Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Subject: search.filters.subject.LSTM

Search Results

Now showing 1 - 10 of 22
  • No Thumbnail Available
    Item
    Inner Attention Based bi-LSTMs with Indexing for non-Factoid Question Answering
    (Institute of Electrical and Electronics Engineers Inc., 2018) Sharma, A.; Harithas, C.
    In this paper, we focussed on non-factoid question answering problem using a bidirectional LSTM with an inner attention mechanism and indexing for better accuracy. Non factoid QA is an important task and can be significantly applied in constructing useful knowledge bases and extracting valuable information. The advantage of using Deep Learning frameworks in solving these kind of problems is that it does not require any feature engineering and other linguistic tools. The proposed approach is to extend a LSTM (Long Short Term Memory) model in two directions, one with a Convolutional layer and other with an inner attention mechanism, proposed by Bingning Wang, et al., to the LSTMs, to generate answer representations in accordance with the question. On top of this Deep Learning model we used an information retrieval model based on indexing to generate answers and improve the accuracy. The proposed methodology showed an improvement in accuracy over the referred model and respective baselines and also with respect to the answer lengths used. The models are tested with two non factoid QA data sets: TREC-QA and InsuranceQA. © 2018 IEEE.
  • No Thumbnail Available
    Item
    Indian stock market prediction using deep learning
    (Institute of Electrical and Electronics Engineers Inc., 2020) Maiti, A.; Shetty D, P.
    In this paper, we predict the stock prices of five companies listed on India's National Stock Exchange (NSE) using two models- the Long Short Term Memory (LSTM) model and the Generative Adversarial Network (GAN) model with LSTM as the generator and a simple dense neural network as the discriminant. Both models take the online published historical stock-price data as input and produce the prediction of the closing price for the next trading day. To emulate the thought process of a real trader, our implementation applies the technique of rolling segmentation for the partition of training and testing dataset to examine the effect of different interval partitions on the prediction performance. © 2020 IEEE.
  • No Thumbnail Available
    Item
    Intelligent Code Completion
    (Springer Science and Business Media Deutschland GmbH, 2021) Waseem, D.; Pintu; Chandavarkar, B.R.
    Auto complete suggestions for IDEs are widely used and often extremely helpful for inexperienced and expert developers alike. This paper proposes and illustrates an intelligent code completion system using an LSTM based Seq2Seq model that can be used in concert with traditional methods (Such as static analysis, prefix filtering, and tries) to increase the effectiveness of auto complete suggestions and help accelerate coding. © 2021, Springer Nature Switzerland AG.
  • No Thumbnail Available
    Item
    Covid-19 Fake News Detector using Hybrid Convolutional and Bi-LSTM Model
    (Institute of Electrical and Electronics Engineers Inc., 2021) Surendran, P.; Balamuralidhar, B.; Kambham, H.; Anand Kumar, M.
    Fake news is essentially incorrect and deceiving information presented to the public as news with the motive of tarnishing the reputations of individuals and organizations. In today's world, where we are so closely connected due to the internet, we see a boom in the development of social networking platforms and, thus, the amount of news circulated over the internet. We must keep in mind that fake news circulated on social media and other platforms can cause problems and false alarms in society. In some cases, false information can cause panic and have a dangerous effect on society and the people who believe it to be true. Along with the virus, the Covid-19 pandemic has also brought on distribution and spreading of misinformation. Claims of fake cures, wrong interpretations of government policies, false statistics, etc., bring about a need for a fact-checking system that keeps the circulating news in control. This work examines multiple models and builds an Artificial Intelligence system to detect Covid-19 fake news using a deep neural network. © 2021 IEEE.
  • No Thumbnail Available
    Item
    Long Short Term Memory Networks for Lexical Normalization of Tweets
    (Institute of Electrical and Electronics Engineers Inc., 2021) Nayak, P.; Praueeth, G.; Kulkarni, R.; Anand Kumar, M.
    Lexical normalization is converting a non-standard text into a standard text that is more readable and universal. Data obtained from social media sites and tweets often contain much noise and use non-canonical sentence structures such as non-standard abbrevlatlons, skipping of words, spelling errors, etc. Hence such data needs to be appropriately processed before it can be used. The processing can be done by lexical normalization, which reduces randomness and converts the sentence structure to a predefined standard. Hence. lexical normalization can help in improving the performance of systems that use user-generated text as inputs. There are several ways to perform lexical normalization, such as dictionary lookups, most frequent replacements, etc. However, VVe aim to explore the domain of deep learning to find approaches that can be used to normalize texts lexically. © 2021 IEEE.
  • No Thumbnail Available
    Item
    A Comparative Study of Deep Learning Models for Word-Sense Disambiguation
    (Springer Science and Business Media Deutschland GmbH, 2022) Jadiya, A.; Dondemadahalli Manjunath, T.; Mohan, B.R.
