Kshitij Tripathi - Academia.edu (original) (raw)
Uploads
Papers by Kshitij Tripathi
International Journal of Innovative Technology and Exploring Engineering, 2020
Convolutional Neural Networks (CNN) are very common now especially in the image classification ta... more Convolutional Neural Networks (CNN) are very common now especially in the image classification tasks as CNN’s have better classification accuracy than other techniques available in image classification. Another type of CNN called as Residual Neural Networks (RESNET) are gaining popularity because of better accuracy than normal CNN because of residual block available in it. In the present article the RESNET architecture is used for image classification on CIFAR-10 dataset using cross-validation approach that reflects a consistently better accuracy on the above dataset.
International Journal of Computer Sciences and Engineering, 2018
Asian Journal of Computer Science and Technology
The Document classification system is the field of data mining in which the format of data is bas... more The Document classification system is the field of data mining in which the format of data is based on bag of words (BoW) or document vector model and the task is to build a machine which after successfully learn the characteristic of given data set, predicts the category of the document to which the word vector belongs. In this approach document is represented by BoW where every single word is used as feature which occurs in a document. The proposed article presents artificial neural network approach which is hybrid of n-fold cross validation and training-validation-test approach for classification of data.
INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY
The classification of data is an important field of data mining comes under supervised learning. ... more The classification of data is an important field of data mining comes under supervised learning. In this approach classifier is trained on the pre-categorized data thereafter tested on unseen part called test data to evaluate it. The other related field clustering comes under unsupervised learning is used for categorizing data into different clusters or assigning labels to them which are previously unknown. In this article the classification of data is done and we are using artificial neural networks (ANN) for pre-processing i.e. removing noisy instances through novel clustering technique and then classifying pre-processed data through ANN. Both are exhaustive approaches. The da set used in this article is PIMA Indian diabetes data set ta available on UCI repository.
International Journal of Computer Sciences and Engineering
International Journal of Innovative Technology and Exploring Engineering, 2020
Convolutional Neural Networks (CNN) are very common now especially in the image classification ta... more Convolutional Neural Networks (CNN) are very common now especially in the image classification tasks as CNN’s have better classification accuracy than other techniques available in image classification. Another type of CNN called as Residual Neural Networks (RESNET) are gaining popularity because of better accuracy than normal CNN because of residual block available in it. In the present article the RESNET architecture is used for image classification on CIFAR-10 dataset using cross-validation approach that reflects a consistently better accuracy on the above dataset.
International Journal of Computer Sciences and Engineering, 2018
Asian Journal of Computer Science and Technology
The Document classification system is the field of data mining in which the format of data is bas... more The Document classification system is the field of data mining in which the format of data is based on bag of words (BoW) or document vector model and the task is to build a machine which after successfully learn the characteristic of given data set, predicts the category of the document to which the word vector belongs. In this approach document is represented by BoW where every single word is used as feature which occurs in a document. The proposed article presents artificial neural network approach which is hybrid of n-fold cross validation and training-validation-test approach for classification of data.
INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY
The classification of data is an important field of data mining comes under supervised learning. ... more The classification of data is an important field of data mining comes under supervised learning. In this approach classifier is trained on the pre-categorized data thereafter tested on unseen part called test data to evaluate it. The other related field clustering comes under unsupervised learning is used for categorizing data into different clusters or assigning labels to them which are previously unknown. In this article the classification of data is done and we are using artificial neural networks (ANN) for pre-processing i.e. removing noisy instances through novel clustering technique and then classifying pre-processed data through ANN. Both are exhaustive approaches. The da set used in this article is PIMA Indian diabetes data set ta available on UCI repository.
International Journal of Computer Sciences and Engineering