Soma Bandyopadhyay

Tata Consultancy Services Limited | TCS · TCS Innovation Labs

Data synthesis is an important need in many real-life applications. However, generating data with preserving causal relations is a challenge. Causal relation preservation is an utmost need to boost the explainability of ML-DL based applications. Some of the challenges of preserving causality are unobserved causes in the input observations and unkno...

Identification of user transport mode using mobile phone-based sensors is a key component of Intelligent Transportation System. However, collecting labels/annotations while switching multiple transport modes into different journeys is tedious. Also, transport type identification working across cities and countries is a prime need. This paper propos...

Handling and identification of data distributional changes (DDC) are very sensitive and critical issues for intelligent system monitoring. This demands a continual learning setup to perform robust and efficient identification of data distribution shift due to various operational changes of IoT system. Causes of DDC-presence of drift in sensing syst...

Driving behavior monitoring plays a crucial role in managing road safety and decreasing the risk of traffic accidents. Driving behavior is affected by multiple factors like vehicle characteristics, types of roads, traffic, but, most importantly, the pattern of driving of individuals. Current work performs a robust driving pattern analysis by captur...

A robust driving pattern analysis by capturing variations in driving patterns for addressing diversity in individuals, depending on individual's inherent characteristics and, also based on demographic factors such as age, gender etc.

Time-series generated by end-users, edge devices, and different wearables are mostly unlabelled. We propose a method to auto-generate labels of un-labelled time-series, exploiting very few representative labelled time-series. Our method is based on representation learning using Auto Encoded Compact Sequence (AECS) with a choice of best distance mea...

Getting a robust time-series clustering with best choice of distance measure and appropriate representation is always a challenge. We propose a novel mechanism to identify the clusters combining learned compact representation of time-series, Auto Encoded Compact Sequence (AECS) and hierarchical clustering approach. Proposed algorithm aims to addres...

Objective: Atrial fibrillation (AF) and other types of abnormal heart rhythm are related to multiple fatal cardiovascular diseases that affect the quality of human life. Hence the development of an automated robust method that can reliably detect AF, in addition to other non-sinus and sinus rhythms, would be a valuable addition to medicine. The pr...

With the advent and rapid deployment of Internet of Things (IoT), artificial intelligence (AI), powerful smartphones, and wearable sensor devices (e.g., smartwatch), we are entering into the era of automated, remote, on-demand mobile healthcare services. According to the WHO, cardiovascular disease is the modern-day disease. However, prognosis rate...

Computational analysis on physiological signals would provide immense impact for enabling automated clinical analytics. However, the class imbalance issue where negative or minority class instances are rare in number impairs the robustness of the practical solution. The key idea of our approach is intelligent augmentation of minority class examples...

In this article, we propose a novel technique for classification of the Murmurs in heart sound. We introduce a novel deep neural network architecture using parallel combination of the Recurrent Neural Network (RNN) based Bidirectional Long Short-Term Memory (BiLSTM) & Convolutional Neural Network (CNN) to learn visual and time-dependent characteris...

We present a system to analyze patterns inside pulsatile signals and discover repetitions inside signals. We measure dominance of the repetitions using morphology and discrete nature of the signals by exploiting machine learning and information theoretic concepts. Patterns are represented as combinations of the basic features and derived features....

In this paper, we present CardioFit, a completely noninvasive cardiac condition monitoring system that enhances the clinical utility of health care analytics like lowering false detection of cardiac arrhythmia condition, higher accuracy in heart rate variability (HRV) computation. It performs powerful local analysis to enable accurate as well as ea...

Phonocardiogram (PCG) records heart sound and murmurs, which contains significant information of cardiac health. Analysis of PCG signal has the potential to detect abnormal cardiac condition. However, the presence of noise and motion artifacts in PCG hinders the accuracy of clinical event detection. Thus, noise detection and elimination are crucial...

This paper attempts to project a novel concept where medical sensors, cloud computing and robotic platform are unified to offer state-of-the-art healthcare solutions to a wide variety of scenarios. The proposed solution is most effective if there is scarcity of healthcare providers or if putting them in the field expose them into a high risk enviro...

One of the major concerns of sensor signal analytics is missing or incomplete samples. Data misses occur mainly because of delays or faults in data capturing infrastructure. We propose a novel mechanism for missing data imputation. The novelty of our mechanism arises from its exploitation of the semantics of different features of the sensor signal...

Detection of normal and anomalous events from sensor signal is a key necessity in today's smart world. Here, we propose a novel mechanism to classify normal and anomalous phenomena by using self-learning of signal, i.e., by discovering its pattern. This is the first step in the long drawn out analysis of signals. We demonstrate a prototype of our p...

We aim to develop a reliable and robust algorithm that accurately analyses a single short PCG recording (10–60s) from a single precordial location to determine the presence of heart abnormality for the Physionet/ Computing-in-Cardiology 2016 challenge. We extract timing information for the fundamental Heart Sounds i.e. S1 and S2 using Hidden Markov...

We propose here derivation algorithms for physiological parameters like beat start point, systolic peak, pulse duration, peak-to-peak distance related to heart rate, dicrotic minima, diastolic peak from Photoplethysmogram (PPG) signals robustly. Our methods are based on unsupervised learning mainly following morphology as well as discrete nature of...

Ubiquity of smartphones with array of inbuilt sensors, pave ways to inexpensive mobile-health systems, particularly for cardio-vascular health monitoring. Smartphones, wearable sensors, and body area sensors play an important role as a part of Internet of Things (IoT) m-health ecosystem. In this paper, we present iCarMa to enable an inexpensive aut...

