M. S. Ramaiah Institute of Technology

About: M. S. Ramaiah Institute of Technology is a based out in . It is known for research contribution in the topics: Feature extraction & Cloud computing. The organization has 2853 authors who have published 2434 publications receiving 23507 citations.

Learning From Imbalanced Data

Abstract: Pattern Identification on various domains have become one of the most researched fields. Accuracy of all traditional and standard classifiers is highly proportional to the completeness or quality of the training data. Completeness is bound by various parameters such as noise, highly representative samples of the real world population, availability of training data, dimensionality etc. Another very pressing and domineering issue identified in real world data sets is that the data is well-dominated by typical occurring examples but with only a few rare or unusual occurrences. This distribution among classes make the real world data inherently imbalanced in many domains like medicine, finance, marketing, web, fault detection, anomaly detection etc. This chapter aims to highlight the existence of imbalance in all real world data and the need to focus on the inherent characteristics present in imbalanced data that can degrade the performance of classifiers. It provides an overview of the existing effective methods and solutions implemented towards the significant problems of imbalanced data for improvement in the performance of standard classifiers. Efficient metrics for evaluating the performance of imbalanced learning models followed by future directions for research is been highlighted.

Siamese recurrent architectures for learning sentence similarity

Abstract: We present a siamese adaptation of the Long Short-Term Memory (LSTM) network for labeled data comprised of pairs of variable-length sequences. Our model is applied to assess semantic similarity between sentences, where we exceed state of the art, outperforming carefully handcrafted features and recently proposed neural network systems of greater complexity. For these applications, we provide word-embedding vectors supplemented with synonymic information to the LSTMs, which use a fixed size vector to encode the underlying meaning expressed in a sentence (irrespective of the particular wording/syntax). By restricting subsequent operations to rely on a simple Manhattan metric, we compel the sentence representations learned by our model to form a highly structured space whose geometry reflects complex semantic relationships. Our results are the latest in a line of findings that showcase LSTMs as powerful language models capable of tasks requiring intricate understanding.

A Survey on Security and Privacy Issues of Bitcoin

Abstract: Bitcoin is a popular cryptocurrency that records all transactions in a distributed append-only public ledger called blockchain . The security of Bitcoin heavily relies on the incentive-compatible proof-of-work (PoW) based distributed consensus protocol, which is run by the network nodes called miners . In exchange for the incentive, the miners are expected to maintain the blockchain honestly. Since its launch in 2009, Bitcoin economy has grown at an enormous rate, and it is now worth about 150 billions of dollars. This exponential growth in the market value of bitcoins motivate adversaries to exploit weaknesses for profit, and researchers to discover new vulnerabilities in the system, propose countermeasures, and predict upcoming trends. In this paper, we present a systematic survey that covers the security and privacy aspects of Bitcoin. We start by giving an overview of the Bitcoin system and its major components along with their functionality and interactions within the system. We review the existing vulnerabilities in Bitcoin and its major underlying technologies such as blockchain and PoW-based consensus protocol. These vulnerabilities lead to the execution of various security threats to the standard functionality of Bitcoin. We then investigate the feasibility and robustness of the state-of-the-art security solutions. Additionally, we discuss the current anonymity considerations in Bitcoin and the privacy-related threats to Bitcoin users along with the analysis of the existing privacy-preserving solutions. Finally, we summarize the critical open challenges, and we suggest directions for future research towards provisioning stringent security and privacy solutions for Bitcoin.