Showing papers in "Journal of The Institution of Engineers : Series B in 2021"
TL;DR: A critical review of feature extraction techniques presented in this paper will help the researchers to make an informed choice of an appropriate technique for developing efficient methodologies for ECG signal processing.
Abstract: An Electrocardiogram (ECG) is a primary and most prevalent non-invasive test performed on the subjects’ (i.e. patients’) with suspected heart problems. It helps in diagnosing important cardiological status of the subject’s heart i.e. normal or abnormal by investigating rhythm of the heart. This interpretation is not always possible using naked eyes, especially for minute aberrations. Therefore, advanced feature extraction methods are required for investigating these minute differences that might be a challenge to be detected by the human eye. Hence, a critical review of feature extraction techniques presented in this paper will help the researchers to make an informed choice of an appropriate technique for developing efficient methodologies for ECG signal processing.
47 citations
TL;DR: The importance of having a robust fault identification, classification and localization algorithm which would be successfully able to drive as well as actuate the digital relaying system is laid down.
Abstract: Transmission lines are one of the most widely distributed engineering systems meant for transmitting bulk amount of power from one corner of a country to the farthest most in the other directions. The expansion of the lines over different terrains and geographic locations makes these most vulnerable to different kinds of atmospheric calamities which more often develops faults in line. It is imperative to remove the faulty line at the earliest to restrict undue outflow of bulk power through the faulted point as well as restore system stability earliest to resume normal power flow operation. Here lays the importance of having a robust fault identification, classification and localization algorithm which would be successfully able to drive as well as actuate the digital relaying system. Researchers have worked out several methodologies in developing improved power system protection algorithms which would be able to serve to eliminate faults immediately on occurrence of the same. A brief yet exhaustive review has been presented in this article including the several methodologies adopted by numerous researchers for developing effective fault diagnosis schemes, mentioning about the highlights as well as the shortcoming of each of the methods. This compact and effective survey of literature works would help researchers to take up appropriate techniques for different purposes of transmission line fault analysis.
37 citations
TL;DR: A highlighted headline and link extractor has been created to extract top news for both Hindi and English from Google’s news feed and the methodology clearly shows that it can efficiently identify top news articles and measure the similarity between news reports.
Abstract: The present global size of online news websites is more than 200 million. According to MarketingProfs, more than 2 million articles are published every day on the web, but Online News websites have also circulated editorial content over the internet that specifies which articles to display on their website’s home pages and what articles to highlight, e.g., broad text size for main news articles. Many of the articles posted on a news website are very similar to many other news websites. The selective reporting of top news headlines and also the similarity among news across various news associations is well-identified but not very well calculated. This paper identifies the top news items on the news sites and measures the similarity between two same news items in two languages (Hindi and English) referring to the same event. To accomplish this, a highlighted headline and link extractor has been created to extract top news for both Hindi and English from Google’s news feed. First, translate the Hindi news article into English by using Google translator and then compare it with English news articles. Second, we used the cosine similarity, Jaccard similarity, Euclidean distance measure to calculate news similarity score. The frequency of nouns and the next word of nouns from the news articles are also extracted. Our methodology clearly shows that we can efficiently identify top news articles and measure the similarity between news reports.
31 citations
TL;DR: In this article, an attempt is made to find the effectiveness of online teaching-learning methods for university and college students by conducting an online survey and a questionnaire has been specially designed and deployed among university students.
Abstract: Online teaching–learning methods have been followed by world-class universities for more than a decade to cater to the needs of students who stay far away from universities/colleges. But during the COVID-19 pandemic period, online teaching–learning helped almost all universities, colleges, and affiliated students. An attempt is made to find the effectiveness of online teaching–learning methods for university and college students by conducting an online survey. A questionnaire has been specially designed and deployed among university and college students. About 450 students from various universities, engineering colleges, medical colleges in South India have taken part in the survey and submitted responses. It was found that the following methods promote effective online learning: animations, digital collaborations with peers, video lectures delivered by faculty handling the subject, online quiz having multiple-choice questions, availability of student version software, a conducive environment at home, interactions by the faculty during lectures and online materials provided by the faculty. Moreover, online classes are more effective because they provide PPTs in front of every student, lectures are heard by all students at the sound level of their choice, and walking/travel to reach classes is eliminated.
