MRI image analysis and its segmentation for the accurate and automatic detection of brain tumors at an early stage is very much crucial for diagnosis the disorders and save human lives. Since most ...deep learning models have a large number of layers, they also take longer processing time, making them unsuitable for smaller image datasets. Hence, we have proposed, the detection of abnormality from brain MR images using a Less Layered and less complex U-Net model (LeU-Net) architecture. The principle of LeU-Net is inspired by the Le-Net and U-Net models, but completely different from both the design and architectural perspectives. The abnormality detection indicates the classification of the tumorous cell from overall Magnetic Resonance images. The Proposed deep learning model (LeU-Net) performance was compared with the existing basic CNN models Le-Net, U-Net, and VGG-16. The model performance was evaluated using evaluation metrics accuracy, precision, F-score, recall, and specificity. The experiment is performed on MR Dataset with uncropped images and cropped images (removed unwanted area) and compared the result with all three models. The LeU-Net model registers overall 98% accuracy on cropped images and 94% of accuracy on uncropped images. The LeU-Net model has much faster processing (simulation) time, it only takes 244.42 s and 252.36 s, respectively, to train the model with 100 epochs on the uncropped and cropped images. We have compared the performance of our proposed model with various state-of-the-art techniques, and it provides the best classification accuracy among all.
Over the past few decades, many publications have been made in the area of Load frequency control (LFC) of interconnected power systems. Load frequency control is necessary to develop better control ...in order to achieve less effect on the frequency and tie line power deviations after a load perturbation. However, number of control strategies has been employed in the design of load frequency controllers in order to achieve a better dynamic response and the exact choice of the LFC controller in a particular case requires sufficient expertise because each controller has its own merits and demerits. Due to this, an appropriate review of load frequency control (LFC) mechanism is essential and a few attempts have been made in this concern. This paper presents a detailed survey on load frequency control (LFC) mechanism. The overall study explores the depth study issues related to LFC mechanism based on different sources of power system models. This paper focused on different control techniques of LFC, which also includes all the recent application of FACTS devices. This review reveals the investigation of soft computing based optimization technique and application of Energy Storage System (ESS) and HVDC-link in LFC. These studies also illustrates conventional power system, deregulated of power environment as well as distributed generation and micro grids. This paper is designed in order to highlight the major traits of Load forecasting and some critical case studies on LFC.
The identification and classification of tumors in the human mind from MR images at an early stage play a pivotal role in diagnosis such diseases. This work presents the novel Deep Neural network ...with less number of layers and less complex in designed named U-Net (LU-Net) for the detection of tumors. The work is comprised of classifying the brain MR images into normal and abnormal class from the dataset of 253 images of high pixels. The MR images were 1st resized, cropped, preprocessed, and augmented for the accurate and fast training of deep neural models. The performance of the Lu-Net model is evaluated using five types of statistical assessment metrics Precision, Recall, Specificity, F-score, and Accuracy, and compared with the other two types of model Le-Net and VGG-16. The CNN models were trained and tested on augmented images and validation is performed on 50 untrained data. The overall accuracy of Le-Net, VGG-16 and Proposed model received were 88%, 90%, and 98% respectively.
•LU-Net: A Novel Deep Learning Model designed for brain tumor detection.•Automatic classification of abnormal tumors from brain MRI images.•The proposed model is very efficient, fast and accurate compared to Le-Net, VGG-16 and state-of-the-art techniques.•The simulation time of training of the proposed model is also very short, only 252.36 s.
Photovoltaic (PV) panels used for converting sunlight into electrical energy offer several drawbacks, such as poor efficiency, occupying a larger area, and dependency, on environmental conditions. ...One of the major factors impacting the PV panel performance is the panel surface temperature. High surface temperature leads to lower electrical efficiency of PV panels. Therefore, the researchers have suggested the benefits of hybrid photovoltaic thermal (PVT) system that contributes to heat generation along with controlling the panel temperature. A more appropriate and practical mathematical model is presented in this research to examine the impact of mass flow rate on the effectiveness of an air-cooled hybrid PVT system. Each component of the system is considered for the energy balance equations, and a MATLAB code is written to solve the resultant system of equations. Performance parameters such as electrical and thermal efficiency, PV, and output temperature were recorded with variations in mass flow rate. The outcomes portray that the PV and output temperature falls while thermal, electrical, and overall efficiency improves with a rising mass flow rate. Further, the effectiveness of the PVT system with a curved-groove absorber is compared with the V-groove absorber-based PVT system. At a mass flow rate of 0.2 kg/s, the electrical, thermal, and overall efficiency is 2.23%, 1.24%, and 1.87% higher for the PVT system with a curved-groove absorber in comparison with the system with a V-groove absorber in the channel.
