core-program

pods

pathfinders

programs

about-us

program

team

careers

projects

mentors

project-ideas

blog

mentor-faq

scholars

reviews

symposium

research-archive

research-opportunities-for-high-school-students

Our next winter deadline is December 15, 2023 11:59pm PT. Apply today to lock in your spot!

10-session deep dive into a research topic of your choice

6-week research project with an expert and peers who share your passion

A career discovery experience with 3 expert mentors in your chosen fields

research-ideas-for-high-school-students

research-opportunity-guides

showcasing-opportunities

student-faq

for-mentors

for-educators

for-parents

resources

about

outcomes

In a world where learning languages is a vital skill, one can question the makeup of how different languages are processed in the brain. The world has become a global village. There is diversity not only in terms of human beings, but cultural and language diversity as well. To be successful in the present day world, it is important for people to know more than one language for communication, learning, and business. The accepted definition of bilingualism is being able to “speak two languages fluently”, but the definition in the scientific field has been long debated. The reason for debate behind who is considered bilingual is due to a lot of factors, such as one’s skill level in the language, their nativity to the language, their upbringing, and age. Being bilingual has become very predominant and 43% of the population of the world is bilingual. The purpose of this paper is to discuss the true definition of bilingualism, the various factors involved, one being bilingual and the brain’s area of language production and comprehension. In this paper, **the central question I aim to answer is, does a bilingual brain, even when a bilingual is only using one language, process linguistic information in the same manner as a monolingual brain?** First, I will attempt to define bilingualism and what classifies someone as bilingual with all the factors taken into consideration. Additionally, I will discuss which parts of the brain are involved in language production and comprehension. I will also dissect how a monolingual brain works in comparison to a bilingual brain, and reference various other studies that have investigated how the brain processes language. Finally, I will address my question regarding which processes and areas are the same between monolinguals and bilinguals, and which are different.

Neuroscience, sensory perception, neural circuits, scientific writing, cognitive science

Bilingualism in the Brain

For this project, Chan strives to create an attention-monitoring tool that will ultimately provide computer users with real-time feedback on the quality of their attention ('flow state') and serve as a productivity building tool. Chan will build behavioral models that incorporate indicators of attention such as blinks, head movement, and head rotation to calculate each participant's attention index via webcam recording. He will also develop a backend connection with his model to a google form that contains 36 questions from the validated Flow State Scale (FSS) by Susan A. Jackson to quantify the ground truth measure of participants' flow state throughout the experiment. To follow an organised work flow, store the collected data in a database, and perform data visualization, a Graphic User Interface (GUI) will be developed to be used in the actual experiment. With this software prototype, Chan will then conduct an experiment with design forthcoming that validates his flow state model during different participant tasks. After analysing the correlation between attention and flow state from the database, Chan plans to write up his results in a research paper for junior investigators that summarizes procedures and results of this project. Lastly, all relevant data collected as well as the software prototype of the model will be publicized to enable further possibilities of new research from such data and model.

Medical applications of AI/Machine learning, AI/ML in the field of radiology, cognitive neuroscience topics (especially memory), stroke pathology/imaging/interventions/epidemiology, diagnostic or interventional radiology

Flow State Attention Feedback Tool: Model Training and Validation

This project identifies the most promising treatment for diabetes using regenerative medicine incorporating stem cells. After examining the factors that cause metabolic disorders the potential of stem cell therapies to cure diabetes using different strategies is compared. The terms “stem cells,” and “diabetes” were used in a search of the PubMed database to identify review articles for this study in the past 10 years, 5 articles caught my eye which they directly related to the treatment of diabetes with the use of stem cells.  

Stem cells can engraft into humans and differentiate into insulin-producing cells to effectively treat diabetes. Smit et l., demonstrated that mesenchymal stem cells (MSCs) are effective when treating diabetes and other metabolic disorders and reviewed how effective dosing and delivery methods are important to achieve successful outcomes. Finally, the paper also compares the treatment options that are currently being used with the new stem cell therapy, noting that while stem cell treatment is more expensive than current treatments such as injected insulin, they are only applied once. Therefore, because stem cell treatment can be curative, it could be more effective and efficient than current treatments such as injected insulin.

