The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform

Yingbo Liu - One of the best experts on this subject based on the ideXlab platform.

  • privacy preserving blockchain based federated learning for iot devices
    IEEE Internet of Things Journal, 2021
    Co-Authors: Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Lingjuan Lyu, Yingbo Liu
    Abstract:

    Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a Smart Home System. To help manufacturers develop a Smart Home System, we design a federated learning (FL) System leveraging a reputation mechanism to assist Home appliance manufacturers to train a machine learning model based on customers’ data. Then, manufacturers can predict customers’ requirements and consumption behaviors in the future. The working flow of the System includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile-edge computing (MEC) server. Customers collect data from various Home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL System. Since records on the blockchain are untampered, malicious customers or manufacturers’ activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers’ privacy and improve the test accuracy, we enforce differential privacy (DP) on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under DP protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

  • privacy preserving blockchain based federated learning for iot devices
    arXiv: Cryptography and Security, 2019
    Co-Authors: Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Lingjuan Lyu, Yingbo Liu
    Abstract:

    Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a Smart Home System. To help manufacturers develop a Smart Home System, we design a federated learning (FL) System leveraging the reputation mechanism to assist Home appliance manufacturers to train a machine learning model based on customers' data. Then, manufacturers can predict customers' requirements and consumption behaviors in the future. The working flow of the System includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile edge computing (MEC) server. Customers collect data from various Home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL System. Since records on the blockchain are untampered, malicious customers or manufacturers' activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers' privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under differential privacy protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

Yang Zhao - One of the best experts on this subject based on the ideXlab platform.

  • privacy preserving blockchain based federated learning for iot devices
    IEEE Internet of Things Journal, 2021
    Co-Authors: Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Lingjuan Lyu, Yingbo Liu
    Abstract:

    Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a Smart Home System. To help manufacturers develop a Smart Home System, we design a federated learning (FL) System leveraging a reputation mechanism to assist Home appliance manufacturers to train a machine learning model based on customers’ data. Then, manufacturers can predict customers’ requirements and consumption behaviors in the future. The working flow of the System includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile-edge computing (MEC) server. Customers collect data from various Home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL System. Since records on the blockchain are untampered, malicious customers or manufacturers’ activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers’ privacy and improve the test accuracy, we enforce differential privacy (DP) on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under DP protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

  • privacy preserving blockchain based federated learning for iot devices
    arXiv: Cryptography and Security, 2019
    Co-Authors: Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Lingjuan Lyu, Yingbo Liu
    Abstract:

    Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a Smart Home System. To help manufacturers develop a Smart Home System, we design a federated learning (FL) System leveraging the reputation mechanism to assist Home appliance manufacturers to train a machine learning model based on customers' data. Then, manufacturers can predict customers' requirements and consumption behaviors in the future. The working flow of the System includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile edge computing (MEC) server. Customers collect data from various Home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL System. Since records on the blockchain are untampered, malicious customers or manufacturers' activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers' privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under differential privacy protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

Hagya Nathali Silva - One of the best experts on this subject based on the ideXlab platform.

  • internet of things based energy aware Smart Home control System
    IEEE Access, 2016
    Co-Authors: Murad Kha, Hagya Nathali Silva
    Abstract:

    The concept of Smart Home is widely favored, as it enhances the lifestyle of the residents involving multiple disciplines, i.e., lighting, security, and much more. As the Smart Home networks continue to grow in size and complexity, it is essential to address a handful among the myriads of challenges related to data loss due to the interference and efficient energy management. In this paper, we propose a Smart Home control System using a coordinator-based ZigBee networking. The working of the proposed System is three fold: 1) Smart interference control System controls the interference caused due to the co-existence of IEEE 802.11x-based wireless local area networks and wireless sensor networks; 2) Smart energy control System is developed to integrate sunlight with light source and optimizes the energy consumption of the household appliances by controlling the unnecessary energy demands; and 3) Smart management control System to efficiently control the operating time of the electronic appliances. The performance of the proposed Smart Home is testified through computer simulation. Simulation results show that the proposed Smart Home System is less affected by the interference and efficient in reducing the energy consumption of the appliances used in a Smart Home.

Nagender Kumar Suryadevara - One of the best experts on this subject based on the ideXlab platform.

  • wsn and iot based Smart Homes and their extension to Smart buildings
    Sensors, 2015
    Co-Authors: Hemant Ghayvat, Subhas Chandra Mukhopadhyay, Xiang Gui, Nagender Kumar Suryadevara
    Abstract:

    Our research approach is to design and develop reliable, efficient, flexible, economical, real-time and realistic wellness sensor networks for Smart Home Systems. The heterogeneous sensor and actuator nodes based on wireless networking technologies are deployed into the Home environment. These nodes generate real-time data related to the object usage and movement inside the Home, to forecast the wellness of an individual. Here, wellness stands for how efficiently someone stays fit in the Home environment and performs his or her daily routine in order to live a long and healthy life. We initiate the research with the development of the Smart Home approach and implement it in different Home conditions (different houses) to monitor the activity of an inhabitant for wellness detection. Additionally, our research extends the Smart Home System to Smart buildings and models the design issues related to the Smart building environment; these design issues are linked with System performance and reliability. This research paper also discusses and illustrates the possible mitigation to handle the ISM band interference and attenuation losses without compromising optimum System performance.

Lingjuan Lyu - One of the best experts on this subject based on the ideXlab platform.

  • privacy preserving blockchain based federated learning for iot devices
    IEEE Internet of Things Journal, 2021
    Co-Authors: Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Lingjuan Lyu, Yingbo Liu
    Abstract:

    Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a Smart Home System. To help manufacturers develop a Smart Home System, we design a federated learning (FL) System leveraging a reputation mechanism to assist Home appliance manufacturers to train a machine learning model based on customers’ data. Then, manufacturers can predict customers’ requirements and consumption behaviors in the future. The working flow of the System includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile-edge computing (MEC) server. Customers collect data from various Home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL System. Since records on the blockchain are untampered, malicious customers or manufacturers’ activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers’ privacy and improve the test accuracy, we enforce differential privacy (DP) on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under DP protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

  • privacy preserving blockchain based federated learning for iot devices
    arXiv: Cryptography and Security, 2019
    Co-Authors: Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Lingjuan Lyu, Yingbo Liu
    Abstract:

    Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a Smart Home System. To help manufacturers develop a Smart Home System, we design a federated learning (FL) System leveraging the reputation mechanism to assist Home appliance manufacturers to train a machine learning model based on customers' data. Then, manufacturers can predict customers' requirements and consumption behaviors in the future. The working flow of the System includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile edge computing (MEC) server. Customers collect data from various Home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL System. Since records on the blockchain are untampered, malicious customers or manufacturers' activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers' privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under differential privacy protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.