Design and Prototyping of a Low-Cost Ventilator for Rural Hospitals
This report includes the design and prototyping of a portable automatic bag-valve mask (BVM), or commonly known as the Ambu bag. This development is for use in emergency transport, resource-poor environments, and mass casualty cases like the COVID-19 pandemic. This device replaces the need for human operators whose job is to squeeze the BVMs for extended periods of time. The prototype is made from a stainless-steel skeleton, measuring 470 x 240 x 230 mm, with the addition of acrylic coverings. A repurposed motor from a car is used to drive the squeezing arm. The speed of the arm for inspiration and expiration along with the pausing time between each breath can be adjusted with this prototype. It also features an LCD screen to display the arm speed, along with real-time pressure graph displayed on both phones and computer monitors. For future versions, an app is to be developed to enable the control of the automatic bag-valve mask from phones and tablets, further creating ease for users and increasing portability. Additionally, important requirements will be added: alarm system for over pressurization, control for inspiration to expiration ratio, number of breaths per minute, control for tidal volume, pressure relief valve, and assist-control mode. The cost of this prototype is approximately $430. With this design of an automatic BVM, it allows for the production of a ventilator-like technology that will be able to perform main functions of basic ventilators at a fraction of the current cost.
Potential Diagnosis of Cancerous Cells Through Utilising Optical Spectroscopy
Cancer is responsible for an estimated 9.6 million deaths in 2018. Deaths from cancer worldwide are projected to reach over 13 million in 2030. Thus, developing a device that has the capability to solve today’s toughest global challenge is crucial by utilizing a simple yet robust approach - “SEEING THE UNSEEABLE” through bold innovation. Although removing cancer is much more effective than either radiation or chemotherapy, when unseen residual cancer cells remain, they could grow back into tumour overtime. The reoccurrence of cancer contributes to a greater risk of death. Hence, launching a system that is able to distinguish between the cancerous cell and normal cell is ultimately essential to make sure no cancer is left behind during surgery. This robust optical system is established with quantitative approach by exploring the integration of an algorithm into the developed software. The end result of this device has the capability to provide users an accurate numerical pH value. The developed system is integrated with the smart IoT gateway capability whereby this powerful analytical device is incorporated with the real-time monitoring, data transformation and data analyzer. Harnessing the power of technology lets us fight cancer better. Each time a pathologist analyzes tissue after operation, it can take up 2 to 3 days because the tissue has to be frozen, thinly sliced, and stained so it can be viewed under the microscope during the process of biopsy. Thus, it is crucial to invent this Surgeons’ VisionMetric device which has an IoT-based microcontroller that is capable of providing real-time numerical value on-site.
Improving Particle Classification In Wimp Dark Matter Detection Using Neural Networks
In all experiments for detection of WIMP dark matter, it is essential to develop a classifier that can distinguish potential WIMP events from background radiation. Most often, clas- sifiers are developed manually, via physical modeling and empirical optimization. This is problematic for two reasons: it takes a great deal of time and effort away from developing the experiment, and the resulting classifiers often perform suboptimally (which means that a greater amount of expensive run time is required to obtain a confident experimental result). Machine learning has the potential to automate this and accelerate experimentation, and also to detect patterns that humans cannot. However, two major challenges, which are shared among several dark matter experiments, stand in the way: impure calibration data, which hinders training of models, and unpredictable physical dynamics within the detector itself. My objective was to develop a set of machine learning techniques that address these two problems, and thus more efficiently generate highly accurate classifiers. I was able to obtain raw data for two dark matter experiments which exhibit these challenges: the PICO-60 bubble chamber [2], and the DEAP-3600 liquid argon scintillator [1]. For each experiment, I developed and compared three general-purpose algorithms intended to resolve its inherent challenge (impurity and unpredictable dynamics, respectively). In PICO-60, background alpha and WIMP-like neutron calibration datasets are used for training; however, there is an impurity of 10% alphas in the neutron set. While a conventional classifier was developed (and is believed to be 100% accurate), machine learning in the form of a supervised neural network (NN) has also been previously explored, because of the benefits of automation. Unfortunately, it achieved a mean accuracy of only 80.2% – not usable as a practical replacement for conventional methods in future iterations of the experiment. In DEAP-3600, photons are absorbed by a wavelength shifting medium and re-emitted in an unpredictable direction, before being detected by one of 255 photomultiplier tubes (PMTs) around the spherical detector. The randomness severely limits the accuracy of conventional classifiers; in a simulation, the best so far removes 99.6% of alpha background, while also (undesirably) removing 91.0% of WIMP events. Because of physical limitations, simulated data is used for calibration, with 30 real-world experimental events available for testing. I have written a research paper [11] about my work on PICO-60, which has been approved by the PICO collaboration and pre-published at https://arxiv.org/abs/1811.11308. It is currently undergoing peer review for publication in Computer Physics Communications. All PICO researchers are listed on my paper for their work on the original PICO-60 experi- ment. They did not contribute to this study; I completed and documented it independently.