Network Forensic Analysis Article Swipe

MAKE IMPACT

R. C. Joshi , Emmanuel S. Pilli · YOU? · · 2016 · Open Access · · DOI: https://doi.org/10.1007/978-1-4471-7299-4_6

Network forensic analysis is the activity performed by investigators to reconstruct the network activity over a period. The approach is commonly used to investigate individuals suspected of crimes and reconstruct a chain of events during a network-based activity tool. Machine learning is one of the popular approaches used to analyze the network events that adds computer the power to adopt and react according to the situation. These algorithms are used to build models and make predictions based on previous experiences. Michalski et al. (Machine learning: an artificial intelligence approach. Springer Science & Business Media, Berlin, 2013) precisely defined as a computer program is learning from experience E and increasing its performance P. Machine learning algorithms are used widely in data mining, pattern classification, medical fields, and intrusion detection for analyzing network traffic. It can be broadly classified into three categories as supervised, unsupervised, and semi-supervised. Supervised machine learning algorithms are those algorithms which are used to learn patterns from labeled input data sets. These algorithms build classifier model from these inputs and then that model is used to classify unknown labels. Algorithms like naive Bayes, decision tree, SVM, and KNN come under this category. In unsupervised algorithms unlabeled data set is provided for building model, and the data is categorized according to similar properties of same class data and different properties for different class data. These algorithms are also called clustering techniques. Examples of unsupervised machine learning algorithms are DBSCAN, one-class SVM, K-means, etc. Semi-supervised algorithm combines the features of both supervised and unsupervised algorithms. They provide high performance for unlabeled data set.

Type

book-chapter

Language

en

Landing Page

https://doi.org/10.1007/978-1-4471-7299-4_6

OA Status

hybrid

Cited By

1

References

40

Related Works

10

OpenAlex ID

https://openalex.org/W2558000730

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W2558000730

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.1007/978-1-4471-7299-4_6

Digital Object Identifier

Title

Network Forensic Analysis

Work title

Type

book-chapter

OpenAlex work type

Language

en

Primary language

Publication year

2016

Year of publication

Publication date

2016-01-01

Full publication date if available

Authors

R. C. Joshi, Emmanuel S. Pilli

List of authors in order

Landing page

https://doi.org/10.1007/978-1-4471-7299-4_6

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

hybrid

Open access status per OpenAlex

OA URL

https://doi.org/10.1007/978-1-4471-7299-4_6

Direct OA link when available

Concepts

Artificial intelligence, Machine learning, Computer science, Unsupervised learning, Support vector machine, Decision tree, Cluster analysis, Supervised learning, Semi-supervised learning, Naive Bayes classifier, Classifier (UML), One-class classification, Instance-based learning, Data mining, Artificial neural network

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2024: 1

Per-year citation counts (last 5 years)

References (count)

40

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload