Search

The pulp and paper industry is critical to global industrial and economic development. Recently, India's pulp and paper industries have been facing severe competitive challenges. The challenges have impaired the environmental performance and resulted in the closure of several operations. Assessment and prediction of the performance of the Indian pulp and paper industry using various parameters is a critical task for researchers. This study proposes a framework for performance assessment and prediction based on Data Envelopment Analysis (DEA), Artificial Neural Networks, and Deep Learning (DL) to assist industry administration and decision-making. We presented a case study based on eight industries to demonstrate the methodology's applicability. This study analyses and predicts industry performance based on sample data observations over 30 years. The result suggests the DEA-DL-based efficiency prediction has an overall MSE of 0.08 compared with the actual efficiency. Furthermore, the efficiency rankings are compared between the three techniques. The results suggest that the integrated DEA-DL method is primarily accurate in most scenarios with the actual values. The findings of this study provide a comprehensive analysis of environmental performance for policymakers. [ABSTRACT FROM AUTHOR]

Forecasting of load is essential for operating power systems. India recently witnessed one of the worst power crisis with the highest ever power demand of 207 GW on April 29, 2022. The demand in the month of May and June 2022 was estimated to reach 215 GW. The peak demand this year 2023, according to the electricity ministry, is predicted to be around 230 GW from April to June. The inability to meet certain fundamental issues as power can take a toll on any country's economy. Proper prediction helps in proper decision making and planning. The main objective of this paper is to predict day ahead electrical load demand for Assam. Statistical and Machine Learning Algorithms has been studied. The study has been carried out using real-time data for the years 2016, 2017 and 2018. The paper presents a detailed analysis of the different hyper parameters of the deep learning models and their effect is seen on the learning efficiency. A novel stacked forecasting model is proposed using neural networks as base learners and CatBoost as the meta-learner. The performance of the proposed model has been evaluated and compared with individual models in terms of training time and accuracy using different error metrics namely MAE, MSE, RMSE, MAPE and R2 score. A comparison of the proposed prediction model with the prediction models available in literature has been presented. The conclusion states that both the statistical and machine learning algorithms used in this study act as useful tools for daily load forecasting with considerable accuracy; yet machine learning algorithm outperforms the statistical methods. The entire work has been done in Google Colaboratory using Python as the programming language. [ABSTRACT FROM AUTHOR]

The scenario of developed and developing countries nowadays is disturbed due to modern living style which affects environment, wildlife and natural habitat. Environmental quality has become or is a subject of major concern as it is responsible for health hazard of mankind and animals. Measurements and prediction of hazardous parameters in different fields of environment is a recent research topic for safety and betterment of people as well as nature. Pollution in nature is an after-effect of civilization. To combat the damage already happened, some processes should be evolved for measurement and prediction of pollution in various fields. Researchers of all over the world are active to find out ways of predicting such hazard. In this paper, application of neural network and deep learning algorithms is chosen for air pollution and water pollution cases. The purpose of this review is to reveal how family of neural network algorithms has applied on these two pollution parameters. In this paper, importance is given on algorithm, and datasets used for air and water pollution as well as the predicted parameters have also been noted for ease of future development. One major concern of this paper is Indian context of air and water pollution research, and the research potential presents in this area using Indian dataset. Another aspect for including both air and water pollutions in one review paper is to generate an idea of artificial neural network and deep learning techniques which can be cross applicable for future purpose. [ABSTRACT FROM AUTHOR]

China, India, and the USA are the countries with the highest energy consumption and CO2 emissions globally. As per the report of datacommons.org, CO2 emission in India is 1.80 metric tons per capita, which is harmful to living beings, so this paper presents India's detrimental CO2 emission effect with the prediction of CO2 emission for the next 10 years based on univariate time-series data from 1980 to 2019. We have used three statistical models; autoregressive-integrated moving average (ARIMA) model, seasonal autoregressive-integrated moving average with exogenous factors (SARIMAX) model, and the Holt-Winters model, two machine learning models, i.e., linear regression and random forest model and a deep learning-based long short-term memory (LSTM) model. This paper brings together a variety of models and allows us to work on data prediction. The performance analysis shows that LSTM, SARIMAX, and Holt-Winters are the three most accurate models among the six models based on nine performance metrics. Results conclude that LSTM is the best model for CO2 emission prediction with the 3.101% MAPE value, 60.635 RMSE value, 28.898 MedAE value, and along with other performance metrics. A comparative study also concludes the same. Therefore, the deep learning-based LSTM model is suggested as one of the most appropriate models for CO2 emission prediction. [ABSTRACT FROM AUTHOR]

Sentiment analysis is a way to extract emotion-based information or users' sentiments and opinions from text data. Sentiment analysis uses text analysis, Natural Language Processing (NLP), and computational linguistics. Text mining research has a strong focus on Sentiment Analysis (SA), which deals with the processing of opinions, attitudes, and the subjective aspect of the text. In today's time, we are seeing the availability of extensive web-based data on the Hindi language, which is a national language of India and also a first language used by the majority of the population in India. So, it has become extremely important to analyze customer's/user's opinions about the product, services or company and find out the key insights, particularly for companies and government organizations. The insights of sentiment analysis give a ray to the organizations to set their product/services or company as a key player in the market to survive to the long time period and get good business. This paper explores how we can effectively use deep neural networks in sentiment analysis to classify Hindi sentiments. To do it, we used word embeddings for Hindi text data and then trained the proposed model using Long Short-Term Memory (LSTM) and, subsequently, employed parameters. [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]

Data mining and machine learning algorithms' performance is degraded by data of high-dimensional nature due to an issue called "curse of dimensionality". Feature selection is a hot research topic where a subset of features are selected to reduce the dimensionality and thereby increasing the accuracy of learning algorithms. Redundant and irrelevant features are eliminated. Cervical cancer is most commonly occurring disease and driving reasons for untimely mortality among ladies worldwide especially in emerging low income nations like India. However, literature shows that the early identification and exact conclusion of cervical malignant growth can increase the survival chances. The disease does not show signs of its presence in the early stages of its growth. Automated classification and diagnosis of cervical cancer using machine learning and deep learning techniques is in high demand as it allows timely, accurate and regular study of the patient's health progress. Meta-heuristics algorithms provide a global problem independent optimal solution and applied on feature selection problem since decades. In spite of having a good number of literature, there is no survey on feature selection techniques applied to cervical cancer dataset. This paper presents a brief survey on meta-heuristic, its variants, hybrid meta-heuristic and hyper-heuristic techniques. This survey summarizes the feature selection techniques applied to the cervical cancer data to identify the research gap thereby guiding the researchers in the future research direction. The summary of categorization of the techniques such as nature-inspired or non-nature inspired and trajectory or population based is also highlighted. The survey provides a comparative literature review involving classical feature selection techniques and feature selection using metaheuristic algorithms for cervical cancer classification application. [ABSTRACT FROM AUTHOR]

