Search

Topic models are unsupervised machine learning techniques that output clusters of “topics” represented as co-occurring words with their associated probability distributions. Topic modeling algorithms find latent themes from large document collections by understanding their context. On the other hand, string kernels are supervised machine-learning techniques that quantify string similarities without explicit string encoding. We propose TopicStriKer, a model combining the advantages of unsupervised topic modeling with supervised string kernels for text classification tasks. The co-occurring topic words per topic and topic proportions per document obtained are used to reduce the document corpus to a topic-word sequence. This reduced representation is then used for text classification with the aid of string kernels, significantly improving accuracy and reducing training time. Experiments on the bag-of-words kernel-based string embeddings using the proposed algorithm outperform the traditional text classification approaches. This work extensively compares string kernels with topic modeling on various performance metrics to establish our findings.

Blockchain, the technology infrastructure behind the famous cryptocurrency bitcoin, can take away the notion of trust from centralized organizations to a decentralized platform that is mathematically verifiable and cryptographically secure. It is gaining more significant momentum exponentially and disrupts the way businesses function beyond the digital currency aspects. This work presents a text mining literature analysis of research articles published in major digital libraries on blockchain technology and cybersecurity. This literature analysis employs automated text mining approaches such as topic modeling and keyphrase extraction for unearthing the themes from a vast body of literature. This analysis highlights the multidisciplinary nature of blockchain technology within the cybersecurity domain. The findings also show the cyber threats and vulnerabilities that evolve with blockchain technology developments. This analysis also showcases the computer security research community’s vulnerabilities and provides future research dimensions that are crucial for designing secure blockchain applications and platforms.

This study presents the possible regional climate change over South Asia with a focus over India as simulated by three very high resolution regional climate models (RCMs). One of the most striking results is a robust increase in monsoon precipitation by the end of the 21st century but regional differences in strength. First the ability of RCMs to simulate the monsoon climate is analyzed. For this purpose all three RCMs are forced with ECMWF reanalysis data for the period 1989-2008 at a horizontal resolution of ~25 km. The results are compared against independent observations. In order to simulate future climate the models are driven by lateral boundary conditions from two global climate models (GCMs: ECHAM5-MPIOM and HadCM3) using the SRES A1B scenario, except for one RCM, which only used data from one GCM. The results are presented for the full transient simulation period 1970-2099 and also for several time slices. The analysis concentrates on precipitation and temperature over land. All models show a clear signal of gradually wide-spread warming throughout the 21st century. The ensemble-mean warming over India is 1.5°C at the end of 2050, whereas it is 3.9°C at the end of century with respect to 1970-1999. The pattern of projected precipitation changes shows considerable spatial variability, with an increase in precipitation over the peninsular of India and coastal areas and, either no change or decrease further inland. From the analysis of a larger ensemble of global climate models using the A1B scenario a wide spread warming (~3.2°C) and an overall increase (~8.5%) in mean monsoon precipitation by the end of the 21st century is very likely. The influence of the driving GCM on the projected precipitation change simulated with each RCM is as strong as the variability among the RCMs driven with one., (Copyright © 2013 Elsevier B.V. All rights reserved.)