Search

Due to the change in life style after covid-19 there is demand for non-invasive contact less healthcare monitoring systems. In India oral cancer rate are increasing and becoming the community health issue with high mortality rate. Mortality rate can be reduced by identification of disease at initial stages. The major hindrance in disease identification is availability of dedicated hardware at remote and identification at initial stage. Research is going on to make the device portable and less costly using digital images. Also, research is going on to have hybrid algorithm which can segment smaller area abnormal area and classify reliably. This paper focuses on tongue cancer which is one of the types of oral cancer and presents comparison of hybrid algorithm using firefly and watershed transformation to segment smaller area using digital images which reduces cost of dedicated hardware required. 150 digital images are used which are available on internet or provided by cancer hospital for analysis and classification using CNN along with augmentation. 90.48% accuracy is achieved and desirable results are obtained using hybrid algorithm being used. [ABSTRACT FROM AUTHOR]

Signature is a biometrics trait widely used for personal verification in financial and most other organizations where financial and relevant types of transactions are done manually with signed authorized papers. A signature verification system aims to verify the minor structural differences between genuine and forged signatures, as most skilled forgery signatures look similar to their respective genuine signatures with specific deformations. Signature verification in a multi-cultural country like India is challenging in both writer-independent and script-independent scenarios where the Indian population uses multiple scripts to write their signatures. This paper reports a writer-independent offline signature verification system that uses Convolutional Neural Network (CNN) architecture for feature extraction and classification. The objective of the proposed work is to model a CNN-based adaptable system to verify multi-scripted offline signatures. The model has been trained and tested on two publicly available databases, viz. CEDAR and BH-Sig260, which consist of Hindi, Bengali, and English signatures. Individual signature classes of unique scripts and a combination of these scripts have been considered for testing the proposed model that determines verification accuracies of 90%, 95%, 98.33%, and 93.33%, respectively. Experimental results are compelling, and the proposed model outperforms the verification accuracies of some well-known models. [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]

It is important to recognize the destination city name correctly for a postal document to reach its desired address. In India people often mix up scripts while writing the address. Often the script of the destination city name is different from the other part of the postal document. This is common in India due to the multilingual and multi script nature of the country. In this paper, a Convolutional Neural Network (CNN) based approach towards the recognition of handwritten multilingual multiscript Indian city names is presented. Experiments were performed not only in a single script scenario but also in multi script, considering English, Bangla and Devanagari scripts. An accuracy of 91.72% was obtained on 106 city names in mixed script scenario from the proposed scheme and the data set will be made available to the researcher on request. Further experiments were also performed with different script combinations and obtained results up to 98.01%. The system also produced a mean performance difference of approximately ± 1% for successive changes in the data set size, thereby pointing to the robustness of the proposed architecture. [ABSTRACT FROM AUTHOR]

In recent times, research activity on image caption generation has attracted several researchers. The present work attempt to address the problem of Hindi image caption generation using Hindi Visual genome dataset. Hindi is the official and most spoken language in India. In a linguistically diverse country like India, it is essential to provide a means that can help the people to understand the visual entities in their native languages. In this paper, an encoder-decoder based architecture is proposed where Convolutional Neural Network (CNN) is employed for encoding visual features of an image and stacked Long Short-Term Memory (sLSTM) in combination with both uni-directional LSTM and bi-directional LSTM for generating the captions in Hindi. For encoding the visual feature representation of an image, VGG19 based pre-trained model is used and sLSTM architecture is employed for caption generation at the decoder side. The model is tested over Hindi visual genome dataset to validate the proposed approach's performance and cross-verification is carried out for English captions with Flickr dataset. The experimental results of the proposed approach manifest that the model is qualitatively and quantitatively better than state-of-the-art approaches for Hindi caption generation. [ABSTRACT FROM AUTHOR]

