Machine learning algorithm partially reconfigured on FPGA for an image edge detection system

Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)signal.However,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or spoofing.One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images.But a high effort is required for image edge extraction.Here a support vector regression(SVR)model is proposed to reduce this computational load and processing time.The dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable region.Results show that the implementation in hardware is 68 times faster than that in software.This architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without DPR.This is also the lowest power consumption in current machine learning hardware implementations.Besides,the circuitry area is 41 times smaller.SVR with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning trajectory.This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.

Contextual Challenges in the Implementation of the Alliance for Maternal and Newborn Health Improvement, Prospective Cohort Study, an Experience from Rural Pakistan

Introduction: Improving maternal and newborn survival needs robust data on patterns of morbidity and mortality from well-characterized cohorts. It is equally important for researchers to document and understand the contextual challenges of data collection and how they are addressed. Methods: This was a prospective cohort study implemented from December 2012 to August 2014 in Matiari, Pakistan. A total of 11,315 pregnancies were enrolled. Participants were approached at home for sequential data collection through the standard pretested structured questionnaires. Some indicators were sourced through health facility records. Information on field challenges gathered through field diaries and minutes of meetings with field staff. Results: Inaccurate reporting of last menstrual period (LMP) dates caused difficulties in the planning and completion of antenatal data collection visits at scheduled gestational weeks. We documented ultrasound reports wherever available, relied on quickening technique, and implemented a seasonal event calendar to help mothers’ recall their LMP. Health system coordinators of public sector and private healthcare providers were individually approached for maximum data collection. But an unregulated private health system with poor record maintenance and health care providers’ reluctance for cooperation posed a greater challenge in data collection. Conclusions: Within a broader understanding of the health systems and socio-cultural environment, temporal and spatial feasibility of data collection should be considered thoroughly at the early stages of study designing, planning, resource allocation, and implementation. Pre-defined regular and need-based meetings with each tier of data collection teams and study managers help to reinvigorate field execution plans and optimize both quantity and quality of study data.

A SWITCHED HYPERCHAOTIC SYSTEM AND ITS FPGA CIRCUITRY IMPLEMENTATION

This paper introduces a switched hyperchaotic system that changes its behavior randomly from one subsystem to another via two switch functions, and its characteristics of symmetry, dissipation, equilibrium, bifurcation diagram, basic dynamics have been analyzed. The hardware implementation of the system is based on Field Programmable Gate Array (FPGA). It is shown that the experimental results are identical with numerical simulations, and the chaotic trajectories are much more complex.