18 citations
TL;DR: The architecture of FPGAs and their types in detail is illustrated and the various advantages of using reconfigurable computing design over conventional Application-Specific Integrated Circuits for achieving high level of performance for a desired application are shown.
Abstract: Reconfigurable computing is a potential paradigm which has been effectively performing mostly in the developments of devices likely Field Programmable Gate Arrays (FPGAs). This paper illustrates the reconfigurable architecture of FPGA and its types. Most widely used high-speed computation fabrics utilized in reconfigurable computing are FPGAs. This paper demonstrates the architectures used in reconfigurable computing and shows the various advantages of using reconfigurable computing design over conventional Application-Specific Integrated Circuits for achieving high level of performance for a desired application. The survey deals with the architecture of FPGAs and their types in detail. This paper also explains the highlights and challenges of fine-grained and coarse-grained architectures. FPGAs have supported partial reconfiguration over the few years. This survey also includes the partial reconfiguration techniques and the various applications of reconfigurability.
17 citations
TL;DR: The present review outlines the status, challenges, and need to promote telemedicine's rapid progression in India, especially during the pandemic emergency rooms.
Abstract: Telemedicine is considered as the "Natural evolution of healthcare in the digital world." In India, considering the vast geographical spread, predominant rural population, and sound medicinal services overwhelmingly accessible in urban areas, telemedicine has immense potential to grow from its nascent stages. The progression of technology-enabled transformations will provide an impetus to reshape the contours of India's healthcare. Epidemics and pandemics pose a monumental challenge for healthcare professionals. To mitigate the impacts, extending telemedicine's emergence and utilization can serve as one of the most effective approaches to broaden our perspectives. Further proactive intervention and exploration to increase comprehension of how telemedicine could be applied during pestilence circumstances needs to be expedited. The prospects for smart healthcare are vast; thus, embracing the recent advancement of information and communication technology can lead to indelible healthcare management changes. The present review outlines the status, challenges, and need to promote telemedicine's rapid progression in India, especially during the pandemic emergency rooms.
16 citations
TL;DR: In this paper, the authors have presented the possible factors that determine the uneven distribution of COVID-19 deaths in SAARC countries compared to the First World Nations, and the risk index of each factor has been labeled using analytical hierarchy process (AHP)-based MCDM, i.e., multiple criteria decision-making technique.
Abstract: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) which caused an outbreak of pneumonia in December 2019 in Wuhan, China, has spread rapidly throughout the world. This ongoing pandemic has resulted over 55.6 million cases of COVID-19 leading to 1.34 million deaths in more than 188 countries. However, it has been observed that the death rate is significantly in the lower side for the SAARC countries compared to the First World Nations. In this paper, the possible factors have been represented that determine this uneven distribution of COVID-19 deaths. The significance of the factors has been presented in this paper after the data analysis of the factors from 165 different countries. Based on the correlation of the factors and their critical impact towards the concerned countries death toll, the risk index of each factor has been labeled using analytical hierarchy process (AHP)-based MCDM, i.e., multiple criteria decision-making technique. The risk index of all the factors has been used to generate the susceptibility of COVID-19 for each of the countries in study, specifically the SAARC Nations. Finally, the hierarchical clustering was applied to visualize the death toll of the countries corresponding to their susceptibility index.
15 citations
TL;DR: A novel technique, i.e., fractional wavelet transform (FrWT) is proposed to be used as a feature extraction technique and results establish robustness of the proposed technique will go a long way in assisting the cardiologists in improving overall health care system in hospitals.
Abstract: An electrocardiogram (ECG) is an essential and fundamental diagnostic tool for assessing cardiac arrhythmias. It is mainly a combination of P, QRS, and T waves. But visual inspection of these waves may lead to wrong diagnosis due to physiological variability and noisy QRS complexes. Hence, computer-aided diagnosis (CAD) is required for accurate and efficient diagnosis of the clinical information. Therefore, in this paper, a novel technique, i.e., fractional wavelet transform (FrWT) is proposed to be used as a feature extraction technique. Afterward, Probabilistic Principal Component Analysis (PPCA) and K-Nearest Neighbor (KNN) are jointly used as classification (i.e., detection of R-peaks) tools for diagnosing heart abnormalities in various morphologies of the ECG signal robustly. The proposed technique has been evaluated on the basis of sensitivity (Se), detection error rate (Der), and positive predictive value (Ppv) for records in the MIT-BIH Arrhythmia database (M/B Ar DB). The proposed technique yields Se of 99.98%, Der of 0.036%, and Ppv of 99.98% for M/B Ar DB. These results establish robustness of the proposed technique, which will go a long way in assisting the cardiologists in improving overall health care system in hospitals.