Indian economy depends a lot on agriculture. Around 38% of the land in India is suitable for agriculture. The crop in the agricultural land is threatened by the diseases. These diseases may have been caused by microorganisms, viruses, fungi, and bacteria. The traditional method of identifying the crop disease by the naked eye needs enormous labor, expertise with crop diseases, and needs a lot of time. In most cases, by the time the results are out, the damage is already done. To avoid such problems, an automated system can be adapted for the detection of plant diseases. The aim is to build a model that is fast, accurate, and reliable that can be used for the identification of leaf diseases. In this article, we compared three deep learning neural networks we evaluated the performance of three deep neural networks and analyzed the strengths of each neural network interms of accuracy. We also determined the working of each model and its applications. [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]

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]

Like other applications, under the purview of pattern classification, analyzing speech signals is crucial. People often mix different languages while talking which makes this task complicated. This happens mostly in India, since different languages are used from one state to another. Among many, Southern part of India suffers a lot from this situation, where distinguishing their languages is important. In this paper, we propose image-based features for speech signal classification because it is possible to identify different patterns by visualizing their speech patterns. Modified Mel frequency cepstral coefficient (MFCC) features namely MFCC- Statistics Grade (MFCC-SG) were extracted which were visualized by plotting techniques and thereafter fed to a convolutional neural network. In this study, we used the top 4 languages namely Telugu, Tamil, Malayalam, and Kannada. Experiments were performed on more than 900 hours of data collected from YouTube leading to over 150000 images and the highest accuracy of 94.51% was obtained. [ABSTRACT FROM AUTHOR]

Agricultural sector is one of the main sectors in India. Productive growth and high yield production of fruits is important and required for the agricultural industry. Application of computer vision and image processing has aid agriculture to boost yield rating, disease spotting, irrigation, fruit classification and maturity grading. Computer vision and image processing approach can be used to lower the time utilization and has made it economical. A convolutional neural network (CNN) is a type of artificial neural network used in image identification and processing that is mainly planned to process pixel data. This paper utilized a convolutional neural network (CNN) to classify bananas into raw or ripe without requiring labour. Bananas were classified by their colour appearance in the CNN classification and not only this it can be also used to classify many other types of fruits and vegetables. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNN) are playing a vital role nowadays in every aspect of computer vision applications. In this paper we have used the state of the art CNN in recognizing handwritten Tamil characters in offline mode. CNNs differ from traditional approach of Handwritten Tamil Character Recognition (HTCR) in extracting the features automatically. We have used an isolated handwritten Tamil character dataset developed by HP Labs India. We have developed a CNN model from scratch by training the model with the Tamil characters in offline mode and have achieved good recognition results on both the training and testing datasets. This work is an attempt to set a benchmark for offline HTCR using deep learning techniques. This work have produced a training accuracy of 95.16% which is far better compared to the traditional approaches. [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]

Tomatoes, which are extensively grown in Indian agricultural fields, are among the commonly cultivated vegetable crops. The tropical climate in India provides favorable conditions for tomato cultivation. However, various factors, including climatic conditions and other elements, can adversely affect the normal growth of tomato plants. Plant diseases present a significant risk to crop production and can lead to economic losses, adding to the challenges posed by climate conditions and natural disasters. Unfortunately, traditional methods of detecting diseases in tomato crops have proven to be ineffective and time-consuming. This study primarily aims to accurately identify tomato plant leaf diseases that are found using image analysis. Various methods have been applied for extracting the features that have been used to improve the accuracy of classification. Alex Net, InceptionV3, and a CNN (Conv Net) algorithm have been utilized to classify many types of tomato plant diseases. When comparing the results, it is notable that the CNN (Conv Net) classifier outperforms the other two models. The findings demonstrate the practical applicability of the model in real-life scenarios. [ABSTRACT FROM AUTHOR]

