Internet Traffic Data Research Articles

5GT-GAN-NET: Internet Traffic Data Forecasting With Supervised Loss Based Synthetic Data Over 5G

5GT-GAN-NET: Internet Traffic Data Forecasting With Supervised Loss Based Synthetic Data Over 5G

Hybrid Approach with Membership-Density Based Oversampling for handling multi-class imbalance in Internet Traffic Identification with overlapping and noise

Internet Traffic identification is a crucial method for monitoring Internet application activities and is essential for Internet management and security. Internet traffic data typically displays imbalanced distributions. The uneven distribution of instances in each class indicates the class imbalance problem. This problem can cause a decrease in classification performance because the classifier assumes the dataset has a balanced class distribution. Internet Traffic Identification dataset is often accompanied by overlapping and noise. The hybrid approach to handling class imbalances involving data-level and ensemble-based approaches is usually chosen to overcome this problem. Data-level with oversampling using SMOTE is the choice because of its ability to synthesize new samples for minority classes. However, SMOTE-generated samples tend to be noisy and overlap with the majority of samples. This research proposes the application of a Hybrid Approach with Membership-density-based Oversampling to tackle this challenge. This research emphasizes the importance of applying membership degrees in determining samples that will group samples into safe, overlapping, and noisy areas. Then, top samples will be selected based on density ratio, stability, and score for safe and overlapping safe areas. The study findings that the proposed method effectively addresses multi-class imbalances in six Internet Traffic Identification datasets, yielding slightly improved average accuracy, FbMeasur, and class balance accuracy results compared to other testing methods, though the difference is not statistically significant. The noise and overlapping scenes experiments demonstrate that the average accuracy obtained is superior, showing a considerable difference compared to all test methods.

A low-rank and sparse enhanced Tucker decomposition approach for tensor completion

In this paper, we introduce a unified low-rank and sparse enhanced Tucker decomposition model for tensor completion. Our model possesses a sparse regularization term to promote a sparse core of the Tucker decomposition, which is beneficial for tensor data compression. Moreover, we enforce low-rank regularization terms on factor matrices of the Tucker decomposition for inducing the low-rankness of the tensor with a cheap computational cost. Numerically, we propose a customized splitting method with easy subproblems to solve the underlying model. It is remarkable that our model is able to deal with different types of real-world data sets, since it exploits the potential periodicity and inherent correlation properties appeared in tensors. A series of computational experiments on real-world data sets, including internet traffic data sets and color images, demonstrate that our model performs better than many existing state-of-the-art matricization and tensorization approaches in terms of achieving higher recovery accuracy.

MF-Net: Multi-frequency intrusion detection network for Internet traffic data

The rapid growth of Internet technology renders intrusion detection an important research topic in the field of pattern recognition. Considering that traffic data relate to not only temporal information, but also attack frequency, this paper presents a novel deep learning framework termed the multi-frequency intrusion detection network (MF-Net). MF-Net regards the pattern of Internet traffic as a superposition of sequential data with various frequencies, and is able to recognize the multi-frequency nature of network traffic data. The core of MF-Net is the multi-frequency LSTM (MF-LSTM) and multi-frequency transformer (MF-Transformer) module, both of which consist of high-frequency and low-frequency layers. In comparison with other state-of-the-art approaches on 4 public datasets, namely UNSW-NB15, KDD Cup 99, NSL-KDD and CICIDS 2017, as well as an IPv6 traffic dataset we created, MF-Net has shown better result in both binary and multi-class classification, which demonstrates the superiority of MF-Net over other compared approaches on network traffic intrusion detection.

Analyzing Unorganized Data: A Study on Internet Traffic Using Informatica

Abstract: The exponential growth of internet traffic has led to the need for advanced tools and techniques for analyzing network traffic in IT divisions. This research paper explores the use of Informatica, powerful data integration and transformation tool, for analyzing internet traffic data. Specifically, the paper focuses on the use of IP, source, and destination addresses as key parameters for analyzing internet traffic in IT divisions. The paper describes the process of creating an Informatica mapping file for processing internet traffic data, and presents the results of an analysis of internet traffic data collected from a sample IT division. The findings of the research demonstrate the effectiveness of using Informatica for analyzing internet traffic in IT divisions and provide insights into the patterns of internet traffic in such settings.