15 citations
TL;DR: Separate machine learning algorithms for instance Random Forest, Support Vector Machine, Decision Tree, Artificial Neural Networks, K-Nearest Neighbors, and Naïve Bayes are evaluated for attacks detection against ICS and the outcome shows great execution of machineLearning algorithms in identifying assaults.
Abstract: The Industrial Internet of Things corresponds to several industrial devices that are equipped with sensors connected to networks gathering and sharing data. These devices are being used by the industry, providing a new global industrial system on a scale never seen before, called Industry 4.0. The conjunction of industrial IoT and intelligent automation has been an asset for many enterprises, allowing the machines to take on tasks that previous generations of automation could not handle. On the other hand, the number of cyber attacks is increasing since the industrial devices have become connected to the Internet. In this paper, separate machine learning (ML) algorithms for instance Random Forest, Support Vector Machine (SVM), Decision Tree, Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN) and Naive Bayes are evaluated for attacks detection against ICS and their performance metrics are recorded. The outcome shows great execution of machine learning algorithms in identifying assaults, furthermore, shows a meager erroneous alarm rate thus implies, it identifies ordinary traffic very well.
14 citations
TL;DR: The paper presents a principal component analysis (PCA)-based method for localization of various power system faults in a 150 km long single side fed transmission line using quarter-cycle pre-fault and half-cycle post-f fault sending end line current signals, producing a highly accurate localization.
Abstract: The paper presents a principal component analysis (PCA)-based method for localization of various power system faults in a 150 km long single side fed transmission line using quarter-cycle pre-fault and half-cycle post-fault sending end line current signals. The proposed work uses fault signals of ten different types of seven intermediate locations along the length of the line to develop three-phase PCA score indices. The localizer model is also designed for practical fitment, with fault signals contaminated with power system noise. These seven sets of indices are further used with the best-fit curve fitting method in the MATLAB environment to develop fault curves. Minimum root mean square error criteria are followed for selecting the fit type. Each fault class is designed with the required number of curves to estimate fault location. The proposed work produces a highly accurate localization, with only 0.1271% average percentage error for fault localization, and a maximum percentage error of 0.5821% for the 150 km line.
14 citations
TL;DR: In this article, the authors proposed a novel deep learning-based strategy to address the challenges of facial expression recognition from images, which is developed in such a manner that it learns hidden nonlinearity from the input facial images, and achieves an accuracy of around 69.57%.
Abstract: Facial expression recognition is an intriguing and demanding subject in the realm of computer vision. In this paper, we propose a novel deep learning-based strategy to address the challenges of facial expression recognition from images. Our model is developed in such a manner that it learns hidden nonlinearity from the input facial images, which is critical for discriminating the type of emotion a person is expressing. We developed a deep convolutional neural network model composed of a sequence of blocks, each consists of multiple convolutional layers and sub-sampling layers. Investigations on the benchmark FER2013 dataset indicate that the proposed facial expression recognition network (FERNet) surpasses existing approaches in terms of performance and model complexity. We trained our model on the FER2013 dataset, which is the most challenging of all the available datasets for this task, and achieve an accuracy of around 69.57%. Furthermore, we investigate the effects of dropout, batch normalization, and augmentation, as well as how they aid in the reduction of over-fitting and improved performance.
TL;DR: The optimization algorithm is applied under different cases to check its effectiveness for optimal planning and the suggested framework can be considered as part of comprehensive energy management.
Abstract: The microgrid is an economical and feasible alternative to provide the electrification of current, and future scenarios as the depletion rate of conventional fuel are high. It is essential to optimize microgrid components, including batteries, to analyze the total system cost and reliability. In the present work, a rural microgrid is planned to integrate wind, solar, diesel generator, and battery systems. The remote region of Uttarakhand (India) selected for the techno-economic and feasibility analysis of the proposed microgrid. The planned objective is concerned with determining the least per unit cost of energy and viability of the model. The optimization algorithm is applied under different cases to check its effectiveness for optimal planning. The suggested framework can be considered as part of comprehensive energy management. The simulation results indicate the high potential of saving.
