Performance comparison of machine learning methods in the bus arrival time prediction problem

Agafonov, Anton; Yumaganov, Alexander

doi:10.18287/1613-0073-2019-2416-57-62

Cited by 5 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The modular API is designed to seamlessly integrate a diverse array of machine learning models to enhance threat detection within a private cloud environment. The selected models, including random forest [28,29], support vector machines [28,30], neural networks [31,32], k-nearest neighbors [33,34], decision tree [35,36], stochastic gradient descent [37,38], naive Bayes [39,40], logistic regression [41,42], gradient boosting [41,[43][44][45] and AdaBoost [46], each bring unique capabilities to the framework. Random forest's robustness is rigorously assessed for identifying network anomalies, while support vector machines focus on precise threat identification with minimal false positives.…”

Section: Machine Learning Model Evaluationmentioning

confidence: 99%

Evaluation of the Omni-Secure Firewall System in a Private Cloud Environment

Mahmood,

Hasan,

Yahaya

et al. 2024

Knowledge

View full text Add to dashboard Cite

This research explores the optimization of firewall systems within private cloud environments, specifically focusing on a 30-day evaluation of the Omni-Secure Firewall. Employing a multi-metric approach, the study introduces an innovative effectiveness metric (E) that amalgamates precision, recall, and redundancy considerations. The evaluation spans various machine learning models, including random forest, support vector machines, neural networks, k-nearest neighbors, decision tree, stochastic gradient descent, naive Bayes, logistic regression, gradient boosting, and AdaBoost. Benchmarking against service level agreement (SLA) metrics showcases the Omni-Secure Firewall’s commendable performance in meeting predefined targets. Noteworthy metrics include acceptable availability, target response time, efficient incident resolution, robust event detection, a low false-positive rate, and zero data-loss incidents, enhancing the system’s reliability and security, as well as user satisfaction. Performance metrics such as prediction latency, CPU usage, and memory consumption further highlight the system’s functionality, efficiency, and scalability within private cloud environments. The introduction of the effectiveness metric (E) provides a holistic assessment based on organizational priorities, considering precision, recall, F1 score, throughput, mitigation time, rule latency, and redundancy. Evaluation across machine learning models reveals variations, with random forest and support vector machines exhibiting notably high accuracy and balanced precision and recall. In conclusion, while the Omni-Secure Firewall System demonstrates potential, inconsistencies across machine learning models underscore the need for optimization. The dynamic nature of private cloud environments necessitates continuous monitoring and adjustment of security systems to fully realize benefits while safeguarding sensitive data and applications. The significance of this study lies in providing insights into optimizing firewall systems for private cloud environments, offering a framework for holistic security assessment and emphasizing the need for robust, reliable firewall systems in the dynamic landscape of private clouds. Study limitations, including the need for real-world validation and exploration of advanced machine learning models, set the stage for future research directions.

show abstract

Section: Machine Learning Model Evaluationmentioning

confidence: 99%

Evaluation of the Omni-Secure Firewall System in a Private Cloud Environment

Mahmood,

Hasan,

Yahaya

et al. 2024

Knowledge

View full text Add to dashboard Cite

show abstract

“…In delay time prediction, the target attribute is the delay time, which is the difference between the observed and planned travel time ( 6 ). In speed prediction, the target attribute is the future speed of the bus on a given segment of the route ( 56 ).…”

Section: Problems and Solutions Retrieved From The Literature Related...mentioning

confidence: 99%

“…The travel time prediction, arrival time prediction, delay time prediction, and speed prediction solutions are considered equivalent because when predicting the target attribute by one of these models, it is possible to obtain the corresponding target attribute expected by the other models. For example, Agafonov and Yumaganov ( 56 ) and Zheng et al ( 57 ) used a speed predictor to predict the bus speed on a segment and thus indirectly obtain the bus’s travel time or arrival time. Thus, these solutions were grouped, and the name travel time prediction was adopted in this paper to refer to this group of equivalent solutions.…”

Section: Categorizing the Retrieved Solutionsmentioning

confidence: 99%

Machine Learning Applied to Public Transportation by Bus: A Systematic Literature Review

Alexandre

Bernardini

Viterbo

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Machine learning (ML) solutions have been proposed to make public transportation more attractive. Works that employ ML in bus transportation focus on various problems, such as travel time prediction or passenger flow prediction. These solutions look to improve elements of transportation services, such as the availability of information on passengers’ travel time and the reliability and regularity of the service. An analysis of the solutions proposed in the literature for public transportation by bus can reveal opportunities for data scientists and transportation professionals, and highlight problems that have been only slightly explored. In addition, mapping information about modeling these solutions (e.g., types of data produced by devices on the transportation network, which can be used in modeling a solution) could help beginner data scientists develop public transportation solutions. Transportation professionals can benefit from an overview of possible transportation solutions to improve transportation problems and direct government agency efforts to implement these solutions. This paper presents a survey of ML-based solutions for public bus transportation and details the modeling of these solutions (e.g., data types, ML algorithms). In addition, the problems tackled in the literature are categorized into four themes, and the solutions proposed to deal with them are schematized, highlighting problems that are little explored.

show abstract

“…(Berbey et al 2012;Hu et al 2016;Hagenauer and Helbich 2017). Naturally, a study may use both historical and realtime data (Agafonov and Yumaganov 2019). Sensor data and questionnaire data represent data that have been collected using different types of sensors (e.g., position data, temperature data, video data) or questionnaires (e.g., concerning user behaviour, conditions and opinions).…”

Section: Data Needsmentioning

confidence: 99%

Artificial intelligence for improving public transport: a mapping study

Jevinger,

Zhao,

Persson

et al. 2023

Public Transp

View full text Add to dashboard Cite

The objective of this study is to provide a better understanding of the potential of using Artificial Intelligence (AI) to improve Public Transport (PT), by reviewing research literature. The selection process resulted in 87 scientific publications constituting a sample of how AI has been applied to improve PT. The review shows that the primary aims of using AI are to improve the service quality or to better understand traveller behaviour. Train and bus are the dominant modes of transport investigated. Furthermore, AI is mainly used for three tasks; the most frequent one is prediction, followed by an estimation of the current state, and resource allocation, including planning and scheduling. Only two studies concern automation; all the others provide different kinds of decision support for travellers, PT operators, PT planners, or municipalities. Most of the reviewed AI solutions require significant amounts of data related to the travellers and the PT system. Machine learning is the most frequently used AI technology, with some studies applying reasoning or heuristic search techniques. We conclude that there still remains a great potential of using AI to improve PT waiting to be explored, but that there are also some challenges that need to be considered. They are often related to data, e.g., that large datasets of high quality are needed, that substantial resources and time are needed to pre-process the data, or that the data compromise personal privacy. Further research is needed about how to handle these issues efficiently.

show abstract

Performance comparison of machine learning methods in the bus arrival time prediction problem

Cited by 5 publications

References 18 publications

Evaluation of the Omni-Secure Firewall System in a Private Cloud Environment

Evaluation of the Omni-Secure Firewall System in a Private Cloud Environment

Machine Learning Applied to Public Transportation by Bus: A Systematic Literature Review

Artificial intelligence for improving public transport: a mapping study

Contact Info

Product

Resources

About