Search

In order to survive, mankind needs air. The quality of life depends on the purity of the air we breathe in. Hazardous pollutants are stirred up in our environment by various activities everyday. In a developing country like India, which has huge population, protecting public health is important. In general, air quality is measured using the air quality index, which records the pollutants level in the air. These recordings are to be mentioned across various places, to know about the air quality level. The advancement of the recent artificial intelligence can be replaced by the human efforts and to automate the system in flowless manner. Hence, an effort has been taken in this paper, by proposing a framework of predicting the air quality seasonally using regularized combinational LSTM (REG-CLSTM). For an efficient air quality level prediction with an improved error rate, time, and accuracy, the study has implemented Reg-CLSTM with a large amount of real-time dataset. To improvise the comprehensiveness and the potentiality of the proposed model, the significant feature is extracted by the rough set-wrapper method. The significant challenge is to provide a seasonal limit range for each considered pollutant in place of a generalized range partition. Aiming at this problem, the proposed model is able to identify the highest concerning pollutants occurrence in individual seasons. Through this study, pyramid learning-based hybridized deep learning framework is developed which can play a crucial role in warning the policy maker to reduce the activities that instigate air pollution. [ABSTRACT FROM AUTHOR]

In India, rice crops are very significant. Rice cultivation comprises several phases, and it is crucial to keep an eye on the crop's development to avoid any leaf diseases and to provide a good yield. To avoid yield loss, crop diseases need to be determined at the initial stage. Deep learning-based pre-trained CNN architecture is used in this study to identify rice leaf diseases. This paper discusses four different CNN architectures to classify and identify healthy and diseased leaves such as Brown spot, Hispa, and Leaf Blast. Initially, to avoid vanishing gradient problems that degrade the performance of the Network, ResNet34 and ResNet50 are used. Even though the CNN model performs the feature extraction, Self-attention with ResNet18 and ResNet34 architecture is utilized to improve the feature selection process. As a result of enhanced feature extraction, the accuracy of rice leaf disease identification and classification has improved. Finally, high accuracy of 98.54% is achieved with the proposed ResNet34 with self-attention architecture when compared to other CNN models used in this paper. In terms of multiclass classification, the proposed model offers improved outcomes when compared to state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Deep learning models in recent times have shown promising results for solar energy forecasting. Solar energy depends heavily on local weather conditions, and as a result, typically hundreds of models are built, which need site and season-specific training. The model maintenance and management also become a tedious job with such a large number of models. Here, we are motivated to use transfer learning to accommodate local variations in the solar pattern over the available global pattern. It may also be noted that apparently transfer learning has been rarely/never used for solar forecasting. In this paper, we have proposed a bidirectional gated recurrent unit (BGRU) based model, which employs transfer learning for short-term solar energy forecasting. The said model yields better forecasting accuracy compared to site-specific models with a lower variance. It also takes 39.6% less parameters and 76.1% reduced time for training. The current literature suggests that selection of base scenario for transfer learning is an open problem and in this paper, we have also proposed an intuitive strategy for the same. The effectiveness of the same is established through empirical study. [ABSTRACT FROM AUTHOR]

Corona Virus Disease 2019 (COVID-19) is a continuing extensive incident globally affecting several million people's health and sometimes leading to death. The outbreak prediction and making cautious steps is the only way to prevent the spread of COVID-19. This paper presents an Adaptive Neuro-fuzzy Inference System (ANFIS)-based machine learning technique to predict the possible outbreak in India. The proposed ANFIS-based prediction system tracks the growth of epidemic based on the previous data sets fetched from cloud computing. The proposed ANFIS technique predicts the epidemic peak and COVID-19 infected cases through the cloud data sets. The ANFIS is chosen for this study as it has both numerical and linguistic knowledge, and also has ability to classify data and identify patterns. The proposed technique not only predicts the outbreak but also tracks the disease and suggests a measurable policy to manage the COVID-19 epidemic. The obtained prediction shows that the proposed technique very effectively tracks the growth of the COVID-19 epidemic. The result shows the growth of infection rate decreases at end of 2020 and also has delay epidemic peak by 40–60 days. The prediction result using the proposed ANFIS technique shows a low Mean Square Error (MSE) of 1.184 × 10–3 with an accuracy of 86%. The study provides important information for public health providers and the government to control the COVID-19 epidemic. [ABSTRACT FROM AUTHOR]