TL;DR: In this paper, the authors used Accelerated Gradient Long Short Term Memory (AG-LSTM) and Kalman filter to predict the stock market in Yahoo and Twitter.
Abstract: Stock Market Prediction system provides an overview for the business to gain high profit in the share market. The rise of a large volume of data related to the financial market makes it difficult to analyze and predict the stock market effectively. This research focuses on to improve the effectiveness of the stock market prediction based on the Kalman filter. The financial data from Yahoo and Twitter are used to forecast the stock market values. The technical indices are extracted from the data to investigate the stock values. Twitter data related to the company’s stock value are extracted and analyzed the sentiment. Next, the Kalman filter is applied to reduce the errors from data. Kalman filter is used here to smoothen the noise created by sudden peaks in the data or to filter out the abnormal incidents in the data for training. Hence, the classification algorithm is not trained with irrelevant features value. The Accelerated Gradient Long-Short Term Memory (AG-LSTM) is used for stock market prediction. The output of the method is analyzed with and without Kalman filter and this showed that the Kalman filter technique increased the performance of the stock market prediction. In Microsoft stock data, the accuracy of the proposed AG-LSTM with Kalman filter model has achieved accuracy of 90.42%, while existing AG-LSTM model has achieved 57.53%.
TL;DR: Phasor measurement unit (PMU)-based islanding detection technique is presented, the requirement of channel limits of PMUs is also incorporated, and significant results of industry and utility have been obtained.
Abstract: The advancements in the field of wind turbine, solar photovoltaic (PV), fuel cell coupled with improved power electronics have increased reliability of renewable energy sources. The environmental benefits of these sources have forced the power industry to switch over for more distributed generations to meet the increasing load demand. Islanding in distribution system occurs when a portion of distribution system gets isolated from the rest of the grid and continues to supply the local load. Practically, all distributed generations (DG) are required to be disconnected immediately after the formation of island. It is done primarily to take care of safety of the operating personnel and to prevent power quality issues. Effective detection of islanding is an important area of concern. Prior to the integration of DG to the main electrical grid, each DG must be equipped with a suitable anti-islanding detection technique. In this paper, phasor measurement unit (PMU)-based islanding detection technique is presented. The requirement of channel limits of PMUs is also incorporated, and significant results of industry and utility have been obtained. The study has been carried out using MATLAB/Simulink (version 2018a) creating several islanding and non-islanding cases in a PV integrated distribution grid.
TL;DR: In this paper, the assessment of performance indices of a 3MW utility-scale ground-mounted grid-tied solar farm located in Northern India is carried out in this work, where real-time SCADA data of energy generation and other input parameters are utilized to evaluate performance indicators like Performance Ratio, Capacity Factor, efficiencies, losses, etc.
Abstract: The assessment of performance indices of a 3 MW utility-scale ground-mounted grid-tied solar farm located in Northern India is carried out in this work. Real-Time SCADA data of energy generation and other input parameters are utilized to evaluate performance indicators like Performance Ratio, Capacity Factor, efficiencies, losses, etc. The real-time and simulation results of the considered performance indicators are presented for the period from 1st January 2018 to 31st December 2018. The values of PR, CF and energy loss obtained are 80%, 16.35% and 19.42%, respectively. Among temperature, wind speed and level of accumulation of dust particles, ambient temperature is the most influential parameter that affects the PV performance in the considered region. The performance indicators estimated using PVSYST specifically for the detailed analysis of energy loss utilizing the three-stage conversion approach. The obtained estimated results are found to be in line with the actual values. These results could serve as a guideline for the application of solar PV in the northern part of India and in other countries with similar climatic conditions.
TL;DR: The simulation results and the Opal-RT real-time digital simulation results corroborate that VOC gives a superior dynamic performance as compared to droop control.