    Word-sense disambiguation (WSD) has been a persistent issue since its introduction to the community of natural language processing (NLP). It has a wide range of applications in different areas like information retrieval (IR), sentiment analysis, knowledge graph construction, machine translation, lexicography, text mining, information extraction, and so on. Analysis of the performance of deep learning algorithms with different word embeddings is required to be done since various deep learning models are deployed for the task of disambiguation of word sense. In this paper, comparison of several deep learning models like CNN, LSTM, bidirectional LSTM, and CNN + LSTM is done with trainable as well as pretrained GloVe embeddings with common preprocessing methods. Performance evaluation of temporal convolutional network (TCN) model is done along with the comparison of the same with the formerly mentioned models. This paper shows that using GloVe embeddings may not result in better accuracy in the case of word-sense disambiguation, i.e., trainable embeddings perform better. It also includes a framework for evaluating deep learning models for WSD and analysis of the usage of embeddings for the same. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Price Prediction of Agricultural Products Using Deep Learning
    (Springer Science and Business Media Deutschland GmbH, 2022) Kankar, M.; Anand Kumar, A.M.
    Every field in the world is undergoing a significant change because of the influence of technology. The agricultural sector of the Indian economy needs more technological support for its development and growth in India. Price prediction of agricultural products helps ensure that the farmers either get good returns or recover their investments. Hence, the characteristics of deep neural networks such as CNN and deep learning models can be used in predicting prices. A convolution neural network-based model can indirectly predict fruits and vegetable prices by classifying images to their variety. Deep learning models such as long short-term memory (LSTM) and bidirectional LSTM (BiLSTM) can also help predict the market price of agricultural products. Fruits and vegetable prices mainly depend on a few things, variety, quality, and market rate. We use the CNN model to deal with variety and quality, different varieties of a single fruit or vegetable having different prices, followed by prediction using LSTM and bidirectional LSTM to deal with market price prediction in a volatile market. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Stock Price Prediction Using Corporation Network and LSTM
    (Institute of Electrical and Electronics Engineers Inc., 2022) Bisarya, U.; Parekh, V.; Bhattacharjee, S.
    The problem of stock price prediction is addressed in this work by incorporating additional stock-related factors and using them to model relations between stocks. We have built a corporation network that displays the relation between stocks based on common shareholders and their shareholding ratio. The network is constructed by including all involved corporations based on investment facts from the real market. In this work, we have used a deep learning-based model, long short-term memory (LSTM) for the prediction of stock prices. We have considered node embedding methods that can store the properties of the nodes in the network, and use this information to make the model more accurate. The results produced by an initial and a revised LSTM model are compared, which have achieved a minimum mean average percentage error (MAPE) value of 4.121% for the initial LSTM model, and 1.788% for the revised LSTM model. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Solar Irradiance forecasting using Recurrent Neural Networks
    (Institute of Electrical and Electronics Engineers Inc., 2022) Shekar, D.D.; Hiremath, A.C.; Keshava, A.; Vinatha Urundady, U.
    Solar irradiance being the chief constituent of the solar power extraction is dominated by the atmospheric conditions. Prediction of irradiance data is highly sought after in the field of forecasting and predictive maintenance. For this purpose various machine learning methods are being used to improve the accuracy of the forecasted value. This paper aims at prediction of solar irradiance using Recurrent Neural Networks (RNN) using Long Short Term Memory (LSTM) architecture. Using different combinations of input in the supervised learning method the accuracy for single as well as multiple time steps are determined. The results are shown in the form of evaluation metric as well as the forecasted values and actual value comparison. It is seen that for single time step prediction the LSTM RNN puts out highly accurate values but error for higher time steps prediction accumulates in a compounded manner. It is also observed that using time based models along with the inputs increases the accuracy of the forecasted values. © 2022 IEEE.
  • No Thumbnail Available
    Item
    IoT-based Human Activity Recognition Models based on CNN, LSTM and GRU
    (Institute of Electrical and Electronics Engineers Inc., 2022) Kolkar, R.; Singh Tomar, R.P.; Vasantha, G.
    Smartphones' ability to generate data with their inbuilt sensors has made them used for Human Activity Recognition. The work highlights the importance of Human Activity Recognition (HAR) systems capable of sensing human activities like the inertial motion of a human body. The sensors are worn on a body part and tracked from whole-body motions and monitoring. Real-time signal processing is used to sense human body movements using wearable sensors. The work aims to provide opportunities for promising health applications using IoT. There are many challenges to recognising human activities, including accuracy. This work analyses Human Activity recognition concerning CNN, LSTM, and GRU deep learning models to improve the accuracy of the human activity recognition in the UCI-HAR and WISDM datasets. The comparative analysis shows promising results for Human activity recognition. © 2022 IEEE.