Air is the basis for the existence of life on Earth; but in the present age of modernization the degrading quality of air year by year, due to the growth of Industrialization, urbanization, automobiles, coal-fired thermal power plants, and various other factories is the matter of real concern. To predict the future growth of air pollutants numerous prediction models have been developed by researchers. Time-series ARIMA model although quite useful for forecasting but fails to handle non-stationary problems. Among all the existing forecasting models, wavelets along with the Machine learning models have proved to be very successful and have been widely used in various fields like mathematical modeling, signal recognition, image recognition, classification, function approximation, data processing, filtering, clustering, compression, robotics, and decision making. It is also used in the field of mathematical forecasting for developing efficient prediction models. This paper aims to develop a wavelet-ANFIS conjugation model and a wavelet-ARIMA coupled model along with the time-series ARIMA model for the prediction of black carbon concentration over the Raniganj, Jharia, and Bokaro coal mines of India, by considering a long term data obtained by NASA (http://nasa.gov/) and compare the results obtained by these models for determining the best prediction model. The validity of the results is tested with the help of error measures like RMSE, MSE, MAPE, MAE, and relative error. Results over the three sample sites conclude that the Wavelet-ANFIS conjugation approach outperforms the wavelet-ARIMA coupled approach and the simple time-series ARIMA model. [ABSTRACT FROM AUTHOR]

Social media are the main contributors to spreading fake images. Fake images are manipulated images altered through software or by other means to change the information they convey. Fake images propagated over microblogging platforms generate misrepresentation and stimulate polarization in the people. Detection of fake images shared over social platforms is extremely critical to mitigating its spread. Fake images are often associated with textual data. Hence, a multi-modal framework is employed utilizing visual and textual feature learning. However, few multi-modal frameworks are already proposed; they are further dependent on additional tasks to learn the correlation between modalities. In this paper, an efficient multi-modal approach is proposed, which detects fake images of microblogging platforms. No further additional subcomponents are required. The proposed framework utilizes explicit convolution neural network model EfficientNetB0 for images and sentence transformer for text analysis. The feature embedding from visual and text is passed through dense layers and later fused to predict fake images. To validate the effectiveness, the proposed model is tested upon a publicly available microblogging dataset, MediaEval (Twitter) and Weibo, where the accuracy prediction of 85.3% and 81.2% is observed, respectively. The model is also verified against the newly created latest Twitter dataset containing images based on India's significant events in 2020. The experimental results illustrate that the proposed model performs better than other state-of-art multi-modal frameworks. [ABSTRACT FROM AUTHOR]

Electric vehicles (EVs) have emerged as a fast-growing industry not only in India but all over the world due to their environment friendly and economic properties. Moreover, it is being seen as a future replacement for fast depleting fossil fuels. But still, the international vehicle market cannot accept EVs as a ubiquitous vehicle manufacturing standard due to their short cruising range and underdeveloped charging infrastructure. Therefore, as an immediate and cost-effective solution to a problem subject to limited battery capacity, the EV route regularization, i.e., optimum energy usage route selection becomes utmost important. To accomplish this objective, this paper proposes a meta-heuristic routing model based on the principles of Artificial Bee Colony (ABC). The proposed model has been designed to consider prominent energy consumption influencing parameters like speed, battery health, road elevation, etc. Moreover, tractive effort modeling on different road surfaces like dry, wet, snow, and icy is also embedded in the design of EV route modeling. The simulation of the proposed model has been done to quantify its performance bys utilizing route maps as well as real-time information of vehicles' location by the Warrigal project as input. The analysis of obtained results has revealed the traces of saving in EVs' energy consumption of about 7.1% in comparison with Google maps if the route suggested by the proposed model is followed. [ABSTRACT FROM AUTHOR]

