JONAS LEE YEW HWA

Abstract:

It has been the end of 4 weeks spent at the NUS Department of Electrical and Computer Engineering and it really has been a fruitful attachment period. Our project was really heavily research-based and there were not really many hands-on moments but through the heavy and in-depth research we did to complete our tasks, we have gained a deeper insight into our given topic. My group, consisting of Shannen, Lexuan, Doris, Remy and I definitely had our ups and downs but the experience and knowledge gained was all worth it in the end.

NUS Department of Electrical and Computer Engineering

Background Info of ECE NUS:

Department of Electrical Engineering (changed to Electrical and Computer Engineering in 2000) was established in 1969, as one of the three departments of the Faculty of Engineering (FoE), in the Singapore University (predecessor of the National University of Singapore) with an inaugural batch of about 30 students and 10-15 academic staff members embarking on campus life at the old Singapore Polytechnic campus at Prince Edward Road, next to the Singapore Conference Hall. The founding Head of Department was Professor (Dr) Jimmy WY Chen.

The Department (together with FoE) moved to the current Kent Ridge Campus in 1977

Currently, ECE is the largest department in the Faculty of Engineering at NUS with over 80 tenure-track and teaching faculty and 1700 undergraduate, masters, and doctoral students.

ECE is a research-intensive department. Their faculty and research staff and students are engaged in cutting-edge research activities that span a diversity of areas. These include Communications & Networks; Control, Intelligent Systems & Robotics; Integrated Circuits & Embedded Systems; Power & Energy Systems; Microelectronic Technologies & Devices; Microwave & RF; and Signal Analysis & Machine Intelligence. By leveraging on expertise in these core areas, ECE engages industry and government agencies to address challenges embodied in the Smart Nation initiative such as the creation of intelligent built environments, transportation, urban sustainability, security, and health-care. ECE attracts more than S$30m of new competitive research grants every year. This level of funding together with their well-equipped facilities have raised their research profile to place them amongst the top Electrical & Computer Engineering departments globally.

Background Information of tasks/project we were involved in:

We were attached to Prof. Arthur Tay and Mr. Jermyn Lai for our WOW period, both of whom were researchers in NUS's Department of Electrical and Computer Engineering. The research lab was primarily focused on machine learning through sensors in specific relation to diseases like Parkinson’s. As a result, the tasks and project assigned to us was specifically tailored for us such that we could understand more about what they were trying to accomplish through machine learning and the extent of application of machine learning in the telehealth industry in the future. The project aims to allow us to understand more about the impact of machine learning in the telehealth industry and how it is being applied to treat and assess Parkinson’s Disease

Elaboration of tasks/project assigned:

1) Literature Review

For the first week of our attachment, we received a bunch of articles and research papers from Mr. Jermyn Lai and were told to complete a literature review on Parkinson’s Disease. We explored many different outlets for the assessment and treatment for Parkinson’s Disease, both already implemented and in the future. For the literature review, the process was very arduous as we had to skim through each and every research paper, taking note of the important points of each research paper and the conclusions drawn from the experimentations. We also had to know how to identify the important points of each research paper and not just copy and paste a whole paragraph into our literature review. We had to read in between the lines to fully understand the research papers and for words we did not understand, we had to find out their meanings ourselves. There were benefits to such a tedious process as we learnt to be self-directed in our learning, searching up information that we were unfamiliar with or words that we did not fully understand, taking learning into our own hands instead of always relying on other people to spoon-feed us with the information that we lacked.

2) Individual Presentation

After our literature review, Professor Arthur Tay felt that we were only scratching the surface on PD so he assigned us some topics to do more in-depth research on. They were the telehealth industry, gait analysis, sensors and the math behind clinical indexes used to treat Parkinson’s and machine learning. We were also instructed to do up a PowerPoint slides presentation. The topic assigned to me was “Sensors and the Maths behind clinical Indexes used in the assessment of Parkinson’s Disease” The challenge we were met with when attempting to complete the task lied within the short duration given and the lack of knowledge that we had surrounding our assigned topic. Hence, instead of depth, we instead chose to focus on the breadth of our research. We had to search for our own sources and also had trouble finding relevant information to include in our presentation and report. As for the mathematical equations behind certain clinical indexes, in order to understand the equations, we had to solve it step by step and some of the maths involved were way above the maths we had already learnt at our level, hence, we ran into a lot of trouble when trying to understand these equations. However, what we gained from these challenges was the determination to produce work that was still of a high standard even if we were unfamiliar with the topic or encountered a lot of trouble during the process. Whatever happened, the end product is what others will see and judge you based on, so whatever the cost, we learnt that the end product must be upheld to a very high standard and quality.