Stem cell therapy is an option for the treatment of diabetes because of its safety, effectiveness, and curative potential. While there were many debates at first on whether stem cell treatment was safe and effective, recent research shows that stem cell treatment could treat diabetes by differentiating into insulin-producing cells to potentially cure diabetes.

Preparation for Pre-Med or STEM Undergraduate studies. Entrepreneurship and Business. Scientific Research. Data Science and Analytics.

Different Types of Stem Cells in an efficient treatment of Diabetes

Kelly is working on an Animal welfare project in the food industry. She shares a great passion for animal rights, and shes working towards finding a solid foundation for implementing or maybe proposing new welfare regulations in the industry; Shes is researching Countries such as Switzerland and S.Korea which have the best and most strict rules and are highly efficient with low inflation rates and comparing them to the current regulations we have in the united states to demonstrate the difference and introduce Points of improvement. 

Animal welfare, not only for companion animals, but also for livestock has been discussed for a long time, regarding its physical and mental well-being. Being incorporated into the Guidelines for Multinational Enterprises on Responsible Business Conduct of the The Organisation for Economic Co-operation and Development (OECD), animal welfare is now encouraged internationally and protected by legislations in most economically-stable countries. However, there is no global treaty governing the protection of animal welfare, which results in extreme fluctuations in the degree of animal welfare protected by law in each country. Thus, this paper aims to compare and contrast the animal welfare legislations regarding the egg, pork and dairy industry in three countries, South Korea, Israel, and Switzerland in order to identify differences and investigate the improvement able to be made to each country.

Veterinary Medicine,Microbiology,Public Health, Epidemiology, Food Hygiene and Food Science,Infectious Disease,Genetics

Comparison of Animal Welfare Regulations for the Egg, Port, and Milk Industry in US, Switzerland, and South Korea and Investigation on Improvements in Animal Welfare

Eating Disorders include such disorders as Anorexia Nervosa, Bulimia Nervosa, and Binge Eating Disorder. Patients with anorexia nervosa suppress their hunger, exercise too much, have low Body Mass Indices, and are dangerously thin. Bulimia Nervosa is characterized by binge-purge cycles, in which a patient eats more than is medically recommended in a very short period of time, only to remove the extra calories through a purging process, like throwing up or excessively exercising. Binge eating disorder includes unusual eating habits in which patients eat large amounts of food in a short period of time. However, patients do not purge these extra calories, causing patients with binge eating disorder to grow obese quickly and have high Body Mass Indices. Patients with binge eating disorder have comorbidities like Gastroesophageal Reflux Disease (GERD), where stomach acid shoots up burning the esophagus and sometimes the mouth.

My research focuses on creating an integrated Artificial Intelligence solution to finding eating disorder (such as anorexia nervosa, bulimia nervosa, or binge eating disorder) prevalence based on the responses to a questionnaire developed from the National Longitudinal Survey of Adolescent to Adult Health (ADD Health) database. Analysis centered around question H3GH8, "Have you ever been told by a doctor that you have an eating disorder, such as anorexia nervosa or bulimia?". By using Recursive Feature Elimination, I was able to decrease the number of variables used by the model from the original number in thousands to a number just below 100. My research has been sent to the International Youth Neuro Association, and will be published in their November 2022 issue.

Machine Learning, Medicine, Web Design or Podcast Creation, Large Dataset Analysis/Data Science, Mental Health, Psychiatry

How could AI assist in the prediction and search for risk factors of anorexia nervosa?


While traditional research papers include adult responses, rather than those of young
adults, the data that was collected for this paper was assembled exclusively from a group of children and teenagers. In this paper, we will explore the minds of a diverse group of young adults through the prism of their feelings and fears about COVID-19. Within this research, we compared an emotion score against a fear level; though these are normally considered to be dependent variables, the emotion score was averaged out within three questions. These three questions focused on how someone felt with masks, their comfort level, and how well they focused on schoolwork. The objective of this study was to see how the fear of COVID-19 depended on the emotion of masks. An infographic was also designed as an overview of the results and to draw attention for others to read about it!

