Search

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]

According to researches, there are around 188 million unemployed people around the globe. We may find many job vacancies on job portals and across the internet to help the job seekers. India alone has more than a hundred job portals. One major issue people face here is that the job seekers are not sure if the employer is real or fake. Most of these portals do not have a system that could check if the employer, posting a job is real or fake. Scammers are making use of this opportunity to post fake job offers which might look genuine to the job seekers applying for it. This way the poor job seekers might lose a large amount of money and time. A best possible solution for this problem would be that the job portal itself being able to identify if the job being posted is real or fake. This paper suggests using a machine learning model to achieve this goal. The idea here is to use natural language processing to understand and analyze the job posting and then making use of a machine learning model to predict if the job posting is real or fake. The first step is to import a dataset which has real life real and fake job posting. In this project, Employment Scam Aegean Dataset provided by University of Aegean Laboratory of Information and Communication system Security is being used. This dataset contains 18000 samples containing real life job postings. Various text cleaning techniques like lemmatization, stop words removal and special characters and punctuation removal is done on the data. Once the text data is processed, various algorithms like Random Forest, Linear SVC, Gradient Boosting Classifier, Gaussian naïve Bayes classifier and XGB classifier is used to test the performance of the model. The best two algorithms with respect to the percentage of accuracy with which the models could classify real and fake job posting was taken into consideration. Random Forest and Linear SVC could give accuracy close to 98%. Both of these algorithms were tuned using GridSearchCV, a library function which is a part of sklearn's model selection package. After tuning, the performance of both these algorithms increased and Linear SVC gave a better accuracy score of 99%. Hence Linear SVC is being used in this project for predicting real and fake job posting on a job portal.. [ABSTRACT FROM AUTHOR]

Agricultural product costs play a significant part in the horticultural market. In India, vegetables, for example, tomatoes have the biggest supply and price variances among farming items. As tomatoes are grown around the year, outdoor and indoor, their yields change because of various factors, it is hard to settle tomatoes' inventory and costs. Although the Government puts numerous efforts to balance out the supply and costs of vegetables, continuous meteorological changes have prompted unstable supply and price fluctuations of vegetables. Accordingly, the right anticipating of vegetable costs is a significant issue. To oblige these, in this paper, an attempt has been made to dissect the costs and yield of tomatoes in India by utilizing a Machine Learning approach. This will unquestionably help the farmers and the Government if the anticipated costs are getting higher in the forthcoming months, then appropriate strategies can be made to diminish the costs of tomatoes. [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]

The emergent technology has been increasingly incorporated with the tourism industry. In the digital world, social media plays an important role in identifying the most visited tourist places. More than 80% of people commonly used the social media platform called 'Twitter'. By using tweet reviews, tourists around the world know about the feelings, suggestions and opinions of most visited tourist places in the selected region. This paper recommends an approach for the development of trip planning in South India based on tourist's preferences. For the research, we use Twitter Application Programming Interface to collect information about the most visited tourist places in South India by using tweets reviews and store it as South India Tourism Tweet reviews database. This paper mainly focuses on analyzing Twitter reviews, which are very helpful to locate the most visited tourist place. In the tweets where reviews are mostly unstructured and heterogeneous, which are then classified into positive tweets, negative tweets and neutral tweets by using the preprocessing technique and machine learning algorithm called support vector machine. Performance measures are calculated by using the classification results. Finally, the results are plotted by using the classification results and performance measures as a wordcloud. This can be very useful for tourists to select the most visited tourist locations. The proposed system can satisfy individual tourist needs. [ABSTRACT FROM AUTHOR]

Introduction: Accurate estimation of dementia prevalence is essential for making effective public and social care policy to support individuals and families suffering from the disease. The purpose of this paper is to estimate the prevalence of dementia in India using a semi-supervised machine learning approach based on a large nationally representative sample. Methods: The sample of this study is adults 60 years or older in the wave 1 (2017–2019) of the Longitudinal Aging Study in India (LASI). A subsample in LASI received extensive cognitive assessment and clinical consensus ratings and therefore has diagnoses of dementia. A semi-supervised machine learning model was developed to predict the status of dementia for LASI participants without diagnoses. After obtaining the predictions, sampling weights and age standardization to the World Health Organization (WHO) standard population were applied to generate the estimate for prevalence of dementia in India. Results: The prevalence of dementia for those aged 60 years and older in India was 8.44% (95% CI: 7.89%–9.01%). The age-standardized prevalence was estimated to be 8.94% (95% CI: 8.36%–9.55%). The prevalence of dementia was greater for those who were older, were females, received no education, and lived in rural areas. Discussion: The prevalence of dementia in India may be higher than prior estimates derived from local studies. These prevalence estimates provide the information necessary for making long-term planning of public and social care policy. The semi-supervised machine learning approach adopted in this paper may also be useful for other large population aging studies that have a similar data structure. [ABSTRACT FROM AUTHOR]

Natural disasters such as earthquakes endanger human lives and infrastructure, particularly in urban areas. With the advancements in science and technology in understanding natural hazards, recent studies have attempted to mitigate them by mapping the risks using geospatial technology. In this paper, we attempt to integrate the multi-criteria decision-making (MCDM) models, namely the Analytical Hierarchy Process (AHP) and the Criteria Importance Through Inter-criteria Correlation (CRITIC), besides using the artificial neural network (ANN) to assess the seismic risk in the eastern coast of India. The AHP-CRITIC technique is used to evaluate the earthquake coping capacity and vulnerability and has been further used to generate a training base for earthquake probability mapping by ANN. The earthquake probability and spatial intensity information are used to develop the hazard map. Following that, integrating vulnerability, hazard and coping capacity spatial information assessed earthquake risk. Our results indicate that approximately 5% of the study area is at high risk, whilst more than 11% of the population is at high risk due to seismic induced hazards. The area under the curve of the receiver operating characteristic curve is 0.85, which indicates reliable results. The results of this study may help various agencies involved in planning, development and disaster mitigation to develop seismic hazard mitigation methods by better understanding their impacts on the eastern coastal region of India., (© 2024. The Author(s), under exclusive licence to Springer Nature Switzerland AG.)

