validating the efficacy of the IEMTFP technique, an extensive experimental validation is carried out. The resultant values ensured the goodness of the IEMTFP model in terms of energy management and TFP.

Human Resource Analytics using Power Bi Visualization Tool

Abstract: Human resource(HR) management is a subject of vast knowledge in which predictive analytics is one of its main components which includes employee turnover analysis, employee work performance analysis, and training requirements analysis as results. The main purpose of Human Resource management is to measure the work achievement of employees and their role in the services or business which acts as benefits to the company and to analyze employee period in the company. The main motto of Human Resource analytics is to identify skilled individuals who strive extremely for the return of investment for the organization by considering several factors which help for a better understanding of the individual by predictive analysis. Employee churn is considered a major problem for many organizations. It is one of the crucial problems to identify because it affects sustainability and also the organization’s planning and enhancing work culture harmony. Therefore, the Human Resource department in every organization is striving hard and paying attention to identify the underlying improvements. By identifying this demand, the study aims to increase the ability to identify employee churn using POWER BI with the help of real-time data insights such as dashboards which run machine learning models like Logistic Regression and Random Forest in background.

Text Categorization with K-Nearest Neighbor Approach

Abstract: World Wide Web is the store house of abundant information available in various electronic forms. In the past two decades, the increase in the performance of computers in handling large quantity of text data led researchers to focus on reliable and optimal retrieval of information already exist in the huge resources. Though the existing search engines, answering machines has succeeded in retrieving the data relative to the user query, the relevancy of the text data is not appreciable of the huge set. It is hence binding the range of resultant text data for a given user query with appreciable ranking to each document stand as a major challenge. In this paper, we propose a Query based k-Nearest Neighbor method to access relevant documents for a given query finding the most appropriate boundary to related documents available on web and rank the document on the basis of query rather than customary Content based classification. The experimental results will elucidate the categorization with reference to closeness of the given query to the document.

Interactive Transport Enquiry with AI Chatbot

Abstract: Public transportation is used efficiently by millions of people all over the world. People tend to travel to different places and at certain times they may feel completely lost in a new place. Our chatbot comes to rescue at this time. A Chatbot is often described as one of the most promising tools for communication between humans and machines using artificial intelligence. It is a software application that is used to conduct an online chat conversation via text by using natural language processing (NLP) and deep learning techniques. It provides direct contact with a live human agent in the form of GUI. This AI chatbot confirms the current location and the final destination of the user by asking a few questions. It examines the user’s query and extracts the appropriate entries from the database. The deep learning techniques that are used in this chatbot are responsible for understanding the user intents accurately to avoid any misconceptions. Once the user’s intention has been recognized, the chatbot provides the most relevant response for the user’s query request. Then the user gets all the information about the bus names along with their numbers so that the person can travel safely to the desired location. Our chatbot is implemented in python's Keras library and used Tkinter for GUI.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

The Internet of things.

Abstract: Keynote David Rose The New Vanguard for Business: Connectivity, Design, and the Internet of Things The Internet of Things is the hottest topic of the moment a shift predicted to be as momentous as the impact of the internet itself. The internet has allowed us to share ideas and data largely input by humans. What about a world where data from objects as diverse as umbrellas, fridges, and gas tanks all flows through the internet?

Evaluation of Text Generation: A Survey

Abstract: The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years We group NLG evaluation methods into three categories: (1) human-centric evaluation metrics, (2) automatic metrics that require no training, and (3) machine-learned metrics For each category, we discuss the progress that has been made and the challenges still being faced, with a focus on the evaluation of recently proposed NLG tasks and neural NLG models We then present two examples for task-specific NLG evaluations for automatic text summarization and long text generation, and conclude the paper by proposing future research directions

Distance and Similarity Measures Effect on the Performance of K-Nearest Neighbor Classifier - A Review

Abstract: The K-nearest neighbor (KNN) classifier is one of the simplest and most common classifiers, yet its performance competes with the most complex classifiers in the literature. The core of this classifier depends mainly on measuring the distance or similarity between the tested examples and the training examples. This raises a major question about which distance measures to be used for the KNN classifier among a large number of distance and similarity measures available? This review attempts to answer this question through evaluating the performance (measured by accuracy, precision and recall) of the KNN using a large number of distance measures, tested on a number of real-world datasets, with and without adding different levels of noise. The experimental results show that the performance of KNN classifier depends significantly on the distance used, and the results showed large gaps between the performances of different distances. We found that a recently proposed non-convex distance performed the best when applied on most datasets comparing to the other tested distances. In addition, the performance of the KNN with this top performing distance degraded only about $20\%$ while the noise level reaches $90\%$, this is true for most of the distances used as well. This means that the KNN classifier using any of the top $10$ distances tolerate noise to a certain degree. Moreover, the results show that some distances are less affected by the added noise comparing to other distances.