Impact on online research on celebrities' uncommon diseases: the curious case of Justin Bieber and Ramsay Hunt syndrome.

We investigated how to use Internet user searches to gauge the impact of a celebrity illness on global public interest. The study design is cross-sectional. Data on Internet searches were obtained from Google Trends (GT) for the period between 2017-2022 using the search words "Ramsay Hunt syndrome" (RHS), "Ramsay Hunt syndrome type 2," "Herpes zoster," and "Justin Bieber." The frequency of specific page views for "Ramsay Hunt syndrome," "Ramsay Hunt syndrome type 1," Ramsay Hunt syndrome type 2," Ramsay Hunt syndrome type 3," "Herpes zoster," and "Justin Bieber" were collected via a Wikipedia analysis tool that shows the number of times a specific page is viewed. Statistical analyses were performed using the Pearson (r) and Spearman's rank correlation coefficient (rho). GT data, in 2022, show a strong correlation for Justin Bieber and RHS or RHS type 2 (r = 0.75); similarly, Wikipedia data show a strong correlation for Justin Bieber and the others explored terms (r > 0.75). Furthermore, the correlation was strong between GT and Wikipedia for RHS (rho = 0.89) and RHS type 2 (rho = 0.88). The peak search times for the GT and Wikipedia pages were during the same period. Useful new tools and analyses of Internet traffic data may be effective in assessing the impact of announced celebrity uncommon illnesses on global public interest.

A parallel low rank matrix optimization method for recovering internet traffic network data via link flow measurement

Internet traffic network data recovery via link flow measurement is an important problem in wireless communication network, but as the problem scale grows rapidly, it is quite challenging to give consideration to both recovery accuracy and computational cost. We construct a novel parallel low-rank matrix optimization model to accurately and quickly recover internet traffic network data via link flow measurement. This model takes full advantage of the low-rankness of traffic network data. Then, an inexact symmetric Gauss–Seidel-based majorized semi-proximal alternating direction method of multipliers is proposed to solve the model. Our method is proved to be globally convergent, and the numerical experiments on the classical Abilene and GÉANT datasets indicate that the performance of our method for fast and accurate recovery of traffic network data is better than that of the state-of-the-art methods. Specially, the numerical results on the large-scale HOD dataset demonstrates that our method is quite suitable for traffic network data recovery problem from realistic scenarios.

Investigation of the Chemical Content and User Comments on Facial Cleansing Products.

The goal of skin cleansing is to reduce sebum and exogenous pollutants and control the skin microbiome. Surfactants in cleansers dissolve hydrophobic substances in an aqueous phase and allow them to move away from the skin's surface. The negative effect of surfactants on the skin barrier can be reduced by changing the solution properties. As a dermatologist in the group of patients we encounter in our clinical dermatology practice who recommends face wash products, we thought of conducting this research in order to determine the product contents to identify the products with the highest user satisfaction so that we can easily make the selection of the right product and direct the patients correctly. We planned to conduct cross-sectional research. Ten facial cleansing products sold on the most popular website that sells dermo-cosmetic products online in our country were selected. In the selection of the website, the criterion of having the most Internet traffic was sought. Internet traffic data was obtained from www.similarweb.com. The classification of the identified key ingredients according to their chemical properties was used on https://cosmeticanalysis.com. Reviews for each of the ten products in total were examined from the most recent date to the oldest. We detected 87 different chemicals in ten different products. These basically consisted of surfactants, emollients (moisturizers), emulsifiers (cleansers), buffering (denaturators), herbal ingredients-antioxidants, solvents, and moisturizers. A total of 30 different surfactants were identified as the main cleaning ingredient in the examined products. Counterfeit product reporting was especially high on expensive products. No correlation was found between the number of surfactants in the products and the positive effects, such as cleansing and acne reduction and increase, and the negative effects, such as dryness, redness, burning, and smoothing/softening (p>0.05). There was a negative correlation between the cleansing effect of the products and the improvement and worsening of acne(p<0.05, p<0.001, respectively). The bottom line is that a good facial cleansing product doesn't have to contain a lot of chemicals and surfactants. It should be kept in mind that expensive products may be counterfeit and should question whether the product is original or not on the local product detection system from the barcode number.