3 content knowledge/ skills learnt:

1) 4 different types of sensors used in the assessment of severity of Parkinson’s Disease

1. Accelerometers

An accelerometer is a compact device used to measure non-gravitational acceleration. When an object goes from a standstill to any velocity, the accelerometer responds to the vibrations associated with such movement. Microscopic crystals in the accelerometer will undergo stress when vibrations occur, thus allowing a voltage to be generated to create a reading on any acceleration. The force caused by vibration/change in motion causes the mass to squeeze the piezoelectric material which produces an electric charge that is proportional to the force applied on it. Since the charge is proportional to the force, and mass is a constant, the charge would be proportional to the acceleration. (F=ma) Accelerometers are integral to devices that track fitness and other measurements in quantified self-movement.

2. Gyroscopes

A gyroscope is a device that implores the usage of Earth’s gravitational force to deduce the orientation of an object. It is usually made up of a freely-rotating disk called a rotor, mounted onto a spinning axis in the center of a larger and more stable wheel. As the axis turns, the rotor remains stationary to indicate the central gravitational pull, and thus which direction indicates ‘down’.

3. Magnetometer

A magnetometer is a device that measures the direction, strength, or relative change of a magnetic field. It is often used in navigation devices and sometimes used in IMUs. They are able to measure small changes in the Earth’s magnetic field to pinpoint the user’s location. Unfortunately, magnetometers suffer from magnetic disturbances and these interferences may lead to some inaccuracies. However, even in the presence of such inaccuracies, magnetometers are still relatively drift free, and can be used to correct the drift in gyroscopes.

4. Inertial Measurement Unit (IMU)

An IMU is usually an electronic device that measures and reports a body’s specific force, angular velocity and sometimes, the orientation of the body. It usually consists of 3 accelerometers, 3 gyroscopes and sometimes, even 3 magnetometers (one for each axis in 3D space)

An inertial measurement unit works by detecting linear acceleration using one or more accelerometers and rotational rate using one or more gyroscopes. Some also include a magnetometer which is commonly used as a heading reference. Typical configurations contain one accelerometer, gyro, and magnetometer per axis for each of the three vehicle axes: pitch, roll and yaw. (alternatively designated as vertical, transverse and longitudinal respectively)

2) Causes of Parkinson’s Disease

The main cause of PD is the loss of nerve cells in the part of the brain called the substantia nigra. Nerve cells in this part of the brain are responsible for producing a chemical called dopamine which acts as a messenger between the parts of the brain and nervous system that help control and coordinate body movements. If these nerve cells die or become damaged, the amount of dopamine in the brain is reduced. PD affects patients’ physical movements as well as mental areas like their mood and cognition. This degeneration of nerve cells in the subthalamic area can be attributed to many factors including possible genetic influences, premorbid and nonmotor issues, and a variety of neurologic, cognitive, and psychiatric symptoms. (Cite NHS) Current thinking is that major gene mutations cause only a small proportion of all cases and that in most cases, non-genetic factors play a part, probably in interaction with susceptibility genes.

3) Electroencephalogram (EEG) as a possible treatment method for PD

EEG signals can be used in the early detection of FOG in PD’s patient. Complemented with special treatment such as sensory cuing, this classification system could be used in helping PD’s patient with FOG to ’unfreeze’ this symptom before it affected the movement. EEG subbands Wavelet Energy and Total Wavelet Entropy features can be used to represent changing during onset and freezing period. Classification done by BP-NN has a promising result and shows the feasibility of using EEGs for FOG detection. Moreover, this study support analysis of physiological brain dynamics during FOG. It may lead to better understanding of its underlying mechanism. Further exploration on other features, different area of the brain and classification methods will be our near future work before implementing it in a device.

2 interesting aspects of my learning:

1) Firstly, one thing that I found interesting about my learning process was that it was very self-directed with only small inputs from the professor. Most of the adjustments, research and inquiries were either done or put forth by us and the professor only helped out by giving us his expert opinions on what could be done to improve our project. The professor’s hands-off approach really pushed us to be more responsible over our own learning and to always ask questions and seek to improve.

2) Secondly, another interesting thing that presented itself to me was that the satisfaction that you feel when completing a task all on your own is something out of this world. The knowledge that all these was based off of your own hard work and that it all came to fruition is really the icing on top of the cake.

1 takeaway for life:

My 1 takeaway for life is that you should always enjoy what you are doing. Even if you find success with a certain thing, if you do not enjoy doing it, what’s the point. Something that you enjoy doing will always present you with bigger rewards and satisfaction than something that you find a chore to do or merely just a responsibility to uphold.