Vinay Kumar Jain

Extraction of emotions from multilingual text using intelligent text processing and computational linguistics

Abstract Extraction of Emotions from Multilingual Text posted on social media by different categories of users is one of the crucial tasks in the field of opining mining and sentiment analysis. Every major event in the world has an online presence and social media. Users use social media platforms to express their sentiments and opinions towards it. In this paper, an advanced framework for detection of emotions of users in Multilanguage text data using emotion theories has been presented, which deals with linguistics and psychology. The emotion extraction system is developed based on multiple features groups for the better understanding of emotion lexicons. Empirical studies of three real-time events in domains like a Political election, healthcare, and sports are performed using proposed framework. The technique used for dynamic keywords collection is based on RSS (Rich Site Summary) feeds of headlines of news articles and trending hashtags from Twitter. An intelligent data collection model has been developed using dynamic keywords. Every word of emotion contained in a tweet is important in decision making and hence to retain the importance of multilingual emotional words, effective pre-processing technique has been used. Naive Bayes algorithm and Support Vector Machine (SVM) are used for fine-grained emotions classification of tweets. Experiments conducted on collected data sets, show that the proposed method performs better in comparison to corpus-driven approach which assign affective orientation or scores to words. The proposed emotion extraction framework performs better on the collected dataset by combining feature sets consisting of words from publicly available lexical resources. Furthermore, the presented work for extraction of emotion from tweets performs better in comparisons of other popular sentiment analysis techniques which are dependent of specific existing affect lexicons.

Big Data Analytic Using Cloud Computing

Innovations in technology and greater affordability of digital devices with internet made a new global world of data called big data. The continuous increase in the volume and detail of data captured by enterprises, such as the rise of social media, Internet of Things (IoT), and multimedia, has produced an overwhelming flow of data in either structured or unstructured format. It is a fact that data that is too big to process is also too big to transfer anywhere, so its just the analytical program which needs to be moved -- not the data. This is possible with cloud computing, as most of the public data sets such as Facebook, Twitter, financial markets data, weather data, genome datasets and aggregated industry-specific data live in the cloud and it becomes more cost-effective for the enterprise to analysis this data in the cloud itself. This paper discusses various problems related to big data computation and possible solution using cloud computing.

Simulation and control of a complex nonlinear dynamic behavior of multi-stage evaporator using PID and Fuzzy-PID controllers

Abstract The dynamic model of heptads’ stage evaporative unit employed in concentrating black liquor in paper industry show tremendous complexity. In this work, linearization of such a complex nonlinear model consisting of 14 first order nonlinear differential equations and determination of the system transfer functions has been explored through an exhaustive state space representation technique. The transfer functions that relate the product concentration change to liquor flow rate deviation have been evaluated and presented through this work for the first time. These serve as an input to design a PID controller and study its response for a set point change in product concentration. The response analysis indicated a noticeable overshoot, undershoot and Integral Square Error (ISE), that may collectively influence the product quality. To overcome this issue and to make controlling of product concentration more robust, an intelligent Mamdani type Fuzzy Logic-Proportional-Integral-Derivative (FLC-PID) controller has been additionally designed and its response simulated. A comparison of response of FLC-PID and PID indicated that the rise time of former is larger than the latter. However, FLC-PID response settles faster with ∼49% smaller settling time than PID, possesses zero undershoot, a ∼93% reduced overshoot and 21% reduced ISE. The results demonstrate improved tracking capability, and hence, better control performance of FLC-PID for transient changes in product concentration.

A fuzzy neural network approach for automatic K-complex detection in sleep EEG signal

Abstract The study of sleep stages and the associated signals have emerged as a very important parameter to identify the neurological disorders and test of mental activities nowadays. Electroencephalogram (EEG) is an electrophysiological method for monitoring, managing, and diagnosing the mental disorders or neurological problems. The EEG signals are highly transient and nonlinear in nature. It varies with the mental conditions. In the sleep state, a non-stationary wave generates with comparatively higher peaks is known as K-complex. The K-complex is a kind of transient wave which can be seen in the NREM stage II sleep. The main difficulty behind the design of the automated K-complex detection system is a nonlinear and dynamic characterization of it. The other difficulty for the system design is the very much similar behaviour of K-complex to other EEG wave. To overcome these problems, in this paper we are giving the detailed description for developing an automatic K-complex detector using fuzzy neural network approach. In this method, fuzzy C-means algorithm is utilized for the rough and rapid recognition of K-complex and the neural network classifier does the exact evaluation on the detected K-complex. One more fast computing Back Proportion algorithm is used for train the network in this work. This technique of detection of K-complex with a well-known pattern present in sleep EEG is a fuzzy neural based software solution in the field of biomedical signal processing.

