PriMPSO: A Privacy-Preserving Multiagent Particle Swarm Optimization Algorithm.

Centralized particle swarm optimization (PSO) does not fully exploit the potential of distributed or parallel computing and suffers from single-point-of-failure. Particularly, each particle in PSO comprises a potential solution (e.g., traveling route and neural network model parameters) which is essentially viewed as private data. Unfortunately, previously neither centralized nor distributed PSO algorithms fail to protect privacy effectively. Inspired by secure multiparty computation and multiagent system, this article proposes a privacy-preserving multiagent PSO algorithm (called PriMPSO) to protect each particle's data and enable private data sharing in a privacy-preserving manner. The goal of PriMPSO is to protect each particle's data in a distributed computing paradigm via existing PSO algorithms with competitive performance. Specifically, each particle is executed by an independent agent with its own data, and all agents jointly perform global optimization without sacrificing any particle's data. Thorough investigations show that selecting an exemplar from all particles and updating particles through the exemplar are critical operations for PSO algorithms. To this end, this article designs a privacy-preserving exemplar selection algorithm and a privacy-preserving triple computation protocol to select exemplars and update particles, respectively. Strict privacy analyses and extensive experiments on a benchmark and a realistic task confirm that PriMPSO not only protects particles' privacy but also has uniform convergence performance with the existing PSO algorithm in approximating an optimal solution.

TeleOph: a secure real-time teleophthalmology system.

Teleophthalmology (TeleOph) is an electronic counterpart of today's face-to-face, patient-to-specialist ophthalmology system. It enables one or more ophthalmologists to remotely examine a patient's condition via a confidential and authentic communication channel. Specifically, TeleOph allows a trained nonspecialist in a primary clinic to screen the patients with digital instruments (e.g., camera, ophthalmoscope). The acquired medical data are delivered to the hospital where an ophthalmologist will review the data collected and, if required, provide further consultation for the patient through a real-time secure channel established over a public Internet network. If necessary, the ophthalmologist is able to further sample the images/video of the patient's eyes remotely. In order to increase the productivity of the ophthalmologist in terms of number of patients reviewed, and to increase the efficiency of network resource, we manage the network bandwidth based on a Poisson model to estimate patient arrival at the clinics, and the rate of ophthalmologist consultation service for better overall system efficiency. The main objective of TeleOph is therefore to provide the remote patients with a cost-effective access to specialist's eye checkups at primary healthcare clinics, and at the same time, minimize unnecessary face-to-face consultation at the hospital specialist's center.

A secure and synthesis tele-ophthalmology system.

This paper describes a secure and synthesis ophthalmology telemedicine system, referred to as TeleOph. Under a Secure Socket Layer (SSL) channel, patient prerecorded data can be safely transferred via the Internet. With encrypted videoconference and white-board, the system not only supports hospital-to-clinic consultation, but also supplies hospital-tohospital joint discussion. Based on Directshow technology (Microsoft Corporation, Redmond, WA), video cameras connected to the computer by firewire can be captured and controlled to sample video data. By using TWAIN technology, the system automatically identifies networked still cameras (on fundus and slitlamp devices) and retrieves images. All the images are stored in a selected format (such as JPEG, DICOM, BMP). Besides offline-transferring prerecorded data, the system also supplies online sampling of patient data (real-time capturing from remote places). The system was deployed at Tan Tock Seng Hospital, Singapore and Ang Mo Kio, Singapore, where 100 patients were enrolled in the system for examination. TeleOph can be successfully used for patient consultation, and hospital joint discussion. Meanwhile, TeleOph can supply both offline and online sampling of patient data.

Tailored reversible watermarking schemes for authentication of electronic clinical atlas.

It is accepted that digital watermarking is quite relevant in medical imaging. However, due to the special nature of clinical practice, it is often required that watermarking not introduce irreversible distortions to medical images. The electronic clinical atlas has such a need of "lossless" watermarking. We present two tailored reversible watermarking schemes for the clinical atlas by exploiting its inherent characteristics. We have implemented the schemes and our experimental results look very promising.

A smart-card-enabled privacy preserving E-prescription system.

Within the overall context of protection of health care information, privacy of prescription data needs special treatment. First, the involvement of diverse parties, especially nonmedical parties in the process of drug prescription complicates the protection of prescription data. Second, both patients and doctors have privacy stakes in prescription, and their privacy should be equally protected. Third, the following facts determine that prescription should not be processed in a truly anonymous manner: certain involved parties conduct useful research on the basis of aggregation of prescription data that are linkable with respect to either the patients or the doctors; prescription data has to be identifiable in some extreme circumstances, e.g., under the court order for inspection and assign liability. In this paper, we propose an e-prescription system to address issues pertaining to the privacy protection in the process of drug prescription. In our system, patients' smart cards play an important role. For one thing, the smart cards are implemented to be portable repositories carrying up-to-date personal medical records and insurance information, providing doctors instant data access crucial to the process of diagnosis and prescription. For the other, with the secret signing key being stored inside, the smart card enables the patient to sign electronically the prescription pad, declaring his acceptance of the prescription. To make the system more realistic, we identify the needs for a patient to delegate his signing capability to other people so as to protect the privacy of information housed on his card. A strong proxy signature scheme achieving technologically mutual agreements on the delegation is proposed to implement the delegation functionality.