P. H. Tsai

Smart Medication Dispenser: Design, Architecture and Implementation

This paper presents the architecture and implementation of an automatic medication dispenser for users who take medications without close professional supervision. By relieving the user from the error-prone tasks of interpreting medication directions and administrating medications accordingly, the device can improve the rigor in compliance and prevent serious medication errors. By taking advantage of scheduling flexibility provided by medication directions, the device makes the users medication schedule easy to adhere and tolerant to tardiness whenever possible. The medication scheduler and dispenser controller do this work collaboratively in an action-oriented manner. An advantage of this design is that new functions can be added and existing ones removed or revised with little or no need to modify the dispenser control structure.

Compliance Enforcement of Temporal and Dosage Constraints

Medication dispensers treated in this paper are designed to help improve compliance by users who live at homes and take medications over long periods of time. The paper first presents an overview of medication specifications that define constraints for dispensers and dispenser components that administer medications as specified. When given a specification and constraints defined by it, the dispenser scheduler checks for consistency and feasibility of constraints and schedules medications to meet the constraints. Several basic algorithms needed for these purposes are described and evaluated

APAMAT: A Prescription Algebra for Medication Authoring Tool

We describe here the prescription algebra and its implementation for medication authoring tools. The tools are parts of medication use process, which consists of prescription entry systems, medication authoring tool, medication scheduling specification, medication scheduler, and programmable pill dispenser. A medication authoring tool aids the pharmacists to collect and integrate prescriptions, to verify drug-drug interactions amongst prescriptions one took for the prescribed duration, and to generate the scheduling specifications for pill dispensers. We design a prescription algebra for medication authoring tool to correctly complete its work. We have implemented the platform-independent medication authoring tool using JAVA. The screen snapshot are shown in the paper.

Smart phone based medicine in-take scheduler, reminder and monitor

Out-patient medication administration was identified as the most error-prone procedure in modern healthcare. Most medication administration errors were made when patients ac-quired prescribed and over-the-counter medicines from several drug stores and use them at home without proper guidance. In this paper, we introduce Wedjat, a smart phone application that helps patients to avoid these mistakes. Wedjat can remind its users to take the correct medicines on time and keep an in-take record for later review by healthcare professionals. Wedjat has two distinguished features: (1) it can alert the patients about potential drug-drug/drug-food interactions and plan an in-take schedule that avoids these adverse interactions; (2) it can revise an in-take schedule automatically when a dose was missed. In both cases, the software always produces the simplest schedule with least number of in-takes. Wedjat works with the calendar application available on most smart phones to issue medicine and meal reminders. It also shows pictures of the medicine and pro-vides succinct in-take instructions. As a telemonitoring device, Wedjat can maintain medicine in-take records on board, syn-chronize them with a database on a host machine or upload them onto an electronic medical records (EMR) system. A prototype of Wedjat has been implemented on Window Mobile platform. This paper introduces the design concepts of Wedjat with emphasis on its medication scheduling and grouping algorithms.

iMAT: Intelligent medication administration tools

iMAT is a system of automatic medication dispensers and software tools. It is for people who take medications on long term basis at home to stay well and independent. The system helps its users to improve rigor in compliance by preventing misunderstanding of medication directions and making medication schedules more tolerant to tardiness and negligence. This paper presents an overview of the assumptions, models, architecture and implementation of the system.

A Framework for Fusion of Human Sensor and Physical Sensor Data

Many disaster warning and response systems can improve their surveillance coverage of the threatened area by supplementing in situ and remote physical sensor data with crowdsourced human sensor data captured and sent by people in the area. This paper presents fusion methods which enable a crowdsourcing enhanced system to use human sensor data and physical sensor data synergistically to improve its sensor coverage and the quality of its decisions. The methods are built on results of classical statistical detection and estimation theory and use value fusion and decision fusion of human sensor data and physical sensor data in a coherent way. They are the building blocks of a central fusion unit in a crowdsourcing support system for disaster surveillance and early warning applications.

iNuC: An Intelligent Mobile Nursing Cart

Intelligent Nursing Cart (iNuC) is a mobile, point-of-care medication administration tool for the purpose of preventing medication errors and enhancing patient safety. It provides its user with work and time management and record keeping capabilities as well as a web portal to hospital services and information system. In addition, iNuC has several labor-saving and automation capabilities, including generating shift report from data and notes collected during the users shift, tracking medication and medical supply usages and automating requests for medication replenishment.

Component Model and Architecture of Smart Devices for Elderly

This paper describes a component model and component-based architecture of smart devices and systems that are designed to enhance life quality and well being of elderly individuals. In addition to providing the traditional view of hardware, firmware and software components, the model also provides developers with an operational view. The view enables the developer to specify device-user interactions as executable workflows and allows the device operations and user actions to be experimented with and their correctness ascertained throughout the design and development process. The paper also presents a simulation environment for this purpose.

Participant selection for crowdsourcing disaster information

Experiences with past major disasters tell us that people with wireless devices and social network services can serve effectively as mobile human sensors. A disaster warning and response system can solicit eye-witness reports from selected participants and use information provided by them to supplement surveillance sensor coverage. This paper describes a natural formulation of the participant selection problem that the system needs to solve in order to select participants from available people given their qualities as human sensors and the costs of deploying them. For this, we developed a greedy algorithm, named PSPG, that first calculates the benefit-to-cost (B2C) factor of each participant. It then dispatches participants to regions according to participants’ B2C. We compared PSP-G with the two well-known optimization methods, BARON and BONMIN. The results show that PSP-G delivers a near optimal solution with a low time complexity. In particular, the time PSP-G needs can be merely one tenth of the execution time of the existing optimization methods, which makes PSP-G a practical solution for emergency needs in disaster areas.

Design And Implementation Of Participant Selection For Crowdsourcing Disaster Information

A typical disaster surveillance and early warning system often needs to make timely and critically important preparedness decisions before disasters strike. When crowdsourcing observational data from people to enhance its sensor coverage, the system must be able to make effective use of volunteers, guide them during their exploration of the threatened area, and process reports from them in real time to extract decision support information of sufficiently good quality. This article focuses on the participant selection problem (PSP) which the system must solve in order to select participants from available volunteers given the benefits and costs of deploying them. The PSP-Greedy (PSP-G) algorithm proposed is known to be a near-optimal solution with a small fraction of execution time when compared with well-known optimization methods. The article describes an implementation of the PSP-G algorithm and the integration of the resultant PSP-G module into the Ushahidi platform. Performance data from two case studies based on Haiti Earthquake, 2010, and Typhoon Morakot, 2009, also described here, clearly show that PSP-G is a general practical solution.