In the present situation, the sustainable development goal on "Gender Equality" (SDG 5) is a challenging problem over the entire globe, also in India. In this paper, the fuzzy graph theory is used to analyse the overall performance of India for the SGD 5. To solve this problem, the new concept of pseudo-vertex-covering set of a fuzzy graph to make a well coverage of the entire fuzzy graph with the combined coverage of vertex-covering set and underlying edge-covering set of the fuzzy graph is defined. With this new covering concept of pseudo-vertex-covering set of fuzzy graphs, an analysis of the performance status of India for SDG 5 is made with the individual performance status of all the states/UTs of India. We show a nice covering of the whole country by some particular states/UTs which are actively helping to make the pseudo-vertex-covering of the transformed form of the graph of India as a fuzzy graph. At last, a comparison between the covering score and index score for SDG 5 is given. Here, covering score is a new term in fuzzy graph theory for coverage of a fuzzy graph by some vertices with underlying some edges. Also, an analysis is given which reflecting a clean idea of the methodology for the performance status of India and these help to find the self-governing states/UTs in India for a better performance. [ABSTRACT FROM AUTHOR]

Tackling air pollution has become of utmost importance since the last few decades. Different statistical as well as deep learning methods have been proposed till now, but seldom those have been used to forecast future long-term pollution trends. Forecasting long-term pollution trends into the future is highly important for government bodies around the globe as they help in the framing of efficient environmental policies. This paper presents a comparative study of various statistical and deep learning methods to forecast long-term pollution trends for the two most important categories of particulate matter (PM) which are PM2.5 and PM10. The study is based on Kolkata, a major city on the eastern side of India. The historical pollution data collected from government set-up monitoring stations in Kolkata are used to analyse the underlying patterns with the help of various time-series analysis techniques, which is then used to produce a forecast for the next two years using different statistical and deep learning methods. The findings reflect that statistical methods such as auto-regressive (AR), seasonal auto-regressive integrated moving average (SARIMA) and Holt–Winters outperform deep learning methods such as stacked, bi-directional, auto-encoder and convolution long short-term memory networks based on the limited data available. [ABSTRACT FROM AUTHOR]

Fuzzy logic is, inter alia, a simple and flexible approach of modelling that can be used in river basins where adequate hydrological data are unavailable. In order to improve the real-time forecasting of floods, this paper proposes a Takagi–Sugeno fuzzy inference system termed as flood model Sugeno. A total of 12 input parameters were used to develop two fuzzy flood models—Mamdani and Sugeno. Whereas Sugeno FIS performed exceptionally well in predicting the river discharge, the Mamdani FIS failed to deliver the accurate results. The river Jhelum flowing through the Kashmir Valley in the northern Himalayas, India, was hit in September 2014 by a major flood and has been chosen as the case study to apply the fuzzy flood models. With a total of 24 rules in the rule base and five levels of linguistic variables, the flood model Sugeno predicted the river discharge with Nash–Sutcliffe model efficiency of 0.887, coefficient of correlation (R2) of 90.74%, mean square error of 0.00122, root mean square error of 0.0349, mean absolute error of 0.0139 and combined accuracy of 0.0466. The efficiencies of the developed model show acceptable levels according to the tested performance indicators implying the potential of establishing a flood forecasting system using the developed model. [ABSTRACT FROM AUTHOR]

Many crime reports are available online in various blogs and Newswire. Though manual annotation of these massive reports is quite tedious for crime data analysis, it gives an overall crime scenario of all over the world. This motivates us to propose a framework for crime data analysis based on the online reports. Initially, the method extracts the crime reports and identifies named entities. The intermediate sequence of context words between every consecutive pair of named entities is termed as a crime vector that provides relationships between the entities. The feature vectors for each entity pair are generated from these crime vectors using the Word2Vec model. The paper considers three different types of named entity pairs to facilitate the major crime data analysis task, and for each type, similarity between every pair of entities is measured using respective feature vectors. For each type of named entity pair, a separate weighted graph is generated with entity pairs as vertices and similarity score between them as the weight of the corresponding edge. Then, Infomap, a graph-based clustering algorithm, is applied to obtain optimal set of clusters of entity pairs and a representative entity pair of each cluster. Each cluster is labelled by the relationship, represented by the crime vector, of its representative entity pair. In reality, all the entity pairs in a cluster may not reflect contextual similarity with their representative entity pair. So the clusters are further partitioned into subclusters based on WordNet-based path similarity measure which makes the entity pairs in each subcluster more contextually similar compared to their original cluster. These subclusters provide us various statistical crime information over the time period. The method is experimented only using the crime reports related to crime against women in India. The experimental results demonstrate the effectiveness and superiority of the method compared to others for analysing the crime data. [ABSTRACT FROM AUTHOR]