The widespread growth in social media platforms provides a plethora of opportunities to enhance interaction and bring awareness about recent activities happening across the countries. Many people use social media to share their thoughts and opinions on societal and political issues. Nonetheless, some individuals misuse these platforms by posting toxic, hostile, and insulting comments. Hence, detecting and controlling such content at its earliest stage is crucial since its spread can harm social relations and negatively impact a person's life. In current scenarios, social media text consisting non-English languages is increasing due to active participation from multilingual societies. Of several non-English languages, Hindi English code-mixed is more prevalent in India. Most of the previous work to detect cyber aggression concentrates on English texts; therefore, there is high scope left to work on other languages such as Hindi English code-mixed. This paper has proposed a code-mixed hybrid embedding (CMHE) at the character and word level to capture similarly spelled and contextually related words. Furthermore, proposed embedding contributes significantly to the reduction of out of vocabulary words and capture words having similar polarity. After this, a deep learning framework based on CMHE, and a self-attention mechanism is proposed to retrieve significant features for classification. To evaluate proposed model, experiments were performed with two publicly available datasets: TRAC 2-2020 Hindi English code-mixed dataset (77.54% accuracy, 77.09% weighted average f1 score) and hate speech dataset (75.23% accuracy, 73.34% weighted average f1 score). The attained experimental results validate the effectiveness of proposed approach against the state-of-the-art. [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]

COVID-19 has laid an impact on every sector of the world. Howsoever severe, vaccines have acted as the sole source of a protective guard to prevent the further spread of the COVID-19 pandemic. In this research, the authors broadly focus on the trends in the vaccination drive of India. The paper revolves around a prediction and evaluation approach, which depending on the past and the current trends of daily vaccinations, obtain comparable results using a self-built recurrent neural network of LSTM layers for this study on time series evaluation. Through the neural network, the study predicts the exact vaccination figures likely to be achieved 1 year after vaccine introduction in the Indian subcontinent. The gathered data from January 16, 2021, until September 30, 2021, follow effective visualization of how the model outputs resemble the vaccination numbers for October 2021 and the predictions until January 16, 2022. Finally, the paper follows an extensive data analysis keeping in mind, the analogy of the number of COVID-19 cases and deaths before and after the vaccination system was centralized, to prove how sustainable the framework has been so far. [ABSTRACT FROM AUTHOR]

Even after scavenging the existence of mankind for the past year, the wrath of CoVID-19 is yet to die down. Countries like India are still getting haunted by the devastating conundrum, with coronavirus ripping through its citizens in the concurrent second wave. The surge of cases has prompted rapid intervention, with medical authorities pushing it to the limit to curve a roadblock to its aggressive growth. But, even after effortless work, human intervention remains slow and insufficient. Furthermore, relevant testing methodologies have shown weakness while detecting threats, with the recent growth of post-Covid complexities, thereby leaving a painful mark. This as such created a major requirement for technological advancements, which can cater to the mass. The growth of computational prowess in the past decade made the field of Deep Learning a major contributor in curving out algorithms to solve this. Adding to the excellent foundation of Deep Learning, this paper, proposes a novel CoWarriorNet model for rapid detection of CoVID-19, via chest X-ray images, which adds in an extra layer of precision and confirmation in the detection of cases in both pre-Covid and post-Covid conditions. The proposed classification model curves out an excellent accuracy of 97.8%, with the major eye-candy being the sensitivity rate of 0.99 when detecting CoVID-19 cases. This model introduces a new concept of Alpha Trimmed Average Pooling, which along with the novel architecture adds a subtle touch to its high efficiency, thereby giving a much-needed solution to the medical experts. The two-mouthed architecture provides the added benefit of a confidence score, deducing human aid in case of discrepancy. [ABSTRACT FROM AUTHOR]

India is a hotspot of the COVID-19 crisis. During the first wave, several lockdowns (L) and gradual unlock (UL) phases were implemented by the government of India (GOI) to curb the virus spread. These phases witnessed many challenges and various day-to-day developments such as virus spread and resource management. Twitter, a social media platform, was extensively used by citizens to react to these events and related topics that varied temporally and geographically. Analyzing these variations can be a potent tool for informed decision-making. This paper attempts to capture these spatiotemporal variations of citizen reactions by predicting and analyzing the sentiments of geotagged tweets during L and UL phases. Various sentiment analysis based studies on the related subject have been done; however, its integration with location intelligence for decision making remains a research gap. The sentiments were predicted through a proposed hybrid Deep Learning (DL) model which leverages the strengths of BiLSTM and CNN model classes. The model was trained on a freely available Sentiment140 dataset and was tested over manually annotated COVID-19 related tweets from India. The model classified the tweets with high accuracy of around 90%, and analysis of geotagged tweets during L and UL phases reveal significant geographical variations. The findings as a decision support system can aid in analyzing citizen reactions toward the resources and events during an ongoing pandemic. The system can have various applications such as resource planning, crowd management, policy formulation, vaccination, prompt response, etc. [ABSTRACT FROM AUTHOR]

Kidney cancer is the most common type of cancer, and designing an automated system to accurately classify the cancer grade is of paramount importance for a better prognosis of the disease from histopathological kidney cancer images. Application of deep learning neural networks (DLNNs) for histopathological image classification is thriving and implementation of these networks on edge devices has been gaining the ground correspondingly due to high computational power and low latency requirements. This paper designs an automated system that classifies histopathological kidney cancer images. For experimentation, we have collected Kidney histopathological images of Non-cancerous, cancerous, and their respective grade of Renal Cell Carcinoma (RCC) from Kasturba Medical College (KMC), Mangalore, Karnataka, India. We have implemented and analyzed performances of deep learning architectures on a Field Programmable Gate Array (FPGA) board. Results yield that the Inception-V3 network provides better accuracy for kidney cancer detection as compared to other deep learning models on Kidney histopathological images. Further, the DenseNet-169 network provides better accuracy for kidney cancer grading as compared to other existing deep learning architecture on the FPGA board. [ABSTRACT FROM AUTHOR]

Understanding the connections between human activities and the natural environment depends heavily on information about land use and land cover (LULC) in the form of accurate LULC maps. Environmental monitoring using deep learning (DL) is rapidly growing to preserve a sustainable environment in the long term. For establishing effective policies, regulations, and implementation, DL can be a valuable tool for assessing environmental conditions and natural resources that will positively impact the ecosystem. This paper presents the assessment of land use and land cover change detection (LULCCD) and prediction using DL techniques for the southwestern coastal region, Goa, also known as the tourist destination of India. It consists of three components: (i) change detection (CD), (ii) quantification of LULC changes, and (iii) prediction. A new CD assessment framework, Spatio-Temporal Encoder-Decoder Self Attention Network (STEDSAN), is proposed for the LULCCD process. A dual branch encoder-decoder network is constructed using strided convolution with downsampling for the encoder and transpose convolution with upsampling for the decoder to assess the bitemporal images spatially. The self-attention (SA) mechanism captures the complex global spatial-temporal (ST) interactions between individual pixels over space-time to produce more distinct features. Each branch accepts the LULC map of 2 years as one of its inputs to determine binary and multiclass changes among the bitemporal images. The STEDSAN model determines the patterns, trends, and conversion from one LULC type to another for the assessment period from 2005 to 2018. The binary change maps were also compared with the existing state of the art (SOTA) CD methods, with STEDSAN having an overall accuracy of 94.93%. The prediction was made using an recurrent neural network (RNN) known as long short term memory network (LSTM) for the year 2025. Experiments were conducted to determine area-wise changes in several LULC classes, such as built-up (BU), crops (kharif crop (KC), rabi crop (RC), zaid crop (ZC), double/triple (D/T C)), current fallow (CF), plantation (PL), forests (evergreen forest (EF), deciduous forest (DF), degraded/scurb forest (D/SF)), littoral swamp (LS), grassland (GL), wasteland (WL), waterbodies max (Wmx), and waterbodies min (Wmn). As per the analysis, over the period of 13 years, there has been a net increase in the amount of BU (1.25%), RC (1.17%), and D/TC(2.42%) and a net decrease in DF (3.29%) and WL(1.44%) being the most dominant classes being changed. These findings will offer a thorough description of identifying trends in coastal areas that may incorporate methodological hints for future studies. This study will also promote handling the spatial and temporal complexity of remotely sensed data employed in categorizing the coastal LULC of a heterogeneous landscape. [ABSTRACT FROM AUTHOR]

