Suchetana Chakraborty

Bio: Suchetana Chakraborty is an academic researcher from Indian Institutes of Information Technology. The author has contributed to research in topics: Computer science & Wireless sensor network. The author has an hindex of 6, co-authored 25 publications receiving 105 citations. Previous affiliations of Suchetana Chakraborty include Indian Institute of Technology Guwahati.

Dynamic Tree Switching for Distributed Message-Passing Applications

Abstract: The changes in environmental parameters may demand switching between underlying topologies for better performance of distributed message passing applications. Arbitrary topology switching using distributed tree construction may lead to loss or redundancy in delivery of application messages. In this work, a set of algorithms has been proposed for dynamic switching between two spanning trees to offer better adaptivity towards the environment for different applications. Here, two extreme cases of spanning trees, a Breadth First Search (BFS) tree and a Depth First Search (DFS) tree, rooted at the core node, have been considered for switching. The core node initiates the switching and all other nodes cooperatively change their parents on the fly maintaining the DFS or BFS properties as required. However, the application remains transparent to the switching that assures the availability of the system at any instance of time. Simulation results show that each application message is delivered correctly to the destination without any loss or redundancy. The proposed scheme is scalable and the control message overhead for switching is linear with respect to the number of edges in the communication graph. Furthermore, there is no control message overhead to assure the delivery of application messages at the time of switching.

Activity Recognition through Feature Learning and Annotations using LSTM

Abstract: The tremendous growth in ubiquitous sensor networks and IoT has led to Human Activity Recognition (HAR) emerging to be an exciting challenge. Machine learning approaches proposed in this direction have proved to be competent solutions. HAR data treatment in a recurrent form, and further analysis using deep networks such as RNNs or LSTM is largely unexplored. In this work, we treat data generated from a smart home setup towards HRA, as a series of events and perform feature extraction using a the popular LSTM variant of LSTMs. We use the Aruba dataset from the CASAS project [2]. We apply LSTM to extract features and perform annotations. Additionally we apply standard classification techniques to recognize and evaluate the different activities in the newly annotated data. From experimentations using our method we can achieve annotation accuracies of up to 79.5% which is 13.6% better than other state-of-the-art solutions.

Motivating In-network Fusion for Smart Infrastructure Monitoring

Abstract: The evolution of Internet of Things (IoT) has given a new direction to our day to day activities. As IoT strongly relies on sensors of several kinds, a large amount of sensory data is generated daily. The vast heterogeneity among the generated data items induces new challenges. Moreover, Quality of Service $(\mathrm {Q}\mathrm {o}\mathrm {S})$ requirements vary widely based on the application versatility. Traditionally, the processing and analysis of these data are performed at a distant server. However, off-site data processing tends to waste a lot of system resources and incurs high overhead with low QoS for the running applications. This brings in the need of low-cost in-network data management techniques that also suits the resource constrained nature of the sensor networks. This work aims to study the need of context adaptive sensing coupled with invocation of in-network data fusion strategy in a smart building environment. Based on the planned testbed we also justify the effectiveness of the proposed system by considering contextual parameters and in-network data fusion using Kalman Filter.

Formalization of a Fully-Decoupled Reactive Tuple Space Model for Mobile Middleware

Abstract: This paper suggests an approach for formalizing Tuple Space based Mobile Middleware (TSMM) that contains a fully-decoupled reactive tuple space model as coordination medium Formalization of TSMM is carried out using Mobile UNITY

A novel crash-tolerant data gathering in wireless sensor networks

Abstract: Event driven data gathering or convergecast through sensor nodes requires efficient and correct delivery of data at the sink. A tree rooted at the sink is an ideal topology for data gathering which utilizes sensor resources properly. Resource constrained sensor nodes are highly prone to sudden crash. A set of algorithms, proposed in this paper, builds a data gathering tree rooted at the sink. The tree eventually becomes a Breadth First Search(BFS) tree where each node maintains the shortest distance in hop-count to the root to reduce the routing delay and power consumption. The data gathering tree is repaired locally within a constant round of message transmissions after any random node fails. Simulation result shows that the repairing delay is very less in average, and the proposed scheme can repair from arbitrary node failure using constant number of message passing.

Blockchain-Enabled Cross-Domain Object Detection for Autonomous Driving: A Model Sharing Approach

Abstract: Object detection for autonomous driving is a huge challenge in the cross-domain adaptation scenario, especially for the time- and resource-consuming task. Distributed deep learning (DDL) has demonstrated a considerably good balance between efficiency and computation complexity. However, the reliability of DDL is low. Moreover, the cost of training data and model is not priced well. In this article, a novel blockchain-enabled model sharing approach is proposed to improve the performance of object detection with cross-domain adaptation for autonomous driving systems. Based on the blockchain and mobile-edge computing (MEC) technology, a domain-adaptive you-only-look-once (YOLOv2) model is trained across nodes, which can reduce significantly the domain discrepancy for different object categories. Furthermore, smart contracts are developed to perform data storage and model sharing tasks efficiently. The reliability of model sharing is ensured with blockchain consensus. We evaluate the proposed method under public data sets. The simulation results demonstrate that the efficiency and reliability of the proposed approach are better than the reference model.