D. Haritha

Bio: D. Haritha is an academic researcher from K L University. The author has contributed to research in topics: Statistical process control & Big data. The author has an hindex of 4, co-authored 17 publications receiving 59 citations.

Review on Word2Vec Word Embedding Neural Net

Abstract: The word2vec model consists of more useful applications in different NLP tasks. The semantic meaning given by word2vec for each word in vector representations has served useful task in machine learning text classification. They are employed in finding analogy, syntactic, and semantic analysis of words. Word2vec falls in two flavors CBOW and Skip-Gram. Given a context, they used to predict a word and vice versa are also true. In order to optimize the efficiency of word2vec, they have introduced two computational techniques namely hierarchical softmax and negative sampling. The proposed research work is more focused on introducing the models, computational technique, and various fields of word2vec applications. Word2vec is compared based on the metrics and their performance is evaluated by comparing with other existing models.

Survey on high performance analytics of bigdata with apache spark

Abstract: This paper lays attention upon the advantages of Apache Spark over Hadoop MapReduce and analysis of real time data using time-series analysis. As Hadoop MapReduce is a widely used and famous execution engine for working with the storage and analysis of large datasets. In MapReduce, the data is read from the disk and the result is written to the Hadoop Distributed File System (HDFS) after a particular iteration and then the data is read from the HDFS for the next iteration. This whole process consumes a lot of disk space and time as well. The users had been objecting the problem of high latency and fault tolerance of the entire system. To overcome the issues and disadvantages of MapReduce, Apache Spark was developed. Apache Spark is an open-source project that ensures lower latency queries, iterative computations and real time processing on similar data. This paper also focuses on time-series analysis in Hadoop and Spark environment which processes and does analysis of real-time data and generates a pattern out of it to get a clearer glimpse of the statistics and characteristics of data thus making Spark even more efficient over MapReduce.

Levels of sentiment analysis and its challenges: A literature review

Abstract: Sentiment analysis is a machine learning approach in which machines break down and characterize the human's opinions, feelings, sentiments and so forth about some theme which are communicated as either content or discourse. The literary information accessible in the web is expanding step by step. So as to upgrade the offers of an item and to enhance the consumer loyalty, a large portion of the on-line shopping destinations give the chance to clients to compose surveys about items. These audits are vast in number and to mine the general assessment or conclusion extremity from every one of them, opinion mining can be utilized. Manual investigation of such vast number of surveys is essentially unthinkable. Along these lines computerized approach of a machine has critical part in illuminating this hard issue. The real test of the zone of Sentiment investigation and Opinion mining lies in recognizing the feelings communicated in these writings. This writing study is done to concentrate the conclusion investigation issue top to bottom and to acquaint with different works done regarding the matter.

An Intelligent System for Classification of Brain Tumours With GLCM and Back Propagation Neural Network

Abstract: Currently, technology has shown a lot of advancement in the field of medicine. Modalities available for capturing the brain images are Magnetic Resonance Imaging (MRIs), Positron Emission Tomography (PET) scan, and Computed Tomography (CT) scan. Among these MR is the most significantly used tool for judgment related to the anatomy of the brain. It is very essential for the classification of tumors in early-stage which supports avoiding the deaths due to brain tumors. Computerized classification of the tumor using MRI is proposed where features are extracted using the Gray Level Co-occurrence Matrices (GLCM) and classification using the BPNN. An accuracy of 94% is achieved with the proposed methodology.

Predicting Airline Crash due to Birds Strike Using Machine Learning

Abstract: The objective of this proposed work is to predict whether the airline crash has occurred due to a bird strike or not by using data mining techniques. Risk and safety are not always guaranteed within the field of aircraft. Bird strikes are dangerous for aircraft due to the relative speed of the plane with reference to the bird. The characteristics of aircraft damage from bird strikes, which is critical enough to make a high risk to continue a safe flight, differs in step with the dimensions of aircraft. Data from the National Transportation Safety Board (NTSB), which records all the aircraft accidents, are used as a training data set for the proposed system. Machine learning is the most effective technology to harnessing the useful information and knowledge from big data. The proposed work intended at building a prediction model using machine learning techniques such as decision trees and Bayesian classifications, which can be very useful in the aviation safety system and is utilized to conjecture the air crafts mishaps ahead of time so that there is an extension to the reduction in aircraft crash rate. The prediction results are range between 80% to 90%. The proposed aircraft crash prediction model is also assessed by using synthetic data sets.

A Combined CNN and LSTM Model for Arabic Sentiment Analysis

Abstract: Deep neural networks have shown good data modelling capabilities when dealing with challenging and large datasets from a wide range of application areas. Convolutional Neural Networks (CNNs) offer advantages in selecting good features and Long Short-Term Memory (LSTM) networks have proven good abilities of learning sequential data. Both approaches have been reported to provide improved results in areas such image processing, voice recognition, language translation and other Natural Language Processing (NLP) tasks. Sentiment classification for short text messages from Twitter is a challenging task, and the complexity increases for Arabic language sentiment classification tasks because Arabic is a rich language in morphology. In addition, the availability of accurate pre-processing tools for Arabic is another current limitation, along with limited research available in this area. In this paper, we investigate the benefits of integrating CNNs and LSTMs and report obtained improved accuracy for Arabic sentiment analysis on different datasets. Additionally, we seek to consider the morphological diversity of particular Arabic words by using different sentiment classification levels.

A Combined CNN and LSTM Model for Arabic Sentiment Analysis

Abstract: Deep neural networks have shown good data modelling capabilities when dealing with challenging and large datasets from a wide range of application areas. Convolutional Neural Networks (CNNs) offer advantages in selecting good features and Long Short-Term Memory (LSTM) networks have proven good abilities of learning sequential data. Both approaches have been reported to provide improved results in areas such image processing, voice recognition, language translation and other Natural Language Processing (NLP) tasks. Sentiment classification for short text messages from Twitter is a challenging task, and the complexity increases for Arabic language sentiment classification tasks because Arabic is a rich language in morphology. In addition, the availability of accurate pre-processing tools for Arabic is another current limitation, along with limited research available in this area. In this paper, we investigate the benefits of integrating CNNs and LSTMs and report obtained improved accuracy for Arabic sentiment analysis on different datasets. Additionally, we seek to consider the morphological diversity of particular Arabic words by using different sentiment classification levels.

A Comparative Study on the Recent Smart Mobile Phone Processors

Abstract: Cell phones have become a necessity for many people throughout the world. The ability to keep in touch with family, business associates, and access to email are only a few of the reasons for the increasing importance of cell phones. However, the mobile-phones in early times were bulky, restrictive to only some features and worked only in areas where there was a good connection. All these problems were resolved by integrating a processor within a cell-phone. The processor is the central hub of your smartphone. It receives and executes every command, performing billions of calculations per second. The effectiveness of the processor directly affects every application you run, whether it's the camera, the music player, or just a simple email program. In the following journal, we have discussed the distinctive features, merits, and demerits of the latest mobile phone processors of different Tech companies.