Abstract: Renewable Energy Sources (RES) have been found as viable alternatives for conventional power generation systems in recent times. The power electronic-based converters are the main medium of interface for connecting RES to the utility grid system. The prime focus of this paper is on inverter coordination methods to maintain system stability. The work is also attentive on the comparative examination of simple droop control, modified droop control, and Virtual Oscillator Control (VOC) methods for the control of parallel inverters operating in the standalone Microgrid (MG). The two different droop control methods are operated based on the active and reactive powers, which are phasor quantities, measured by sensed output voltage and current. Because of the phasor quantities, the dynamic response of the droop controller is insignificant. The VOC control mechanism works on instant current feedback signals, such that the dynamic performance of the system differs remarkably. The simulation results and the Opal-RT real-time digital simulation results corroborate that VOC gives a superior dynamic performance as compared to droop control.
TL;DR: For the least interrupted power supply, a new method for locating and identifying the faulted part of the distribution system with the presence of distributed generation is studied based on the impedance matrix of the Distribution network which has high speed and accuracy in fault location and also has high accuracy in simulations considering the asymmetry of loads and network.
Abstract: The study of “fault rapid detection and resolution” in the power network is particularly important in sensitive areas of the network. Today, the use of distributed generation in the distribution network is increasing. In the event of an accident, if the fault location is quickly identified, the recovery of the faulty network is accelerated and the shutdown time is minimized. Since distributed generation networks do not have the traditional methods of fault location, accurate and efficient performance, so in this paper, for the least interrupted power supply, a new method for locating and identifying the faulted part of the distribution system with the presence of distributed generation is studied. The proposed method is based on the impedance matrix of the distribution network which has high speed and accuracy in fault location and also has high accuracy in simulations considering the asymmetry of loads and network. In this paper, simulations are implemented in OpenDSS software under various fault conditions and the results are processed in MATLAB software.
TL;DR: The presented comparative analyses and dynamic responses validate the superiority of the proposed controller compared to recent adopted control schemes.
Abstract: In recent decades, penetrations of various renewable energy sources (RESs) and their intermittent nature result a drastic mismatch of power between the generation and load in microgrid (MG) systems. Presently, the forefront issues are to ensure the system stability and reliability by minimizing the power mismatch under the presence of these intermittent RES units. In response to this challenge, a novel moth flame optimization (MFO) based fuzzy proportional integral derivative (PID) controller is implemented to ensure better stability and proper power management in the islanded MG systems. Further, the performance verification of the proposed intelligent controller is carried out considering various case studies under different MG scenarios. In order to analyze robustness and sensitivity of the proposed controller, detailed investigations are also carried out implementing variations in solar-wind power output under random load perturbation (RLP). Further, the presented comparative analyses and dynamic responses validate the superiority of the proposed controller compared to recent adopted control schemes.
TL;DR: Results show that the TLBO technique is an efficient and effective method for determining the sizing of FACT devices in power system.
Abstract: In the modern power system, under heavy stress conditions, there is always the probability of line outage and resulting in voltage instability. This paper focuses on the optimal siting and sizing of Flexible AC Transmission Systems (FACTS) in the IEEE 30 bus transmission system. The optimization technique Teaching Learning Based Optimization (TLBO) algorithm is utilized to determine the optimal size of the FACT device to minimize real power loss. To reduce search space and computational burden, dv/dq index method is used to identify the weak buses for the placement of the FACTs device. The load flow analysis is performed using a Newton Raphson method. Results show that the TLBO technique is an efficient and effective method for determining the sizing of FACT devices in power system.
TL;DR: Wang et al. as discussed by the authors proposed VGG16 and MobileNet-V2, which makes use of ADAM and RMSprop optimizers for the automatic identification of the COVID-19 images from other pneumonia chest X-ray images.
