2019 16th International Bhurban Conference on Applied Sciences and Technology (IBCAST) 2019
DOI: 10.1109/ibcast.2019.8667245
|View full text |Cite
|
Sign up to set email alerts
|

Classical and Deep Learning Classifiers for Anomaly Detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
11
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(11 citation statements)
references
References 2 publications
0
11
0
Order By: Relevance
“…Similarly, to pump and dump mani-pulations, the main goal is to artificially drive the stock price up to sell for a higher profit. Deep learning approaches to this problem were introduced in [1] [7] to find an innovative solution to detect stock market manipulations. A deep general adversarial network (GAN) approach was first introduced in [1] and it showed a promise in detecting pump and dump manipulations.…”
Section: Stock Market Fraudmentioning
confidence: 99%
See 1 more Smart Citation
“…Similarly, to pump and dump mani-pulations, the main goal is to artificially drive the stock price up to sell for a higher profit. Deep learning approaches to this problem were introduced in [1] [7] to find an innovative solution to detect stock market manipulations. A deep general adversarial network (GAN) approach was first introduced in [1] and it showed a promise in detecting pump and dump manipulations.…”
Section: Stock Market Fraudmentioning
confidence: 99%
“…However, the solution was limited only to detect this one type of manipulation and had a drop-in accuracy when executed on unseen data. A 10-layer deep learning approach called Variational Auto Encoder was implemented in [7], highlighting the ability to detect anomalies without needed a labeled dataset. This solution did not perform as well as some supervised approaches as it has a high False Positive Rate.…”
Section: Stock Market Fraudmentioning
confidence: 99%
“…Activation functions are used to bound the outputs of this layer and to provide a given behavior, e.g., non-linear [15]. Equation 1shows the general formulation of this kind of layer: (1) in which l refers to the current layer, i and j are the indexes of the elements of the previous and current layers, respectively, is a set of input maps, k is the weight matrix of the i-th convolutional kernel of the l -th layer applied to the j-th input feature map. b is the bias.…”
Section: A Convolutional Neural Networkmentioning
confidence: 99%
“…Anomaly detection has gained importance in many applications, and it can be applied to multiple domains, e.g., fraud detection [1], network security [2], among others. It consists of identifying non-conforming patterns (anomalies) regarding an expected behavior [3].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation