Maharaja Surajmal Institute of Technology

About: Maharaja Surajmal Institute of Technology is a based out in . It is known for research contribution in the topics: Cluster analysis & Computer science. The organization has 407 authors who have published 540 publications receiving 3581 citations.

Automated Deep Transfer Learning-Based Approach for Detection of COVID-19 Infection in Chest X-rays.

Abstract: The most widely used novel coronavirus (COVID-19) detection technique is a real-time polymerase chain reaction (RT-PCR) However, RT-PCR kits are costly and take 6-9 hours to confirm infection in the patient Due to less sensitivity of RT-PCR, it provides high false-negative results To resolve this problem, radiological imaging techniques such as chest X-rays and computed tomography (CT) are used to detect and diagnose COVID-19 In this paper, chest X-rays is preferred over CT scan The reason behind this is that X-rays machines are available in most of the hospitals X-rays machines are cheaper than the CT scan machine Besides this, X-rays has low ionizing radiations than CT scan COVID-19 reveals some radiological signatures that can be easily detected through chest X-rays For this, radiologists are required to analyze these signatures However, it is a time-consuming and error-prone task Hence, there is a need to automate the analysis of chest X-rays The automatic analysis of chest X-rays can be done through deep learning-based approaches, which may accelerate the analysis time These approaches can train the weights of networks on large datasets as well as fine-tuning the weights of pre-trained networks on small datasets However, these approaches applied to chest X-rays are very limited Hence, the main objective of this paper is to develop an automated deep transfer learning-based approach for detection of COVID-19 infection in chest X-rays by using the extreme version of the Inception (Xception) model Extensive comparative analyses show that the proposed model performs significantly better as compared to the existing models

Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN).

Abstract: Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network's recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.

Improvement in automatic generation control of two-area electric power systems via a new fuzzy aided optimal PIDN-FOI controller.

Abstract: Automatic generation control (AGC) executes a vital role to supply quality power in an interconnected power system. To cultivate good quality of power supply via preserving area frequency and tie-line power oscillations following consumer's load demand disturbances, the controller designed for AGC of power system should display excellent disturbance rejection expertise. Hence, in this paper, a maiden attempt is made to propose a fuzzy aided integer order proportional integral derivative with filter-fractional order integral (FPIDN-FOI) controller for AGC of multi-area power systems. A more recent intelligent optimization technique termed as imperialist competitive algorithm (ICA) is fruitfully employed for concurrent tuning of various parameters of the proposed controller. It is observed from the simulation results that the proposed FPIDN-FOI controller outperforms the various existing control strategies and PID/PIDN/FPIDN controller designed in the study for five different power system models. Effect of variation in fractional order value of integral on the system performance is analyzed. A sensitivity analysis is conducted to test the robustness of the designed controller under variations in the system parameters, load demands and existence of the system nonlinearities. It is perceived that the proposed controller is robust and executes adequately under variations in system parameters, random load disturbance patterns and nonlinearities.

BFOA-scaled fractional order fuzzy PID controller applied to AGC of multi-area multi-source electric power generating systems

Abstract: In the fast developing world of today, automatic generation control (AGC) plays an incredibly significant role in offering inevident demand of good quality power supply in power system. To deliver a quality power, AGC system requires an efficient and intelligent control algorithm. Hence, in this paper, a novel fractional order fuzzy proportional-integral-derivative (FOFPID) controller is proposed for AGC of electric power generating systems. The proposed controller is tested for the first time on three structures of multi-area multi-source AGC system. The gains and fractional order parameters such as order of integrator (λ) and differentiator (µ and γ) of FOFPID controller are optimized using bacterial foraging optimization algorithm (BFOA). Initially, the proposed controller is implemented on a traditional two-area multi-source hydrothermal power system and its effectiveness is established by comparing the results with FOPID, fuzzy PID (FPID) and PI/PID controller based on recently published optimization techniques like hybrid firefly algorithm-pattern search (hFA-PS) and grey wolf optimization (GWO) algorithm. The approach is further extended to restructured multi-source hydrothermal and thermal gas systems. It is observed that the dynamic performance of the proposed BFOA optimized FOFPID controller is superior to BFOA optimized FPID/FOPID/PID and differential evolution (DE)/genetic algorithm (GA) optimized PID controllers. It is also detected that the dynamic responses obtained under different power transactions with/without appropriate generation rate constraint, time delay and governor dead-zone effectively satisfy the AGC requirement in deregulated environment. Moreover, robustness of the suggested approach is verified against wide variations in the nominal initial loading, system parameters, distribution company participation matrix structure and size and position of uncontracted power demand.