Shirou Wakayama

Cost-effective Product Traceability System Based on Widely Distributed Databases

A cost-effective and easy way of introducing a product traceability system is to start from a small system and gradually extend it to a large-scale system. Traceability systems used in previous field tests are unsuitable for largescale deployment because they use a single, centralized database. This paper describes an extendable traceability system proposed by Toshiba that employs distributed databases. Our proposed system called LoTR consists of two components, a DHT-based ID-DB resolution mechanism and TraceBack method. The ID-DB resolution mechanism is used to acquire a DB location from an ID. We apply the DHT to accomplish required scalability. We have developed a DHTDNS mounter to achieve seamless access to DHT-based IDDB resolution from ordinary DNS resolvers. In addition, the TraceBack method creates links to bind distributed databases. We have evaluated the operation of the system with a real field trial. As the next step, we shall analyze its qualitative behavior through large-scale experiments.

Extendable product traceability system from small start

A cost-effective and easy way to introduce a product traceability system is to start from a small system and gradually extend it to large-scale systems. Traceability systems used in existing field tests are unsuitable for large-scale deployment because they use a single, centralized database. This paper describes a extendable traceability system proposed by Toshiba that employs distributed databases and ID-hash values. We have evaluated the proper operation of this system with a trial system and plan to analyze its qualitative behavior through large-scale experiments

Ecosystem of naming systems: discussions on a framework to induce smart space naming systems development

In this paper, we discuss the ecosystem of naming systems for smart spaces. Since we think resolution of detected object names should be a common trigger of smart space applications, we focus on naming systems. We aim at a naming system framework to enable the following. First, each application developer of smart spaces can design and implement new applications freely. Minimal limitations should be imposed on developers. Second, users can interact with applications opaquely. We propose combination of the following two approaches to induce naming systems evolution for smart space applications. The first approach is integration of independent naming systems for simple client resolvers. The second approach is a client resolver model to handle independent naming systems concurrently. We also describe some case studies concerning smart space application scenarios.

On scalability of DHT-DNS hybrid naming system

In this paper, we describe our evaluation work of a DHT-DNS hybrid naming system together with our prototype design and implementation of the DHT-DNS mounter. For the evaluation we conducted a series of experiments in a large-scale emulation testbed. We found a bottleneck limiting scalability of the proposed hybrid naming system at the mounter.

A Design for Distributed Backup and Migration of Distributed Hash Tables

To realize huge-scale information services, many Distributed Hash Table (DHT) based systems have been proposed. For example, there are some proposals to manage item-level RFID information with DHT In such services, service reliability is important. A DHT service is believed to be highly reliable because it is distributed. However, even if the entire service does not stop, the risk of data loss is unavoidable because a DHT consists of many physical nodes. Clearly, in order to avoid compromising the scalability of a DHT-based service, a scalable backup and loss-recovery scheme is required. To solve the problem, we propose a framework of distributed-to-distributed data copy. The proposed design utilizes the distributed manner of DHT algorithms, and it enables coping from a distributed system to a DHT system with minimal bottlenecks.

Kallima: a tag-reader protocol for privacy enhanced RFID system

Privacy is a major concern with RFID tags and many solutions have been proposed. As many approach requires secure hash function on each tag, cost of tags imposed by those solutions is significantly high for wide development. We propose a protocol that uses pre-calculated Bloom filter to send tag identity for increased privacy with little additional cost per tag. In our approach, secure hash function calculation is done in tag production phase and each tag does not have any hash functions. Instead, each tag must have random number generator and volatile memory.