General psychology, social psychology, cognitive psychology, politics, research methods and statistics, theatre

Mask Mayhem

(Included in notebook as well)
When we open a web page, play an online game, or watch a video online, we send and receive data. This data can be separated into two main categories: benign and malicious. Benign traffic is your everyday "regular" traffic where the data you send and receive are expected by the service you are using. In other words, everything you're telling the service is normal and you're just trying to use it normally. Malicious traffic is when someone sends unexpected data that the server was never designed to handle with the intention of negatively impacting the server. This can include slowdowns or even full outages of a service. My project focuses on DDoS attacks. 

A DDoS attack is short for a Distributed Denial of Service attack. It involves a third party flooding a host with malicious requests with the intention of slowing down or even halting operations. This can result in anything from minor dips in server performance to a complete outage of a service. DDoS attacks work by using up system resources. For example, a server's CPU may be forced to spend most of its cycles performing operations on garbage data sent by a DDoS botnet rather than handling legitimate requests from actual people. 

If DDoS traffic is detected and dropped before it can be fully processed, the vast majority of the attack's effect will be mitigated and users may not even notice a difference. We approached this by using machine learning. By using CatBoost, we were able to accurately and efficiently detect malicious traffic.
(Note - the zip I'm sending is just the final product, please let me know if I should submit additional resources)

Social Sciences, Computational Social Sciences, Social Media, Graph Analysis, Depression on Social Media, Cyberbullying on Social Media, Hate Speech and Fake News Detection, Digital Epidemiology, Natural Language Processing, Artificial Intelligence, Machine Learning, Data Science, Threat Intelligence, Internet Security, Denial of Service Attacks, Network Traffic Analysis, Computer Science, Computer Networks

Using Machine Learning to Detect Malicious DDoS Attack Traffic

Abstract:
	Many people in the world are into the stock market as they see it as a way to make passive income both in the short and long run. However, many people don’t have the time to sit around and watch the stock market daily. This is why people such as stockbrokers and financial analysts exist, but they are expensive. Taking this into account, creating a potentially free application that analyzes the stock market in real-time and provides the user with easy-to-understand and valuable information on specific companies can significantly help them for a variety of reasons. People can easily save money, for starters, as they won’t have to invest in people who help them with stocks. Additionally, they won’t have to spend hours analyzing the market as the application will tell them if it is a good idea to invest or sell. So, this research being conducted around a distinct question matters because it will be able to make the stock market more accessible to people in the sense that they won’t have to spend time analyzing it, but rather just access a reliable application that gives them everything they need to make a decision. Overall, I hope that this research and project development allows me to help people make money off the stock market long-term without spending hours watching the constantly changing stock market.

How the Code Works:
      For this specific application, the method used is taking in user input of how much they have to invest, how okay they are with risk on a scale of 1 to 100 (1 being not wanting risk and 100 being completely okay with risk), and if they want to make a short or long term investment (short-term being 5 years and long term being 10 years). Based on this input, the program will generate a list of three companies that the user should invest in to achieve the best return. The program will generate and produce three graphs of the company’s historical stock growth, which is imported from Yahoo Finance so that the user can visually see the investment they are making. Additionally, the program will do some calculations in the background and present the user with an estimate as to their expected return and how much money they should expect to have in both five and ten years. The output to the code will give the user their return rate and expected return for both the short and long term so that they can see the impact of investing for the short and long term and make the decision for themselves. 

Findings:
	To quickly summarize what the outcome of my research was: I found that if people were more okay with risk, they would want to invest more for the long term. This led me to decide to recommend major stock companies such as Apple for them to invest in because that is what would allow them to maximize their profit in accordance with the risk level. Additionally, I found that people that were not as keen to risk would want to invest more in the short term. This led me to decide to recommend more bonds and index funds to them so that they could get the best return possible.

Further Research/Code Development
	If I were to further develop this code, I would use portfolio theory to determine how much money a user should invest in different stocks so that they can attain the best return for the lowest amount of risk and protect themselves against the unpredictability of the stock market.

Business, Analytics, Finance, Literature, Economics, Behavioral Finance, Foreign Policy, Military, Renewable Energy, Machining Learning AI

Simplified market  for young investors.

