Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Online social networks turn out to be a potential data source to discover worthwhile information from microblogs. Conversely, time-critical exploration of microblog data during catastrophic events such as flood, cyclone, forest fire, and violence carries critical challenges to machine learning techniques. For instance, the microblog from Twitter is utilized to identify event along with its location-specific orientation. In this paper, convolution neural network (CNN) technique is used to identify the retrospective event from the microblog. The existing state of-the-art classification methodologies require substantial volume of labeled data detailed to an unambiguous event during training phase. In addition, it requires feature to attain better outcomes. During the experiments, the n-gram CNN model is trained from the tweets intended for multi-class tweet classification which was related to the specified events in the past without feature engineering. The proposed CNN shows the event detection high accuracy which in turn yields improved performance when compared with other state-of-the-art methods. © Springer Nature Singapore Pte Ltd 2020.

Computer Science

School of Computer Science and Engineering

Chennai Campus

World University root node

Lecture Notes in Electrical Engineering

Detecting new events from microblogs using convolutional neural networks

Social Internet of things (SIoT) has obtained significant attention to address the computational intelligence for handling emergencies which can be sensed through the Internet of smart social things. In recent years, humans act as a social sensor to disseminate the information via microblogs in Online Social Networks (OSNs) such as Twitter, Weibo. At times, the reaction to certain microblogging prompts thousands of people to rethink and impulsively react on that which can handle humanity unrest situations during earthquakes, floods, Tsunamis, etc. In this paper, the streaming microblog tweets are investigated to detect the disaster events for a specified time and location. Firstly, the real-time Twitter streaming data is sensed via Apache Flume service agent. Secondly, the tweets are preprocessed and filtered tweets are clustered using the microblog-DBSCAN algorithm. The tweets belonging to various sliding window from diversified geographic event locations during disasters are aggregated. In addition, the crowdsourced photographs are added with geo-tags (location) during the period of analysis stood up as supplementary evidence to detect an event which acts as crisis recovery. The dynamic hive queries are executed to filter location-level tweets for the analysis. In contrast to conventional approaches which mainly focus the microblog textual content, we incorporate significant metadata features, namely photographs and its geo-tag, to precisely identify the events in real time. © Springer Nature Singapore Pte Ltd. 2019.

Advances in Intelligent Systems and Computing

Social IoT-enabled emergency event detection framework using geo-tagged microblogs and crowdsourced photographs

The demand for Cyber Social Networks has increasingly become the main source of information propagation due to the rapid growth of micro-blogging activity between socially connected people. The process of detecting disaster events, in huge volumes, on fast-streaming platform is quite challenging. In this paper, an information entropy based event detection framework is proposed to identify the event and its location by clustering relatively high-density ratio of tweets using Twitter data. The Shannon entropy of target users, location, time intervals and hashtags are estimated to quantify the dissemination of events as "how-far about" in real-world using entropy maximization inference model. The geo-Tagged (spatial) tweets are extracted for a specified time period (temporal) to identify the location of an event as "where-when about"; and visualizes the event in geo-maps. The evaluation parameters of Entropy, Cluster Score, Event Detection Hit and False Panic Rate during four major disaster events are identified to illustrate the effectiveness of the proposed framework. The retweeting activity of the Twitter user is classified as human signatures and bots. The experimental outcome determines the scope and significant dissemination direction of finding events from a new perspective which demonstrates 96% of improved event detection accuracy. © 2019 - IOS Press and the authors.

Journal of Intelligent and Fuzzy Systems

Information entropy based event detection during disaster in cyber-social networks

The deep learning techniques namely Long Short Term Memory (LSTM) network and Bi-directional Gated Recurrent Unit (BGRU) network turn to be de facto to build an optimal assembly line for neural network models. The prevailing state-of-the-art approaches require a substantial amount of labeled data detailed to an unambiguous event in the training phase. In this paper, embedded bi-directional GRU and LSTM learning models is applied for disaster event prediction that uses deep learning techniques to categorize the tweets. The performance of the proposed neural network model is evaluated on CrisisLexT26 benchmarking dataset. The resulting validation accuracy is estimated by comparing LSTM and bi-directional GRU with and without word embeddings. The experiments demonstrate the model selector choose the deep learning techniques to predict the disaster event with reasonably high accuracy. © 2019 Procedia Computer Science. All rights reserved.

Fulltext

Procedia Computer Science

Embedded Bi-directional GRU and LSTMLearning Models to Predict Disasterson Twitter Data

The enormous usage of Online Social Networks (OSN) leads to unleashing usage of the smart technologies in social life which becomes intertwined. Generating meaningful patterns out of various location-based streaming social big data fascinated the techies around the globe to develop innovative approaches to enhance emergency support on-demand. In the specific situation like disasters, nature setbacks down at unpredictable instances. During such circumstances, a scalable and low latency analytics approach is highly required to identify the event and its location at very high speed for recovery. In this paper, the spatiotemporal event detection approach is proposed based on dynamic features emerged from the location of interest in OSN using a map-reduce framework. The experimental results address the advantage of MapReduce paradigm is indeed suitable for scalable and high-speed data streams with minimal latency. In addition, an information theoretic emergency logistic mapper is discussed as a part of disaster recovery phase which can be accomplished via social big data analysis in near future. © 2017 IEEE.

2017 9th International Conference on Advanced Computing, ICoAC 2017

Feature Constrained Parallel Data Processing Approach for Spatiotemporal Event Detection

Online social streams has become a prominent channel for facilitating new sources of information and quick communication links, specifically during mass emergencies. The task of event burst detection focuses on monitoring Twitter streams, to identify emergent patterns based on tweet arrival rate. The vital features of rising sharply in frequency for modelling an event in text streams leads to burst activity. In this paper, a statistical approach is framed for Twitter streaming channel with a sudden change in the frequency of tweet showing a log-normal distribution of data arrival γ. The burstiness of event is framed as the Z-score of the tweet arrival rate λ which corresponds to the frequency of tweets delimited in the time window w. Moreover, the proposed approach identify events which generates a stratified representation of the set of keyword bursts. The experimental outcome determines a hierarchical composition of event detection on the diversified stream by choosing optimal parameters. © 2018 IEEE.