In India, Telecom sector has been enduring a massive growth for over two and half decades in the bandwidth, preference of services and depth of penetration in urban, semi-urban and rural areas. Exploring the service providers or selecting the best cellular mobile telephone service providers (CMTSPs/TSPs) according to operational performance parameter can help to achieve the goal of telecom service provider selection (TSPS). Here, this assessment generally comprises various TSPs alternatives and different operational performance criteria; therefore, TSPS could be considered as a multi-criteria decision-making (MCDM) problem. The analytical data have been taken from the Telecom Regulatory Authority of India (TRAI), Jan–Mar 2017. Most of the data vary from 1 month to another. Thus, these small ranges of variation in the data are incorporated with the intuitionistic fuzzy numbers (IFNs). In this paper, we develop an outranking method, intuitionistic fuzzy ELECTRE (IF-ELECTRE), for MCDM problems. Proposed method is based on divergence measure, operators of IFNs, some modifications of classical ELECTRE method. In the MCDM, the criterion weight determination is a vital issue for the accuracy of evaluation results. In the process of calculation of criterion weight, concordance and discordance values, we propose new Jensen–Shannon divergence (JS-divergence) for IFSs to overcome the shortcoming of the existing ones and demonstrate different elegant properties of the proposed one. Since the uncertainty is an inevitable feature of MCDM problems, the proposed method can be a valuable tool for decision-making in an uncertain atmosphere to determine the partial-preference outranking order. To express the strength and reasonableness of the proposed method in the real-world MCDM problems, a TSPS problem is implemented. Using the proposed framework, a decision expert can make a strategy to improve the performance by benchmarking operational parameters. Finally, a comparison is discussed between the results of the proposed method and the existing ones for validating the proposed method. This analysis shows that the proposed method is efficient and well consistent with the other methods. [ABSTRACT FROM AUTHOR]

Feature selection plays a key role in reducing the dimensionality of a feature vector by discarding redundant and irrelevant ones. In this paper, a Genetic Algorithm-based hierarchical feature selection (HFS) model has been designed to optimize the local and global features extracted from each of the handwritten word images under consideration. In this context, two recently developed feature descriptors based on shape and texture of the word images have been taken into account. Experimentation is conducted on an in-house dataset of 12,000 handwritten word samples written in Bangla script. This database comprises names of 80 popular cities of West Bengal, a state of India. Proposed model not only reduces the feature dimension by nearly 28%, but also enhances the performance of the handwritten word recognition (HWR) technique by 1.28% over the recognition performance obtained with unreduced feature set. Moreover, the proposed HFS-based HWR system performs better in comparison with some recently developed methods on the present dataset. [ABSTRACT FROM AUTHOR]

This paper presents a prototype to classify stroke that combines text mining tools and machine learning algorithms. Machine learning can be portrayed as a significant tracker in areas like surveillance, medicine, data management with the aid of suitably trained machine learning algorithms. Data mining techniques applied in this work give an overall review about the tracking of information with respect to semantic as well as syntactic perspectives. The proposed idea is to mine patients' symptoms from the case sheets and train the system with the acquired data. In the data collection phase, the case sheets of 507 patients were collected from Sugam Multispecialty Hospital, Kumbakonam, Tamil Nadu, India. Next, the case sheets were mined using tagging and maximum entropy methodologies, and the proposed stemmer extracts the common and unique set of attributes to classify the strokes. Then, the processed data were fed into various machine learning algorithms such as artificial neural networks, support vector machine, boosting and bagging and random forests. Among these algorithms, artificial neural networks trained with a stochastic gradient descent algorithm outperformed the other algorithms with a higher classification accuracy of 95% and a smaller standard deviation of 14.69. [ABSTRACT FROM AUTHOR]