Nanoparticles (NP) have shown great potential as drug delivery systems that are highly effective while also enhancing the chemical properties of the drug itself. In the last decade, numerous studies and clinical trials have shown that nanotechnology-based strategies are significantly efficient and versatile in the field of biomedicine especially as nanocarriers for treatments in rare neural, cardiovascular and blood disorders. Nanoparticle-based drug delivery systems are especially prominent solutions for neurological diseases because of the blood-brain barrier (BBB) and blood-cerebrospinal fluid barrier (BCSFB) that both block most endogenous and exogenous substances from entering into the central nervous system (CNS). Spinal Muscular Atrophy (SMA) is a rare genetic neurodegenerative disease affecting lower motor neurons and is the leading cause of genetic infant mortality. Antisense Oligonucleotides (ASOs) are a genetic treatment for SMA by split-slicing pre-messenger RNA (pre-mRNA) and halting protein translation. Due to its poor penetration and low cellular uptake, it is inefficacious when trying to mediate sites in the CNS. However, cell-penetrating peptide nanoparticles (CPPs) have shown to be significant nanocarriers that enhance the drug’s chemical properties in offsetting the disease and allow it to reach into the CNS with increased target specification. This review provides a discussion of advancement in nanotechnology-based drug delivery systems specified to amelioration of ASOs relevant to SMA disease progression and its usage in developing further treatment for SMA patients.

Data Science, Data Analytics, Machine Learning, Sports Analytics, Natural Language Processing, Data Visualization, Computer Science, Biotechnology

Review of Nanoparticle-Based Drug Delivery Methods for the Treatment of Spinal Muscular Atrophy

Avi's project will be a full treatment of supervised learning. The culmination of the project will involve attempting to tackle a supervised learning problem in NLP end-to-end. To start, we will discuss the setup of a supervised learning problem and a general framework that we can approach any such problem with. We'll discuss how to train our models on observed data and conduct the proper experiments to validate that the model will perform as well as needed on incoming, previously unseen data. At the end of the project Avi will know how to identify problems which are suitable for supervised learning, train a model on seen data, verify that a model is ready for real world use, and understand what it means for a computer specifically an algorithm) to have "learned something". 

Machine Learning, Data Science, Quantitative Modeling, Statistics, Mathematics

An Introduction to Supervised Learning and Applications in NLP

From the Black Death, which decimated Europe, to the Spanish flu, which had an estimated death toll of up to 100 million, pandemic viruses have been a major force in human history. Both the bubonic plague and Spanish flu resulted in drastic changes on many levels, ultimately altering every facet of life during this time. More recently, the COVID-19 global health emergency, caused by the novel SARS CoV-2 virus, emerged in 2019 and quickly overwhelmed healthcare systems around the world. Globally people were asked to isolate and stay at home. These widespread lockdowns led to rapid changes in the way humans interacted with each other and the world. Not only has the SARS CoV-2 pandemic affected the way of life of humans, it has also affected the ecological balance of other respiratory viruses. There are many reasons for this change in existing balance, including sanitization and social distancing, masking, and virus-virus interference. In this review article, I summarize epidemiological and laboratory data on how and why the SARS CoV-2 pandemic has changed the prevalence and seasonality of other common respiratory viruses. This information may be helpful in predicting when infections with various viruses may arise, and help health care providers determine the types and timings of interventions such as medications and vaccinations.

Molecular Biology, Virology, Metabolism, Immunology, Proteomics

How the COVID-19 pandemic has affected the transmission, prevalence, and seasonality of other respiratory viruses.

Selective mutism (SM) is a rare pediatric anxiety disorder in which a child fails to speak in specific social situations. Due to its classification as a rare disorder that affects less than 1% of the world’s population, research on this disorder is limited, inhibiting available treatment options for SM patients. Thus, it is critical to research more on this relatively unexplored disorder. Social anxiety disorder (SAD) is a prevalent anxiety disorder characterized by the fear, self-consciousness, and embarrassment in social situations in which a person may be judged or evaluated negatively. SM is known to present with other anxiety disorders, primarily SAD. The main treatment for SM is cognitive-behavioral therapy (CBT), followed by pharmacological interventions such as selective serotonin reuptake inhibitors (SSRIs). With limited knowledge of this rare disorder, this paper attempts to suggest a potential novel treatment for SM, serotonin-norepinephrine reuptake inhibitors (SNRIs) which are a common treatment option for SAD. SNRIs are a class of antidepressants used to increase both an individual’s serotonin and norepinephrine levels in the brain. Previous case studies of SM and research on these specific antidepressants used commonly to treat comorbid SAD elucidate the antidepressant’s potential on SM. With its strong usage in the treatment of SAD, SNRIs may also be effective as a treatment for SM, a disorder that has similar clinical presentations and therapeutic approaches to SAD. In conclusion, this review paper calls to attention the lack of research on selective mutism and identifies a novel alternative approach for its effective treatment.