The automobile industry has been growing at a high rate in the past few decades, contributing about 7.5% to India's total Gross Domestic Product (GDP). As the number of vehicle owners are increasing the demand and need for automobile service is also high, but people are busy with their routines, hence failing to perform proper maintenance on their vehicles. This paper uses machine learning algorithms and object detection to come up with the idea to develop a web application that suggests users some offers and timing for their car maintenance by analyzing a car using computer vision without the owner's involvement. This project aims at both the owner's convenience and the growth of the service provider's business. Generally, we do not realize that multiple tasks can be done at a time, which results in incomplete tasks. This paper presents a machine learning-based automated car maintenance system with effective time utilization, by using the Internet of Things (IoT) device that could be installed at the parking's main gate in places where people tend to spend many hours, like offices or malls. This device consists of a camera that is responsible for detecting a car image from the live video. These images are then sent to the device, which uses pre-trained models to detect any damages or dirtiness in the vehicle. [ABSTRACT FROM AUTHOR]

Since the first fully homomorphic encryption scheme was published in 2009, many papers have been published on fully homomorphic encryption and its applications. Machine learning is one of the most interesting applications and has drawn a lot of attention from researchers. To better represent and understand the field of Homomorphic Encryption in Machine Learning (HEML), this paper utilizes automated citation and topic analysis to characterize the HEML research literature over the years and provide the bibliometrics assessments for this burgeoning field. This is conducted by using a bibliometric statistical analysis approach. We make use of web-based literature databases and automated tools to present the development of HEML. This allows us to target several popular topics for in-depth discussion. To achieve these goals, we have chosen the well-established Scopus literature database and analyzed them through keyword counts and Scopus relevance searches. The results show a relative increase in the number of papers published each year that involve both homomorphic cryptography and machine learning. Using text mining of articles titles, we have found that cloud computing is a popular topic in this field, which also includes neural networks, big data, and the Internet of Things. The analysis results show that China, the US, and India have generated almost half of all the research contributions in HEML. The citation statistics, keyword statistics, and topic analyses give us a quick overview of the development of the field, which can be of great help to new researchers. It is also possible to apply our methodology to other research areas, and we see great value in this approach. [ABSTRACT FROM AUTHOR]

Precise food price forecasting is crucial for any country, and searching for appropriate approach(s) from an assortment of available strategies toward this objective is an open problem. The current Indian Wholesale Price Index (WPI) series contains sixty individual food items in the 'manufacture of food product' category. This work considered the monthly data from April 2011 to June 2022, i.e., one hundred thirty-five months' data of these sixty WPIs. The researchers extracted the linearity, curvature, and autocorrelation features for each WPI. The curvature and linearity-based grouping of these WPIs revealed that the WPIs are heterogeneous. This work proposed an extreme learning machine (ELM) approach for forecasting these WPIs. The present work employed the following twenty-two time-series forecasting techniques: six standard methods (Auto ARIMA, TSLM, SES, DES, TES, and Auto ETS), five neural networks (Auto FFNN, Auto GRNN, Auto MLP, Auto ELM, and proposed ELM), and eleven state-of-art techniques (two ARIMA-ETS based ensembles, an ARIMA-THETAF-TBATS based ensemble, one MLP, and seven LSTM-based models) to identify the best forecasting approach for these WPIs. For the majority of WPIs, the offered ELM attained suitable performance in the case of fifteen months of out-of-sample forecasting. Nearly eighty-seven percent of cases achieved high accuracy (MAPE = ten) and outshined others. Upon accuracy comparison, both forecast-MAPE and forecast-RMSE, between the proposed ELM and others, this paper observed that the proposed ELM's performance is more favorable. This paper's findings imply that the proposed ELM is a promising prospect to offer accurate forecasts of these sixty WPIs. [ABSTRACT FROM AUTHOR]

Artificial Intelligence is quickly emerging as a technological solution for the agriculture industry to surmount its classical challenges. Artificial Intelligence is facilitating farmers to refine their products and alleviate unfavourable impacts due to the environment. The central concern of this paper is predictive analytics to develop a machine learning model to identify and predict crop yield based on multiple environmental factors. In this paper, a hybrid learner 'RaNN' is proposed that combines the feature sampling and majority voting technique of Random Forest in-combination with the multilayer Feedforward Neural Network to predict the crop yield. Research has also ascertained the essential features responsible for accurate yield prediction. The proposed model works for rice yield prediction, one of the chief grains of India. The region chosen for the work is Punjab, which is among the largest producer states of India for rice. The dataset consists of 15 attributes comprising the weather and agriculture data collected from the Indian Meteorological Department Pune, and Punjab Environment Information System (ENVIS) Center, Government of India. The study has also made a comparative assessment of 'RaNN' with machine learning methods like Multiple Linear Regression, Random Forest, Decision Tree, Boosting Regression, Support Vector Machine Regression, Ensemble Learner, and Artificial Neural Network. Our model RaNN has listed a better prediction accuracy with minimal error among the other techniques providing a 98% correlation between the actual and the predicted yield. Abbreviations: AI – Artificial Intelligence; ANN – Artificial Neural Network; BR – Boosting Regression; Chem Fert – chemical fertilisers; DT – Decision Tree; EL – Ensemble Learner; ENVIS – Punjab Environment Information System; GBM – Stochastic Gradient Boosting Method; GPS – Global Positioning System; HMAX – highest maximum temperature in degrees C; IMD – Indian Meteorological Department; L1 – Lasso regression; L2 – Ridge regression; LMIN – lowest minimum temperature; ML – Machine Learning; MAE – Mean Absolute Error; MEVP – mean evaporation in mm; MLR – Multiple Linear Regression; MMAX – mean maximum temperature in degrees C; MMIN – mean minimum temperature in degrees C; MSSH – Mean sunshine duration in hours; MWS – mean wind speed in km/h; P1 – number of days with precipitation (0.1–0.2 mm); P2 – number of days with precipitation (greater than or equal to 0.3 mm); RaNN – Hybrid RF-ANN model; RMSE – Root Mean Squared Error; $${R^2}$$ R 2 – Coefficient of determination; RD – number of rainy days; RF – Random Forest; SVM Reg – Support Vector Machine Regression; TMRF – total rainfall per month in mm [ABSTRACT FROM AUTHOR]