Wind power is the most reliable and developed renewable energy source over past decades. With the rapid penetration of the wind generators in the power system grid, it is very essential to utilize ...the maximum available power from the wind and to operate the wind turbine (WT) at its maximal energy conversion output. For this, the wind energy conversion system (WECS) has to track or operate at the maximum power point (MPP). A decent variety of publication report on various maximum power point tracking (MPPT) algorithms for a WECS. However, making a choice on an exact MPPT algorithm for a particular case require sufficient proficiency because each algorithm has its own merits and demerits. For this reason, an appropriate review of those algorithms is essential. However, only a few attempts have been made in this concern. In this paper, different available MPPT algorithms are described for extracting maximum power which are classified according to the power measurement i.e. direct or indirect power controller. Merits, demerits and comprehensive comparison of the different MPPT algorithms also highlighted in the terms of complexity, wind speed requirement, prior training, speed responses, etc. and also the ability to acquire the maximal energy output. This paper serves as a proper reference for future MPPT users in selecting appropriate MPPT algorithm for their requirement.
The paper deals with the performance checking of an optimally designed LCL-filter connected along the grid-side converter (GSC) in a doubly fed induction generator (DFIG) based wind energy conversion ...system (WECS) in attenuating harmonics. A repetitive approach is required for designing the parameters of the LCL-filter. The reasons being the explicitness of design parameters and design requirements of the proposed filter like IEEE-519 Std. for harmonic current attenuation, maximum voltage difference allowed in between two sides of the filter to limit switching losses, and limit of reactive power compensation. The proposed filter is compared with the conventional LCL-filter. Based on the proposed method, a minimal inductance and optimal capacitance-based filter is obtained in this paper which is validated using a 2.2 kW DFIG based WECS. Comparative stability analysis of DFIG system with and without proposed filter is performed using small signal stability analysis. The system under study is simulated using MATLAB/Simulink and OPAL-RT 4510, simultaneously. Simulation results validates the effective use of proposed filter design method into DFIG system in terms of harmonic attenuation, total harmonic distortion and reactive power compensation.
We analyze a model where the government has to decide whether to impose a lockdown in a country to prevent the spread of a possibly virulent disease. If the government decides to impose a lockdown, ...it has to determine its intensity, timing and duration. We find that there are two competing effects that push the decision in opposite directions. An early lockdown is beneficial not only to slow down the spread of the disease, but creates beneficial habit formation (such as social distancing, developing hygienic habits) that persists even after the lockdown is lifted. Against this benefit of an early lockdown, there is a cost from loss of information about the virulence and spread of the disease in the population in addition to a direct cost to the economy. Based on the prior probability of the disease being virulent, we characterize the timing, intensity and duration of a lockdown with the above mentioned tradeoffs. Specifically, we show that as the precision of learning goes up, a government tends to delay the imposition of lockdown. Conversely, if the habit formation parameter is very strong, a government is likely to impose an early lockdown.
•We characterize the trade-offs involved in a lockdown of a nation.•Lockdown prevents disease propagation and induces changes in population habits.•Early lockdown leads to benefits from habit formation but impedes learning.•Strength of learning versus habit changes determines optimal lockdown policy.•Policy also depends on the strength of the economic loss and public backlash
The unceasing deterioration of the environment and the sharp rise in the price of conventional sources of energy led scientists to search for more resilient and long-lasting energy sources. As one of ...the numerous forms of renewable energy sources available, solar energy is the most cost-effective, clean, free, and environmentally friendly alternative. Photovoltaic and thermal (PVT) energy systems are becoming increasingly popular as they maximise the benefits of solar radiation, which generates electricity and heat at the same time. This paper elaborates on various aspects of PVT systems including the concept, material, and methods of review, classifications of PVT systems, air-type, water-type, PVT with nano-fluid applying a range of methodologies, and building-integrated PVT (BIPVT) systems. Based on existing literature, PVT systems are also compared in terms of performance parameters and improved efficiency. From the findings of various studies, an unglazed air collector is found to be better for improving thermal efficiency, also this PVT system is technically cheaper in terms of accounting. This study suggests that to decrease the cost and enhance the effectiveness of such systems further research is needed.
This paper presents a modified minimal realization technique to reduce single input single output (SISO) systems from higher-order SISO systems. The reduction process is based on restructuring the ...Hankel matrix, which consists of two major elements, i.e., Time Moments and Markov parameters. The system transformation is executed to reduce the order of the system by maintaining the desired system properties. The modified Hankel Matrix is proposed to obtain an expected reduce order model, i.e.,
k
th order reduced model by selecting
k
×
k
order square matrix and using Silverman’s algorithm. This paper presents a simple solution of model order reduction with the advantages of minimizing the steady-state error, fast convergence of steady-state behavior, better approximation in terms of rise time, peak time, and settling time at higher frequencies. Three different cases have been taken from the literature to validate the proposed technique with the comparisons of performance in terms of a quality check through performance indices and response matching between original and reduced-order models.
In this article, authors proposed a useful technique for order reduction of large-scale linear dynamic time-invariant systems using the dominant pole retention, Pole Spectrum Analysis, and Pade ...approximations. The denominator dynamics of the simplified system is obtained by using PSA and pole dominance algorithm; numerator dynamics of the same is obtained by using Pade approximation. The approximation is based on the principle that the mean of the poles (pole centroid) and centroid-based system stiffness are same for both large-scale and simplified systems. For a stable higher-order system, the method promises the stability of the simplified system. To validate the proposed technique, some numerical illustrations have been considered from the literature with the comparisons of performance in terms of a quality check through performance index and response matching between original higher-order and simplified systems.