Robust low-rank tensor completion via new regularized model with approximate SVD

Tensor recovery with tensor singular value decomposition has recently become increasingly popular in the computer vision field. One of the most important subproblem is the low-rank tensor completion with the partial and/or corrupted observations. In this paper, we propose a new low-rank tensor completion model with the robust form by minimizing the reconstruction error of approximate SVD and the γ nuclear norm of the lower triangular tensor, and then give their equivalent forms with the tensor slices in the Fourier domain. The efficient iterative algorithm is developed to solve the minimization problem, and the convergence of the algorithm is discussed. Experimental results on real-world visual data and the internet traffic data show that the proposed approaches outperform the state of the art algorithms in both (robust) recovery accuracy and computing time.

Neighbor Graph Based Tensor Recovery For Accurate Internet Anomaly Detection

Detecting anomalous traffic is a crucial task for network management. Although many anomaly detection algorithms have been proposed recently, constrained by their matrix-based traffic data model, existing algorithms often suffer from low detection accuracy. To fully utilize the multi-dimensional information hidden in the traffic data, this paper uses the tensor model for more accurate Internet anomaly detection. Only considering the low-rank linearity features hidden in the data, current tensor factorization techniques would result in low anomaly detection accuracy. We propose a novel Graph-based Tensor Recovery model (Graph-TR) to well explore both low-rank linearity features as well as the non-linear proximity information hidden in the traffic data for better anomaly detection. We encode the non-linear proximity information of the traffic data by constructing nearest neighbor graphs and incorporate this information into the tensor factorization using the graph Laplacian. Moreover, to facilitate the quick building of neighbor graph, we propose a nearest neighbor searching algorithm with the simple locality-sensitive hashing (LSH). Besides only detecting random anomalies, our algorithm can also effectively detect structured anomalies that appear as bursts. We have conducted extensive experiments using Internet traffic trace data Abilene and GÈANT. Compared with the state of art algorithms on matrix-based anomaly detection and tensor recovery approach, our Graph-TR can achieve higher Accuracy and Recall.

Modelling Internet Traffic Streams with Ga/M/1/K Queuing Systems under Self-similarity

High-intensity concurrent arrivals of request packets in Internet traffic can cause dependence of event-to-event-times of the requests being served, which causes non-memoryless, modelled with heavy-tail distributions unlike common known traffics. The performance of Internet traffic can be examined using analytical models for the purpose of optimizing the system to reduce its operating costs. Therefore, our study examined a Ga/M/1/K Internet queue class (Gamma arrival processes, Ga; with memoryless-Poisson service process, M; a single server, 1, and K waiting room) and proposed specific derivations of its performance indicators. Real-life data of a corporate organisation Internet server was monitored at both peak and off-peak periods of its usage for Internet traffic data analysis. The minimum ‘0’ in the arrival process indicates self-similarity and was assessed using Hurst parameter, H, and their (standard deviation). ‘H’ &gt; 0.5 arrival process in the peak period only, indicates self-similarity. Performance of Ga/M/1/K was compared with various queuing Internet traffic models used in existing literatures. Results showed that the value of the waiting room size for Ga/M/1/K has closest ties with true self-similar model at peak-periods usage of the Internet, which indicates possible concurrent arrival of clients' requests leading to more usage of the waiting room, but with light-tailed queue model at the off-peak periods. Therefore, the proposed Ga/M/1/K model can assist in evaluating the performance of high-intensity self-similar Internet traffic. &#x0D; Keywords: Internet traffic; self-similarity; Ga/M/1/K model; gamma distribution

Optimal determination of hidden Markov model parameters for fuzzy time series forecasting

