A Smart City Ecosystem Enabling Open Innovation

Ahlers, Dirk; Wienhofen, Leendert W. M.; Petersen, Sobah Abbas; Anvaari, Mohsen

doi:10.1007/978-3-030-22482-0_9

Cited by 21 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The addition of IoT platforms to home, corporate, and industrial networks is considered inevitable [19,20]. However, the inclusion of one or more IoT ecosystems also changes network traffic in several ways.…”

Section: The Unique Nature Of Iotmentioning

confidence: 99%

Robustness Evaluations of Sustainable Machine Learning Models against Data Poisoning Attacks in the Internet of Things

2020

View full text Add to dashboard Cite

With the increasing popularity of the Internet of Things (IoT) platforms, the cyber security of these platforms is a highly active area of research. One key technology underpinning smart IoT systems is machine learning, which classifies and predicts events from large-scale data in IoT networks. Machine learning is susceptible to cyber attacks, particularly data poisoning attacks that inject false data when training machine learning models. Data poisoning attacks degrade the performances of machine learning models. It is an ongoing research challenge to develop trustworthy machine learning models resilient and sustainable against data poisoning attacks in IoT networks. We studied the effects of data poisoning attacks on machine learning models, including the gradient boosting machine, random forest, naive Bayes, and feed-forward deep learning, to determine the levels to which the models should be trusted and said to be reliable in real-world IoT settings. In the training phase, a label modification function is developed to manipulate legitimate input classes. The function is employed at data poisoning rates of 5%, 10%, 20%, and 30% that allow the comparison of the poisoned models and display their performance degradations. The machine learning models have been evaluated using the ToN_IoT and UNSW NB-15 datasets, as they include a wide variety of recent legitimate and attack vectors. The experimental results revealed that the models’ performances will be degraded, in terms of accuracy and detection rates, if the number of the trained normal observations is not significantly larger than the poisoned data. At the rate of data poisoning of 30% or greater on input data, machine learning performances are significantly degraded.

show abstract

Section: The Unique Nature Of Iotmentioning

confidence: 99%

Robustness Evaluations of Sustainable Machine Learning Models against Data Poisoning Attacks in the Internet of Things

2020

View full text Add to dashboard Cite

show abstract

“…This paper is part of the European Union (EU) H2020 funded +CityxChange project (https://cityxchange.eu/) which objective is to develop and implement Positive Energy Blocks and Districts (PEB/PED) in smart cities and communities as part of emission decrease to attain the Paris Climate Goals by 2050 and measure these out in accordance with the European Clean Energy Transition in municipalities (Ahlers et al 2019). Respectively, PEB is defined by the EU as numerous buildings that dynamically manage their electricity consumption and the power flow between them and the entire energy system to annual accomplish positive electricity balance.…”

Section: Introductionmentioning

confidence: 99%

Big data-oriented energy prosumption service in smart community districts: a multi-case study perspective

et al. 2019

Self Cite

View full text Add to dashboard Cite

The smart grid achieves bidirectional information and energy flow between energy consumer and utility grid, aiding energy users not only to utilize energy, but also to produce, sell, and share energy with other consumers or with the utility grid. This type of energy user is referred to as the "prosumer". Thus, prosumer management structures are important within energy market. However, prior studies on energy sustainability has paid little attention on prosumer involvement and management. Likewise, the continuous growth of cities has increased data processing complexity. Consequently, processing and analysis of historical, online, and real-time streaming data from energy sensors and metering devices has become a major issue in smart cities. Therefore, this research aims to present an architecture based on big data to improve energy prosumption in smart community districts by applying enterprise architecture approach grounded on The Open Group Architecture Framework (TOGAF). Accordingly, qualitative methodology is adopted to collect data by employing case study by focus group interview from two energy companies in Norway to preliminarily validate the architecture. Findings from the case studies was demonstrated in ArchiMate modeling language to evaluate the applicability of the architecture. Moreover, findings from this study provides practical scenario that energy service providers can refer to in designing their own energy data platforms. Essentially, the architecture can be utilized as a guide to help municipalities and policy makers in creating approach for energy data analytics in smart community districts towards making decisions for future energy prosumption planning.

show abstract

“…Over the years there have been development towards e-mobility mainly in the emergence of EVs that enable decrease of carbon dioxide emissions, improves collaborative e-bicycles, e-cars, and segways sharing, and management of EV fleets in urban environment [4]. Improving transport services and data management is just the first step towards realizing smart cities [32]. But processing and using big data into valuable and usage insights for various mobility applications is an issue [3].…”

Section: Discussionmentioning

confidence: 99%

A Practice Based Exploration on Electric Mobility as a Service in Smart Cities

AnthonyJr.

Petersen

2020

Information Systems

Self Cite

View full text Add to dashboard Cite

With increase in urban residents and CO2 emission from vehicles, there is need to deploy smart electric mobility services termed as Electric Mobility as a Service (eMaaS) facilitated by innovations in Information Communication Technology (ICT) to mitigate environmental issues, improve social inclusion, and enhance economic growth. However, citizens and stakeholders are faced with issues related to acquiring appropriate information needed to make decisions which impacts their wellbeing and natural environment due to heterogenous data being generated from various sources. Therefore, this study adopts Enterprise Architecture (EA) and integrates Application Programming Interfaces (APIs) to improve interoperability for acquisition, processing, retaining, and dissemination of mobility relevant data. Secondary data from the literature and ArchiMate modeling tool was utilized to model eMaaS case to verify the feasibility of EA to improve city transport services. Findings from ArchiMate reveal that EA provides a theoretical and practical approach that supports mobility services in smart cities.

show abstract

A Smart City Ecosystem Enabling Open Innovation

Cited by 21 publications

References 12 publications

Robustness Evaluations of Sustainable Machine Learning Models against Data Poisoning Attacks in the Internet of Things

Robustness Evaluations of Sustainable Machine Learning Models against Data Poisoning Attacks in the Internet of Things

Big data-oriented energy prosumption service in smart community districts: a multi-case study perspective

A Practice Based Exploration on Electric Mobility as a Service in Smart Cities

Contact Info

Product

Resources

About