Corn is one of the most popular food grains in the India and crop loss due to diseases substantially affects the Indian economy and threatens the food availability. Recent access of smart devices can be utilized to provide automatic diagnosis of corn diseases and prevent severe crop losses. This paper presents a real time method based on deep convolutional neural network for corn leaf disease recognition. Deep neural network performance is improved by tuning the hyper-parameters and adjusting the pooling combinations on a system with GPU. Further, the number of parameters of the developed model is optimized to make it suitable for real time inference. The pre-trained deep CNN model was deployed onto raspberry pi 3 using Intel Movidius Neural Compute Stick consisting dedicated CNN hardware blocks. During the recognition of corn leaf diseases, the deep learning model achieves an accuracy of 88.46% demonstrating the feasibility of this method. The presented corn plant disease recognition model is capable of running on standalone smart devices like raspberry-pi or smart-phone and drones. [ABSTRACT FROM AUTHOR]

Agriculture being the pillar of the economy for a developing country like India has a vital role in the survival of living beings on earth. Wheat is the most widely consumed grain on the planet. Deep learning is an evolving technology that is having a significant effect in the field of agriculture, assisting farmers in modernizing their operations. One such application is the identification of plant diseases using image classification which is necessary for long-term agriculture sustainability. Wheat plants are susceptible to a variety of fungal diseases. Hence early identification of diseases of crops like wheat and rice that are staple food of people in many countries is critical. Using deep learning algorithms such as CNN, this proposed system aims to predict wheat diseases. We are introducing a deep learning-based model for image classification to predict wheat diseases. Previous approaches used machine learning algorithms for a general dataset that included all types of crop diseases. To achieve better precision, we built our own dataset and combined it with existing similar datasets to account for 4 major classes of wheat diseases. The dataset consists of 700 images of wheat plants. Based on the input, our system determines if the plant is healthy or diseased so that precautionary measures can be taken to prevent losses in wheat cultivation, which could lead to food shortages. [ABSTRACT FROM AUTHOR]

The primary direction of most of the research done so far on the effects of Lockdown due to pandemic have been limited to areas such as clinical studies, possible impact on the global economy, or issues related to migrant workers. However, during this period, little attempt has been made to understand the emotions of Generation Z, one of the prime victims of this pandemic. Members of this generation were born after 1996. So, most of them are studying in various schools, colleges, or universities. In the proposed work, the emotions of some students of an engineering college in West Bengal, India, have been analyzed. A multimodal approach has been applied to obtain vivid pictures of 74 students' minds. The valence-arousal inspired Organize-Split-Fuse (OSF) model has been proposed to achieve this objective. Two conventional Convolutional Neural Network (CNN) models have been employed separately, to classify human emotions using Acoustic Information (AcI) and Facial Expressions (FE) from the generated dataset. The employed models have achieved satisfactory performance (91% and 72.7% accuracy respectively) on the benchmark dataset. Afterward, classified emotions have been organized and split successfully. Finally, a fuzzy rule-based classification system has been used to fuse both emotions at the decision level. The results show that junior students have higher positivity and less Neutral emotions than the senior. In-depth analysis shows that boys are more apprehensive than girls while girls have a more optimistic outlook for the future. The year-wise observations show the chaotic state of students' minds. [ABSTRACT FROM AUTHOR]

Many people and children in the world go missing every day, which the police and local authorities must deal with. The police and municipal authorities deal with many missing persons and kid cases every day. In 2020, National Crime Records Bureau (NCRB) listed around 300 thousand missing persons in India. The general process normally deals with investigation, which requires experience and can be time-consuming if the missing person is migrated. The overall procedure usually entails inquiry, which is time-consuming and requires experience. Our research intends to create an AI system that can identify and evaluate a person's facial features and then compare them to a face in the database, even if they are located years after going missing. Using the Yale Face Dataset on Kaggle containing over 70,000 images for the model, the training of such large dataset improved the model for the Eigenface as well as the GAN algorithm with the use of OpenCV and HaarCascade library helped improve and enhance the accuracy with the result of near 99. [ABSTRACT FROM AUTHOR]

