Big network traffic data visualization

Ruan, Zichan; Miao, Yuantian; Pan, Lei; Xiang, Yang; Zhang, Jun

doi:10.1007/s11042-017-5495-y

Cited by 9 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dimension reduction methods aim to project high-dimension datasets into low-dimension datasets, which facilitate the visualization of big traffic data on 2D or 3D figures. For example, the t-SNE method achieves great performance in dimension reduction for various applications, such as traffic speed [43], geographical location data [44], traffic flow [45,46], and driving behaviors [47]. It would be interesting to investigate the use of t-SNE in parking data analysis.…”

Section: Data-driven Clustering Methodsmentioning

confidence: 99%

Clustering Analysis of the Spatio-Temporal On-Street Parking Occupancy Data: A Case Study in Hong Kong

2022

Sustainability

View full text Add to dashboard Cite

Parking plays an essential role in urban mobility systems across the globe, especially in metropolises. Hong Kong is a global financial center, international shipping hub, fast-growing tourism city, and major aviation hub, and it thus has a high demand for parking. As one of the initiatives for smart city development, the Hong Kong government has already taken action to install new on-street parking meters and release real-time parking occupancy information to the public. The data have been released for months, yet, to the best of our knowledge, there has been no study analyzing the data and identifying their unique characteristics for Hong Kong. In view of this, we examined the spatio-temporal patterns of on-street parking in Hong Kong using the data from the new meters. We integrate the t-SNE and k-means methods to simultaneously visualize and cluster the parking occupancy data. We found that the average on-street parking occupancy in Hong Kong is over 80% throughout the day, and three parking patterns are consistently identified by direct data visualization and clustering results. Additionally, the parking patterns in Hong Kong can be explained using land-use factors. Overall, this study can help the government better understand the unique characteristics of on-street parking and develop smart management strategies for Hong Kong.

show abstract

Section: Data-driven Clustering Methodsmentioning

confidence: 99%

Clustering Analysis of the Spatio-Temporal On-Street Parking Occupancy Data: A Case Study in Hong Kong

2022

Sustainability

View full text Add to dashboard Cite

show abstract

“…The direction, inter-packet length, and inter-arrival times are the most important properties in the flow-based feature formulation: total duration (dur) and destination-to-source-time-to-live (dttl) are two examples of flow-based features. The features are categorized into three sets, namely basic (6)(7)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18), content (19)(20)(21)(22)(23)(24)(25)(26), and time (27)(28)(29)(30)(31)(32)(33)(34)(35). Features 36-40 and 41-47 are labeled as general-purpose features and connection features, respectively.…”

Section: Unsw-nb15 Datasetmentioning

confidence: 99%

“…Ruan et al 12,13 deployed a hash algorithm, weight table, and sampling method to address volume, variety, and velocity issues arising from big data. They formed a weight table and assigned large weights to the classes with a smaller population to guarantee the less probable data records to be selected by the sampling method.…”

Section: Introductionmentioning

confidence: 99%

UNSW‐NB15 computer security dataset: Analysis through visualization

Zoghi

Serpen

2023

Security and Privacy

View full text Add to dashboard Cite

Class imbalance refers to a major issue in data mining where data with unequal class distribution can deteriorate classification performance. Although it alone affects the performance of the classifiers, the joint‐effect of class imbalance and overlap is more damaging. Data overlap happens when multiple classes are assigned to a single data point causing the classifiers to misidentify the class boundaries. This study offers a deep insight into the intricacies of the UNSW‐NB15 dataset and two issues that may lead the data‐driven models to demonstrate poor performance. The most commonly used visualization methods such as bar chart, 3D and 2D scatter plots, intercluster distance map, and parallel coordinate diagram were employed to depict the data imbalanced and overlap. However, their limitations in capturing the overlapping issue led us to propose an accurate, easy‐to‐interpret, and scalable overlapping visualization method. The method clearly detects the data overlap and illustrates the effect of several data scalers in dealing with the data overlap. To verify the accuracy of the proposed method, a number of classifiers were implemented along with the scalers and the calculated AUC scores were compared to those calculated from the classifiers that were implemented on the original dataset.

show abstract

“…Profiling a network traffic involves finding metadata in a large amount of data [16] that moved across network at certain time [17]. Example of network traffic profiling usage is to understand Internet users' behavior [18] and to map the level of security treat and identify suspected abuser [10].…”

Section: Review Of the Literaturementioning

confidence: 99%

Network Traffic Profiling Using Data Mining Technique in Campus Environment

Ariffin¹

2020

IJATCSE

View full text Add to dashboard Cite

The exponential growth of internet usage poses a challenge in managing the bandwidth and securing the campus network environment. The ability differentiates and profile different type of data traversing in the Internet traffic is essential for ensuring effective bandwidth distribution and safeguarding network security. This work implements unsupervised data mining approach to analyze the network traffic trend and type of traffic in campus network. In this research, Orange tool is used in implementing K-Means Clustering Algorithm to find a network trend pattern of user accessing the Internet and to produce network traffic profiling in high volume traffic. Three clusters have been created based on the network traffic data described as high, medium and low number of hits towards the protocol services and unique IP address. Results shows that 74,869 hits come from DNS (UDP), 40,658 hits from MySQL and 3191 hits from HTTP. These are the high traffic that consume the bandwidth. Data mining process lead to reveal the information gather for profiling purposes and identify type of traffic passing through the campus network. The outcome of this study can be a recommendation of managing or shaping the bandwidth usage and strengthen the security policy of the network.

show abstract

Big network traffic data visualization

Cited by 9 publications

References 34 publications

Clustering Analysis of the Spatio-Temporal On-Street Parking Occupancy Data: A Case Study in Hong Kong

Clustering Analysis of the Spatio-Temporal On-Street Parking Occupancy Data: A Case Study in Hong Kong

UNSW‐NB15 computer security dataset: Analysis through visualization

Network Traffic Profiling Using Data Mining Technique in Campus Environment

Contact Info

Product

Resources

About