Gene editing, Disease Biology, Translational Science, Sensory Neuroscience, molecular biology, Python, Java, cell biology

A Prospective Treatment for Selective Mutism through an Analysis of Social Anxiety Disorder

The project's aim is to determine the viability of a system where cars in traffic are able to produce electricity that can be used to assist the existing power grid. The idea is that a car will act as a moving magnetic field through a passive coil built into tunnels on the roads and produce electricity that can be used. This is all built on the concepts from Faraday's law and Lenz's law. The student is working on figuring out the how the theorems relate to each other and how they can be applied to this concept. 

Hardware Software Engineering, Programming, 3D modeling, Hardware, Circuits, PCB Design, Coding Games, Robotics

Inertial Harvesting of Energy Through Induction Using Road Cars

When there is a task in which there is freedom in the options available, humans can have a hard time finding the solution in all of the other options. Computers, however, are faster at finding the solutions because they can analyze all of the available options more rapidly than humans. In this paper, we will use genetic algorithms to determine the optimal route a bus should take to pick up students in a particular area. For this we would need to consider the bus stops, the distance from one stop to the other, and the traffic in the area. Using all of that information we can draw the best bus route for every bus in a district.  In other words, we can take the time these bus route workers use to draw routes and use a genetic algorithm that does the work for them. In the event of a changing environment such as a missing bus driver or changes in traffic, a genetic algorithm can likely adapt better than a human and still find the best routes available. In addition, in the event that a machine does not provide the best route because it didn’t have enough time to find all of the alternate routes, we should still have a fairly better route than a human given the same amount of time. In conclusion, an algorithm that can find the best route is needed because it saves time and can adapt to special circumstances in which bus map drawers can not. Our use case demonstrates that a machine learning algorithm is capable of performing a task with more efficiency and better results than humans alone. These results provide evidence that machine learning using a genetic algorithm may be used throughout the commercial industry to improve productivity in many fields.

Astrodynamics, orbital mechanics, spacecraft trajectory design and navigation, Aerospace Engineering, and robotics

Can a genetic algorithm be trained to optimize the routes for buses in a variable environment?

Comparative study of PTSD in veterans and domestic violence survivors. 

1. introduction
- introduce brain, disease, explore from psychiatric, neuroscientific, biochemical perspectives

2. 4 patients- 2 who have suffered domestic violence, 2 who are veterans

3. analysis: 3 perspectives: psychiatric, neuroscientific, biochemical

4. compare/constrast

5. draw conclusions

Molecular Biology, Biotechnology, & Neuroscience

Comparative study of PTSD in Veterans and Domestic Violence Survivors. 

There is a widespread issue in STEM where females experience limited representation in certain fields like engineering, math and computer science. This research project examines the role that students in a New Jersey public high school believe teachers play in their desire to pursue more advanced STEM studies. Previous research studies have found a difference between genders in their desire to pursue STEM studies and careers, with teachers playing a role in the development of this interest. Studies have shown that teachers have demonstrated implicit bias against females in STEM classes and particularly in math, engineering, and computer science classes. On the other hand, teachers who have encouraged girls to pursue more advanced STEM studies have been correlated with positive outcomes. My research question is: How do male and female high school students in this New Jersey public high school describe their learning experiences in STEM classes? Further, do these students believe their STEM classroom learning experiences have helped them develop their confidence in pursuing more advanced STEM studies? The experiences of male versus female students will be examined. After receiving administrator and parent permissions, I will launch a pilot survey. After the pilot, I will make any necessary refinements before launching the final online survey to a sample size of approximately 100 students at this high school. I have already conducted and written a preliminary literature review that discusses the role of parents, teachers, peers, and spatial skills as they relate to gender differences in girls’ and boys’ confidence and anxiety levels when it comes to STEM. Positive teacher interactions have been found to boost their interest in STEM subjects and seems to be covered less in the literature than the parental role. For these reasons, STEM classroom learning experiences, including teacher-student interactions, will be examined in this study.