In real-world applications such as autonomous driving and driver safety, Traffic Sign Recognition (TSR) systems play a critical role. In a country like India, where new technology is quickly adopted, automatic vehicles will adapt quickly. Even significant corporate in India Tata Motors is working on bringing self-driving cars to India. Tesla, the biggest developers of selfdriven cars is granted the right to sell cars in India. According to reports, Tesla will be selling cars in India by the end of 2022. The state-of-the-art of object detection models such as YOLOv3, Tiny-YOLOv4 and YOLOv4 is examined in this work. Transfer learning is used to tailor these models to the domain of traffic sign detection. As we are focusing on India, we finetune these state-of-art object detection model trained on COCO dataset using Indian Traffic Sign Detection (ITSD) Dataset. There is no such database, hence this work contribute a new Indian Traffic Sign Detection dataset obtained from random Indian road scenes. The task of recognition is made up of two parts. Detection and classification are two steps in the process. In this work, detection module is implemented using three different YOLO (You Look Only Once) versions and classification using custom Convolutional Neural Network (CNN) model. The German Traffic Sign Detection Benchmark (GTSDB) dataset is also utilized to evaluate the system because it is the most widely used dataset. With a threshold of 0.5, the detectors made with YOLOv4, YOLOv3, and Tiny-YOLOv4 were tested on the ITSD dataset and achieved mean average precision (mAP) of 99.35%, 97.20%, and 80.89%, respectively. [ABSTRACT FROM AUTHOR]

Geoscientists have extensively used machine learning for geological mapping and exploring the mineral prospect of a province. However, the interpretation of results becomes challenging due to the complexity of machine learning models. This study uses a convolutional neural network (CNN) and Shapley additive explanation (SHAP) to estimate potential locations for gold mineralisation in Rengali Province, a tectonised mosaic of volcano-sedimentary sequences juxtaposed at the interface of the Archaean cratonic segment in the north and the Proterozoic granulite provinces of the Eastern Ghats Belt in Eastern India. The objective is to integrate multi-thematic data involving geological, geophysical, mineralogical and geochemical surveys on a 1:50 K scale with the aim of prognosticating gold mineralisation. The available data utilised during the integration include aero-geophysical (aeromagnetic and aerospectrometric), geochemical (national geochemical mapping), ground geophysical (gravity), satellite gravity, remote sensing (multispectral) and National Geomorphology and Lineament Project structural lineament maps obtained from the Geological Survey of India Database. The CNN model has an overall accuracy of 90%. The SHAP values demonstrate that the major contributing factors are, in sequential order, antimony, clay, lead, arsenic content and a magnetic anomaly in CNN modelling. Geochemical pathfinders, including geophysical factors, have high importance, followed by the shear zones in mineralisation mapping. According to the results, the central parts of the study area, including the river valley, have higher gold prospects than the surrounding areas. Gold mineralisation is possibly associated with intermediate metavolcanics along the shear zone, which is later intruded by quartz veins in the northern part of the Rengali Province. This work intends to model known occurrences with respect to multiple themes so that the results can be replicated in surrounding areas. [ABSTRACT FROM AUTHOR]

To combat the recent coronavirus disease 2019 (COVID-19), academician and clinician are in search of new approaches to predict the COVID-19 outbreak dynamic trends that may slow down or stop the pandemic. Epidemiological models like Susceptible–Infected–Recovered (SIR) and its variants are helpful to understand the dynamics trend of pandemic that may be used in decision making to optimize possible controls from the infectious disease. But these epidemiological models based on mathematical assumptions may not predict the real pandemic situation. Recently the new machine learning approaches are being used to understand the dynamic trend of COVID-19 spread. In this paper, we designed the recurrent and convolutional neural network models: vanilla LSTM, stacked LSTM, ED_LSTM, BiLSTM, CNN, and hybrid CNN+LSTM model to capture the complex trend of COVID-19 outbreak and perform the forecasting of COVID-19 daily confirmed cases of 7, 14, 21 days for India and its four most affected states (Maharashtra, Kerala, Karnataka, and Tamil Nadu). The root mean square error (RMSE) and mean absolute percentage error (MAPE) evaluation metric are computed on the testing data to demonstrate the relative performance of these models. The results show that the stacked LSTM and hybrid CNN+LSTM models perform best relative to other models. • Various variants of LSTM and CNN deep learning architectures have been designed. • Predicted COVID-19 confirmed cases for India and its four most affected states. • RMSE and MAPE are computed to compare the performance of the designed models. • Experimental results show that predicted cases are very close to actual cases. [ABSTRACT FROM AUTHOR]

