Mechanisms and techniques to enhance the security of big data analytic framework with MongoDB and Linux Containers

Mailewa, Akalanka; Mengel, Susan; Khan, Hafiz

doi:10.1016/j.array.2022.100236

Cited by 7 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We will use the RBF kernel for our study since it allows us to do non-linear classification on our dataset. The RBF may be stated mathematically as (5).…”

Section: Support Vector Machinementioning

confidence: 99%

“…Unseen assaults, on the other hand, are the most significant for our study. Zero-day malware is a sophisticated type of attack since no prior knowledge about the danger is available [4], [5]. Training the intrusion detection system (IDS) to deal with this type of assault would necessitate the use of a security mechanism capable of discriminating between regular and aberrant network traffic.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting anomalies in computer networks using autoencoder-based representation learning

Khan,

Mailewa

2024

IJ-ICT

View full text Add to dashboard Cite

<span>Recent improvements in the internet of things (IoT), cloud services, and network data variety have increased the demand for complex anomaly detection algorithms in network intrusion detection systems (IDSs) capable of dealing with sophisticated network threats. Academics are interested in deep and machine learning (ML) breakthroughs because they have the potential to address complex challenges such as zero-day attacks. In comparison to firewalls, IDS are the initial line of network security. This study suggests merging supervised and unsupervised learning in identification systems IDS. Support vector machine (SVM) is an anomaly-based classification classifier. Deep autoencoder (DAE) lowers dimensionality. DAE are compared to principal component analysis (PCA) in this study, and hyper-parameters for F-1 micro score and balanced accuracy are specified. We have an uneven set of data classes. precision-recall curves, average precision (AP) score, train-test times, t-SNE, grid search, and L1/L2 regularization methods are used. KDDTrain+ and KDDTest+ datasets will be used in our model. For classification and performance, the DAE+SVM neural network technique is successful. Autoencoders outperformed linear PCA in terms of capturing valuable input attributes using t-SNE to embed high dimensional inputs on a two-dimensional plane. Our neural system outperforms solo SVM and PCA encoded SVM in multi-class scenarios.</span>

show abstract

“…We will use the RBF kernel for our study since it allows us to do non-linear classification on our dataset. The RBF may be stated mathematically as (5).…”

Section: Support Vector Machinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting anomalies in computer networks using autoencoder-based representation learning

Khan,

Mailewa

2024

IJ-ICT

View full text Add to dashboard Cite

show abstract

“…DBMS manipulates every aspect of the information without affecting the user, so choosing an appropriate one facilitates tasks such as triggers, user management, user authentication method and authentication recovery [32]. A review and comparison were made of some nonSQL DBMSs [32], such as MongoDB [33], Apache [34],…”

Section: Selection Of Dbmsmentioning

confidence: 99%

Securing mobility in Bucaramanga

Angarita Reina,

Aparicio Duran,

Arias Quintero

et al. 2023

ing. Solidar

View full text Add to dashboard Cite

Introduction: The smart city paradigm is made up of a set of actors who must operate jointly to guarantee road flow. However, sometimes there are accidents, and they affect productive apparatus, cause minor or temporary injuries and sometimes death of the individuals involved. Problem: Events occur for multiple reasons and the authorities have difficulties in implementing controls that minimize their occurrence since they do not have the necessary tools to capture and analyze timely information on the claims that have been presented. Objective: The objective is to increase road safety control and safeguard mobility in Bucaramanga. For this, a mobile application is designed to capture accident data by implementing the Flutter framework and the Model- View design pattern methodology. Controller (MVC). Methodology: The development of software to analyze the large amount of information on road events. A da- tabase is developed where said information is stored and processed using programming languages, coding and data hosting. Design and process factors are also considered according to the user’s needs, which will determine the interface and expected performance. Results: A structured system for data capture with the ability to integrate the general community, streamline the availability of information and facilitate decision making that deals with the problem in real time. Conclusion: It is concluded that its implementation in the city fosters self-care for pedestrians and drivers, facilitating the design of effective control measures by territorial entities, bringing the city of Bucaramanga closer to sustainability. Originality: This methodology for integrating events is unique in the country and is developed based on the city’s own characteristics. Limitations: The lack of information provided by the government actors.

show abstract