Sensors are one of the primary building blocks of IoT. Owing to close proximity of physical world, sensors often collect sensitive information. Invariably, sensor data has rich information content. Here we propose a novel solution IAS: Information Analytics for Sensors to unlock massive potential of sensor data through information analytics and dem...

Management of bulk sensor data is one of the challenging problems in the development of Internet of Things (IoT) applications. High volume of sensor data induces for optimal implementation of appropriate sensor data compression technique to deal with the problem of energy-efficient transmission, storage space optimization for tiny sensor devices, a...

IoT (Internet of Things) systems are resource-constrained and primarily depend on sensors for contextual, physiological and behavioral information. Sensitive nature of sensor data incurs high probability of privacy breaching risk due to intended or malicious disclosure. Uncertainty about privacy cost while sharing sensitive sensor data through Inte...

Secure yet lightweight protocol for communication over the Internet is a pertinent problem for constrained environments in the context of Internet of Things (IoT) / Machine to Machine (M2M) applications. This paper extends the initial approaches published in [1], [2] and presents a novel cross-layer lightweight implementation to establish a secure...

This paper attempts to project a novel concept where medical sensors, cloud computing and robotic platform are unified to offer state-of-the-art healthcare solutions to a wide variety of scenarios. The proposed solution is most effective if there is scarcity of healthcare providers or if putting them in the field expose them into a high risk enviro...

Purpose – The purpose of this paper is to study lightweight security scheme for Internet of Things (IoT) applications using Constrained Application Protocol (CoAP). Resource-constrained characteristics of IoT systems have ushered in compelling requirements for lightweight application protocol and security suites. CoAP has already been established a...

In this paper we aim to reduce overall resource usage and improve throughput of an intelligent transportation tracking application. Primary improvements in terms of bandwidth and latency are achieved using CoAP (Constrained Application Protocol). We propose a novel approach to adapt CoAP’s reliability mode for data transfer by inferring vehicle’s m...

The present invention provides a computationally efficient system and method for aggregation of bandwidth of multiple active physical Interfaces based on an application layer. The said system comprises: a user interface for receiving the user defined input; at least one routing table updater for creating and updating routing table that lists the ro...

The problem of privacy disclosure hinders large number of ubiquitous applications to collect, disseminate and analyze personal data from providing useful and important services. It is understood that sharing private data has high potential for facilitating innumerable benefits as well as inviting intended or unintended malicious activities leading...

Privacy breaching attacks pose considerable challenges in the development and deployment of Internet of Things (IoT) applications. Though privacy preserving data mining (PPDM) minimizes sensitive data disclosure probability, sensitive content analysis, privacy measurement and user's privacy awareness issues are yet to be addressed. In this paper, w...

The resource constrained characteristic of M2M systems has made secure channel establishment for sensor data communication a challenging task. While the proposed Constrained Application Protocol (CoAP) from Internet Engineering Task Force (IETF) enables lightweight application layer for sensor devices and gateways, lightweight security protocol on...

In this paper we present a unique approach to make use of CoAP (Constrained Application Protocol) [1] from IETF (Internet Engineering Task Force) in a situation aware mode. The protocol adapts its characteristic for resource optimization depending on the indication inferred from sensed data. We consider a use-case for vehicular telemetry using a co...

In this paper we present a lightweight security scheme for authentication and key management to establish a secure channel for Intelligent Transportation System (ITS) for an IoT (Internet of Things) application. We choose Constrained Application Protocol (CoAP) as lightweight application layer protocol. Low overhead security is still an open challe...

Lightweight Internet protocols are increasingly being used in ubiquitous environment in order to optimize the resource usage of a constrained device like a smart mobile gateway. This paper presents a study on the various such protocols to optimize the usage of energy, and network resources, computation cost of a constrained gateway device. Comprehe...

This article presents generic IoT (Internet of Things) reference architecture proposed by standard organization. It compares different IoT reference ar-chitectures proposed by different standards institutes, specially emphasizing lightweight requirements of IoT reference architecture. These architectures define multiple interfaces. Functionalities...

This Smart environments, starting from smart home to more complex one like smart city, demand efficientinteroperation mechanism among different heterogeneous sensors including the discovery and themanagement of these devices. The diverse domains of applications also require interoperation amongthemselves. The middleware plays a key role to achieve...

Internet of things (IoT) brings forth a coupling among diverse sensors and diverse domains of applications and services. Sensors primarily provide the sensed observations, which are utilized by various applications and services. Applications are meant to serve personalized needs of the user, based on their various requirements. Therefore, in IoT, t...

Reduction of packet loss in communication network by modifying the transmit queue length is an important research topic. A cross layer aware transmission queue adaptation system of a fixed computing system having multiple physical interfaces is presented here. The proposed system determines the condition of communication channel/network associated...

The ever increasing demand to develop smart environments starting from small scale environment like smart home to more complex one like smart city, extensively require complex middleware to support interoperation among various diverse domains of applications and different heterogeneous sensors. The middleware is also responsible for providing abstr...

Internet of Things (IoT) has been recognized as a part of future internet and ubiquitous computing. It creates a true ubiquitous or smart environment. It demands a complex distributed architecture with numerous diverse components, including the end devices and application and association with their context. This article provides the significance of...

This paper provides a survey of middleware system for Internet of Things (IoT). IoT is considered as a part of future internet and ubiquitous computing, and it creates a true ubiquitous or smart environment. The middleware for IoT acts as a bond joining the heterogeneous domains of applications communicating over heterogeneous interfaces. Comprehen...

This article presents an approach towards aggregating bandwidths of multiple physical layers i.e. transmitting and receiving data simultaneously through the multiple physical interfaces of a fixed computing system. The data over physical layers can communicate over both wired and wireless communication medium at the same time. This proposed bandwid...