Given the state of healthcare in our nation, the unavoidable reality is that, although being a fundamental right, it is not always accessible and, even when it is, it is not always of high quality. According to a poll done by Thomson Reuters in 2011, a large percentage of misdiagnosis occurs in many healthcare institutions, resulting in lasting repercussions and affecting the person's livelihood. Thyroid and Arthritis are two such disorders. While it is believed that 42 million people in India alone suffer from Arthritis, 210 million people worldwide suffer from it in some form or another. In order to determine whether or not a person has Arthritis and Thyroid, our model use the CNN algorithm. It takes image data from users, feeds it into an algorithm, and decides whether the user has Arthritis. When it comes to thyroid detection, the model analyses thyroid scans to see whether there are any nodules present. And correctly infers whether the individual has an abnormal growth around the thyroid gland. [ABSTRACT FROM AUTHOR]

The changes in weather have beneficial and harmful effects on crop yields. There will be a loss of yield because of the diseases in crops. With the growing population, the fundamental want of food is growing. That is why agriculture gains a prominent position all around the world. It eventually ends up by a massive defeat for the farmers and the financial boom of India. The article's primary goalis to bring together farmers and cutting-edge technologies to minimise diseases in plant leaves. To enforce the idea, 'Tomato' is selected in which leaf sicknesses are expected and identified by the Artificial Intelligence algorithms, CNN (Convolution Neural Network) with pc technological know-how. Tomato is a mere consumable vegetable in India. In this investigation, seven types of tomato leaf disorders were sensed, including one wholesome elegance. The farmers are able to check the symptoms with the shapes of images of the tomato leaves with those expecting diseases. Its comparison of various classification and filters/methods with different techniques, such as K-Means classifier, SVM (Support Vector), RBF(Radial Basis Function) Kernel, Optimised MLP(Multilayer perceptron), NN classifier, BPNN (back-propagation neural network) and CNN Classifier. The classification accuracy of the existing method after experiment is RBF − 89%, k-means – 85.3%, SVM – 88.8%, Optimised MLP – 91.4%, NN – 97, BPNN – 85.5%, CNN – 94.4%. The proposed architecture can achieve the desired accuracy of 99.4%. [ABSTRACT FROM AUTHOR]

Tropical cyclone prediction is essential to limit death toll and damage caused by them. In this paper, a model has been formulated to classify the cyclone as no cyclone, minimal, moderate, extensive, extreme and catastrophic in view of attributes such as Wind Speed(10 m), Rainfall, Wind Direction(10 m), Sea Surface Temperature(2 m), Sea Level Pressure(2 m) and Relative humidity(2 m). The models have been trained using the meteorological data from MERRA-2 Web service which provides time-series data with spatial resolution of approximately 50 km. The cyclone data is taken from RSMC — New Delhi for Tropical cyclone disturbances over Indian Oceans. Initially, the models are trained using deep learning networks like MLP, LSTM, GRU, RNN, BI-LSTM and CNN. Since CNN gives better results, the CNN model is chosen for further analysis. The hyper parameters of the CNN model are optimized using genetic algorithm. The values drawn from genetic algorithm appear to be promising than the values which were chosen manually in random. The model is then modified by removing the fully connected layer which operates as a classifier in CNN network. The conventional machine learning classifiers like — Decision Tree, K-Nearest neighbor, logistic regression, Naive Bayes, Random Forest, SVM and XGBoost are used as a classifier in the place of a fully connected layer in CNN. Further to increase the prediction accuracy, C4.5 Decision tree algorithm is modified to be used as a classifier in CNN. Classification is performed by considering the Spatio-temporal data of various important cities in India. The model was tested to classify the category for 5 different cyclones and was also compared with Saffir–Simpson's scale to validate the correctness of the model. The proposed model gives a better performance compared to the conventional machine learning and deep learning classifiers in terms of time complexity, accuracy, precision and recall and this can supplement the cyclone prediction process of current NWP models. • Cyclone Prediction is proposed using CNN, modified C4.5 and genetic algorithms. • CNN is used for feature extraction and genetic algorithm for hyper parameter tuning. • Modified C4.5 is proposed to solve the limitations of C4.5 decision tree algorithm. • Accuracy of the proposed model is significantly improved compared to the existing works. [ABSTRACT FROM AUTHOR]

