Open Source Tools for Machine Learning with Big Data in Smart Cities

Ulusar, Umit Deniz; Ozcan, Deniz Gul; Al‐Turjman, Fadi

doi:10.1007/978-3-030-14718-1_8

Cited by 6 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another survey [145] presents existing open source tools for Big Data (e.g., Hadoop, Spark, Storm, and Flink) and Machine Learning (e.g., Mahout, Spark MLLib, and SAMOA). In [88] the authors present the challenges associated with Machine Learning in the context of Big Data and categorize them according to the Velocity, Volume, Variety, and Veracity dimensions of Big Data.…”

Section: Combining Data Analytics and Learning On The Cloudmentioning

confidence: 99%

Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review

Rosendo

Costan

Valduriez

et al. 2022

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Section: Combining Data Analytics and Learning On The Cloudmentioning

confidence: 99%

Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review

Rosendo

Costan

Valduriez

et al. 2022

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

“…In order to adapt to this rapid urbanization growth while making cities more sustainable, livable, and equitable, designers must utilize qualitative and quantitative tools to make better-informed decisions about future cities [1]. In addition, big urban data is now readily available online, allowing the opportunity to utilize this information to generate new urban analyses between various features within the urban fabric [2]. A new digital layer can be added toward urban complexity through the novel perspective of data accumulation.…”

Section: Introductionmentioning

confidence: 99%

“…This method previously addressed some urban issues, including smart cities, mobility, climate, density, and energy. However, the evolution of that research indicates a promising future and outcome for ML application in this area [2]. In contemporary research, the ML algorithms applied are deep learning, artificial neural networks (ANN), support vector machines, neuro-fuzzy, and decision trees.…”

Section: Introductionmentioning

confidence: 99%

AI Urban Voids: A Data-Driven Approach to Urban Activation

Algamdey

Mastalski

Chronis

et al. 2023

Computational Design and Robotic Fabrication

View full text Add to dashboard Cite

With the development of digital technologies, big urban data is now readily available online. This opens the opportunity to utilize new data and create new relationships within multiple urban features for cities. Moreover, new computational design techniques open a new portal for architects and designers to reinterpret this urban data and provide much better-informed design decisions. The “AI Urban Voids'' project is defined as a data-driven approach to analyze and predict the strategic location for urban uses in the addition of amenities within the city. The location of these urban amenities is evaluated based on predictions and scores followed by a series of urban analyses and simulations using K-Means clustering. Furthermore, these results are then visualized in a web-based platform; likewise, the aim is to create a tool that will work on a feedback loop system that constantly updates the information. This paper explains the use of different datasets from Five cities including Melbourne, Sydney, Berlin, Warsaw, and Sao Paulo. Python, Osmx libraries and K-means clustering open the way to manipulate large data sets by introducing a collection of computational processes that can override traditional urban analysis.

show abstract