Skripsi Prediksi Harga Saham Menggunakan Deep Learning LSTM oleh Gesang Paudra Jaya

Heart disease is still a major worldwide health concern since it is one of the leading causes of mortality and morbidity in India. Early and precise diagnosis of heart disease can save lives and reduce medical costs. Conventional diagnostic methods, however, are often expensive and need specific equipment and expertise.

Image captioning using different deep learning techniques

Abstractive Text summarization using deep learning.

Image captioning using LSTM attention

Project Based Learning App Code For Sign To Text Translation System Using Arabic Sign Language

A machine learning project that predicts the future price of Ethereum (ETH) using the price data gathered from coincodex.com.

Projet de Data Science, réalisé dans le cadre de ma formation à l'ICAM. Étude de la base de données Open Food Facts et classification des allergènes en utilisant plusieurs modèles de machine learning, de l'arbre de décision au réseau de neurones récurrent LSTM.

MatLab scripts for performing a sensitivity analysis of LSTM networks for fall detection wearable sensors based on the SisFall dataset

This generates a concise and contextual summary for a given cricket match video utilizing only visual information

Deep convolutional and LSTM feature extraction approach with 784 features.

Sipaling is a web application that predicts stock prices using an LSTM deep learning model

In the IBM Advanced Data Science specialization, an interactive real-time web application was developed using LSTM networks in TensorFlow to predict stock market trends for global companies.

This project develops sentiment classification models for IMDB reviews using shallow RNN, unidirectional LSTM, and bidirectional LSTM. It employs GloVe embeddings, evaluates performance with accuracy, precision, recall, and F1 score, and aims to assess the impact of LSTM layers on model effectiveness.

This project aims to predict the next user purchase based on a sequence of past transactions. Using a combination of LSTM and SimpleRNN layers in a neural network, the model processes encoded purchase sequences and predicts future buying behavior, leveraging a synthetic dataset of 47 e-commerce platforms.

lstm based language modelling (next-word prediction)

LLM Supported SEC Report Analyzer Chat Assistant

Fingers coordinates prediction using LSTM neural network

Ondokuz Mayıs Üniversitesi Bilgisayar Mühendisliği Bitirme Projesi

Monitoring the dynamic pricing scheme for QoS in LTE networks