Western countries entertain speech recognition-based applications. It does not happen in a similar magnitude in East Asia. Language complexity could potentially be one of the primary reasons behind this lag. Besides, multilingual countries like India need to be considered so that language identification (words and phrases) can be possible through speech signals. Unlike the previous works, in this paper, we propose to use speech signal patterns for spoken language identification, where image-based features are used. The concept is primarily inspired from the fact that speech signal can be read/visualized. In our experiment, we use spectrograms (for image data) and deep learning for spoken language classification. Using the IIIT-H Indic speech database for Indic languages, we achieve the highest accuracy of 99.96%, which outperforms the state-of-the-art reported results. Furthermore, for a relative decrease of 4018.60% in the signal-to-noise ratio, a decrease of only 0.50% in accuracy tells us the fact that our concept is fairly robust. [ABSTRACT FROM AUTHOR]

In this paper, we have discussed the application of the artificial neural networks in wind speed prediction. They will be used to predict the average monthly wind speed at three wind gauging stations in Gujarat, India. The wind speed data on an hourly basis are collected by NIWE (National Institute of Wind Energy) and located in the coastal areas of Western India, primarily Gujarat. The short-term and long-term data consisting of wind speeds have been considered for the period from 2015 to 2017. An artificial neural network is utilized for wind speed prediction using data measured from these stations for training and testing the given information. The data were studied using the nonlinear autoregressive models, NAR and NARX and the chaotic time series prediction models. The model is predicted using the historical data of the same station. The data are measured at a height of 100 m. The mean absolute percentage error (MAPE) and mean average error (MAE) concerning the predicted and measured wind speed were found to be 5.09 × 10−3, 5.33 × 10−3 and 2.9 × 10−3, respectively. The results of the ANN technique were compared with the Mackey–Glass equation-based time series prediction. Additionally, studies have been done on calculating the production and supply capacity of wind energy. [ABSTRACT FROM AUTHOR]

Supplier selection is one of the key activities of purchase management in supply chain. Supplier selection is a multifaceted problem relating qualitative and quantitative multi-criteria. This paper deals with a supplier selection problem in an Indian automobile company. The work presents selection of headlamp supplier using integrated fuzzy multi-criteria decision-making approaches: analytical hierarchy process (AHP) and technique for order of preference by similarity to ideal solution (TOPSIS). The selection process starts with identifying the criteria based on literature review and interviewing industry experts. Weights to criteria are assigned using AHP, and suppliers are ranked using AHP and TOPSIS. Consistency tests are carried out to check the quality of expert’s inputs. Also, sensitivity analysis is done to check the robustness of the approach. The results address that fuzzy approaches could be effective and more accurate than the existing approaches for supplier selection problems. [ABSTRACT FROM AUTHOR]

This research paper presents a novel sequential wavelet-artificial neural network (ANN) with embedded ANN-particle swarm optimization (PSO) for short-term day-ahead forecasting of market clearing price (MCP) in the Indian energy exchange. A precise price forecasting helps suppliers to set up bidding strategies, make investment decisions and be cautious against risks. Conversely, consumers can use price forecasting to exploit appropriate power purchasing strategies for maximum utility utilization. Here the most influential historical data, namely purchase bid and MCP, are considered for training the feed-forward back-propagation neural network. The proposed model involves three sequential phases. Initially, the raw historical data are smoothened by removing the high-frequency components using a wavelet transform method which may enable better training of neural network. Then, ANN is used to train historical patterns. More number of trials is carried out, and the final weights that give the least training error are stored. In the final phase, the stored weights that are obtained from various trials are used as the initial population for the embedded ANN-PSO model. Here the performance of the proposed forecasting model is carried out using three error indices, namely mean absolute percentage error, normalized mean square error and error variance. [ABSTRACT FROM AUTHOR]

