Soumya Sourav

Nabil Ibtehaz, S. M. Shakhawat Hossain Sourav, Md. Shamsuzzoha Bayzid et al.

Background: The inception of next generations sequencing technologies have exponentially increased the volume of biological sequence data. Protein sequences, being quoted as the `language of life', has been analyzed for a multitude of applications and inferences. Motivation: Owing to the rapid development of deep learning, in recent years there have been a number of breakthroughs in the domain of Natural Language Processing. Since these methods are capable of performing different tasks when trained with a sufficient amount of data, off-the-shelf models are used to perform various biological applications. In this study, we investigated the applicability of the popular Skip-gram model for protein sequence analysis and made an attempt to incorporate some biological insights into it. Results: We propose a novel $k$-mer embedding scheme, Align-gram, which is capable of mapping the similar $k$-mers close to each other in a vector space. Furthermore, we experiment with other sequence-based protein representations and observe that the embeddings derived from Align-gram aids modeling and training deep learning models better. Our experiments with a simple baseline LSTM model and a much complex CNN model of DeepGoPlus shows the potential of Align-gram in performing different types of deep learning applications for protein sequence analysis.

Soumya Sourav, Devashish Khulbe, Naman Kapoor

With the development in the field of smartphones and ever growing base of Internet, various softwares are left prone to many malicious activities like pharming, phishing, ransomware, spam, spoofing, spyware, eavesdropping, etc. These threats have not spared the smartphones which are equally prone to them. In this work, we aim to detect these malwares with accuracy and efficiency. This being essentially a classification problem, we use various machine learning methods for this task. We observe that across models, Attention based Artificial Neural Networks (ANN), or broadly speaking, Deep Learning, are most suitable for this problem. Attention based ANNs are an amalgamation of accuracy and efficiency, the crux of our work. The accuracy achieved by our model is around 96.75\%. Our model runs the test on Android Package Files (APKs) to determine whether a particular application is malicious or not by doing behavior analysis on android application under consideration.

Devashish Khulbe, Soumya Sourav

We present an approach to estimate the severity of traffic related accidents in aggregated (area-level) and disaggregated (point level) data. Exploring spatial features, we measure complexity of road networks using several area level variables. Also using temporal and other situational features from open data for New York City, we use Gradient Boosting models for inference and measuring feature importance along with Gaussian Processes to model spatial dependencies in the data. The results show significant importance of complexity in aggregated model as well as as other features in prediction which may be helpful in framing policies and targeting interventions for preventing severe traffic related accidents and injuries.