Abstract: After the World War II, every country throughout the world is experiencing the biggest crisis induced by the devastating Coronavirus disease (COVID-19), which initially arose in the city of Wuhan in December 2019. This global pandemic has severely affected not only the health of billions of people but also the economy of countries all over the world. It has been evident that novel virus has infected a total of 20,674,903 lives as on 12 August 2020. The dissemination of the virus can be regulated by detecting the positive COVID cases as soon as possible. The reverse-transcriptase polymerase chain reaction (RT-PCR) is the basic approach used in the identification of the COVID-19. As RT-PCR is less sensitive to determine the novel virus at the beginning stage, it is worthwhile to develop more robust and other diagnosis approaches for the detection of the novel coronavirus. Due to the accessibility of medical datasets comprising of radiography images publicly, more robust diagnosis approaches are contributed by the researchers and technocrats for the identification of COVID-19 images using the techniques of deep leaning. In this paper, we proposed VGG16 and MobileNet-V2, which makes use of ADAM and RMSprop optimizers for the automatic identification of the COVID-19 images from other pneumonia chest X-ray images. Then, the efficiency of the proposed methodology has been enhanced by the application of data augmentation and transfer learning approach which is used to overcome the overfitting problem. From the experimental outcomes, it can be deduced that the proposed MobileNet-V2 model using ADAM and RMSprop optimizer achieves better accomplishment in terms of accuracy, sensitivity and specificity when contrasted with the VGG 16 using ADAM and RMSprop optimizers.
TL;DR: In this paper, a hybrid forecasting model has been proposed to determine the number of confirmed cases for upcoming 10 days based on the earlier confirmed cases found in India, the proposed model is based on adaptive neuro-fuzzy inference system (ANFIS) and mutation-based Bees Algorithm (mBA).
Abstract: In India, the first confirmed case of novel corona virus (COVID-19) was discovered on January 30, 2020. The number of confirmed cases is increasing day by day, and it crossed 21,53,010 on August 9, 2020. In this paper, a hybrid forecasting model has been proposed to determine the number of confirmed cases for upcoming 10 days based on the earlier confirmed cases found in India. The proposed model is based on adaptive neuro-fuzzy inference system (ANFIS) and mutation-based Bees Algorithm (mBA). The meta-heuristic Bees Algorithm (BA) has been modified applying 4 types of mutation, and mutation-based Bees Algorithm (mBA) is applied to enhance the performance of ANFIS by optimizing its parameters. Proposed mBA-ANFIS model has been assessed using COVID-19 outbreak dataset for India and USA, and the number of confirmed cases in the next 10 days in India has been forecasted. Proposed mBA-ANFIS model has been compared to standard ANFIS model as well as other hybrid models such as GA-ANFIS, DE-ANFIS, HS-ANFIS, TLBO-ANFIS, FF-ANFIS, PSO-ANFIS and BA-ANFIS. All these models have been implemented using Matlab 2015 with 10 iterations each. Experimental results show that the proposed model has achieved better performance in terms of Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean absolute error (MAE) and Normalized Root Mean Square Error (NRMSE). It has obtained RMSE of 1280.24, MAE of 685.68, MAPE of 6.24 and NRMSE of 0.000673 for India Data. Similarly, for USA the values are 4468.72, 3082.07, 6.1, and 0.000952 for RMSE, MAE, MAPE, and NRMSE, respectively.
TL;DR: In this article, the authors have studied different real-time health monitoring system based on diseases which are common in elderly people like diabetes, blood pressure, heart disease, sleep apnea, and cancer, etc.
Abstract: Nowadays, due to modernization or advancement in the Internet of Things (IoT) especially in the Healthcare area, we want to take care of our elders with some monitoring equipment, and the Internet of Things can play a significant role in it. The motivation of writing this paper is to collect the information of various existing Internet of Things Architecture and Communication Techniques used in Healthcare Monitoring System to observe that how efficiently, different researchers have used it. So we have studied different real-time health monitoring system based on diseases which are common in elderly people like diabetes, blood pressure, heart disease, sleep apnea, and cancer, etc. In this real-time health monitoring system, researchers introduced many new measures, communication techniques like ZigBee, Long-Range Wide Area Network (LoRawan), Radio Frequency Identification (RFID). Apart from this, it was also observed that remote monitoring system in Healthcare is incomplete without data processing and early prediction in such diseases. Though, Machine learning provides efficient techniques to extract knowledge from diagnostic medical datasets collected from the patients. That is why we highlighted the current role of various Machine Learning algorithms like Support Vector Machine, K-Nearest Neighbor, Random Forest, etc., for processing of Healthcare data and also helpful to predict the output more precisely.
TL;DR: In this paper, planning and economic analysis of a standalone solar photovoltaic system was carried out for the electrification of the rural community in the Indian scenario, where the size of the PV modules and capacity of the battery were estimated for all load profiles.