India is developing at a fast speed as is the utilization of innovation in the developing areas of the country. A significant mass of the populace is as yet reliant and rehearsing horticulture as its essential type of revenue. India has been in a persistent tryst with its cultivating infra, rehearses and related networks since freedom. Price Prediction, these days, has turned into a vital agrarian issue which is to be addressed just in light of the accessible information. The point of this paper is to anticipate the yield cost for the following revolution. This work depends on observing appropriate information models that aides in accomplishing high exactness and over-simplification for price prediction, Yield prediction and fertilizer recommendation. For taking care of this issue, different Machine learning strategies were assessed on various information sets. This work presents a framework which involves information examination strategies to foresee the cost of the yield. The proposed framework will apply AI calculations and foresee the cost of the harvest in view of different factors like Area collected, Area planted and so on. This furnishes a rancher with knowledge of what the future cost of the yield that he will gather. Along these lines, the paper fosters a framework by incorporating information from different sources, information investigation, expectation examination which can assist with foreseeing the objective cost of the yield and increment the benefit edges of rancher helping them over a more drawn-out run. The total examination comes up to a resolution that XGBoost and Gradient boosting algorithm is the reasonable strategy for our task. [ABSTRACT FROM AUTHOR]

The COVID-19 has affected and threatened the world health system very critically throughout the globe. In order to take preventive actions by the agencies in dealing with such a pandemic situation, it becomes very necessary to develop a system to analyze the impact of environmental parameters on the spread of this virus. Machine learning algorithms and artificial Intelligence may play an important role in the detection and analysis of the spread of COVID-19. This paper proposed a twinned gradient boosting machine (GBM) to analyze the impact of environmental parameters on the spread, recovery, and mortality rate of this virus in India. The proposed paper exploited the four weather parameters (temperature, humidity, atmospheric pressure, and wind speed) and two air pollution parameters (PM2.5 and PM10) as input to predict the infection, recovery, and mortality rate of its spread. The algorithm of the GBM model has been optimized in its four distributions for best performance by tuning its parameters. The performance of the GBM is reported as excellent (where R2 = 0.99) in training for the combined dataset comprises all three outcomes i.e. infection, recovery and mortality rates. The proposed approach achieved the best prediction results for the state, which is worst affected and highest variation in the atmospheric factors and air pollution level. [ABSTRACT FROM AUTHOR]

The government of India is the final authority for country-wide policy making and policy implementation in the country. Recent times have witnessed increasing use of data-driven approaches in policy and decision making. This is true for public policy formulation as well. This paper is an effort to highlight how data science and artificial intelligence have the potential to revolutionize the field of public policy in India. The paper discusses some such applications and lists down the likely challenges. An extensive review of the research activities in this field has been undertaken. Cases of data science and artificial intelligence reviewed in this paper span over various sectors of public policy such as- policy making process, health, education, environment, agriculture, economy, and security. This paper, thus, aims to facilitate collaboration in the fields of public policy and data technology, in order to enable higher levels of public service in India. [ABSTRACT FROM AUTHOR]

Pregnancy and fetus development is an incredibly intricate biological process that can go wrong when the health of fetus or the mother gets worse. Currently, India has the highest number of stillbirths, with an estimated 5,92,100 deaths per year, and a WHO estimated rate of 22 per 1000 total births. Cardiotocography is one procedure used to check whether the fetus is growing as expected. This diagnostic procedure measures the mother's uterine contractions and the fetus' heartbeat, usually in the third trimester of pregnancy when the fetus heart is fully developed. This paper aims to classify the results into one of three states (physiological, suspicious or abnormal) based on cardiotocographic data using machine learning algorithms and compare the accuracies of different ML classification models such as logistic regression, k-nearest neighbor, decision tree, random forest classifier and support vector machine. [ABSTRACT FROM AUTHOR]

The state of India was situated on fertile land and river deltas with appropriate agricultural land. In 2019, agricultural fields, primarily cropland, occupy more than 40% of the country's total surface area. Moreover, agricultural industry revenues less than 3% of the country's Gross Provincial Product (GPP). While manufacturing has become the country's major financial activity, accounting countries represent half of GPP's revenues. The objective of the study is to find a way to improve the financial profitability and efficiency of farming supply chain networks as follows: (1) Fixation of national-level targets for zonal-level groups information after assessment and forecasts that affect production and distribution of agriculture. (2) Producers risk can be reduced by directing people to multiple factory and industrialization options based on market assessment. (3) Insurance costs and reduction of bank borrowing by standardizing the connection between bankers and producers using the structure to centralise land information. (4), Stabilize the agricultural sector by looking at nearby potential destinations for production and regulation of the Public Distribution System (PDS) flow for the security stock. In this paper, the novel ML target prediction algorithm to inform the farmers about the market target product and improve the relationships between the farmer and bankers for centralizing the information about recent government plans. The crop prediction ML algorithm proposed to improve the revenue of agriculture field. [ABSTRACT FROM AUTHOR]

The future of agriculture may be fully realized using knowledge of artificial intelligence (AI) accumulated by human expertise. With increasing climate change and population pressure challenges, new technologies, such as AI and RS in vital sectors like agriculture is urgently required to assess agricultural suitability, optimize productivity, and then support sustainable development. This paper presents bibliometric and review analyses on AI and geospatial analysis applied to the agricultural field. Based on the prestigious database, Scopus, thousands of documents were retrieved in the period 1992–2021 and processed using Scopus online tool and VOSviewer software. The results show a growing trend in the number of publications during this period. Earth and Planetary Sciences is the top domain, remote sensing (RS) is the leading source, while the United States and India are the most influential countries. RS, machine learning (ML), GIS, land-use, decision-making, decision trees, and satellite imagery are the most occurring topics in this search. Otherwise, research in this field is turning toward ML and deep learning techniques, whereas agricultural robots and antennas are the top trending tools. The current study provides specific information about the connections between artificial intelligence, geospatial analysis, and agriculture in the period 1992–2021, the fruitful period where the AI coupled to geospatial technologies is in full development. [ABSTRACT FROM AUTHOR]

