id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-193910-7p3f3znj	Zhang, Xiangxie	Comparing Machine Learning Algorithms with or without Feature Extraction for DNA Classification	2020-11-01		.txt	text/plain	7724	436	59	In the experiments, the performances of feature extraction using primers and random DNA sequences will be compared to several other machine learning approaches. Finally, three state-of-the-art methods, namely a con-volutional neural network (CNN), a deep neural network (DNN), and an N-gram probabilistic model, which were fed the unprocessed DNA sequences without prior feature extraction, were tested. Different machine learning algorithms will be trained and tested using each set of feature vectors in the experiments. For each data set, the results of all six machine learning algorithms using the random DNA sequence feature extraction method are presented in Table ( 8) containing mean accuracy and standard deviation over the ten folds of the cross-validation. It can be concluded that the Levenshtein distance feature extraction yields the best and most consistent results across the six different machine learning algorithms when the distance between a primer and a DNA sequence is taken.	./cache/cord-193910-7p3f3znj.txt	./txt/cord-193910-7p3f3znj.txt