In India, a significant portion of the annual crop is lost due to plant diseases. It is required to monitor agriculture's growth and health status of plants to help farmers take prompt actions regarding any plant disease. An automatic plant disease classification algorithm is necessary to identify and prevent plant diseases at an early stage. This paper aims to classify plant diseases using a lightweight transfer learning model using only a few samples. Few-shot classification aims to identify unseen classes while training with small labeled data. The proposed work uses an aggregated loss function formed by the combination of triplet loss and cross-entropy loss with MobileNetV2 as a base model for the effective classification of plant disease using small samples. Two publicly available datasets (PlantVillage having 54,303 leaf samples and Plantdoc having 2598 Leaf samples) were considered for the evaluation of the proposed work. Different domain splits were considered to divide the dataset into the source, and target domains, and a large quantum of experimentation is conducted on the target dataset considering various sample sizes. For the analysis of plantvillage dataset, four domain splits were considered, and it is found that an average improvement in accuracy, when compared with recent work, is 1.49% for split-1, 16.25% for split-2, 2.9% for split-3, and 2.1%for split-4 using the proposed aggregated loss and the lightweight transfer learning model for the target domain data (K-ways, N-shot). Two domain splits were considered for the plantdoc dataset, and it gives an accuracy of around 81% using 30 samples and more than 40% using only 1 sample. The proposed work is compared with several state-of-the-art works using different evaluation metrics like, loss functions, execution time, model size, and model parameters. [ABSTRACT FROM AUTHOR]

Image denoising is an important preprocessing step in low-level vision problems involving biomedical images. Noise removal techniques can greatly benefit raw corrupted magnetic resonance images (MRI). It has been discovered that the MR data is corrupted by a mixture of Gaussian-impulse noise caused by detector flaws and transmission errors. This paper proposes a deep generative model (GenMRIDenoiser) for dealing with this mixed noise scenario. This work makes four contributions. To begin, Wasserstein generative adversarial network (WGAN) is used in model training to mitigate the problem of vanishing gradient, mode collapse, and convergence issues encountered while training a vanilla GAN. Second, a perceptually motivated loss function is used to guide the training process in order to preserve the low-level details in the form of high-frequency components in the image. Third, batch renormalization is used between the convolutional and activation layers to prevent performance degradation under the assumption of non-independent and identically distributed (non-iid) data. Fourth, global feature attention module (GFAM) is appended at the beginning and end of the parallel ensemble blocks to capture the long-range dependencies that are often lost due to the small receptive field of convolutional filters. The experimental results over synthetic data and MRI stack obtained from real MR scanners indicate the potential utility of the proposed technique across a wide range of degradation scenarios. [ABSTRACT FROM AUTHOR]

Crop pests and diseases are major threats to food security globally. The mung bean (Vigna Radiata) is one of the leading crops in India. A large part of the population in India is completely dependent on mung bean. So, high production efficiency for the mung bean is required, which does not happen due to the excessive damage from pests and diseases. Recently, with the advancement of Deep Learning techniques, remarkable performance has been achieved in the field of image classification by employing Convolutional Neural Networks (CNNs). This brings a lot of promise in the field of pest and disease identification by effective image classification. In this paper, we have proposed a novel deep learning-based technique to identify the mung bean pest and disease. In order to handle the limitation arising due to less number of mung bean crop images for the purpose of training, we have adopted transfer learning, which is able to generate a very promising result for quick and easy pest and disease detection. The developed model has successfully recognized 6 different types of mung bean diseases and 4 types of pests out of healthy and affected leaves collected in different seasons. Based on the experiments conducted, the proposed smartphone-based deep learning model for the mung bean pest and disease detection has achieved an average accuracy of 93.65%. [ABSTRACT FROM AUTHOR]

It has been declared by the World Health Organization (WHO) the novel coronavirus a global pandemic due to an exponential spread in COVID-19 in the past months reaching over 100 million cases and resulting in approximately 3 million deaths worldwide. Amid this pandemic, identification of cyberbullying has become a more evolving area of research over posts or comments in social media platforms. In multilingual societies like India, code-switched texts comprise the majority of the Internet. Identifying the online bullying of the code-switched user is bit challenging than monolingual cases. As a first step towards enabling the development of approaches for cyberbullying detection, we developed a new code-switched dataset, collected from Twitter utterances annotated with binary labels. To demonstrate the utility of the proposed dataset, we build different machine learning (Support Vector Machine & Logistic Regression) and deep learning (Multilayer Perceptron, Convolution Neural Network, BiLSTM, BERT) algorithms to detect cyberbullying of English-Hindi (En-Hi) code-switched text. Our proposed model integrates different hand-crafted features and is enriched by sequential and semantic patterns generated by different state-of-the-art deep neural network models. Initial experimental results of the proposed deep ensemble model on our code-switched data reveal that our approach yields state-of-the-art results, i.e., 0.93 in terms of macro-averaged F1 score. The dataset and codes of the present study will be made publicly available on the paper's companion repository [https://github.com/95sayanta/COVID-19-and-Cyberbullying]. [ABSTRACT FROM AUTHOR]

COVID-19 has emerged as the greatest threat in recent times, causing extensive mortality and morbidity in the entire world. India is among the highly affected countries suffering severe disruptions due this pandemic. To overcome the adverse effects of COVID-19, vaccination has been identified as the most effective preventive measure globally. However, a growing amount of hesitancy has been observed among the general public regarding the efficacy and possible side-effects of vaccination. Such hesitancy may proved to be the greatest hindrance towards combating this deadly pandemic. This paper introduces a multimodal deep learning method for Indian Twitter user classification, leveraging both content-based and network-based features. To explore the fundamental features of different modalities, improvisations of transformer models, BERT and GraphBERT are utilized to encode the textual and network structure information. The proposed approach thus integrates multiple data representations, utilizing the advances in both transformer based deep learning as well as multimodal learning. Experimental results demonstrates the efficacy of proposed approach over state of the art approaches. Aggregated feature representations from multiple modalities embed additional information that improves the classification results. The findings of the proposed model has been further utilized to perform a study on the dynamics of COVID-19 vaccine hesitancy in India. [ABSTRACT FROM AUTHOR]

The increasing use of social media to communicate is an emerging trend compared to traditional phone calls and SMS. WhatsApp is one of the popular social messaging applications used in India. Identification of demographic features of authors in social media is known as author profiling. Author profiling is helpful for many applications such as forensics, security and marketing. Author profiling helps to identify fake profiles in social media. By analysing their WhatsApp messages in code-mixed Tamil, this paper focuses on identifying the socio-demographic appearance of author traits or features such as gender, age-group, marital and education status. Even though many studies have been conducted on Author Profiling in English and other resources-rich languages, the research on the Indian language is still nascent. This study is the first Author Profiling task for code-mixed Tamil on WhatsApp. As a part of this study, we have created the benchmark WhatsApp dataset in code-mixed Tamil language to develop the author profiling system. We propose a stacked Convolutional Network (CNN) combined with k-max pooling and Bidirectional Long Short Term Memory (BiLSTM) to enhance the classification performance of CNN. Multiple experiments have been conducted to demonstrate the effectiveness of the proposed model, including the comparison against existing models with diverse parameter settings. We have also incorporated Focal loss and context embedding based data augmentation to handle the data imbalance. The proposed model outperforms state-of-the-art deep learning models with a better performance. [ABSTRACT FROM AUTHOR]