Deep convolution network for surveillance records super-resolution

The aim of image super resolution (SR) is to recover low resolution (LR) input image or video to a visually desirable high-resolution (HR) one. The task of identifying an object in surveillance records is interesting, yet challenging due to the low resolution of the video. This paper, proposed a deep learning method for resolution recovery, the low-resolution objects and points in the surveillance records are up-sampled using a deep Convolutional Neural Network (CNN) to avoid problems of image boundary the data padded with zeros. The network is trained and tested on two surveillance datasets. Dissimilar to the outdated methods which operate components individually, our model performs combined optimization for all the layers. The proposed CNN model has a lightweight structure and minimal data pre-processing and computation cost. Testing our model and comparing with advanced techniques, we observed promising results. The code is accessible at https://github.com/Mzareapoor/Super-resolution

Magnetic optimization algorithm for data clustering

Abstract In this paper, a new clustering algorithm inspired by magnetic force is proposed. This algorithm is not sensitive to the initialization problem of cluster centroids. Centroid particles change their position according to the total magnetic force applied by data points. The position of the particle gets updated by employing magnetic resultant force to find the best position of centroid particle for clustering. To evaluate the performance of the proposed algorithm, numerical experiments are conducted on eleven benchmark data sets taken from UCI repository and are compared with five different clustering algorithms. The results show that the proposed algorithms are more accurate, efficient and robust as compared to the other clustering algorithms.

Effective surveillance and predictive mapping of mosquito-borne diseases using social media

Abstract Healthcare Emergency Management involves preventing, handling, organizing and controlling of specific events and in response to emergency situations. A social media based mosquito-borne disease surveillance and outbreak management using spatial and temporal information which help in identification, characterization, and modeling of user behavioral patterns on the web have been presented through this paper. The proposed predictive mapping based on geo-tagging data has a significant impact on preventing and tracking mosquito-borne disease in the specific area with limited resources. The tracking of real-time public sentiments provides an early discovery or alarming related to outbreak. Latent Dirichlet allocation (LDA) based topic modeling techniques have been applied to filter out relevant topics related to symptoms, prevention and fear. The two steps fine-grained classifications of data have been performed using Naive Bayes and Support Vector machine. The proposed framework focused on alternative methods of analysis and visualization of users opinions that do not depend upon the assumption of normality. A novel intelligent surveillance process model has been presented which help government agencies for proper management of time and resources. The utilization of standard kernel density estimate (KDE) with important factors derived from Twitter and RSS feeds have been presented for predictive mapping. The model uses latent Dirichlet allocation for identification of coherent topics from collected data set at a particular interval. This model has been applied to predict the occurrence of mosquito-borne disease in India.

M-Cloud Computing Based Agriculture Management System

Modernization in agriculture sector is one of the major challenging problems in India. Currently, Indian farmers faced many problems in agriculture domain such as lack of irrigation infrastructure, market infrastructure and transport infrastructure along the presence of a chain of middlemen through whom most agricultural commodities must circulate before finally reaching consumers etc. One of the possible solutions for improvement is by using mobile applications help in gathering information from farmers such location-based information and environmental. This chapter presents a framework to solve the problems in agriculture by using Mobile based Cloud computing platform which makes smart farmers and increases the productivity. This framework promotes a fast development of agricultural modernization, realize smart agriculture and effectively solve the problems concerning agriculture, countryside, and farmers.

Fuzzy logic based similarity measure for multimedia contents recommendation

Collaborative filtering is one of the mainstream approaches to provide recommendations in various online environments such as Ecommerce. Although this is a popular method for service recommendation, it still suffers from sparsity issue where only a small number of rating records are available for some new items or users in the system. Consequently, the accuracy of rate prediction is often compromised. Unlike the conventional collaborative filtering methods that directly compute the similarity between users, this paper presents a fuzzy logic based approach to refine the similarity obtained using traditional approaches like Pearson correlation, Cosine, Adjusted Cosine etc. Experiments were conducted on the two popular benchmark datasets and it shows that the proposed method obtains better prediction accuracy as compare to other traditional similarity measures.

LeaderRank based k -means clustering initialization method for collaborative filtering

Abstract Collaborative filtering based Recommender System is one of the most common technique used for personalized product ranking. It aids the consumer in decision-making process. It helps to choose a product according to the consumers preference from a large pool of choices.Despite its success, collaborative filtering suffers from the sparsity problem which limits the quality of recommendations. In this paper, we investigate the application of clustering collaborative framework. A unique centroid selection approach for k-means clustering algorithm is proposed that aims to improve clustering quality. The results on three benchmark datasets depict the improvement in the quality of recommendations made.