Electronics

Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

In recent days, deep learning has been widely used in signal and information processing. Among the deep learning algorithms, Convolution Neural Network (CNN) has been widely used for image recognition and classification because of its architecture, high accuracy and efficiency. This paper proposes a method that uses the CNN on audio samples rather than on the image samples in which the CNN method is usually used to train the model. The one-dimensional audio samples are converted into two-dimensional data that consists of matrix of Mel-Frequency Cepstral Coefficients (MFCCs) that are extracted from the audio samples and the number of windows used in the extraction. This proposed CNN model has been evaluated on the TIDIGITS corpus dataset. The paper analyzes different convolution layer architectures with different number of feature maps in each architecture. The three-layer convolution architecture was found to have the highest accuracy of 97.46% among the other discussed architectures. © Springer Nature Singapore Pte Ltd. 2020

VIT Unitversity

Electrical

School of Electrical Engineering

Chennai Campus

School of Electronics Engineering

First International Conference on Sustainable Technologies for Computational Intelligence Advances in Intelligent Systems and Computing

Experimental Evaluation of CNN Architecture for Speech Recognition

Energy resources such as gas often transported through pipes which play a significant role in cities, industries. Gas leakage in pipes prompts misfortune just as a danger since they can likewise prompt flame mishaps. The point of this work is to structure an independent robot for in-pipe investigation. The system utilized includes a focal pole whereupon a translational component is fitted which thusly is associated with three edges of connections and wheels. DC motors are joined to the wheels to accomplish the drive required. The component considers little settlement in-pipe distances across. Setting sensors on each segment of pipe is in all respects exorbitant. A pipe crawling robot prototype that can detect the leakage of Methane, Butane, LPG, Smoke in a pipe by moving horizontally and vertically to prevent mishaps in industries. The Internet of Things (IoT) module is interfaced with a robot to give a real-time analysis on the cloud platform and GPS to give the exact location of the leakage. © 2020, Springer Nature Singapore Pte Ltd.

World University root node

Lecture Notes in Electrical Engineering

Industrial IoT-Based Gas Pipe Leakage Detector Robot

The single-event transients in MOSFETs due to heavy ion strikes introduce soft errors in sub-50 nm CMOS VLSI circuits. These transients are easily captured and propagated in high-frequency CMOS VLSI circuits. The capture rate mainly depends on the single-event transient (SET) pulse width and the clock frequency of the circuits. An estimation of the SET pulse width through a physics-based model that considers the device electrostatics is necessary to predict and mitigate these soft errors in VLSI circuits. In this article, a physics-based bias-dependent model is developed to determine the SET pulse width of a double-gate (DG) CMOS inverter with the heavy-ion strike on OFF state NMOS. The output voltage perturbations due to ion strike in the CMOS inverter and the SET pulse width model are derived from the bias-dependent SET current model previously reported. The variations in the output voltage of the inverter and the pulse width obtained from the developed model for different Linear Energy Transfer (LET), supply bias, strike positions, device dimensions, and load capacitances are validated with TCAD mixed-mode simulations. © 2001-2011 IEEE.

IEEE Transactions on Device and Materials Reliability

A physics-based single event transient pulse width model for cmos vlsi circuits

Single-event transient (SET) due to heavy-ion strike is a serious reliability concern for devices operated in radiation environment. Due to technology scaling, nodal capacitance decreases which increases the SET vulnerability. In this paper, the sensitivity of SET pulse width in 45 nm bulk and SOI MOSFET to linear energy transfer (LET), heavy-ion track length, angle of strike, characteristic radius, and characteristic time of the track is analysed. The modification of SET pulse width while propagating through 45 nm bulk-and SOI-based CMOS chain of inverters and its dependence on aforementioned radiation parameters is also analysed. The results show that all the pulses produced in SOI-based inverter chain get attenuated during propagation and do not reach the last stage. However, in the case of bulk, any SET having pulse width greater than 37 ps (measured using full width at half maximum) propagates and reaches the last stage of the inverter chain. Thus, the SOI devices are more immune to SET compared to the bulk, for different heavy-ion track parameters. © 2020, © 2020 IETE.

IETE Journal of Research

Sensitivity of SET Pulse-Width and Propagation to Radiation Track Parameters in CMOS Inverter Chain

Most of mankind’s living and workspace have been or going to be blended with smart technologies like the Internet of Things. The industrial domain has embraced automation technology, but agriculture automation is still in its infancy since the espousal has high investment costs and little commercialization of innovative technologies due to reliability issues. Machine vision is a potential technique for surveillance of crop health which can pinpoint the geolocation of crop stress in the field. Early statistics on crop health can hasten prevention strategies such as pesticide, fungicide applications to reduce the pollution impact on water, soil, and air ecosystems. This paper condenses the proposed machine vision relate research literature in agriculture to date to explore various pests, diseases, and weeds detection mechanisms. © The authors. Licensee MDPI, Basel, Switzerland.