A significant majority of the population in India makes their living through agriculture. Different illnesses that develop due to changing weather patterns and are caused by pathogenic organisms impact the yields of diverse plant species. The present article analyzed some of the existing techniques in terms of data sources, pre-processing techniques, feature extraction techniques, data augmentation techniques, models utilized for detecting and classifying diseases that affect the plant, how the quality of images was enhanced, how overfitting of the model was reduced, and accuracy. The research papers for this study were selected using various keywords from peer-reviewed publications from various databases published between 2010 and 2022. A total of 182 papers were identified and reviewed for their direct relevance to plant disease detection and classification, of which 75 papers were selected for this review after exclusion based on the title, abstract, conclusion, and full text. Researchers will find this work to be a useful resource in recognizing the potential of various existing techniques through data-driven approaches while identifying plant diseases by enhancing system performance and accuracy. [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 rampant adoption of digital technologies made momentous changes in all economic sectors. The agriculture sector cannot abstain from the digital revolution. Agriculture and farming are one of the oldest and most important professions in India. The sector remains the backbone of the Indian rural economy, which desperately demands technological impetus for the socio-economic development of rural areas. Smart agriculture is a revolution in the agriculture industry which helps to guide the actions that are required to modify and reorient the agricultural systems. The paper made an extensive survey of various technologies proposed for the agriculture sector. We have surveyed various smart agricultural applications developed and proposed a taxonomy for classifying them. Network infrastructure and connectivity remains the major challenge for rural areas. The paper explores the viability of deploying IoT-based technologies in agricultural sectors along machine learning techniques to optimize resource utilization, planning and cultivation, marketing, pesticide selection, price prediction, etc. An in-depth coverage of recent research works is also mentioned which will help the future researchers to address specific challenge and adopt suitable technology to help the farmers to improve their productivity and better decision making in cultivation. Apart from listing the applications, we also propose an architecture for smart agriculture and implemented smart price prediction model for crops like cotton and cardamom along with a prototype for smart irrigation. [ABSTRACT FROM AUTHOR]

Legal predictive models are of enormous interest and value to legal community. The stakeholders, particularly, the judges and attorneys, can take the best advantages of these models to predict the case outcomes to further augment their future course of actions, for example speeding up decision making, support arguments, strengthening the defense, etc. However, accurately predicting the legal decisions and case outcomes is an arduous process, which involves several complex steps—finding suitable bulk case documents, data extracting, cleansing and engineering, etc. Additionally, the legal complexity further adds to its intricacies. In this paper, we introduce our newly developed Machine Learning (ML)-enabled legal prediction model and its operational prototype, eLegPredict , which successfully predicts the Indian supreme court decisions. The eLegPredict is trained and tested over 3072 supreme court cases and has achieved 76% accuracy (F1-score). The eLegPredict is equipped with a mechanism to aid end users, where as soon as a document with new case description is dropped into a designated directory, the system quickly reads through its content and generates prediction. To our understanding, eLegPredict is one of the first few legal prediction models trying to predict Indian supreme court decisions. [ABSTRACT FROM AUTHOR]

Globally, the rapid loss of mangrove forests often creates long-lasting environmental damage alongside coastlines, mudflats, and river banks. All-weather, physical monitoring of such areas is almost impossible because of inaccessibility to swampy areas and a hostile substrate. Subsequently, conventional field surveys are relatively unavailable to monitor human encroachment in coastal areas like the Mumbai mangrove region of India. In this context, the polarimetric synthetic aperture radar (PolSAR) remote sensing tool becomes a potential candidate for mangrove conservation and management. Since the Mumbai mangrove region of India exists over the extensive land cover, the large-scale classification can articulate the continuous encroachment because of the location of human settlements or activities across this metropolitan coastal city. For this, the traditional algorithms need the essential improvisation to apply for large-scale data analysis, aiming simultaneously at getting the highest decisive and time efficiency. Here, we introduce a shallow learning model of MapReduce-based Multi-Layer Perception (MLP) algorithm to classify the hybrid compact polarimetric (CP) and fully polarimetric (FP) feature space. Even though a shallow learning model of the automated method is easily scalable, it requires a distinctive shallow learnable feature set for better land cover classification. In this effort, this paper investigates the efficacy of derived feature space compared to direct polarimetric measurements of sensors and shows that the shallow learnable feature set is more effective with both CP & FP observations. Simultaneously, the relevancy of the proposed distributed model of MLP is also justified compared to distributed extreme learning machine (DELM) algorithm and provides a practically implementable scaled-MLP algorithm of shallow learning model. Ultimately, this paper comes up with a better polarimetric signature of land types for both the CP and FP datasets, which can be used in an alternative manner as per data availability for a multi-sensor data analysis. [ABSTRACT FROM AUTHOR]

In India and over the world, Cancer has become a deadly disease that is adversely affecting women from different age groups. According to a survey, one in every 30 women suffers from this deadly disease in their lifetime. This project was first thought of because of the increase in cases of breast cancer and if we can detect it at an early stage then there is an increased chance of it getting cured. This paper lays a foundation in making the detection of cancer automated from histopathological images using deep learning algorithms so that more and more people can get it diagnosed at an early stage and subsequently get cured. To enhance the capability of histopathology image classification, a powerful deep learning algorithm and a sizable, varied dataset are required. In this paper, we have proposed an automatic and precise histopathological image analytical method, to detect breast cancer at an early stage. Deep learning techniques have recently made significant strides and produced outstanding results in the fields of computer vision and image processing, which has encouraged many researchers to use this method for the categorization of histopathology images. [ABSTRACT FROM AUTHOR]

Background: This research adds to the growing body of work demonstrating the vital role of image categorization in the medical sector. The efficiency of illness diagnosis is being greatly enhanced using image classification. A brain tumor is a collection of abnormal cells in the brain. Diagnostic precision is required when looking for a tumor in the brain because even the smallest error in human judgement can have disastrous results. To get around this problem, the medical community has implemented an automated brain tumor segmentation system. A variety of methods are employed to segment a brain tumor, but the results are inconsistent. To improve the quality of MRI images, we present our findings in this paper. Deep learning methods for image segmentation and classification are discussed in this paper. Methods: In this paper we a very robust deep learning method for image segmentation and classification. For image classification, we are employing the enhanced faster R-CNN method. The ResNet50 model is used to differentiate between tumor and non-tumor images. The next step in this framework is to use Deep Residual UNET for segmentation. RESUNET is an FCNN that maximizes efficiency. The proposed method works well in terms of its ability to find and classify things accurately. Results: The accuracy rate for identifying tumours in MRI scans using the proposed technique is 94.23%. Using transfer learning with Resnet50 as the base model and the use of discriminative learning rates, our model achieved superior results than other recent models. Conclusion: Within the scope of this study, we have integrated the residual networks with the U-Net to make the network stronger. This strategy improves the efficiency of classification and segmentation tools. To achieve a higher level of accuracy, the model may be trained further, or additional data may be applied in the training process. [ABSTRACT FROM AUTHOR]

