Dr.Deepika Pantola

EconVisor is an interactive time series analysis application designed to assist users in predicting Indian economic indicators such as GDP, sales, employment opportunities, and other relevant information. This prediction is tailored to the user’s selected industry type and desired future time frame. The application leverages time series analysis techniques to provide insights and forecasts specific to the Indian economic landscape, helping users make informed decisions based on anticipated… Show more

EconVisor is an interactive time series analysis application designed to assist users in predicting Indian economic indicators such as GDP, sales, employment opportunities, and other relevant information. This prediction is tailored to the user’s selected industry type and desired future time frame. The application leverages time series analysis techniques to provide insights and forecasts specific to the Indian economic landscape, helping users make informed decisions based on anticipated economic trends within their chosen sector and timeframe. This tool provides valuable insights into the
economic implications of different industries, supporting decision-makers in policy formulation, investment strategies, and resource allocation. In the research work, an extensive dataset of over 20 years’ time span is used. The dataset is integrated from 10 reputable organizations, including the National Association of Software and Services Companies (NASSCOM), the International Telecommunication Union (ITU), The World Bank, the Ministry of Tourism (MoT), the Federation of
Indian Chambers of Commerce and Industry (FICCI), Society of Indian Automobile Manufacturers (SIAM), The Indian Pharmaceutical Alliance (IPA), the Annual Building Construction Cost Index from 1981 to 2022, the Petroleum Planning and Analysis Cell (PPAC) of the Ministry of Petroleum and Natural Gas (MoPNG), the Government of India, and the Central Electricity Authority of India (CEA). In the proposed work, four statistical and Machine Learning (ML) models are applied such as Auto-regressive Integrated Moving Average (ARIMA), Random Forest (RF), Long-Short Term Memory (LSTM), and simple Recurrent Neural Networks (RNN). These models are chosen for their different strengths and capabilities, allowing users to select the most suitable model for their specific forecasting needs. The outcome shows that the RNN model performs better in comparison to other models. Show less

Crop production plays an important role in the advancement of a country. Hence, it is necessary to conserve and protect plants. Early detection of plant disease is crucial for the world economy and growth. This research presents the use of the PlantVillage dataset to diagnose plant illnesses using the CondenseNet (which is a Dynamic neural network) model. Static Neural Networks such as AlexNet, GoogleNet, VGG16, DenseNet121, and ResNet50 models are compared in order to assess CondenseNet's… Show more

Crop production plays an important role in the advancement of a country. Hence, it is necessary to conserve and protect plants. Early detection of plant disease is crucial for the world economy and growth. This research presents the use of the PlantVillage dataset to diagnose plant illnesses using the CondenseNet (which is a Dynamic neural network) model. Static Neural Networks such as AlexNet, GoogleNet, VGG16, DenseNet121, and ResNet50 models are compared in order to assess CondenseNet's model efficacy. Floating-point operations per second (FLOPs), model accuracy, and parameter count are among the evaluation parame-ters that are used in this study. The results show that by obtaining a higher accuracy of 99.20% with fewer FLOPs of 690.02M and a smaller number of parameters i.e., 3.77M, CondenseNet outperforms other models. CondenseNet's dynamic architecture uses a learned group convolutional technique and performs better than the static models. Because of its adaptability and ongoing learning capabilities, the model's ability to precisely identify and categorize a wide range of plant diseases has significant benefits for agriculture. By incorporating CondenseNet into farming practices, farmers may efficiently detect and cure crop illnesses, cut-ting losses and promoting sustainable farming practices. Show less