Pathological slowing in the electroencephalogram (EEG) is widely investigated for the diagnosis of neurological disorders. Currently, the gold standard for slowing detection is the visual inspection of the EEG by experts, which is time-consuming and subjective. To address those issues, we propose three automated approaches to detect slowing in EEG: Threshold-based Detection System (TDS), Shallow Learning-based Detection System (SLDS), and Deep Learning-based Detection System (DLDS). These systems are evaluated on channel-, segment-, and EEG-level. The three systems perform prediction via detecting slowing at individual channels, and those detections are arranged in histograms for detection of slowing at the segment- and EEG-level. We evaluate the systems through Leave-One-Subject-Out (LOSO) cross-validation (CV) and Leave-One-Institution-Out (LOIO) CV on four datasets from the US, Singapore, and India. The DLDS achieved the best overall results: LOIO CV mean balanced accuracy (BAC) of 71.9%, 75.5%, and 82.0% at channel-, segment- and EEG-level, and LOSO CV mean BAC of 73.6%, 77.2%, and 81.8% at channel-, segment-, and EEG-level. The channel- and segment-level performance is comparable to the intra-rater agreement (IRA) of an expert of 72.4% and 82%. The DLDS can process a 30 min EEG in 4 s and can be deployed to assist clinicians in interpreting EEGs. [ABSTRACT FROM AUTHOR]

One of the major setbacks to the economy of a country is the production of fake currency. In recent past due to advancements in technologies in color printing, duplicating newer ways of faking the currency are coming into the picture. The problem has even risen in larger scale after demonetization in India and many fake curren- cies have entered the market. According to recent data, the Reserve Bank of India has estimated nearly around 2 trillion worth currency as counterfeit currency. This increase in fake currency has been a ma- jor problem, especially for a common person, and now that even the banks and ATM's are disbursing fake currency. Almost everyone from a vegetable seller to a businessman is wary of accepting currencies in denominations of 500 and 2000 because they look almost exactly like a real note. The only solution to this problem is fake currency detector machines which are widely used and are mostly available in banks but which is not reachable every time by the average citizen. By building this system we hope to build an easy and efficient way to identify fake currencies which can be of great help to the common citizen. The application would be easily accessible to common peo- ple. Not only identifying if a note is fake or not, but our system is also even capable of recognizing the currency scanned. We have per- formed currency recognition and verification using Transfer Learning on AlexNet. The idea proposed by our system is to capture the image of currency notes of domination's 100, 200, 500, 2000 through mobile and after processing tell if the currency is fake or not and check its denomination value. Verifying the currency has many applications in banks as they have to deal with counterfeit currency every day. Our system would be extremely useful for a person with a mobile phone to check the authenticity of his currency note. Recognizing the cur- rency note can be a useful feature for the visually impaired as there would also be a voice announcement on recognizing and verification of a currency note. [ABSTRACT FROM AUTHOR]