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

Department of Control and Automation

A new single-phase 15-level inverter with a reduced number of components for the Solar PV application is proposed in this paper. It is incorporate the proposed inverter with a boost converter to extract energy from the solar PV modules, the proposed inverter aids to generate fifteen stepped output voltage levels with lower THD. The proposed inverter can improve efficiency and reduce losses, cost, and complexity of the overall system. The conventional boost converter will boost the output voltage to a maximum voltage from Solar PV with MPPT(PO). The proposed inverter is tested experimentally using the dSPACE RTI 1104 controller along with MATLAB/Simulink. A detailed comparison with existing MLIs with the proposed inverter. The work presents experimental results not only to show its efficiency but also to the effectiveness under different circumstances of linear and non-linear loads. The inverter is stable during the non-linear loads and well suits for grid-connected systems. © 2013 IEEE.

School of Electrical Engineering

Vellore Campus

World University root node

Fulltext

IEEE Access

Design and Implementation of a Single-Phase 15-Level Inverter with Reduced Components for Solar PV Applications

The pandemic of Coronavirus Disease-19 (COVID-19) has spread around the world, causing an existential health crisis. Automated detection of COVID-19 infections in the lungs from Computed Tomography (CT) images offers huge potential in tackling the problem of slow detection and augments the conventional diagnostic procedures. However, segmenting COVID-19 from CT Scans is problematic, due to high variations in the types of infections and low contrast between healthy and infected tissues. While segmenting Lung CT Scans for COVID-19, fast and accurate results are required and furthermore, due to the pandemic, most of the research community has opted for various cloud based servers such as Google Colab, etc. to develop their algorithms. High accuracy can be achieved using Deep Networks but the prediction time would vary as the resources are shared amongst many thus requiring the need to compare different lightweight segmentation model. To address this issue, we aim to analyze the segmentation of COVID-19 using four Convolutional Neural Networks (CNN). The images in our dataset are preprocessed where the motion artifacts are removed. The four networks are UNet, Segmentation Network (Seg Net), High-Resolution Network (HR Net) and VGG UNet. Trained on our dataset of more than 3,000 images, HR Net was found to be the best performing network achieving an accuracy of 96.24% and a Dice score of 0.9127. The analysis shows that lightweight CNN models perform better than other neural net models when to segment infectious tissue due to COVID-19 from CT slices. © 2021. Iyer et al.

PeerJ Computer Science

Performance analysis of lightweight CNN models to segment infectious lung tissues of COVID-19 cases from tomographic images

Accurate modeling of liquid flow systems is necessary for the effective operation of the plant under different conditions. The plant dynamics may change with time, and due to this, the operation may not be satisfactory. In this article, relay autotuning of a liquid flow-line is proposed. Well-known describing function approximation is utilized for the estimation of gain of relay used in a feedback loop to excite the plant to be identified. The expressions are derived for the identification of a class of overdamped second-order plus dead-time and first-order plus dead-time plant dynamics. The identification method tested on different standard systems shows that the proposed method has good identification accuracy. Therefore, the proposed identification method is applied to a liquid flow line pressure control system. The experimental results show that an accurate dynamic model is extracted using the proposed method with a minimal set of data from an obtained limit cycle oscillation. The measured quantities of the limit cycle are utilized in the derived explicit expressions for the identification of unknown variables of the dynamic plant model. A distributed process control system is utilized here as a standard industrial platform to design virtual relay and conduct the proposed autotuning. The efficiency of the modeling method is demonstrated through the comparison of Nyquist and relay response plots with the transfer functions obtained from the MATLAB system identification toolbox. © The Author(s) 2020.

Transactions of the Institute of Measurement and Control

Transfer function identification of a liquid flow-line pressure control system from simple relay auto-tuning

To model, control, and analyze an electric power steering system used for autonomous driving. Firstly, a linearized model of steering system is obtained. The open-loop behavior is obtained to study system behavior. For control purpose, a proportional integral and derivative (PID) controller is used and the performance of controller (MSE/settling time/overshoot) is analyzed using simulation. The behavior of assist angle produced by motor in response to steering wheel movement is analyzed. © 2021, Springer Nature Singapore Pte Ltd.

Lecture Notes in Electrical Engineering

Modeling and Control of Electric Power Assist System in Steering

This paper provides an overview simulation and brief discussion about model predictive control of quasi-z-source inverter in shoot-through case and also non-shoot-through case. Model predictive control strategy related with different tasks related to closed-loop control of voltages and currents such as current across inductor and voltage across capacitor provides high dynamic performance and is useful toward controlling of power converters and drives. The steady-state and transient conditions are analyzed for both buck and boost case with experimental results. This approach improves overall performance of inverter and reduces switching losses of inverter. © 2021, Springer Nature Singapore Pte Ltd.