Curfews and lockdowns around the world in the Covid-19 era have increased the usage of the internet drastically and accordingly the amount of data shared on social media. In addition to using social media for sharing useful information, some miscreants are using the power of social media to spread hate speech and offensive content. Filtering the offensive language content manually is a laborious task due to the huge volume of data. Further, rapid developments in hardware and software technology have provided opportunities for users to post their comments not only in English but also in their native language scripts. However, based on the ease of Roman script usage, social media users specifically in multilingual countries like India, prefer to comment in code-mixed and multi-script texts. The typical systems that are employed to process and analyze monolingual texts are usually not appropriate for these kinds of texts. Further, as these texts do not adhere to the rules and regulations of any language to frame the words and sentences, the complexity of analyzing such texts increases. The novelty of the present study is to address the Offensive Language Identification (OLI) task in code-mixed and multi-script texts, this paper proposes to use relevant syllable and character n-grams features to train Machine Learning (ML) classifiers. The performance of the proposed models is evaluated on three Dravidian language pairs, namely: Malayalam-English, Tamil- English, and Kannada-English. The performances of ML classifiers prove the effectiveness of syllable and character n-grams features for code-mixed and multi-script texts analysis. [ABSTRACT FROM AUTHOR]

The road is the most commonly used means of transportation and serves as a country's arteries, so it is extremely important to keep the roads in good condition. Potholes that happen to appear in the road must be repaired to keep the road in good condition. Spotting potholes on the road is difficult, especially in a country like India where roads stretch millions of kilometres across the country. Therefore, there is a need to automate the identification of potholes with high speed and real-time precision. YOLOX is an object detection algorithm and our main goal of this article is to train and analyse the YOLOX model for pothole detection. The YOLOX model is trained with a pothole dataset and the results obtained are analysed by calculating the accuracy, recall and size of the model which is then compared to other YOLO algorithms. The experimental results in this article show that the YOLOX-Nano model predicts potholes with higher accuracy compared to other models while having low computational costs. We were able to achieve an Average Precision (AP) value of 85.6% from training the model and the total size of the model is 7.22 MB. The pothole detection capabilities of the newly developed YOLOX algorithm have never been tested before and this paper is one of the first to detect potholes using the YOLOX object detection algorithm. The research conducted in this paper will help reduce costs and increase the speed of pothole identification and will be of great help in road maintenance. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to identify, prioritise and explore the relationships between the various barriers that are hindering the machine learning (ML) adaptation for analysing accident data information in the Indian petroleum industry. Design/methodology/approach: The preferred reporting items for systematic reviews and meta-analysis (PRISMA) is initially used to identify key barriers as reported in extant literature. The decision-making trial and evaluation laboratory (DEMATEL) technique is then used to discover the interrelationships between the barriers, which are then prioritised, based on three criteria (time, cost and relative importance) using complex proportional assessment (COPRAS) and multi-objective optimisation method by ratio analysis (MOORA). The Delphi method is used to obtain and analyse data from 10 petroleum experts who work at various petroleum facilities in India. Findings: The findings provide practical insights for management and accident data analysts to use ML techniques when analysing large amounts of data. The analysis of barriers will help organisations focus resources on the most significant obstacles to overcome barriers to adopt ML as the primary tool for accident data analysis, which can save time, money and enable the exploration of valuable insights from the data. Originality/value: This is the first study to use a hybrid three-phase methodology and consult with domain experts in the petroleum industry to rank and analyse the relationship between these barriers. [ABSTRACT FROM AUTHOR]

In India, agriculture serves as the backbone of the economy, and is a primary source of employment. Despite the setbacks caused by the COVID-19 pandemic, the agriculture and allied sectors in India exhibited resilience, registered a growth of 3.4% during 2020–2121, even as the overall economic growth declined by 7.2% during the same period. The improvement of the agriculture sector holds paramount importance in sustaining the increasing population and safeguarding food security. Consequently, researchers worldwide have been concentrating on digitally transforming agriculture by leveraging advanced technologies to establish smart, sustainable, and lucrative farming systems. The advancement in remote sensing (RS) and machine learning (ML) has proven beneficial for farmers and policymakers in minimizing crop losses and optimizing resource utilization through valuable crop insights. In this paper, we present a comprehensive review of studies dedicated to the application of RS and ML in addressing agriculture-related challenges in India. We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and evaluated research articles published from 2015 to 2022. The objective of this study is to shed light on the application of both RS and ML technique across key agricultural domains, encompassing "crop management", "soil management", and "water management, ultimately leading to their improvement. This study primarily focuses on assessing the current status of using intelligent geospatial data analytics in Indian agriculture. Majority of the studies were carried out in the crop management category, where the deployment of various RS sensors led yielded substantial improvements in agricultural monitoring. The integration of remote sensing technology and machine learning techniques can enable an intelligent approach to agricultural monitoring, thereby providing valuable recommendations and insights for effective agricultural management. [ABSTRACT FROM AUTHOR]

The outbreak of Coronavirus 2019 (COVID‐19) has impacted everyday lives globally. The number of positive cases is growing and India is now one of the most affected countries. This paper builds predictive models that can predict the number of positive cases with higher accuracy. Regression‐based, Decision tree‐based, and Random forest‐based models have been built on the data from China and are validated on India's sample. The model is found to be effective and will be able to predict the positive number of cases in the future with minimal error. The developed machine learning model can work in real‐time and can effectively predict the number of positive cases. Key measures and suggestions have been put forward considering the effect of lockdown. [ABSTRACT FROM AUTHOR]

A court of a country is the main source of justice, to the respective country's citizens. Every individual approaches courts to seek justice when his/her rights are violated. The main power house of these courts is the supreme court and each country has its own respective supreme court, in a country like India with a huge population every day hundreds and hundreds of new and appeal cases have been filed to the supreme court and seek justice. The objective of this paper is to classify the cases and to predict the behavior of the court (whether the appeal case will be accepted or dismissed by the Supreme Court). This paper gives the individual an ideology about how the case will be taken and treated by the court. The model considers past 20 years of cases from the Supreme Court of India database containing all types of cases to predict leave granted and Disposed off parameters. The proposed model is tested as three modules (i) classification module (ii) prediction module and (iii) baseline module and also compares various ML algorithms using Accuracy and F-measure as performance metrics. [ABSTRACT FROM AUTHOR]

