Digital Cities Roadmap

Keywords :Machine learning, big data analytics, Internet of Things, smart building, resilient building, sustainable building

The hyperconnectivity generated by IoT will enhance the assurance of Smart Sustainable Resilient Building (SSRB) as all basic construction facilities and goods from your home electronics to your plant vessels have now been connected [1 –5]. Nevertheless, this hyperconnectivity could hinder the control of SSRBs at the same time. In particular, massive quantities of streaming data are required from SSRB and its residents. The management of large data streams is becoming more and more relevant with ML, testing, compaction, learning and filtration technologies. In order to obtain a greater interpretation of human beings than their environment computers, the amount of sensory data obtained by sensors and devices needs to be processed by algorithms, converted into details and derived expertise [6 –8]. This awareness can also contribute, and most significantly, innovative goods and services that change our lives drastically. For starters, smart meter readings may be used to help estimate and control power usage. To optimize this convenience, reduce expenses adapting to requirements of its residents, the SSRB requires sophisticated tools to understand, anticipate and make intelligent decisions. SSRB must also provide a variety of wearable sensor data linked to its patients and produce new remote sensors. SSRB algorithms include estimation, decision analysis, robots, smart devices, wireless sensor networks, interactive, web computing and cloud computing and include several other developments. Cognitive maintenance of offices is necessary in several SSRB programs for starters, fitness, safety, energy management, illumination, repair, the elderly and digital entertainment through these technologies.

While several SB-focused survey papers have been released, none focuses on the role of data analysis and ML within SBs. All the relevant survey papers are comprehensively presented in Table 1.1.

Table 1.1Report data of a survey.

Chan et al. in 2008 [12] gave a description of intelligent home study. It even speaks about smart and friendly robotics. The article examines the nation and the continent’s smart home programs. Alam et al. [13] presented information on sensors, apps, algorithms and protocols of communication used in smart homes. The paper explores intelligent homes focused on their facilities and study aims: protection, fitness and comfort.

Lobaccaro et al. [14] shared the notion of a smart house but smart grid technology and address obstacles, advantages and potential developments of intelligent home technology. Pan et al. [15] analyzed the research of SBs with microgrids on efficient energy usage. The study explores subjects for analysis and latest developments in SBs and microgrid vision.

For multiple study articles research on making the autonomous lives of seniors for smart homes simpler has been checked. Ni et al. [16] have reported on sensing machine features including practices which can help elderly people reside peacefully in intelligent residences. Rashidi and Mihailidis provided a study on environmental assistance systems for elderly people [17]. Peetoom et al. [18] concentrated software tracking that understands householder existence, including reduced identification and changes of safety condition. Salih et al. [19] proposed a health-assisted urban knowledge report surveillance system identifying different methods included in current research literature, as well as connectivity and wireless sensor network technology.

A brief list of the different algorithms for machine learning [49] in sustainable and resilient building is obtained below.

Decision Tree—Decision Tree is a supervised learning system used for classification or regression. A training model is built in Decision Tree Learning and the importance of the results is determined through the learning decision rules derived from the data attributes. In Big data there are many drawbacks to these decision tree algorithms. Firstly, if the data are very large, it is very time to build a decision tree. Secondly, there is no optimal solution to the distribution of data that contributes to higher communication cost.

Support Vector Machine (SVM)—Support Vector Machine is a supervised learning approach that can be used for either regression or classification. When used on big data, due to its high machine complexity, the SVM technique is not successful. The demand for measurement and storage is increased considerably for enormous amount of data.