The rapid spread of the novel corona virus disease (COVID-19) has disrupted the traditional clinical services all over the world. Hospitals and healthcare centers have taken extreme care to minimize the risk of exposure to the virus by restricting the visitors and relatives of the patients. The dramatic changes happened in the healthcare norms have made it hard for the deaf patients to communicate and receive appropriate care. This paper reports a work on automatic sign language recognition that can mitigate the communication barrier between the deaf patients and the healthcare workers in India. Since hand gestures are the most expressive components of a sign language vocabulary, a novel dataset of dynamic hand gestures for the Indian sign language (ISL) words commonly used for emergency communication by deaf COVID-19 positive patients is proposed. A hybrid model of deep convolutional long short-term memory network has been utilized for the recognition of the proposed hand gestures and achieved an average accuracy of 83.36%. The model performance has been further validated on an alternative ISL dataset as well as a benchmarking hand gesture dataset and obtained average accuracies of 97 % and 99.34 ± 0.66 % , respectively. [ABSTRACT FROM AUTHOR]

Devanagari script is the most widely used script in India and other Asian countries. There is a rich collection of ancient Devanagari manuscripts, which is a wealth of knowledge. To make these manuscripts available to people, efforts are being done to digitize these documents. Optical Character Recognition (OCR) plays an important role in recognizing these documents. Convolutional Neural Network (CNN) is a powerful model that is giving very promising results in the field of character recognition, pattern recognition etc. CNN has never been used for the recognition of the Devanagari ancient manuscripts. Our aim in the proposed work is to use the power of CNN for extracting the wealth of knowledge from Devanagari handwritten ancient manuscripts. In addition, we aim is to experiment with various design options like number of layes, stride size, number of filters, kenel size and different functions in various layers and to select the best of these. In this paper, the authors have proposed to use deep learning model as a feature extractor as well as a classifier for the recognition of 33 classes of basic characters of Devanagari ancient manuscripts. A dataset containing 5484 characters has been used for the experimental work. Various experiments show that the accuracy achieved using CNN as a feature extractor is better than other state-of-the-art techniques. The recognition accuracy of 93.73% has been achieved by using the model proposed in this paper for Devanagari ancient character recognition. [ABSTRACT FROM AUTHOR]

Fresh water is vital for all living creatures and maintains the hydrological cycle. Surface water bodies conserve freshwater and exhibit dynamic changes yearly due to high/low rainfall and over/underutilization. Therefore, extracting water bodies and determining their extent is imperative for effective water resource management. Water body extraction using Water Indices (WI) and Machine Learning (ML) face threshold selection and feature optimization challenges, respectively. This paper proposes a Lightweight Attention-based Multiscale Neural Network (LWAMNNet) for surface water body extraction from Linear Imaging Self Scanning‒III (LISS-III) remote sensing images. The LWAMNNet is an encoder-decoder architecture designed using a modified residual block in both the encoder and decoder to extract high-level features. Feature Extraction Module (FEM) is sandwiched between encoder and decoder to extract global contextual features. The LWAMNNet replaces convolutions with depthwise separable convolutions to reduce computation complexity. In the decoder, the attention module is incorporated to provide attention to fused features (i.e., combined deep features with spatial encoder features) at different scales. The LWAMNNet effectively extracts different-sized water bodies with non-linear boundaries. The proposed LWAMNNet qualitatively and quantitatively outperforms other DL models in performance metrics (accuracy of 99.5%) and computation complexity (in terms of trainable parameters and time). Additionally, the water extent of five major reservoirs in south India was determined annually from 2016 to 2019. Also, the reason for water dynamics is analyzed with the help of rainfall and water availability data provided by the Indian Metrological Department (IMD). [ABSTRACT FROM AUTHOR]

The Earth is frequently changed by natural occurrences and human actions that have threatened our environment to a certain extent. Therefore, accurate and timely monitoring of transformations at the surface of the Earth is crucial for precisely facing their harmful effects and consequences. This paper aims to perform a change detection (CD) analysis and assessment of the Dakshina Kannada region, being one of the coastal districts of Karnataka, India. The spatial and temporal variations in land use and land cover (LULC) are being monitored and examined from the data received as LULC maps from the National Remote Sensing Agency, Indian Space Research Organization, India. The time-series data from advanced wide-field sensor (AWiFS) Resourcesat2 satellite as LULC maps (1:250k) are analyzed using a deep learning approach with an encoder–decoder architecture with dual-attention modules for the change analysis. The model provides an overall accuracy and meanIOU(intersection over union) of 94.11% and 74.1%. The LULC maps from 2005 to 2018 (13 years) are utilized to decide the variations in the LULC, including urban development, agricultural variations, vegetation dynamics, forest areas, barren land, littoral swamp, and water bodies, current fallow, etc. The multiclass area-wise changes in terms of percentage show a decline in most LULC classes, which raises a point of concern for the environmental safety of the considered area, which is highly exposed to coastal flooding due to increased urbanization. [ABSTRACT FROM AUTHOR]

In India, nearly 12 million visually impaired people had difficulty in identifying the currency notes. There is a need to develop an application that can recognize the currency note and provide a vocal message. In this paper, a novel lightweight Convolutional Neural Network (CNN) model is developed for efficient web and mobile applications to recognize the Indian currency notes. A new dataset for Indian currency notes has been created to train, validate, and test the CNN model. This CNN based web and mobile applications will provide a text and audio output based on the recognized currency note. The proposed model is developed using TensorFlow and improved by selection of optimal hyperparameter value, and compared with existing well known CNN architectures using transfer learning. Based on the results it has been observed that proposed model perform well over six widely used existing architectures in terms of training and testing accuracy. [ABSTRACT FROM AUTHOR]

It is very common for human beings to include both text and non-text data in a handwritten document. Text portion contains alphabets, digits, and mathematical symbols, whereas non-text portion includes various graphical entities like flow chart, transition diagram, etc. This paper proposes a novel method for online handwritten text and non-text stroke classification with text written in Devanagari script, the most popular script in India, using two different architectures of artificial Recurrent Neural Network (RNN)—long-short term memory (LSTM) and bidirectional long-short term memory (BLSTM). In the present work, the classifier classifies an ink as text or non-text stroke when a sequence of strokes of any online handwritten document of both text and non-text data is presented to it. Various structural and directional features related to online handwriting have been extracted from the basic strokes of text and non-text data. The system has been trained in both LSTM and BLSTM architecture based classification platforms. Experiment has also been performed using Convolutional Neural Network (CNN) to make a comparative performance analysis with RNN classifier based results. The classification performance of the present work has been evaluated using a self-generated dataset and it outperforms the CNN based results as well as the existing studies available in the literature in this regard. [ABSTRACT FROM AUTHOR]

Agriculture is the primary source of livelihood for about 70% of the rural population in India. The crop variety cultivated in India is very diverse. There are more than 500 crop varieties grown in India. Despite the technological advances, the agricultural practices are still manual and involve less automation than western countries. Most of the diseases affecting a plant will reflect the damage in the leaves. The diseases affecting the plant can thus be identified from the leaf images. This paper presents an automatic plant leaf damage detection and disease identification system. The first stage of the proposed method identifies the type of the disease based on the plant leaf image using DenseNet. The DenseNet model is trained on images categorized according to their nature, i.e., healthy and the type of the disease. This model is then used for testing new leaf images. The proposed DenseNet model produced a classification accuracy of 100%, with fewer images used during the training stage. The second stage identifies the damage in the leaf using deep learning-based semantic segmentation. Each RGB pixel value combination in the image is extracted, and supervised training is performed on the pixel values using the 1D Convolutional Neural Network (CNN). The trained model can detect the damage present in the leaves at a pixel level. Evaluation of the proposed semantic segmentation resulted in an accuracy of 97%. The third stage suggests a remedy for the disease based on the disease type and the damage state. The proposed method detects various defects in different plants in the experimental analysis, namely apple, grape, potato, and strawberry. The proposed model is compared with the existing techniques and obtained better performance in comparison with those methods. [ABSTRACT FROM AUTHOR]