Over the past decade, extensive research on stock market prediction using machine learning models has been conducted. In this framework, different approaches for data standardisation methods have been used for financial time series analysis and to assess the impact of data standardisation on the final prediction outcome. The paper uses the feature-level optimal rolling-window batch data standardisation method to improve the machine learning model's predictive power significantly. Along with the standardisation method, the paper explores the performance of the automated feature interactions learner (Deep Cross Networks) effect on a plethora of technical indicators aiming at predicting the movements of the NIFTY50 index in India, as these predicted changes are reflected in options contracts. Feature-level optimal rolling window data standardisation can identify the optimal window of time such that the correlation between features and the response variable is maximized, with most features correlating at 0.7. In the experiment, 48% of important technical indicators negatively correlated with the response variable. The Deep Cross Network regression model combined with the optimal rolling window batch data standardisation method outperformed all other model configurations at weekly and monthly data frequency. It achieved a directional hit rate of 69.52% (weekly) and 79.17% (monthly) and root mean square error of 2.82 (weekly) and 5.01 (monthly), generating a profit 5.5 times (weekly) and 2.85 times (monthly) greater than the benchmark buy-and-hold strategy providing opposing evidence to the sub-martingale model. [ABSTRACT FROM AUTHOR]

This paper explores the magnitude of changes that is happening in the Indian banking sector in terms of the technology used, human resource deployed and change in the customer experience. The emergence of gig workforce has made banks rework their strategy. Here, we will describe how Indian banking sector is battling legacy systems and trying to adopt to latest technologies. The gig economy which has been playing a major role in many other sectors have not made a significant impact in the banking industry. The paper discusses the reasons this and gives a first-hand perspective of how the banking sector is getting disrupted. [ABSTRACT FROM AUTHOR]

Purpose: In India, one of the prime focuses of a post-graduate management program is to prepare students and make them job-ready. Masters in Business Management (MBA) program helps students to imbibe theoretical and practical skills which are required by the industry, which can make them hit the ground running from the day they start their career. Many students (almost 40–50%) get pre-placement offers based on their performance in summer internship. The selection for summer interns by the corporate happens within a few months of the student joining the MBA program. Signaling theory in education indicates that the level of productivity of an individual is independent of education, but the educational qualification acts as a testimony for higher ability. However, this theory does not explain the reason for the mismatch between "education and work" or "education and the disparity in salary" between individuals who earn differently but have the same qualification. The paper aims to explore three attributes namely – "employability"– the chance of being employable; "pre-placement offers" – the chance of securing a job offer based on the performance in internship and "salary" – the chance of bagging a good job offer with a high salary. Design/methodology/approach: The authors have used longitudinal data consisting of 1,202 students who graduated from reputable business schools (B-Schools) in India. In the study, the authors have used predictive analytics on six years data set that have been gathered. The authors have considered 24 attributes including educational background at the graduate level (BE, B Tech, B Com, BSc, BBA and others), score secured in class ten (high, medium and low), score secured in class twelve (high, medium and low), score secured in graduation (high, medium and low), competency in soft skills (high, medium and low), participation in co-curricular activities (high, medium and low) and social engagement status (high, medium and low). Findings: The findings of the study contradict the signaling theory in education. The findings suggest that the educational qualification alone cannot be the predictor of the employability and the salary offered to the student. The authors note that the better performance at a lower level of qualification (class 12) is the strong predictor in comparison to the student performance at their graduation and post-graduation level. The authors further observed at the post-graduate management education level that soft skills and participation in co-curricular activities are the major deciding factors to predict employability and pre-placement job opportunity and marks secured in class 12 is one more factor that gets added to this list to predict salary. The paper can immensely help management graduates to focus on key aspects that can help to hone appropriate skills and also can help management institutions to select the right students for management programs. Research limitations/implications: The analysis and the predictive model may apply to Indian B-Schools wherein the quality of students are almost the same or better. Predictive analytics has been used to explain the employability of management graduates alone and not any other. Practical implications: The authors' study might be useful for those students who often fail to understand "what" skills are the most important predictors of their performance in the pre-placement and final-placement interviews. Moreover, the study may serve as a useful guide to those organizations that often face dilemmas to understand "how" to select an ideal candidate for the particular job profile from a campus. Originality/value: The authors believe that the current study is one of the few studies that have attempted to examine the employability of management graduates using predictive analytics. The study further contradicts that the signaling theory in education does not help better explain the employability of the students in extremely high-paced business environments. [ABSTRACT FROM AUTHOR]

Early detection and identification of plant diseases from leaf images using machine learning is an important and challenging research area in the field of agriculture. There is a need for such kinds of research studies in India because agriculture is one of the main sources of income which contributes seventeen percent of the total gross domestic product (GDP). Effective and improved crop products can increase the farmer's profit as well as the economy of the country. In this paper, a comprehensive review of the different research works carried out in the field of plant disease detection using both state-of-art, handcrafted-features- and deep-learning-based techniques are presented. We address the challenges faced in the identification of plant diseases using handcrafted-features-based approaches. The application of deep-learning-based approaches overcomes the challenges faced in handcrafted-features-based approaches. This survey provides the research improvement in the identification of plant diseases from handcrafted-features-based to deep-learning-based models. We report that deep-learning-based approaches achieve significant accuracy rates on a particular dataset, but the performance of the model may be decreased significantly when the system is tested on field image condition or on different datasets. Among the deep learning models, deep learning with an inception layer such as GoogleNet and InceptionV3 have better ability to extract the features and produce higher performance results. We also address some of the challenges that are needed to be solved to identify the plant diseases effectively. [ABSTRACT FROM AUTHOR]

Diabetes is one of the most prevalent non-communicable diseases and is the 6th leading cause of death worldwide. It's a chronic metabolic disorder which has no cure, however, it is a highly treatable condition, if diagnosed and managed on time to avoid its complications. This paper explores and compares various machine learning (ML) approaches that can help in determining the risk of diabetes at an early stage and aid in improving the medical diagnosis of diabetes. The paper considers two real-world datasets one is a diabetic clinical dataset (DCA) collected from a medical practitioner in the state of Assam, India during the year 2017–2018 and other is public PIMA Indian diabetic dataset. To analyze the various machine learning techniques on DCA and PIMA Indian diabetic datasets for the classification of diabetic and non-diabetic patients, different classifiers like perceptron, Gaussian process, linear discriminant analysis, quadratic discriminant analysis, statistical gradient descent, ridge regression classifier, support vector machines, k-nearest neighbors, decision tree, naïve Bayes, logistic regression, random forest and ELM for multiquadric, RBF, sigmoid activation functions are used. The results of numerical experiments suggested that logistic regression yields better performance in comparison to the other techniques. [ABSTRACT FROM AUTHOR]