This paper presents Fuzzy Time Series (FTS) forecasting technique using Hidden Markov Model (HMM) optimized by Particle Swarm Optimization (PSO) and Genetic algorithm (GA). One of the major limitations of HMM is the lack of efficient method for HMM parameter estimation. Traditional methods like Baum Welch Algorithm (BWA) have been used to address the associated problem with HMM model. The BWA in itself does not truly capture the fuzziness in natural data resulting in the HMM algorithm into local minima. To address this challenge, this paper formulates the HMM parameter estimation problem into an optimization problem optimized by GA and PSO algorithms. To solve the problem of insufficiency in data allied with the HMM model, we adopted a method called smoothing to reduce the occurrence of zero in the observation events. Monte Carlo simulation is used at the end of the forecast to maintain stability and efficiency of the developed approach. The performance of developed model is evaluated using data of daily average temperature and cloud density of Taipei Taiwan, the Internet traffic data of Ahmadu Bello University (ABU) and Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX). Experimental results showed that the proposed forecasting models has a good forecasting accuracy when compared with existing models.

Machine learning algorithms for the problem of optimizing the distribution of parcels in time-dependent networks: the case study

In the paper we present machine learning algorithms for the problem of optimizing the distribution of parcels in sto-chastic time-dependent networks, which have been built as a part of some Distribution Optimization System. The prob-lem solved was a modified VRPTW (Vehicle Routing Problem with Time Windows) with many warehouses, a heteroge-neous fleet, travel times depending on the time of departure (stochastic time-dependent network) and an extensive cost function as an optimization criterion. To solve the problem a modified simulated annealing (SATM) algorithm has been proposed. The paper presents the results of the algorithm learning process: the calibration of input parameters and the study of the impact of parameters on the quality of the solution (calculation time, transport cost function value) de-pending on the type of input data. The idea is to divide the input data into classes according to a proposed classifica-tion rule and to propose several strategies for selecting the optimal set of calibration parameters. These strategies consist in solving some multi-criteria optimization tasks in which four criterion functions are used: the length of the designated routes, the computation time, the number of epochs used in the algorithm, the number of designated routes. The subproblem was building a network model of travel times that is used in constructed SATM algorithm to determine the travel time between recipients, depending on the time of departure from the start location. An attempt has been made to verify the research hypothesis that the time between two points can be estimated with sufficient accuracy depending on their geographical location and the time of departure (without reference to the micro-scale, i.e. the detailed structure of the road network). The research was conducted on two types of data for Warsaw: from transport companies and one of the Internet traffic data providers. Learning the network model of travel times has produced very promising results, which will be described in the paper.

The State’s access to data and internet intermediary response – an assessment of India’s attempt to reallocate the legal framework to ensure national security

ABSTRACT Safeguarding national security requires ensuring cyber security of a nation. While India has a wider law framework to ensure national security as against wrongs committed in real world, it is yet to match this framework to suit to the regulatory framework essential to address concerns raised due to the abuse of cyber technology. Though Indian laws including substantive legal provisions empowers the State to regulate acts affecting national as well as cyber security, its procedural rules suffers from being outdated and thereby irrelevant in addressing the concerns specific to cyber space. Ensuring national security requires access to data, both personal as well as non-personal data. While recent legal developments have been focusing on extending wider protection to privacy including data privacy, the State agencies strive to access data, which at times are crucial to the enforcement of laws in general and to ensure national security in specific. Jurisdictional issues further complicates the matter. As a result, the law enforcement agencies expect proactive coordination from internet intermediary in facilitating access to data, e-surveillance, decryption, internet traffic data monitoring, etc. Intermediaries on the other hand are also legally mandated to ensure data privacy, freedom of speech and other rights of internet users. This often has led to the conflicting concerns requiring new legal response. This paper will overview the existing laws as well as assess the changes Indian law is currently undergoing in these regard.

