WITHDRAWN: A Review of Machine Learning Algorithms for Identification and Classification of Non-Functional Requirements

Binkhonain, Manal; Zhao, Liping

doi:10.1016/j.eswa.2019.02.031

Cited by 16 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various natural language processing (NLP) techniques are available for text pre-processing. Some commonly used NLP techniques for requirements classification are described in a survey by Binkhonain and Zhao (2019).…”

Section: Text Pre-processingmentioning

confidence: 99%

“…Most existing ML approaches for requirements classification, such as those included in a recent survey (Binkhonain and Zhao, 2019), do not meet our comparison criteria. Here we introduce the three selected approaches that meet our criteria.…”

Section: Three Related ML Approaches For Evaluating Hc4rcmentioning

confidence: 99%

“…We make our code and data publically available so that further replication or reproduction of our approach can be carried out. We recognize that the lack of the gold standard labelled requirements datasets has been an open challenge to using ML approaches for RE tasks (Binkhonain and Zhao, 2019).…”

Section: Threats To Validitymentioning

confidence: 99%

“…As shown above, requirements are stated in natural language (Zhao et al, 2021), which means that requirements documents are text documents. Consequently, ML approaches to text classification (Sebastiani, 2002;Kowsari et al, 2019) can be adapted to requirements classification, whereby we train a requirements classifier with a set of labelled requirements examples (i.e., the training set) (Binkhonain and Zhao, 2019). In other words, ML approaches to requirements classification are based on supervised text classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A machine learning approach for hierarchical classification of software requirements

Binkhonain

Zhao

2023

Machine Learning with Applications

View full text Add to dashboard Cite

Section: Text Pre-processingmentioning

confidence: 99%

Section: Three Related ML Approaches For Evaluating Hc4rcmentioning

confidence: 99%

Section: Threats To Validitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A machine learning approach for hierarchical classification of software requirements

Binkhonain

Zhao

2023

Machine Learning with Applications

View full text Add to dashboard Cite

“…And so the automatic classification of documents comes in handy. Being a subfield of Artificial Intelligence, Machine Learning is capable of solving various problems in the real world by furnishing learning ability to the computer [1]. ML has matured from the efforts of researchers to make computers assemble knowledge and mimic the human brain.…”

mentioning

confidence: 99%

A Real Time Intelligent Image Based Document Classification Using CNN and SVM

Potharaju,

Tambe,

Tambe

2023

Preprint

View full text Add to dashboard Cite

Artificial Neural Network with multilayers is referred to as Deep Learning. As it is able to handle large amount of data, deep learning has become very popular in recent years. Classification, object tracking, estimation of different poses, text detection & recognition are various fields where deep learning is applied. Convolutional Neural Network(CNN) being one of the most important deep learning methods, has surpassed the traditional methods of classification.This paper presents a Supervised CNN, which is a machine learning algorithm used to classify images into different categories. In a few online registration processes, documents like Aadhaar,PAN,mark sheets etc need to be uploaded. Manual mistakes during upload can be committed as in; in place of Aadhar,some irrelevant document can be uploaded. Manual intervention to detect such mistakes is tedious.Hence we present an Intelligent Image based Document Classification using Machine Learning, where we have applied CNN to predict if the uploaded document is valid or invalid. The system is implemented on 900 images among which 500 are Aadhar images and remaining are PAN. The generated model recorded 90% accuracy to predict the Aadhar document and 93% in case of PAN.The same dataset is compared with Support Vector Machine(SVM) which displayed 88.88% overall accuracy.

show abstract

Software Requirements Classification and Prioritisation Using Machine Learning

Talele

Phalnikar

2020

Machine Learning for Predictive Analysis

View full text Add to dashboard Cite

WITHDRAWN: A Review of Machine Learning Algorithms for Identification and Classification of Non-Functional Requirements

Cited by 16 publications

References 17 publications

A machine learning approach for hierarchical classification of software requirements

A machine learning approach for hierarchical classification of software requirements

A Real Time Intelligent Image Based Document Classification Using CNN and SVM

Software Requirements Classification and Prioritisation Using Machine Learning

Contact Info

Product

Resources

About