Unplanned hospital readmissions bring large social and economic costs to both patients and healthcare organizations. We propose a mobile health platform with the goal of reducing the current high rates of unplanned readmissions, in order to reduce costs while maintaining or improving the quality of care. We designed the platform to mimic intelligent behavior in hospitals - in particular, the behavior of delivering timely “care” to patients based on their needs. The main idea is to expose personalized key symptoms and conditions in real time, to be monitored during the postdischarge period by care providers for fast intervention and patient support. To achieve this, the patient (post discharge) and nursing stations are treated as dynamical discrete-event systems (DES), and the system is designed using DES modeling techniques and supervisory control theory. Software applications and primary components of the platform pertinent to system implementation are discussed conceptually. Examples are provided to shed light on system functionalities.

This paper proposes the design of a flexible multisensor surgical manipulator to be used in Minimally Invasive Surgery (MIS). The proposed system constitutes intrinsically actuated flexible arm, drive mechanism, and control system. Flexibility is achieved by connecting and actuating varying length discrete rigid links with micromotor equipped with rotary encoder. Comprehensive design details are presented on the basis of choice of micromotor, torque requirement, and degree of freedom achievement. The design was tested with dynamic simulation. The proposed system provides infrastructure for semi-automatic control using multivariable control theory to help the surgeon to follow a predetermined surgical path. Furthermore, it accounts for the limitations of existing MIS manipulators. It is believed that the result of the paper will have practical impacts on making flexible surgical arms more accurate and user friendly than its existing counterparts.

This paper introduces a systematic engineering approach to modeling the hospital system as a comprehensive healthcare provider; other healthcare organizations (HCOs) are considered special cases of the hospital system (HS). The objective is to manage HCOs in real time, in a way to maintain an acceptable quality of care (QC) while reducing cost of care (CC). To achieve this, the HS is treated as a dynamical system, for which major Subsystems of healthcare that impact QC and CC are established, and then the relevant system state variables are identified. It will be shown that by minimizing unnecessary waiting time and prioritizing patients on the basis of certain clinical and nonclinical conditions, QC and CC can be improved and reduced, respectively. A key aspect of the proposed approach is in treating the patient in a HCO as a finite state machine. This simplifies the modeling problem to developing a structured finite state automaton, denoted as a Structured Patient Automaton. Examples are provided to shed lights on the proposed modeling approach and waiting time optimization.

In this paper, a novel simultaneous multi-channel data acquisition system is proposed. Analog signals with different bandwidths are applied to an analog multiplexer with a single analog to digital converter. A novel scalable adaptive controller is designed to detect different bandwidths in order to determine the proper sampling rate for each input signal. The analog multiplexer is adaptively controlled to switch between the analog signals of variable bandwidths. The target technology of implementing the proposed design is the Field Programmable Gate Array (FPGA). The Analog-to-Digital Converter interface and the adaptive controller are implemented in the FPGA using hardware description language. The synthesized prototype used only 11% of the total logic elements (of Altera Cyclone II, EP2C35F672C-6N FPGA) and 15% of its total memory bits. The worst-case prorogation delay observed for the system is 12.04 ns, which is less than the 50 MHz clock period of 20ns. The Cyclone-II FPGA consumes power as low as 12 mW. The proposed system can be used in various applications that require heterogeneous multi-channel data acquisition system such as biomedical engineering.

The objective of this paper is to use adaptive wavelets for lung sounds analysis and show that wavelets with one vanishing moment can successfully detect pathological changes of the lung which produce sounds with measurable regularities. Local regularity measures allow us to detect some significant components of adventitious sounds which are difficult to detect by the physician ears due to their short duration. This paper will concentrate on a development of lung sounds pattern recognition features. The key properties of pattern recognition features, Lipschitz regularity at any point of wavelet transform modulus maxima along the maxima lines converging to this point, regularity of some adventitious lung sounds such as Crackles and Wheezes will be analyzed. Numerical results prove that normal lung sound is more regular than crackles lung sounds.

Genetic algorithms(GA), which are based on the idea of natural selection and survival of the fittest, have proven successful in solving complex problems that are not easily solved through conventional methods. Parallel genetic algorithm(PGA) is an extension of the classical GA. The important aspect in PGA is migration and GA operation. This paper presents PGAs that use fuzzy algorithm and natural select concept to migration of subpopulations. Fuzzy algorithm is used to change GA operators. Experimental results show that the proposed methods exhibit good performance compared to the classical method.