In recent times, neural networks and deep learning have made significant contributions in various research domains. In the present work, we report automatic caption generation of an image using these techniques. Automatic image caption generation is an artificial intelligence problem that receives attention from both computer vision and natural language processing researchers. Most of the caption generation tasks exist in the English language and no work has been reported yet in Assamese to the best of our knowledge. Assamese is an Indo-European language spoken by 14 million speakers in the North-East region of India. This paper reports the image caption generation on the Assamese news domain. A quality image captioning system requires an annotated training corpus. However, there is no such standard dataset available for this resource-constrained language. Therefore, we built a dataset of 13000 images collected from various online local Assamese e-newspapers. We employ two different architectures for generating the news image caption. The first model is based on CNN-LSTM and the second model is based on the attention mechanism. These models are evaluated both qualitatively and quantitatively. Qualitative analysis of the generated captions is carried out in terms of fluency and adequacy scores based on a standard rating scale. The quantitative result is evaluated using the BLEU and CIDEr evaluation metrics. We observe that the attention mechanism-based model outperforms the CNN-LSTM based model for our task. [ABSTRACT FROM AUTHOR]

In recent years, the penetration of solar power at residential and utility levels has progressed exponentially. However, due to its stochastic nature, the prediction of solar global horizontal irradiance (GHI) with higher accuracy is a challenging task; but, vital for grid management: planning, scheduling & balancing. Therefore, this paper proposes an ensemble model using the extended scope of wavelet transform (WT) and bidirectional long short term memory (BiLSTM) deep learning network to forecast 24-h ahead solar GHI. The WT decomposes the input time series data into different finite intrinsic model functions (IMF) to extract the statistical features of input time series. Further, the study reduces the number of IMF series by combining the wavelet decomposed components (D1-D6) series on the basis of comprehensive experimental analysis with an aim to improve the forecasting accuracy. Next, the trained standalone BiLSTM networks are allocated to each IMF sub-series to execute the forecasting. Finally, the forecasted values of each sub-series from BiLSTM networks are reconstructed to deliver the final solar GHI forecast. The study performed monthly solar GHI forecasting for one year dataset using one month moving window mechanism for the location of Ahmedabad, Gujarat, India. For the performance comparison, the naïve predictor as a benchmark model, standalone long short term memory (LSTM), gated recurrent unit (GRU), BiLSTM and two other wavelet-based BiLSTM models are also simulated. From the results, it is observed that the proposed model outperforms other models in terms of root mean square error (RMSE) & mean absolute percentage error (MAPE), coefficient of determination (R2) and forecast skill (FS). The proposed model reduces the monthly average RMSE by range from 26.04–58.89%, 5.17–31.35%, 23.26–56.06% & 21.08–57% in comparison with benchmark, standalone BiLSTM, GRU & LSTM networks respectively. On the other hand, the monthly average MAPE is reduced by range from 9 to 51.18%, 12.59–28.14%, 30.43–59.19% & 26.54–58.92% in comparison to benchmark, standalone BiLSTM, GRU & LSTM respectively. Further, the proposed model obtained the value of R2 equal to 0.94 and forecast skill (%) of 47% with reference to the benchmark model. [ABSTRACT FROM AUTHOR]

Water is a prime necessity for the survival and sustenance of all living beings. Over the past few years, the water quality of rivers is adversely affected due to harmful wastes and pollutants. This ever-increasing water pollution is a big matter of concern as it deteriorating the water quality, making it unfit for any type of use. Recently, water quality modelling using machine learning techniques has generated a lot of interest and can be very beneficial in ecological and water resources management. However, they suffer many times from high computational complexity and high prediction error. The good performance of a deep neural network like long short-term memory network (LSTM) has been exploited for the time-series data. In this paper, a deep learning–based Bi-LSTM model (DLBL-WQA) is introduced to forecast the water quality factors of Yamuna River, India. The existing schemes do not perform missing value imputation and focus only on the learning process without including a loss function pertaining to training error. The proposed model shows a novel scheme which includes missing value imputation in the first phase, the second phase generates the feature maps from the given input data, the third phase includes a Bi-LSTM architecture to improve the learning process, and finally, an optimized loss function is applied to reduce the training error. Thus, the proposed model improves forecasting accuracy. Data comprising monthly samples of different water quality factors were collected for 6 years (2013–2019) at several locations in the Delhi region. Experimental results reveal that predicted values of the model and the actual values were in a close agreement and could reveal a future trend. The performance of our model was compared with various state of the art techniques like SVR, random forest, artificial neural network, LSTM, and CNN-LSTM. To check the accuracy, metrics like root mean square errors (RMSE), the mean absolute error (MAE), mean square error (MSE), and mean absolute percentage error (MAPE) have been used. Experimental analysis is carried out by measuring the COD and BOD levels. COD analysis reveals the MSE, RMSE, MAE, and MAPE values as 0.015, 0.117, 0.115, and 20.32, respectively, for the Palla region. Similarly, BOD analysis indicates the MSE, RMSE, MAE, and MAPE values as 0.107, 0.108, 0.124, and 18.22, respectively. A comparative analysis reveals that the proposed model outperforms all other models in terms of the best forecasting accuracy and lowest error rates. [ABSTRACT FROM AUTHOR]

In recent times, active research is going on for bridging the gap between computer vision and natural language. In this paper, we attempt to address the problem of Hindi video captioning. In a linguistically diverse country like India, it is important to provide a means which can help in understanding the visual entities in native languages. In this work, we employ a hybrid attention mechanism by extending the soft temporal attention mechanism with a semantic attention to make the system able to decide when to focus on visual context vector and semantic input. The visual context vector of the input video is extracted using 3D convolutional neural network (3D CNN) and a Long Short-Term Memory (LSTM) recurrent network with attention module is used for decoding the encoded context vector. We experimented on a dataset built in-house for Hindi video captioning by translating M S R - V T T dataset followed by post-editing. Our system achieves 0.369 CIDEr score and 0.393 METEOR score and outperformed other baseline models including RMN (Reasoning Module Networks)-based model. [ABSTRACT FROM AUTHOR]

