Application of learning algorithms in smart home IoT system security

Mao, Jian; Lin, Qixiao; Bian, Jingdong

doi:10.3934/mfc.2018004

Cited by 30 publications

(13 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most of these are classified as assistance services, which provide direct remotely controlled support of lighting, heating, energy, and security systems, and have been designed to minimize daily power and water consumption through environmental monitoring (Gomez et al, 2019; Iqbal et al, 2018; Khan, Babar, Ahmed, Shah, & Han, 2017; Lim et al, 2018; Miorandi et al, 2012; Vlachostergiou et al, 2016). Perhaps the greatest challenge in the smart home service and application sector is the ability to attend to the adaptive personalized interaction between the technology and the user (Vlachostergiou et al, 2016), and security threats (Mao, Lin, & Bian, 2018) Smart factory and Industry 4.0 : The IoT and Cyber‐Physical Systems (CPS) enable smart processes and procedures with or without human intervention. In this sector these technologies support the planning, control, optimization, and production of products and services, thus facilitating proactive maintenance and safety.…”

Section: Resultsmentioning

confidence: 99%

The relationship between the Internet of Things and knowledge management in smart ecosystem development

Ikeda

Silva

Penha

et al. 2021

Knowl Process Manag

View full text Add to dashboard Cite

Creating an environment capable of responding to its users and organizations in real‐time is a challenging task. However, with the advent of the Internet of Things (IoT) ecosystem, a new perspective about creating an intelligent and interconnected world has become a reality. The goal of the present study aims to explore the relationship between IoT and Knowledge Management (KM) when generating a Smart environment. Herein, we conducted a Systematic Literature Review and present a discussion about the evolution of the IoT concept and the IoT ecosystem. More specifically we focused on the main IoT elements that serve as the foundation of the IoT ecosystem and the relationship between the IoT and KM. Although there is a lack of studies about KM supporting the IoT, our study provides evidence that the IoT is composed of a set of technologies that enable KM and KM processes can facilitate the development of IoT Smart environments. Thus, there is an opportunity to study how to generate more intelligence and connectivity, which will support the players of the ecosystem, promote interactions among objects and people and ultimately add value to organizations and users.

show abstract

Section: Resultsmentioning

confidence: 99%

The relationship between the Internet of Things and knowledge management in smart ecosystem development

Ikeda

Silva

Penha

et al. 2021

Knowl Process Manag

View full text Add to dashboard Cite

show abstract

“…За допомогою використання розробленої СКБД, дані структуровано зберігаються у БД та можуть бути у подальшому використані для систем автоматизованого керування приладами будинку за допомогою алгоритмів штучного інтелекту для оптимізації рівня енергоспоживання у помешканні. Збережені стани приладів будинку з відповідними часовими мітками можуть виступати як навчальна вибірка для алгоритмів машинного навчання, які використовуватимуться для оптимальних енергоефективних налаштувань приладів будинку без взаємодії з людиною, а на підставі показників датчиків температури, вологості, руху та вподобань мешканців будинку взятих з історичних даних у БД Toyota Smarthome [9], що представлена набором даних про активність людей у побуті.…”

Section: ʟˈˊ˖ˎ˟˕˃˕ˋ ˇˑ˔ˎ˪ˇˉˈːːˢ ˕˃ ˫˘ ˑ˄ˆˑ˅ˑ˓ˈːːˢunclassified

Selection of the Optimal Structure of Hidden Layers of the Artificial Neural Network for Energy Efficiency Analysis

Kazarian¹,

Teslyuk²,

Kazymyra³

2021

UJIT

View full text Add to dashboard Cite

A method for optimal structure selection of hidden layers of the artificial neural network (ANN) is proposed. Its main idea is the practical application of several internal structures of ANN and further calculation of the error of each hidden layer structure using identical data sets for ANN training. The method is based on the alternate comparison of the expected result values and the actual results of the feedforward artificial neural networks with a different number of inner layers and a different number of neurons on each layer. The method afforces searching the optimal internal structure of ANN for usage in the development of "smart" house systems and for calculation of the optimal energy consumption level in accordance with current conditions, such as room temperature, presence of people, and time of the day. The usage of the presented method allows to reduce the time spent on choosing the effective structure of the artificial neural network at the initial stages of research and to pay more attention to the relationship between the input and output data, as well as to such important parameters of the ANN learning process, as a number of training iterations, minimal training error, etc. The software has been developed that allows to carry out the processes of training, testing, and obtaining the output results of the algorithm of the artificial neural network, such as the expected value of power consumption and operating time of each individual appliance. The disadvantage of the approach used in finding the optimal internal structure of the artificial neural network is that each subsequent structure is created on the basis of the most efficient of the previously created structures without analyzing other structures that showed worse results with fewer hidden layers. It was found that to improve the solution of this problem it is necessary to create a mechanism which will be based on the analysis of input data, output data, will analyze the internal relationships between parameters and will optimize the network structure at each stage using certain logical rules according to the results obtained in the previous step. It is established that this problem is a nonlinear programming problem that can be solved in the further development of this study.

show abstract

“…Blockchain technology has proven to be effective in a variety of smart home applications, including control over access to the home, exchanging data, and so on. The use of blockchain in smart home networks is also justified because it works independently of current heterogeneous protocols commonly used in smart homes (such as Z-Wave, Zigbee, Bluetooth, and Thread) [6]. Nonetheless, using blockchain directly in a smart home is always a challenge due to the high level of resources consumed during mining and consensus procedures and the limitations of node resources in smart home devices.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving Mechanism in Smart Home Using Blockchain

Qashlan

Nanda

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The IoT, or Internet of Things has been a major talking point amongst technology enthusiasts in recent years. The internet of thing (IoT) has been emerged and evolved rapidly, making the world's fabric around us smarter and more responsive. The smart home use one such transformation of IoT, which seems to be the wave of the future. However, with the increasing wide adoption of IoT, data security, and privacy concerns about how our data is collected and shared with others, has also risen. To solve these challenges, an approach to data privacy and security in a smart home using blockchain technology is proposed in this paper. We propose authentication scheme that combines attribute-based access control with smart contracts and edge computing to create a secure framework for IoT devices in smart home systems. The edge server adds scalability to the system by offloading heavy processing activities and using a differential privacy method to aggregate data to the cloud securely and privately. We present several aspects of testing and implementing smart contracts, the differential private stochastic gradient descent algorithm, and system architecture and design. We demonstrate the efficacy of our proposed system by fully examining its security and privacy goals in terms of confidentiality, integrity, and availability. Finally, we undertake a performance evaluation to demonstrate the proposed scheme's feasibility and efficiency.

show abstract

Application of learning algorithms in smart home IoT system security

Cited by 30 publications

References 43 publications

The relationship between the Internet of Things and knowledge management in smart ecosystem development

The relationship between the Internet of Things and knowledge management in smart ecosystem development

Selection of the Optimal Structure of Hidden Layers of the Artificial Neural Network for Energy Efficiency Analysis

Privacy-Preserving Mechanism in Smart Home Using Blockchain

Contact Info

Product

Resources

About