Online digital media has become a lifeline for humankind. But it has also become a major source of disruptions just like climate change. During the global pandemic, COVID-19, while the whole world is trying their best to blunt the spread of coronavirus, there is a vile trend of circulation of disinformation, fake news and sharing false data related to the virus on social media platforms creating panic among people. The review paper found that the present online information ecosystem matrix is driven by exploiters with the objective to demean democratic bodies, inflame societal divides, manipulate public opinion and influence citizens' voting choice to distort the democracy. Examination of the current trend led to disturbing reality as the content, discourse, tone and intent of social media interactions have undergone an evolution that threatens not only free speech, privacy, data protection, national security but democracy as a whole. The study also highlighted about the rise of new-age technologies such as Artificial Intelligence (AI), Algorithm, Robotics, and Machine Learning (ML) have exacerbated the problem to new heights as these technologies play a disproportionately impactful role in disseminating disinformation by amplifying it to distort democracy and free speech. The research work resonated with the growing clamour for greater legal regulation to control the menace of social media misuse among democracies around the globe. It addressed the concerns of internet companies and rights activists who fear tight measures would imperil free speech. The paper tried to examine the challenge how to regulate that doesn't stifle the freedom of expression and speech vis-à-vis keeping online content safe and protected. The fact-finding review paper is based on existing laws, regulations, policies, research papers, media reports, articles on instances of disinformation and fake news to find solutions and future developments keeping India in focus. The subject of study assumes significance in a democracy like India which has recently notified a new regulatory regime - 'The Information Technology (Intermediary Guidelines and digital Media Ethics Code) Rules, 2021,' to strengthen the regulatory architecture to tackle misuse of social media to deal with the fast- growing new communication challenges. The study critically examines these new guidelines and also highlights the patchy policy syndrome of internet content governance in India. [ABSTRACT FROM AUTHOR]

Agriculture is the main source of income, food, employment, and livelihood for most rural people in India. Several crops can be destroyed yearly due to a lack of technical skills and changing weather patterns such as rainfall, temperature, and other atmospheric parameters that play an enormous role in determining crop yield and profit. Therefore, selecting a suitable crop to increase crop yield is an essential aspect of improving real-life farming scenarios. Anticipating crop yield is one of the major concerns in agriculture and plays a critical role in global, regional, and field decision-making. Crop yield forecasting is based on crop parameters and meteorological, atmospheric, and soil conditions. This paper introduces a crop recommendation and yield prediction system using a Hybrid Moth Flame Optimization with Machine Learning (HMFO-ML) model. The presented HMFO-ML method effectively recommends crops and forecasts crop yield accurately and promptly. The proposed model used a Probabilistic Neural Network (PNN) for crop recommendation and the Extreme Learning Machine (ELM) method for the crop yield forecasting process. The HMFO algorithm was used to improve the forecasting rate of the ELM approach. A wide-ranging simulation analysis was carried out to evaluate the HMFO-ML model, showing its advantages over other models, as it exhibited a maximum R² score of 98.82% and an accuracy of 99.67%. [ABSTRACT FROM AUTHOR]

Background: Silicosis has been one of the most serious occupational public health problems worldwide for many decades. The global burden of silicosis is largely unknown, although it is thought to be more prevalent in low and medium-income countries. Individual studies among workers exposed to silica dust in various industries, however, reveal a high prevalence of silicosis in India. This paper is an updated review of the novel challenges and opportunities for silicosis prevention and control in India. Main body: The unregulated informal sector employs workers on contractual appointment thereby insulating the employers from legislative provisions. Due to a lack of awareness of the serious health risks and low-income levels, symptomatic workers tend to disregard the symptoms and continue working in dusty environments. To prevent any future dust exposure, the workers must be moved to an alternative job in the same factory where they will not be exposed to silica dust. Government regulatory bodies, on the other hand, must guarantee that factory owners relocate workers to another vocation as soon as they exhibit signs of silicosis. Technological advances such as artificial intelligence and machine learning might assist industries in implementing effective and cost-saving dust control measures. A surveillance system needs to be established for the early detection and tracking of all patients with silicosis. A pneumoconiosis elimination program encompassing health promotion, personal protection, diagnostic criteria, preventive measures, symptomatic management, prevention of silica dust exposure, treatment, and rehabilitation is felt important for wider adoption. Conclusion: Silica dust exposure and its consequences are fully preventable, with the benefits of prevention considerably outweighing the benefits of treating patients with silicosis. A comprehensive national health program on silicosis within the public health system would strengthen surveillance, notification, and management of workers exposed to silica dust in India. [ABSTRACT FROM AUTHOR]

This paper discusses the importance of investigating DR using machine learning and a computational method to rank DR risk factors by importance using different machine learning models. The dataset was collected from four large population-based studies conducted in India between 2001 and 2010 on the prevalence of DR and its risk factors. We deployed different machine learning models on the dataset to rank the importance of the variables (risk factors). The study uses a t-test and Shapely additive explanations (SHAP) to rank the risk factors. Then, it uses five machine learning models (K-Nearest Neighbor, Decision Tree, Support Vector Machines, Logistic Regression, and Naive Bayes) to identify the unimportant risk factors based on the area under the curve criterion to predict DR. To determine the overall significance of risk variables, a weighted average of each classifier's importance is used. The ranking of risk variables is provided to machine learning models. To construct a model for DR prediction, the combination of risk factors with the highest AUC is chosen. The results show that the risk factors glycosylated hemoglobin and systolic blood pressure were present in the top three risk factors for DR in all five machine learning models when the t-test was used for ranking. Furthermore, the risk factors, namely, systolic blood pressure and history of hypertension, were present in the top five risk factors for DR in all the machine learning models when SHAP was used for ranking. Finally, when an ensemble of the five machine learning models was employed, independently with both the t-test and SHAP, systolic blood pressure and diabetes mellitus duration were present in the top four risk factors for diabetic retinopathy. Decision Tree and K-Nearest Neighbor resulted in the highest AUCs of 0.79 (t-test) and 0.77 (SHAP). Moreover, K-Nearest Neighbor predicted DR with 82.6% (t-test) and 78.3% (SHAP) accuracy. [ABSTRACT FROM AUTHOR]