COVID-19 disease is a major health calamity in twentieth century, in which the infection is spreading at the global level. Developing countries like Bangladesh, India, and others are still facing a delay in recognizing COVID-19 cases. Hence, there is a need for immediate recognition with perfect identification of infection. This clear visualization helps to save the life of suspected COVID-19 patients. With the help of traditional RT-PCR testing, the combination of medical images and deep learning classifiers delivers more hopeful results with high accuracy in the prediction and recognition of COVID-19 cases. COVID-19 disease is recently researched through sample chest X-ray images, which have already proven its efficiency in lung diseases. To emphasize corona virus testing methods and to control the community spreading, the automatic detection process of COVID-19 is processed through the detailed medication reports from medical images. Although there are numerous challenges in the manual understanding of traces in COVID-19 infection from X-ray, the subtle differences among normal and infected X-rays can be traced by the data patterns of Convolutional Neural Network (CNN). To improve the detection performance of CNN, this paper plans to develop an Ensemble Learning with CNN-based Deep Features (EL-CNN-DF). In the initial phase, image scaling and median filtering perform the pre-processing of the chest X-ray images gathered from the benchmark source. The second phase is lung segmentation, which is the significant step for COVID detection. It is accomplished by the Adaptive Activation Function-based U-Net (AAF-U-Net). Once the lungs are segmented, it is subjected to novel EL-CNN-DF, in which the deep features are extracted from the pooling layer of CNN, and the fully connected layer of CNN are replaced with the three classifiers termed "Support Vector Machine (SVM), Autoencoder, Naive Bayes (NB)". The final detection of COVID-19 is done by these classifiers, in which high ranking strategy is utilized. As a modification, a Self Adaptive-Tunicate Swarm Algorithm (SA-TSA) is adopted as a boosting algorithm to enhance the performance of segmentation and detection. The overall analysis has shown that the precision of the enhanced CNN by using SA-TSA was 1.02%, 4.63%, 3.38%, 1.62%, 1.51% and 1.04% better than SVM, autoencoder, NB, Ensemble, RNN and LSTM respectively. The comparative performance analysis on existing model proves that the proposed algorithm is better than other algorithms in terms of segmentation and classification of COVID-19 detection. [ABSTRACT FROM AUTHOR]

Indian coir industry is one among the small-scale cottage industries which contributes a great amount to the economy of India. India and Sri Lanka are the top two international producers, and they account for 90% of world coir manufacturing. The modern digital technologies can monitor the physical, chemical and microbiological properties in agriculture sector and can analyse the data in a faster manner. This paper highlights the large opportunities of deep learning in agriculture as an intelligent method for classifying and predicting the quality of the raw materials and thereby correlating into suitable products in the agricultural sector. Here we gathered the dataset from Central Coir Research Institute, Alappuzha, tested the chemical properties and applied several decision tree algorithms on the dataset and compared for analysis. This paper focuses specifically on a hybrid method with the usage of the back-propagation in deep learning and fuzzy logic decision tree. Experimental results reveal that the proposed method shows an accuracy of 98.75%. The comparison results with various decision tree-based classification algorithms, such as C4.5, ID3, CART, Naïve Bayes, fuzzy, MLP, verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

India is among the largest cultivators and consumers of wheat grains leading to apparent demand for identifying the quality and varietal distribution of wheat to fulfill the specific requirements of food industries. Moreover, with the variations in prices of distinct varieties in different parts of the country, it becomes a vital need for the customers as well as for the cultivators to identify and classify the grains based upon specific end products, demand, and prices of individual variety. The growth of Machine Learning and Computer Vision in agriculture, facilitate the development of such techniques that can successfully identify the classes based on visual features and representation. In this paper, a model has been developed from scratch for the classification of fifteen different varieties of wheat consists of 15000 images based on their visual traits using Convolutional Neural Network. The model has been produced under a different set of hyper-parameters tuned to develop the best model that can classify the varieties of wheat grains with high accuracy and minimum loss. The performance of the different models are compared in terms of classification accuracy and categorical cross-entropy loss. The model which is found best, successfully classifies the wheat varieties with 94.88% training accuracy and 97.53% test accuracy while on the other side reduces loss to 15% for training and 8% for the test set. Hence, the developed model can be deployed for the classification of different grain varieties, plant diseases, plant varieties, and several other fields under agriculture. [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]

In recent years, the concept of sustainable development has enriched numerous scientific researches. Therefore, the combination of economic growth and the environment has been the subject of numerous econometric and statistical models. They demonstrated that there is a two-way relationship between economic growth and pollution. So, we use data from the World Bank database (1971–2014) to assess the possibility that a change (positive or negative) in pollution in India generates a gross domestic product acceleration. Through a Machine Learning approach via artificial neural network analysis, empirical findings show that a deep neural network can predict the outcome under study. The novelty of this paper is to have determined the results through a model based on a comparison with a highly developed country (Japan). The results obtained show that in a country like India, 76% of the time, a change in pollution evolves into a change in the acceleration of the economic growth. [ABSTRACT FROM AUTHOR]

Prediction of long-term rainfall patterns is a highly challenging task in the hydrological field due to random nature of rainfall events. The contribution of monthly rainfall is important in agriculture and hydrological tasks. This paper proposes two data-driven models, namely biogeography-based extreme learning machine (BBO-ELM) and deep neural network (DNN), to predict one, two, and three month-ahead rainfall over India (All-India and six other homogeneous regions). Three other data-driven models called ELM, genetic algorithm (GA)-based ELM, and particle swarm optimization (PSO)-based ELM are used to compare the performance of the proposed models. Firstly, partial autocorrelation function (PACF) is applied in all datasets to select the optimal number of lags for input to the models. Secondly, the wavelet-based data pre-processing technique is applied in selected optimal lags and feed to the proposed models for achieving higher prediction performance. To investigate the performance of proposed models, a non-parametric statistical test, Anderson–Darling' Normality test, is performed in all India dataset. The wavelet-based proposed hybrid models show better prediction capability compared to optimal lag-based proposed models. This study shows the successful application of time-series data using proposed techniques (optimal lags-based BBO-ELM and wavelet-based DNN) in the hydrological field which may be used for risk mitigation from dreadful natural events. [ABSTRACT FROM AUTHOR]

This paper dispenses an exhaustive review on deep learning techniques used in the prognosis of eight different neuropsychiatric and neurological disorders such as stroke, alzheimer, parkinson's, epilepsy, autism, migraine, cerebral palsy, and multiple sclerosis. These diseases are critical, life-threatening and in most of the cases may lead to other precarious human disorders. Deep learning techniques are emerging soft computing technique which has been lucratively used to unravel different real-life problems such as pattern recognition (Face, Emotion, and Speech), traffic management, drug discovery, disease diagnosis, and network intrusion detection. This study confers the discipline, frameworks, and methodologies used by different deep learning techniques to diagnose different human neurological disorders. Here, one hundred and thirty-six different articles related to neurological and neuropsychiatric disorders diagnosed using different deep learning techniques are studied. The morbidity and mortality rate of major neuropsychiatric and neurological disorders has also been delineated. The performance and publication trend of different deep learning techniques employed in the investigation of these diseases has been examined and analyzed. Different performance metrics like accuracy, specificity, and sensitivity have also been examined. The research implication, challenges and the future directions related to the study have also been highlighted. Eventually, the research breaches are identified and it is witnessed that there is more scope in the diagnosis of migraine, cerebral palsy and stroke using different deep learning models. Likewise, there is a potential opportunity to use and explore the performance of Restricted Boltzmann Machine, Deep Boltzmann Machine and Deep Belief Network for diagnosis of different human neuropsychiatric and neurological disorders. [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]