Department of Energy and Power Electronics

Department of Electrical Engineering

Model Predictive Control of Quasi-Z-Source Inverter

Skin cancer is one of the most deadly diseases around the world, wherein one of the three cancers is skin cancer. Early detection of skin cancer is paramount for better treatment planning. This paper investigates a Convolutional Neural Network (CNN), specifically, You Only Look Once (YOLO), to extract features from the skin lesions. The features, obtained from the CNN, are concatenated with traditional features like texture and colour features extracted from the lesion region of the input images. Later, the concatenated features are fed to a Fully Connected Network, which is trained with the specific ground truths to achieve higher classification accuracy. The proposed method improves the detection and classification of skin lesions when compared with other models and YOLO without traditional features. The performance measures of the fusion network are able to achieve the accuracy of 94%, precision of 0.85, recall of 0.88, and area under the curve of 0.95. © 2021, King Fahd University of Petroleum &amp; Minerals.

School of Electronics Engineering

Chennai Campus

Arabian Journal for Science and Engineering

A Dermoscopic Skin Lesion Classification Technique Using YOLO-CNN and Traditional Feature Model

No city can be called as smart without smart waste management system and in the very paper we have developed an integrated platform for waste management where dustbins are installed with a network of sensors and they transmit real-time data indicating the fill percentage of the bin. The purpose of this study is to develop an efficient waste management system based on Internet of things (IoT) for mobile application. We have observed traditional waste management system of India and have identified a number of issues with current systems. They are unhygienic landfills, overflowing waste bins, limited collection, lack of storage in collection vehicles, and less awareness of separated waste collection, recycling, and reuse. Therefore, this study has been proposed as a solution to cope up with the above issues. This study provides a platform for domestic users, drivers of collection vehicle, and garbage collection authority to interact with solid waste management of the country. The idea of our project was to basically alert the concerned authorities whenever the dustbin of a particular region is full and needs to be taken care of. Our objective is to cover all the dustbins of VIT University and install our smart system into those dustbins so that they could be emptied as soon as they get filled to avoid overflow of garbage and increasing the quality of the environment around the campus. We are making a prototype of the above-mentioned system. © 2021, Springer Nature Singapore Pte Ltd.

Garbage Monitoring System Using IoT for Mobile Application

Epilepsy is a chronic neurological disorder in which brain activity becomes abnormal due to sudden and recurrent seizures. In this paper, we have proposed a method to classify EEG signal for epileptic signals and healthy non-epileptic EEG signals. In the proposed method, we have applied Daubechies wavelet and power spectrum on the data. We extract the features of EEG signals. This statistical analysis of EEG signals was plotted and compared. Based on the extracted features, the EEG signal is effectively classified. The performance of the proposed method is assessed by sensitivity (100%), accuracy (99%) and specificity (98%). © 2021, Springer Nature Singapore Pte Ltd.

Classification of Epileptic EEG Signal from Normal EEG Using Wavelet Transforms

Electrical energy is used to machine metals in electric discharge machining (EDM) process. EDM is a thermoelectric process, in which machining occurs without cutting force. Hence, electrical energy is converted to thermal energy to remove material. Usually, straight polarity is used in EDM, i.e., workpiece is connected to positive terminal (anode) and tool is connected to negative terminal (cathode). But, reverse can be possibly have rarely studied. An in-house designed table-top EDM was built to perform the experiments in straight and reverse polarity. Copper material was used as tool and workpiece to avoid the effect of different material. The voltage and polarity have significant effect on removal of material from workpiece. © 2021, Springer Nature Singapore Pte Ltd.

Department of Manufacturing Engineering

School of Mechanical Engineering

Lecture Notes in Mechanical Engineering

Effect of Polarity on MRR and TWR in Electric Discharge Machining

Iterative Learning Control (ILC) aim is to improve control performance through iterations. ILC enhances transient behavior of the system, without knowing entire dynamics of plant model. Applied in feedforward path, it learns from past iteration and improves current iteration. Conventional ILC shows instability for exogenous disturbances, thus various ILC schemes are studied. In this paper, configurations of Iterative Learning Control (ILC) scheme namely, current cycle feedback (CCF), previous cycle feedback (PCF), Previous and Current cycle feedback (PCCF) are analyzed, intended to improve trajectory tracking and comparison of results are made under, Nominal Case, External Disturbance and Model Uncertainty on Magnetic levitation system through HIL Mathematical model of Maglev, obtained using Newton second law. To stabilize the open loop unstable system a PIV feedback controller is implemented. © 2021, Springer Nature Singapore Pte Ltd.