Fulltext

Journal of Phytology

Machine vision detection of pests, diseases and weeds: A review

Optical scanning holography is an incoherent optical image processing system. It is a technique, where the complete information of an object or image will be recorded as a hologram and later reconstructed to get back the original image. In the hologram reconstruction process, a virtual image is formed along with the real image, which appears as a twin image noise. To eliminate such noises, a technique of hybrid algorithm is used while recording the hologram itself. The MATLAB R2012b image processing tool is used for simulation and the simulated values are tabulated and compared with the existing method in terms of peak signal to noise ratio, mean square error. In the reconstruction, the proposed method results are having 26% increment in the MSE and PSNR values. To further improve the MSE and PSNR values a case study using different denoising techniques combined with the proposed hybrid algorithm is used and found considerable improvement of 32%. Hence the image quality is increased. © 2020 Inderscience Enterprises Ltd.

International Journal of Computer Aided Engineering and Technology

Hybrid algorithm for twin image removal in optical scanning holography

A Mobile Ad hoc Network (MANET) is a network composed of numerous autonomous mobile nodes. In recent times, the opportunistic network, a type of MANET is gaining a lot of significance among the researchers, as it is capable of communicating with the sink node through an efficient selection of relay nodes. In the opportunistic networks, the node does not seek any knowledge about the network topology as it selects the efficacious relay node for transmission of packets. However, MANET requires nodal information about network topology. In the opportunistic network, the data stockpiled in the packets are transmitted from a source node to a sink node by utilizing relay node opportunistically for every hop. However, this type of communication leads to delayed data delivery with increased hops as a consequence of the unsystematic selection of relay nodes. To overcome these constraints, this article focuses on the selection of optimal relay nodes for attaining faster data delivery, by unveiling the location and by predicting the mobility pattern of the neighbor nodes. Hence, this research paper proposes Particle Swarm Optimization algorithm for the selection of optimal relay nodes by locating the neighbor nodes within an established Inter-Communication Range employing Cartesian based localization technique and by analyzing their mobility pattern using recurrent neural network-long short-term memory prediction model. The results of the proposed methodology are compared with four other existing methods, namely, MaxProp, Spray and Wait, and Epidemic. The comparative results infer that the proposed method is efficient in terms of performance, reduced hops, reduced delay with enhanced packet delivery ratio, and improved overhead ratio. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

Wireless Personal Communications

Heuristic Relay-Node Selection in Opportunistic Network Using RNN-LSTM Based Mobility Prediction

The past decade has witnessed numerous Routing design proposals for wireless multi-hop network specifically for Wireless Sensor Network (WSN) and recently its allied Low Power, Lossy Networks (LLN) in the era of Internet of Things (IoT). However, experimentation using sensor motes in real test-bed is limited as majority cater to simulation analysis. This work proposes and implements a Hybrid Opportunistic Routing (OR) design for Low Power, Lossy WSN. The routing protocol adopts opportunistic mode of forwarding as the first and last resort to improve end-to-end packet delivery ratio. The protocol switches to unicast mode for successive transmissions by relying on trust-worthy forwarder(s) until link-level transmission error occurs. The OR phases such as candidate selection, prioritization and coordination are carried out on the fly in a completely distributed online manner by eligible forwarders. These forwarder(s) computes its priority order based on cross-layered routing metrics in a fuzzy manner and collaborate via timer coordination with differentiated Back-off Exponent (BE) parameters assignment for packet forwarding. The real test-bed experimentation using IEEE 802.15.4 compliant SENSEnuts platform recorded the lossy-link characteristics during range test measurements. The proposed hybrid OR showed improvement in end-to-end delivery rate with increase in hops and number of forwarding candidates per level compared to level based unicast routing. © 2020 IEEE.

2020 International Conference on COMmunication Systems and NETworkS, COMSNETS 2020

Experimental Test-Bed Implementation of Hybrid Opportunistic Routing Design for Low Power, Lossy Wireless Sensor Network

This study analyzes the soft error sensitivity of SRAM cell which employs double-gate tunnel field effect transistor (DG TFET). The mitigation technique for the data recovery after the heavy ion strike is discussed. The conventional 6T TFET SRAM cell is designed using DG TFET of 30 nm. For the circuit simulation, the symbol of DG TFET is developed with the help of a look-up table based Verilog-A code. The radiation induced single event upset (SEU) causes a change in the stored data of SRAM cell. In order to improve the SEU sensitivity, the radiation hardening-by-design technique (RHBD) is introduced in 6T TFET SRAM cell by connecting the RC feedback loop between the two cross coupled inverters. The standby power of the TFET SRAM cell is calculated and compared before and after the radiation mitigation technique insertion. © 2013 IEEE.