Accurately predicting agricultural commodity prices is crucial for India's economy. Traditional parametric models struggle with stringent assumptions, while machine learning (ML) approaches, though data-driven, lack automatic feature extraction. Deep learning (DL) models, with advanced feature extraction and predictive abilities, offer a promising solution. However, their application to agricultural price data ignored the exogenous factors. Hence, the study explored advanced versions of the well-known univariate models, NBEATSX and TransformerX. The research employed price data for essential crops like Tomato, Onion, and Potato (TOP) from major Indian markets and complemented it with corresponding weather data (precipitation and temperature). To provide a comprehensive analysis, the study also evaluated traditional statistical methods (ARIMAX and MLR) and a suite of ML algorithms (ANN, SVR, RFR, and XGBoost). The performance of these models was rigorously evaluated using error metrics like RMSE, MAE, sMAPE, MASE and QL. The findings were significant indicating DL models, particularly when augmented with exogenous variables, consistently outshone other methods with NBEATSX and TransformerX showing an average RMSE of 110.33 and 135.33, MAE of 60.08 and 74.92, sMAPE of 22.14 and 24.00, MASE of 1.02 and 1.32 and QL of 30.04 and 34.07, respectively. They exhibited lower error metrics, as compare to the statistical and ML models underscoring their effectiveness and potential in agricultural crop price forecasting. This study not only bridged a crucial research gap but also highlighted the robust potential of DL models in enhancing the accuracy of agricultural commodity price predictions in India. [ABSTRACT FROM AUTHOR]

Food security is a crucial requirement in today's world to meet the dietary needs of individuals. As the population continues to grow, the demand for food will increase by 70 to 100 percent by 2050. Therefore, there is an urgent need to develop an approach that can assist farmers in predicting crop yield accurately and in a timely manner before crop harvesting. In this direction, the present study proposed a nature-inspired optimized hybrid convolutional neural network with bidirectional long short-term memory to extract the nonlinear complex relationships among crop attributes. This hybrid deep learning model was optimized using a particle swarm optimization approach to automate the selection of appropriate hyperparameters for wheat yield prediction. The proposed model was developed to estimate wheat yield in a major wheat-producing state in India from 2000 to 2018 using the temporal and spatial characteristics of wheat crops. The experiment was conducted by integrating the historical yield, meteorological data, remote sensing-derived indices, and soil parameters from the October to April season. Furthermore, we also evaluated the performance of the proposed model in terms of the mean absolute error (MAE), root mean square error (RMSE), and mean squared error (MSE) with publicly available datasets such as Agro_data, Soybean_data, and FAO_data. The experimental results showed that the proposed PSO-CNN-Bi-LSTM method achieved an MAE of 0.39, MSE of 0.18, and RMSE of 0.42 (tonnes/ha) and outperformed existing CNN, LSTM, CNN-LSTM, CNN-Bi-LSTM, CNN-LSTM-PSO, CNN-Bi-LSTM-BO-GO, and neural network methods. Our findings demonstrated that the proposed methodology could be a promising alternative for predicting crop yield. [ABSTRACT FROM AUTHOR]

Industrial developments and consumption of massive amount of fossil fuels, vehicle pollution, and other calamities upsurges the AQI (Air Quality Index) of major cities in a drastic manner. Owing to these factors, it is important to take proactive measures for reducing the air pollution in order to avoid life- threatening consequence. Therefore, prediction of air quality is significant for improving the health of living beings as highly polluted regions have a higher concentration of pollutants mixed in the air, affecting the respiratory system and reducing the lifetime. To control pollution, AQI is used as a measure for estimating the pollutant content in the air. Even though many existing techniques have predicted AQI, enhancement is required in prediction algorithms with minimized loss. To address the challenges in traditional algorithms, the proposed smart cities-based AQI prediction intends to utilize the proposed regression algorithm in the dataset, namely Air- Quality-Data, which collected harmful pollutants on an hourly and daily basis from multiple cities in India between 2015 to 2020. To achieve prediction efficiency with reduced loss, pre-processing of input data is being performed using Deep GAN (Generative Adversarial Network). It performs the imputation of data in place of missing values to improve accurate prediction. Additionally, feature scaling normalizes independent real-data features to a fixed scale. With the processed data, regression is done through modified Stacked Attention GRU with KL divergence, which predicts Ernakulam, Chennai and Ahmedabad cities with higher, medium, and low levels of AQI in India. The performance of the proposed regression algorithm is measured using metrics such as MAE (Mean Absolute Error), MSE (Mean Square Error), R2 (Coefficient of determination), MAPE (Mean Absolute Percentage Error), and RMSE (Root Mean Square Error) and better MAE, MSE, R2, MAPE and RMSE obtained by the model is 0.1013, 0.0134, 0.9479, 0.1152 and 0.1156. Internal assessment and comparative analysis performed with existing regression algorithms exhibit lower loss values obtained from the present research, which determines the efficacy of the proposed model. [ABSTRACT FROM AUTHOR]

Infectious diseases are highly contagious due to rapid transmission and very challenging to diagnose in the early stage. Artificial Intelligence and Machine Learning now become a strategic weapon in assisting infectious disease prevention, rapid-response in diagnosis, surveillance, and management. In this paper, a bifold COVID_SCREENET architecture is introduced for providing COVID-19 screening solutions using Chest Radiography (CR) images. Transfer learning using nine pre-trained ImageNet models to extract the features of Normal, Pneumonia, and COVID-19 images is adapted in the first fold and classified using baseline Convolutional Neural Network (CNN). A Modified Stacked Ensemble Learning (MSEL) is proposed in the second fold by stacking the top five pre-trained models, and then the predictions resulted. Experimentation is carried out in two folds: In first fold, open-source samples are considered and in second fold 2216 real-time samples collected from Tamilnadu Government Hospitals, India, and the screening results for COVID data is 100% accurate in both the cases. The proposed approach is also validated and blind reviewed with the help of two radiologists at Thanjavur Medical College & Hospitals by collecting 2216 chest X-ray images between the month of April and May. Based on the reports, the measures are calculated for COVID_SCREENET and it showed 100% accuracy in performing multi-class classification. [ABSTRACT FROM AUTHOR]

Every nation treasures its handloom heritage, and in India, the handloom industry safeguards cultural traditions, sustains millions of artisans, and preserves ancient weaving techniques. To protect this legacy, a critical need arises to distinguish genuine handloom products, exemplified by the renowned "gamucha" from India's northeast, from counterfeit powerloom imitations. Our study's objective is to create an AI tool for effortless detection of authentic handloom items amidst a sea of fakes. Six deep learning architectures—VGG16, VGG19, ResNet50, InceptionV3, InceptionResNetV2, and DenseNet201—were trained on annotated image repositories of handloom and powerloom towels (17,484 images in total, with 14,020 for training and 3464 for validation). A novel deep learning model was also proposed. Despite respectable training accuracies, the pre-trained models exhibited lower performance on the validation dataset compared to our novel model. The proposed model outperformed pre-trained models, demonstrating superior validation accuracy, lower validation loss, computational efficiency, and adaptability to the specific classification problem. Notably, the existing models showed challenges in generalizing to unseen data and raised concerns about practical deployment due to computational expenses. This study pioneers a computer-assisted approach for automated differentiation between authentic handwoven "gamucha"s and counterfeit powerloom imitations—a groundbreaking recognition method. The methodology presented not only holds scalability potential and opportunities for accuracy improvement but also suggests broader applications across diverse fabric products. [ABSTRACT FROM AUTHOR]

Ensemble forecasts from multiple models have gained enormous popularity as it provides a more efficient forecast as compared to the individual counterpart. The linear weighted combination method is most widely utilized for its simplicity and efficiency. Despite hard efforts by various researchers, two considerable challenges still exist: (1) Systematic and robust techniques for selecting suitable forecasting models and (2) Techniques to find appropriate combination weights. To address these challenges a novel framework for optimization-based ensemble technique, 'OptiSembleForecasting' has been proposed in this study. The three components of the proposed framework are (a) Principal Component Analysis-based error index, (b) Model Confidence Set algorithm and (c) Optimization techniques. A total of thirteen forecasting models consisting of five deep learning, five machine learning and three stochastic models and twenty optimization techniques have been implemented in the proposed framework. To examine the effectiveness of the proposed technique, wholesale price of three commodities (TOP: Tomato, Onion, and Potato) each with two major markets in India has been considered. The empirical evaluation of the predictive accuracy of different models with that of the proposed techniques has been carried out by means of root mean square error and mean absolute percentage error. The findings of this study demonstrated the superiority of the proposed algorithm. Moreover, a R-package, namely 'OptiSembleForecasting', has been developed to make the implementation of this technique simple and user-friendly. [ABSTRACT FROM AUTHOR]