This paper evaluates the ability of wavelet transform in improving the accuracy of artificial neural network (ANN) and adaptive neuro-fuzzy interface systems (ANFIS) models. In this study, the performance of hybrid Wavelet-ANN and Wavelet-ANFIS models for estimating daily evapotranspiration in arid regions was evaluated. Prior to the development of models, gamma test was used to identify the best input combinations that could be used under limited data scenario. Performance of the proposed hybrid models was compared to ANN, ANFIS, and conventionally used Hargreaves equation. The results revealed that use of wavelet transform as data preprocessing technique enhanced the efficiency of ANN and ANFIS models. Wavelet-ANN and Wavelet-ANFIS performed reasonably better than other models. Better handling of wavelet-decomposed input variables enabled Wavelet-ANN models to perform slightly better than the Wavelet-ANFIS models. W-ANN2 (RMSE = 0.632 mm/day and R = 0.96) was found to be the best model for estimating daily evapotranspiration in arid regions. The proposed W-ANN2 model used second-level db3 wavelet-decomposed subseries of temperature and previous day evapotranspiration values as inputs. The study concludes that hybrid Wavelet-ANN and Wavelet-ANFIS models can be effectively used for modeling evapotranspiration. [ABSTRACT FROM AUTHOR]

Agricultural price forecasting is one of the challenging areas of time series forecasting. The feed-forward time-delay neural network (TDNN) is one of the promising and potential methods for time series prediction. However, empirical evaluations of TDNN with autoregressive integrated moving average (ARIMA) model often yield mixed results in terms of the superiority in forecasting performance. In this paper, the price forecasting capabilities of TDNN model, which can model nonlinear relationship, are compared with ARIMA model using monthly wholesale price series of oilseed crops traded in different markets in India. Most earlier studies of forecast accuracy for TDNN versus ARIMA do not consider pretesting for nonlinearity. This study shows that the nonlinearity test of price series provides reliable guide to post-sample forecast accuracy for neural network model. The TDNN model in general provides better forecast accuracy in terms of conventional root mean square error values as compared to ARIMA model for nonlinear patterns. The study also reveals that the neural network models have clear advantage over linear models for predicting the direction of monthly price change for different series. Such direction of change forecasts is particularly important in economics for capturing the business cycle movements relating to the turning points. [ABSTRACT FROM AUTHOR]

In this paper, we propose elitist genetic algorithms-based artificial neural network (ANN) model for setting up an early warning system for occurrence of high inflation. The proposed warning system uses values of an appropriate set of economic fundamental variables as input and builds an ANN model for quantifying the possibility of high inflation within a fixed period of time window. Elitism-based generational genetic algorithm is used for optimizing the architecture of the ANN model. We empirically evaluate the proposed neuro-genetic approach to identify the class of leading economic indicators and build an early warning signalling system of an occurrence of high inflation (overall and component inflations) using the data from the Indian economy. We further compare the results of the proposed approach with the commonly used data-driven signals approach. In the empirical studies, we observe promising performance of the proposed neuro-genetic warning system, which is capable of generating accurate early warning signals of an impending high inflation. [ABSTRACT FROM AUTHOR]

The accurate prediction of groundwater level is important for the efficient use and management of groundwater resources, particularly in sub-humid regions where water surplus in monsoon season and water scarcity in non-monsoon season is a common phenomenon. In this paper, an attempt has been made to develop a hybrid neural model (ANN-GA) employing an artificial neural network (ANN) model in conjunction with famous optimization strategy called genetic algorithms (GA) for accurate prediction of groundwater levels in the lower Mahanadi river basin of Orissa State, India. Three types of functionally different algorithm-based ANN models (viz. back-propagation (GDX), Levenberg-Marquardt (LM) and Bayesian regularization (BR)) were used to compare the strength of proposed hybrid model in the efficient prediction of groundwater fluctuations. The ANN-GA hybrid modeling was carried out with lead-time of 1 week and study mainly aimed at November and January months of a year. Overall, simulation results suggest that the Bayesian regularization model is the most efficient of the ANN models tested for the study period. However, a strong correlation between the observed and predicted groundwater levels was observed for all the models. The results reveal that the hybrid GA-based ANN algorithm is able to produce better accuracy and performance in medium and high groundwater level predictions compared to conventional ANN techniques including Bayesian regularization model. Furthermore, the study shows that hybrid neural models can offer significant implications for improving groundwater management and water supply planning in semi-arid areas where aquifer information is not available. [ABSTRACT FROM AUTHOR]