Intelligent data flows management for performance improvement of optical label switched network

Andrushchak, Volodymyr; Maksymyuk, Taras; Dumych, Stepan; Kaidan, Mykola; Urikova, Oksana

doi:10.1109/tcset.2018.8336396

Cited by 14 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the clinical data consists of multivariate time series of observations, it is easy to apply in LSTM. As a result of applying the LSTM model, it proved that the performance is superior to that of the conventional hand-designed model and multi-layer perceptron [3].…”

Section: Existing Researches About Research Datamentioning

confidence: 99%

See 1 more Smart Citation

Improving data quality using a deep learning network

Hwang

Lee

Jung

2020

IJEECS

View full text Add to dashboard Cite

<p>IoT data is collected in real time and is treated as highly reliable data because of its high precision. However, it often exhibits incomplete values for reasons such as sensor aging and failure, poor operating environment, and communication problems. The characteristics of IoT data transmitted with high precision and time series are suitable to use LSTM, which is one kind of RNN. In this paper, when applying LSTM to data quality improvement in IoT environment where data are collected simultaneously from several sensors, it is suggested that it is effective to construct LSTM individually for each sensor accuracy.</p>

show abstract

Section: Existing Researches About Research Datamentioning

confidence: 99%

“…IoT technology helps to create a more sophisticated virtual world by recording the real world more closely. Therefore, IoT technology is the next generation tool that transforms most of our everyday life and industry [1][2][3][4][5][6]. IoT is defined as a global network with an infrastructure that has self-configuring capabilities [7].…”

Section: Introductionmentioning

confidence: 99%

Improving data quality using a deep learning network

Hwang

Lee

Jung

2020

IJEECS

View full text Add to dashboard Cite

show abstract

“…Therefore, most recent studies have focused more on artificial intelligence (AI)-based techniques, which detect certain anomalies of data flows and prevent attacks without deep inspection of each packet. Among all AI-based solutions, the most promising are those based on deep learning, or more specifically deep neural networks [9][10][11][12]. A detailed survey of existing solutions based on deep learning was reported in [13].…”

Section: Introductionmentioning

confidence: 99%

Deep Semisupervised Learning-Based Network Anomaly Detection in Heterogeneous Information Systems

Lutsiv¹,

Maksymyuk²,

Beshley³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

The extensive proliferation of modern information services and ubiquitous digitization of society have raised cybersecurity challenges to new levels. With the massive number of connected devices, opportunities for potential network attacks are nearly unlimited. An additional problem is that many low-cost devices are not equipped with effective security protection so that they are easily hacked and applied within a network of bots (botnet) to perform distributed denial of service (DDoS) attacks. In this paper, we propose a novel intrusion detection system (IDS) based on deep learning that aims to identify suspicious behavior in modern heterogeneous information systems. The proposed approach is based on a deep recurrent autoencoder that learns time series of normal network behavior and detects notable network anomalies. An additional feature of the proposed IDS is that it is trained with an optimized dataset, where the number of features is reduced by 94% without classification accuracy loss. Thus, the proposed IDS remains stable in response to slight system perturbations, which do not represent network anomalies. The proposed approach is evaluated under different simulation scenarios and provides a 99% detection accuracy over known datasets while reducing the training time by an order of magnitude.

show abstract