Abstract: Energy poverty is the main obstacle in developing millions of people worldwide. Electrification can improve the standard of education, living, health condition of the area. In developing countries like India, millions of people are still using conventional fuel for energy needs. The electrification of a rural area standalone solar PV system with the battery can be a feasible option. In the present work, planning and economic analysis of standalone solar photovoltaic system was carried out for the electrification of the rural community in the Indian scenario. For the case study, twelve un-electrified villages of Uttarakhand state of India were investigated under different load profiles. In this work, five different load profiles were considered for performance analysis based on the energy requirement of the rural population. The size of the PV modules and capacity of the battery were estimated for all load profiles. The economic analysis suggested that the proposed optimized load profile has the best design for the electrification of the rural community.
TL;DR: In this paper, a modified version of Type-III wind turbine system using DFIG (Double-Fed Induction Generator) is designed to control the active and reactive power during the transients and unwanted faults cause voltage sags.
Abstract: This research is based on the design of modified version of Type-III wind turbine system using DFIG (Double-Fed Induction Generator). The control technique associated with Type-III wind turbine system is Modified Type-I Fuzzy Logic Controller. Using this advanced form of controller, four different models are designed to control the active and reactive power during the transients and unwanted faults cause voltage sags. Mechanical Drive Train-modified Type-III DFIG-based wind turbine system during various fault conditions like voltage dip conditions, swell conditions with respect to variation in wind speed is explained in MATLAB model with control action of PI controller and Fuzzy Logic Controller (FLC) with grid integration. The research highlights implementations of four types of Fuzzy structures with different modes of operations that are modeled, and comparisons were made between all the structures with PI control structure for both steady state and dynamic state. The model is assembled to the lattice of grid, and the control of the model mechanisms using PI and FLC is studied to estimate the fast response of settling time after the removal of faults. The simulation is done to find the effective controller with respect to cost and economic point of view. The model is based on transient responses to calculate the settling time with application of various fault conditions. In this paper, DFIG, i.e., Double-Fed Induction Generator, is operated through variable speed and variable pitch angle control scheme which is now mostly implemented in power generation and distribution industries. In this paper, DFIG in wind turbine model is assembled to a constant frequency and constant voltage source and tied into a grid which is modeled using MATLAB and to the corresponding generator for operation and control action on active and reactive power are highlighted. The steady state operation and transient characteristics of the whole wind energy conversion system is explained with detail study with respect to the transients due to sudden change in wind speeds.
TL;DR: A novel methodology for the optimization of load shedding based on voltage-dependent load model accounting stability constraints using Black Hole (BH) optimization technique under emergency conditions mitigates a considerable amount of load shed and the system can be prevented from blackouts.
Abstract: This paper proposes a novel methodology for the optimization of load shedding based on voltage-dependent load model accounting stability constraints using Black Hole (BH) optimization technique under emergency conditions Line voltage stability index relation is derived for the selection of load bus Load buses for load shedding are identified on the basis of large sensitivity of minimum value of line voltage stability index with respect to the system load The load shedding has been optimized subject to stability constraints using BH algorithm Testing of the developed algorithm has been done using IEEE 14, 25 and 118 bus power systems The optimized results of the proposed algorithm have been compared on the basis of statistical inference with results obtained using well-established optimization techniques Simulation results authenticate that the proposed methodology mitigates a considerable amount of load shedding and the system can be prevented from blackouts
TL;DR: The results show that the GA-optimized FLC-based MPP tracking method has better performance with improved tracking accuracy and faster response under all weather conditions.
Abstract: This paper presents and discusses the Fuzzy-based MPPT technique optimized using the Genetic Algorithm (GA). The proposed GA simultaneously produces optimized ranges of both membership functions and the rule base of fuzzy. MATLAB coded GA to optimize the Fuzzy Logic Controller (FLC) is integrated with the Simulink model of the Photovoltaic (PV) system and training is performed online by operating the PV system for different conditions. GA provides the optimized membership functions and rule base of FLC upon completion of training. FLC is developed using the optimized values obtained from the training. The SPV system model with the GA-optimized fuzzy MPPT is built and simulation is performed. For a more realistic study, analysis of PV system under abruptly varying weather conditions is carried out using real-time data of a particular day on which the changes are very frequent. Besides, simulation of solar PV system is carried out with fuzzy MPPT and Artificial Neuro Fuzzy Inference System (ANFIS) MPPT for similar cases, the results are presented and discussed. The results show that the GA-optimized FLC-based MPP tracking method has better performance with improved tracking accuracy and faster response under all weather conditions.
TL;DR: An ensemble of convolutional LSTM-based spatiotemporal model can forecast the spread of the epidemic with high resolution and accuracy in a large geographic region and avoids the need of location specific adjacency matrix.
Abstract: The high R-naught factor of SARS-CoV-2 has created a race against time for mankind, and it necessitates rapid containment actions to control the spread. In such scenario short-term accurate spatiotemporal predictions can help understanding the dynamics of the spread in a geographic region and identify hotspots. However, due to the novelty of the disease there is very little disease-specific data generated yet. This poses a difficult problem for machine learning methods to learn a model of the epidemic spread from data. A proposed ensemble of convolutional LSTM-based spatiotemporal model can forecast the spread of the epidemic with high resolution and accuracy in a large geographic region. The feature construction method creates geospatial frames of features with or without temporal component based on latitudes and longitudes thus avoiding the need of location specific adjacency matrix. The model has been trained with available data for USA and Italy. It achieved 5.57% and 0.3% mean absolute percent error for total number of predicted infection cases in a 5-day prediction period for USA and Italy, respectively.
TL;DR: The primary goal of this paper is to discuss the use of emojis that supplement the text to express different emotions and compare some traditional text-based word embeddings and lexicons.
Abstract: Sentiment analysis is now a prominent field of interest owing to a growing trend of users expressing their opinions on social media, review pages, feedback forms, and other online channels. The machine learning approach to sentiment analysis focuses on feature extraction methods like constructing lexicons to learn sentiment polarity or learning word embeddings and applying them for their use in machine learning algorithms for sentiment classification. But most popular machine learning approaches still cannot capture nuanced emotions like sarcasm, irony, etc. Emojis are now being used along with text by the users to express emotions and hence can help researchers improve sentiment classification tasks. Sentiment analysis powered by emojis is still in the nascent phase and has gained some pace in the last five years. The primary goal of this paper is to discuss the use of emojis that supplement the text to express different emotions. This paper compares some traditional text-based word embeddings and lexicons. Then the paper discusses the evolution of emoji-based lexicons and emoji embeddings. Further, some deep learning approaches using emojis to improve existing sentiment classification tasks are studied. The main contribution of this paper is to survey various approaches to use emojis in sentiment analysis which to the best of our knowledge has not been done till now.
TL;DR: In this paper, a MapReduce-based fuzzy C-means algorithm for big document data clustering is proposed, which is extensively experimented with using different sizes of document datasets and executed over the Hadoop cluster of different sizes.
Abstract: The clustering of big data is a challenging task. The traditional clustering algorithms are inefficient for clustering big data. The recent researches in this field suggest that the traditional clustering algorithms needed to be redesigned for the modern architecture of computing. This wok has proposed a novel MapReduce-based fuzzy C-means algorithm for big document data clustering. The algorithm is extensively experimented with using different sizes of document datasets and executed over the Hadoop cluster of different sizes. The proposed algorithm’s efficiency is compared against serial traditional fuzzy C-means and MapReduce-based K-means algorithms. The proposed design of the fuzzy C-means algorithm is scaled well with the Hadoop platform and documents big datasets and resulted in a performance gain.
TL;DR: In this article, the machine learning model has been developed using time series analysis (ARIMA) model for predicting the new cases in India in the next coming days, results are also compared with the predictive values generated from the ARIMA and AR model and concluded that the ARimA model is the best fit model as compared to AR model for prediction the new case in India.
Abstract: Today world is going through a critical phase. The whole world is infected from the coronavirus [COVID 19]. In India also the number of new cases keeps on increasing. In this paper, the machine learning model has been developed using time series analysis (ARIMA model) for predicting the new cases in India in the next coming days. In this work, results are also compared with the predictive values generated from the ARIMA and AR model and concluded that the ARIMA model is the best fit model as compared to AR model for predicting the new cases in India. Python programming language has been used for implementation. The dataset from January 1, 2020 to July 31, 2020 has been taken for analysis. This paper is useful for researchers for further analysis of COVID-19 pandemic in India.