za101 Goto Github PK

30daysofnlp

Saving my 30 days of NLP work in this repository

automatic-number-plate-recognition-using-random-forest-classifier

Automatic Number Plate Recognition System is a mass surveillance embedded system that recognizes the number plate of the vehicle. This system is generally used for traffic management applications. It should be very efficient in detecting the number plate in noisy as well as in low illumination and also within required time frame. This paper proposes a number plate recognition method by processing vehicle’s rear or front image. After image is captured, processing is divided into four steps which are Pre- Processing, Number plate localization, Character segmentation and Character recognition. Pre-Processing enhances the image for further processing, number plate localization extracts the number plate region from the image, character segmentation separates the individual characters from the extracted number plate and character recognition identifies the optical characters by using random forest classification algorithm. Experimental results reveal that the accuracy of this method is 90.9 %.

chemical-compound-classification-using-deep-learning

Classified chemical compounds using multi-layer perceptron.

deep-learning-model-for-fire-detection

dockermnist

efficient-vision-transformer-with-linear-complexity-

haberman-survival-dataset-eda

image-masking-aadhar-card-

Project to mask the first 8 digits (out of 12 digits) of the Aadhar Card using OpenCV.

modified-volo-performs-95.528-on-cifar100-with-27m

quora-question-pair-similarity

recommendation-system-content-and-collaborative-based-

Designed the content and the collaborative based recommendation system using Deep Learning and Cosine Similarity.

satoshi-nakamoto-marketplace

semantic-search-engine

sentiment-analysis-on-imdb-movie-reviews

socrates-coach

stack-overflow-tag-prediction

stock-market-prediction-using-a-hybrid-model

Stock market prediction is important topic in economics and finance which has garnered the interest of researchers. This paper attempts to explore the usage of hybrid model to predict stock market movements. The data under con- sideration was sourced from Quandl, a repository that provides data related to the stock market for a wide variety of companies, and in order to forecast the prices of said stocks in the future, ensemble machine learning methods together with ARIMA for feature prediction have been employed. Hybrid approach for predic- tion stock price is proposed. Comparisons among ensemble learning algorithms are discussed, and interesting results has been obtained and future possibilities are touched upon in this paper. Intensive testing was done by gathering various stock market data from various sectors to explore robustness of the proposed model.

usl

volo-v1