John J. Lee

S. Valli Sanghami, John J. Lee, Qin Hu

In the given technology-driven era, smart cities are the next frontier of technology, aiming at improving the quality of people's lives. Many research works focus on future smart cities with a holistic approach towards smart city development. In this paper, we introduce such future smart cities that leverage blockchain technology in areas like data security, energy and waste management, governance, transport, supply chain, including emergency events, and environmental monitoring. Blockchain, being a decentralized immutable ledger, has the potential to promote the development of smart cities by guaranteeing transparency, data security, interoperability, and privacy. Particularly, using blockchain in emergency events will provide interoperability between many parties involved in the response, will increase timeliness of services, and establish transparency. In that case, if a current fee-based or first-come-first-serve-based processing is used, emergency events may get delayed in being processed due to competition, and thus, threatening people's lives. Thus, there is a need for transaction prioritization based on the priority of information and quick creation of blocks (variable interval block creation mechanism). Also, since the leaders ensure transaction prioritization while generating blocks, leader rotation and proper election procedure become important for the transaction prioritization process to take place honestly and efficiently. In our consensus protocol, we deploy a machine learning (ML) algorithm to achieve efficient leader election and design a novel dynamic block creation algorithm. Also, to ensure honest assessment from the followers on the blocks generated by the leaders, a peer-prediction-based verification mechanism is proposed. Both security analysis and simulation experiments are carried out to demonstrate the robustness and accuracy of our proposed scheme.

Hyo-Eun Kim, Seungwook Kim, Jaehwan Lee

Data is one of the most important factors in machine learning. However, even if we have high-quality data, there is a situation in which access to the data is restricted. For example, access to the medical data from outside is strictly limited due to the privacy issues. In this case, we have to learn a model sequentially only with the data accessible in the corresponding stage. In this work, we propose a new method for preserving learned knowledge by modeling the high-level feature space and the output space to be mutually informative, and constraining feature vectors to lie in the modeled space during training. The proposed method is easy to implement as it can be applied by simply adding a reconstruction loss to an objective function. We evaluate the proposed method on CIFAR-10/100 and a chest X-ray dataset, and show benefits in terms of knowledge preservation compared to previous approaches.