An accurate and practical algorithm for internet traffic recovery problem

It is challenging to recover the large-scale internet traffic data purely from the link-load measurements. With the rapid growth of the problem scale, it will be extremely difficult to sustain the recovery accuracy and the computational cost simultaneously. For the purpose of fast and accurately recovering the traffic data from link-load measurements, we establish a new Sparsity Low-Rank Recovery (SLRR) model based on the intrinsic properties of traffic data and propose an improved Schur Complement Based semi-proximal Alternating Direction Method of Multipliers (SCB-spADMM) to solve the SLRR model. The main contribution lies in the following two aspects. First, we fully exploit the spatial low-rank property and the sparsity of traffic data, which are barely considered in the literature. The model only relates to the traffics in a certain individual time interval. Thus, the scale of the problem is significantly reduced. Second, the global convergence of the proposed ADMM-type algorithm is established and all the intermediate variables’ optimums can be calculated analytically in each iteration. According to the numerical results on the classic datasets Abilene and GÉANT, our method achieves the best accuracy with a low computational cost. Moreover, in our newly released large-scale real-life network traffic dataset HOD, our method perfectly reaches the seconds-level feedback, which meets the essential requirement for practical scenarios.

FastTrafficAnalyzer: An Efficient Method for Intrusion Detection Systems to Analyze Network Traffic

Network intrusion detection systems are software or devices used to detect malignant attackers in modern internet networks. The success of these systems depends on the performance of the algorithm and method used to catch attacks and the time it takes for it. Due to the continuous internet traffic, these systems are expected to detect attacks in real time. In this study, using a proposed pre-processing, internet traffic data becomes more easily processable and traffic is classified by network analysis with machine learning techniques. In this way, the traffic analysis time was significantly shortened and a high level of success was achieved. The proposed model has been tested in the CSE-CIC-IDS2018 dataset and its advantaged verified. Experimental results i) 99.0% detection rate was achieved in the ExtraTree algorithm for binary classification, while a reduction of 82.96% was achieved in the processing time per sample; ii) For multiclass (15 class) detection, 98.5% detection rate was achieved with the Random Forest algorithm, while a 64.43% shortening was achieved in the processing time per sample. As a result, similar classification rate with the studies in the literature has been achieved with much shorter test time.

T-product factorization method for internet traffic data completion with spatio-temporal regularization

T-product factorization method for internet traffic data completion with spatio-temporal regularization

A year in lockdown

In March 2020, the World Health Organization declared the Corona Virus 2019 (COVID-19) outbreak a global pandemic. As a result, billions of people were either encouraged or forced by their governments to stay home to reduce the spread of the virus. This caused many to turn to the Internet for work, education, social interaction, and entertainment. With the Internet demand rising at an unprecedented rate, the question of whether the Internet could sustain this additional load emerged. To answer this question, this paper will review the impact of the first year of the COVID-19 pandemic on Internet traffic in order to analyze its performance. In order to keep our study broad, we collect and analyze Internet traffic data from multiple locations at the core and edge of the Internet. From this, we characterize how traffic and application demands change, to describe the "new normal," and explain how the Internet reacted during these unprecedented times.

A tensor train approach for internet traffic data completion

A tensor train approach for internet traffic data completion

SLRTA: A sparse and low-rank tensor-based approach to internet traffic anomaly detection

Internet traffic anomaly detection (ITAD) is a critical task for various network tasks such as traffic engineering and network security. Matrix-based approaches of ITAD have limitations for traffic data with multi-way structures, while the emerging tensor-based approaches of ITAD lack of sufficient consideration for circumstances including incomplete measurements or link-load measurements. To address these issues, we formulate ITAD by a sparse low-rank tensor optimization model, taking into full consideration the intrinsic and potential properties including the sparsity of anomalies, the low-rankness, the temporal stability and periodicity of the normal traffic data. Although the resulting optimization model is non-convex and discontinuous due to the involved ℓ0-norm and the tensor rank function, optimality analysis via stationarity is established, based on which an efficient proximal gradient method with theoretical convergence to stationary points is designed. Numerical experiments on internet traffic trace data Abilene and GÉANT demonstrate the high efficiency of our proposed sparse and low-rank tensor-based approach (SLRTA) for ITAD.