Water quality strongly influences sustainable growth of a healthy society and green environment. According to the International Initiative on Water Quality (IIWQ) of the UNESCO Intergovernmental Hydrological Programme (IHP), it is essential to address water-quality issues holistically in developed and developing countries. Due to rapid urbanization and industrialization in many developing countries, groundwater - one of the major sources of drinking is getting highly affected. The traditional laboratory-based chemical testing process with conventional statistical methods is often used to analyze water quality. However, it is time-consuming. Recently, Artificial Intelligence (AI) based approaches have proven to be a better alternative for analysis and prediction of the quality of water, provided with its chemical components' data. In this paper, we present research focusing on groundwater quality analysis using Artificial Intelligence (AI) in a case study of Odisha, an eastern- state of India and the data acquired from the Northern delta, the North Central Coast of Vietnam. The dataset in Vietnam is collected by the Ministry of Natural Resources and Environment, providing technical regulations on water resources monitoring. The Central Groundwater Board and the Government of India collect the dataset from India. The target problem is formulated as a multi-class classification problem to predict groundwater quality for drinking suitability by WHO standards. AI methodologies such as logistic regression, K-NN, Support Vector Machine (SVM) variants, decision tree, AdaBoost and XGBoost are used. Prediction results have demonstrated that Adaboost, the XGBoost and the Polynomial SVM model accurately classified the Water Quality Classes with an accuracy of 92% and 98%, respectively. It would help decision-makers effectively choose the best source of water for drinking. [ABSTRACT FROM AUTHOR]

Handwritten script recognition is a vital application of the machine-learning domain. Applications like automatic license plate detection, pin-code detection, and historical document management increases attention toward handwritten script recognition. English is the most widely spoken language in India; hence, there has been a lot of research into identifying a script using a machine. Devanagari is a popular script that is used by a large number of people on the Indian subcontinent. In this paper, a level-wised efficient transfer-learning approach is presented on the VGG16 model of a convolutional neural network (CNN) for identifying isolated Devanagari handwritten characters. In this work, a new dataset of Devanagari characters is presented and made accessible to the public. This newly created dataset is comprised of 5800 samples for 12 vowels, 36 consonants, and 10 digits. Initially, a simple CNN is implemented and trained on this new small dataset. During the next stage, a transferlearning approach is implemented on the VGG16 model, and during the last stage, the efficient fine-tuned VGG16 model is implemented. The obtained accuracy of the fine-tuned model's training and testing came to 98.16 and 96.47%, respectively. [ABSTRACT FROM AUTHOR]

This paper attempts to evaluate the predictive ability of four machine learning models: logit, decision tree, random forest and 2-class support vector machine and to identify the key predictors of default. The models are applied on a dataset of 57 companies under the Insolvency and Bankruptcy Code (IBC) in India and a matched sample of 55 solvent companies spanning over ten years from FY06-FY 2016. The solvent companies are matched on size (log of total assets) and sector and are rated 'AAA' and 'AA'. Thirty-one explanatory variables are identified by us for the study which include (i) financial ratios, (ii) size and age of the company, (iii) ownership pattern and (iv) market ratios. The empirical findings reveal that random forest strongly outperforms all other models in their predictive ability, followed by SVM, DT and logit model. The findings also confirm relevance of size and age of the firm, market ratios and ownership pattern as predictors of default in addition to financial ratios. We conclude that both parametric (logit) and non-parametric models are useful in the study of default prediction as reflected in the robustness of all models with accuracy of over 75%. These models can help banks in strategising their lending decisions based on credit quality of borrower firms. Our contribution is that to the best of our knowledge this is the first paper that is using the database of companies that are legally defined as insolvent and bankrupt and also taking a balanced sample to avoid biasness and inaccuracy from data imbalance. Also, this study has gone beyond traditional financial statements in identifying key default drivers. [ABSTRACT FROM AUTHOR]

This paper explores the different insider employee-led cyber frauds (IECF) based on the recent large-scale fraud events of prominent Indian banking institutions. Examining the different types of fraud and appropriate control measures will protect the banking industry from fraudsters. In this study, we identify and classify Cyber Fraud (CF), map the severity of the fraud on a scale of priority, test the mitigation effectiveness, and propose optimal mitigation measures. The identification and classification of CF losses were based on a literature review and focus group discussions with risk and vigilance officers and cyber cell experts. The CF was analyzed using secondary data. We predicted and prioritized CF based on machine learning-derived Random Forest (RF). An efficient fraud mitigation model was developed based on an offender-victim-centric approach. Mitigation is advised both before and after fraud occurs. Through the findings of this research, banks and fraud investigators can prevent CF by detecting it quickly and controlling it on time. This study proposes a structured, sustainable CF mitigation plan that protects banks, employees, regulators, customers, and the economy, thus saving time, resources, and money. Further, these mitigation measures will improve the reputation of the Indian banking industry and ensure its survival. [ABSTRACT FROM AUTHOR]

Early-stage prediction of a disease is an important and challenging task. The application of machine learning techniques is playing an important role in this era. Thyroid is one of the chronic endocrine diseases, and approximately 42 million people in India are affected by this disease. This paper presents a comprehensive investigation into the enhancement of classification performance through the novel 'FeatureBoostThyro' (FBT) model. The study evaluates various machine learning algorithms, including stochastic gradient descent (SGD), K nearest neighbor (KNN), logistic regression (LR), naive bayes (NB), and support vector machine (SVM), in conjunction with diverse feature selection methods. The research systematically explores the impact of feature selection techniques such as information gain, relief F, chi-square, gini index, forward selection, backward selection, recursive feature elimination, and LASSO on model performance across the chosen algorithms. The analysis reveals notable variations in performance metrics, including accuracy, precision, recall, and F1-score, providing valuable insights into the interplay between algorithm and feature selection. One main contribution of this research is the introduction of the FBT model, which consistently outperforms other models across various feature selection methods, making it a promising tool for addressing complex classification tasks. The findings contribute to a broader understanding of model selection and optimization in machine learning applications. The proposed model undergoes evaluation using two distinct datasets: the primary dataset acquired from Lata Mangeshkar Hospital in Nagpur and the secondary dataset obtained from the UCI dataset. [ABSTRACT FROM AUTHOR]