Advance prediction of crop yield is very critical in the context of ensuring food security as the region specific challenges in social and environmental conditions often infringe plan of policy makers. This study presents a generic methodology to configure and fine tune the state-of-the-art Long Short-Term Memory (LSTM) based Deep Learning (DL) model through hyperparameter optimization for prediction of yield (annual crop production) in Wheat, Groundnut and Barely over India based on multiple independent input variables identified using multicollinearity test. The Monte Carlo cross-validation method is used to validate the optimized LSTM models. Results from the LSTM model tuning showed that among the 4 optimizers tested, Adam was found to perform better irrespective of the crop and Bi-LSTM outperformed sLSTM in terms of prediction accuracy. The percentage reduction in error with Bi-LSTM compared to sLSTM in predicting wheat and groundnut crop yield was 39% and 13% respectively while in case of barley crop, error reduction was marginal (0.34%). The performance of optimized Bi-LSTM model is compared with the performance of traditional machine learning (ML) models such as support vector regression (SVR) and SVR polynomial {2nd and 3rd order}, Auto Regressive Integrated Moving Average (ARIMA) and ARIMAX (ARIMA with exogenous variables) and Vector Auto-regression (VAR). The Bi-LSTM model is found to be superior to ML models; the percentage reduction in mean absolute scaled error with the Bi-LSTM compared to the best performing ML model was 94%, 72%, and 71% in predicting wheat, groundnut and barley yield respectively. This study showed that by choosing proper explanatory (independent) variable and hyperparameter optimization, a simple (single layer) structure of deep neural network (LSTM) outperformed traditional ML models in terms of accuracy for crop yield prediction application. [ABSTRACT FROM AUTHOR]

Residents and visitors throughout the globe respect sophisticated route-guiding systems. Due to India's complicated city design and transportation infrastructure, an efficient and intelligent RG is required. Path planning is a crucial issue with route guiding systems for the road network. Because the time spent due to an accident occurring at an intersection or on the route is more relevant than the actual situation for path planning, it is helpful to investigate the path planning issue and incorporate accident characteristics. To address this problem, in this research, we developed a system that gives better routes by considering accident information. In our suggested framework, we addressed the future design and requirements of the prediction and route planning models for smart cities. We deployed an intelligent camera coupled with a machine learning module to forecast an accident at any junction or on the road. We update our database regularly after receiving accident information and use the route planning algorithm to get the different pathways with distance and accident information. These pathways enable the user to choose the best course for them. It is a dynamic and continuous 24x7 task. Thus, we have deployed VGG16, VGG19, and RESNET DL Architecture to detect the accident images with accuracies of 99.72%, 98.78%, and 82.06%, respectively. In the 2-class dataset, we have taken-accident and non-accident pictures from Kaggle. The number of training images was 900 and 200 for testing in both classes. Based on the Accident detection, the Dijkstra Algorithm was continuously up-to-date to get the path. It has been discovered that enhancing the intelligent RG system with deep learning can significantly improve prediction accuracy. Even though the experiment has some flaws, it offers practical guidance for the subsequent stages of the evolution of the transportation system. [ABSTRACT FROM AUTHOR]

Fine particulate matter (PM2.5) concentration in ambient air has become a major concern across the globe. All major cities of India have reported an elevated concentration of PM2.5 that has severe consequences to the health, economy, and ecosystem of the region. As a result, it becomes imperative to develop adequate tools for forecasting particulate matter concentration. Most of the research works mostly focused on single-step prediction horizon, thereby limiting their use. In the present work, a hybrid model has been proposed to forecast multi-step ahead concentrations of PM2.5 in ambient air across India covering different agroclimatic zones. The hybrid model architecture was an encoder-decoder-based sequence to sequence model framework that was built with convolutional long short-term memory (LSTM), bidirectional LSTM and 3D convolution neural network. The model was tested across 26 Indian cities covering 13 major agroclimatic zones of India. The performance of the model was also analysed for consecutive hour sequential prediction taking last 24-h data as input to the model. The model output was also compared with signal to noise ratio to explore the reason for variations in model performance. A distinct trend was found between signal to noise ratio and model output. As noise increases, the model performances suffer. Overall, the model was found to be stable as its performance errors across different time horizon has little variations. The proposed model has the potential to be used for long-term forecasting by incorporating other predictor variables series. [ABSTRACT FROM AUTHOR]

The growing concerns surrounding water supply, driven by factors such as population growth and industrialization, have highlighted the need for accurate estimation of streamflow at the river basin level. To achieve this, rainfall-runoff models are widely employed as valuable tools in watershed management. For this specific study, two modelling approaches were employed: the Soil and Water Assessment Tool (SWAT) model and a set of eight artificial intelligence (AI) models. The AI models consisted of seven data-driven approaches, namely k-nearest neighbour regression, support vector regression, linear regression, artificial neural networks, random forest regression, XGBoost, and Histogram-based Gradient Boost regression. Additionally, a deep learning model known as Long Short-Term Memory (LSTM) was also utilized. The study focused on monthly streamflow modelling in the Murredu River basin, with a calibration period from 1999 to 2003 and a validation period from 2004 to 2005, spanning a total of 7 years from 1999 to 2005. The results indicated that all nine models were generally suitable for simulating the rainfall-runoff process, with the LSTM model demonstrating exceptional performance in both the calibration (R2 is 0.97 and NSE is 0.96) and validation (R2 is 0.97 and NSE is 0.92) periods. Its high coefficient of determination (R2) and Nash–Sutcliffe efficiency (NSE) values indicated its superior ability to accurately model the rainfall-runoff relationship. While the other models also produced satisfactory results, the findings suggest that selecting the most efficient model, such as the LSTM model, could significantly contribute to the effective management and planning of sustainable water resources in the Murredu watershed. [ABSTRACT FROM AUTHOR]

Designing an automatic vehicle detection (AVD) system from still images or videos would be a useful tool to cater to the requirements of the traffic management system. Over the past few years, numerous databases have been developed for the use of researchers in this field of AVD. However, most of them are not acceptable in the Indian scenarios due to certain practical constraints like the road infrastructure, nature of congestion, and vehicle types commonly found in India. The aim of this research is to develop a still image database, named as JUVDsi v1, which includes nine different types of vehicle classes collected through mobile phone cameras in various ways for designing an automated traffic management system. Identifying and analyzing the shortcomings of existing databases, the developed database presents an improvement to address such bottle-necks. Furthermore, the efficiency of this database is evaluated using an ensemble of three state-of-the-art deep learning architectures. At first, each vehicle in the scene images is localized and categorized. Five base object detection models, namely, YOLOv3, Faster-RCNN, RFCN, SSDv1 and SSDLitev2 are used. Finally, the Weighted Boxes Fusion technique is used as the ensemble method (ensemble of best three out of the five base learners), thereby enhancing the performance obtained by the individual object detection models. The database can be found at: https://github.com/JUVDsi/JUVD-Still-Image-database.git. [ABSTRACT FROM AUTHOR]