Education, social sciences, cultural studies, psychology and emotional well-being, NGO/nonprofits, business, gender issues, poverty, program development and evaluations, parent participation, foreign language learning or teaching, faith/religion

The Role of Teacher-Student Interactions in the Development of Student Confidence in STEM Classrooms

Throughout history, relations between the United States and Russia have evolved. During World War IIr, the U.S. and the Soviet Union were reliant on each other to defeat Germany. However, During the latter half of the 20th century, the diplomatic relations grew more strained, resulting in the Cold War. With the birth of the Russian Federation, from the ashes of the Soviet Union, in December 1991, there were renewed hopes in Moscow and Washington of a stable and prosperous diplomatic relationship.This dream ended with the election of Vladimir Putin in 2000, who had the old mentality of competing against western influence and gaining control of Eastern Europe. Russia’s 2022 invasion of Ukraine under a “special military operation to denazify Ukraine,” has diminished the relations between Washington and Moscow through sanctions.  This research article gives an insight and prediction of what the future diplomatic, military and economic relations between Moscow and Washington will be in the aftermath of the Russian invasion of Ukraine. To effectively do this, I compare the present relations to those during the Cold War. I conclude that the relationship between the Russian Federation and the U.S will not be friendly, at least for the near future. The two nations will try to undermine each other through sanctions . This means that the international community will be more polarized than they have been in the 21st century,  and forced to pick sides between the US and Russia on global matters. I would also like to conclude that this new cold war will be vastly different because Russia is not a superpower while the U.S is, unlike the Cold War.

Environmental Politics, Comparative Politics, African Politics, Political Communication, Qualitative and Quantitative Methods

What would the diplomatic and economic relationship between Russia and the US look like after the Russo-Ukrainian war of 2022?

Because of the simple recording equipment in the early to mid 20th century, hundreds of incredible movies have been stuck with black-and-white video and patchy, static-like audio. Many have forgotten about these classic films and many more refuse to try and watch these movies because of the poor video and audio. Recent advancements in graphical and audio manipulation through computer science models have made it possible to alter each of these fields. By mapping black and white pixels to corresponding red, green, and blue pixels, one would be able to fully transform black-and-white video to colored video. As for audio, one would be able to isolate certain sounds through signal processing, amplify them, and reduce background static, yielding a much clearer audio in the overall film. Combining these two methods, with the help of research mentors at Polygence, would create a unique model that unites both graphical and audio manipulation for proper refinement of vintage films. With such a model, old movies could be easily converted to more modern formats and would be widely more accessible to viewers.

Economics, Statistics, Data Science, Natural Language Processing, Labor Economics, Industrial Organization, Antitrust, Economics of Education,  AI/ML, Text Analysis, Macroeconomics

Revamping Movies with AI

Neural Network model predictions of monthly changes in Apple stock based on the company’s current and past financial data


With the rise of increasingly powerful machine learning algorithms, many have applied these concepts to the stock market in the hopes of creating a portfolio with the maximum amount of profit possible. However, most predictors simply rely on data derived from stock prices themselves in order to make these predictions, such as candlestick trends and patterns. The model this project is working on will focus on one company, Apple, and predict its stock with not only previous stock prices of the company, but also the stock prices of the NASDAQ, of which Apple is a part of. The model will also take into account the stock prices of the other major players of the NASDAQ, such as Amazon and Netflix. In addition, the model will input the financial data of the company, including variables such as the company’s revenue, gross profit, as well as other financial metrics such as gross profit margin and return on equity. The global price of materials of Apple’s most bought products will also be accounted for. These series extend from 2017 to 2022, providing 5 years worth of data. The model will utilize a neural network to identify patterns within this data and determine the monthly change in Apple stock. I chose a neural network in order to use a deep learning model to go through hundreds of data points in order to find trends within the data that would take a human ages to uncover.

Neural Network model predictions of monthly changes in Apple stock based on the company’s current and past financial data

Over 6 million Americans are living with Alzheimer’s disease, and dementia deaths have seen an increase of 16% during the COVID-19 pandemic. Dementia was predicted to cost Americans  $355 billion by the end of 2021. With an increasing percentage of cases and rising healthcare costs, the need for accessible prediction of dementia utilizing the analysis of properties of digital biomarkers is necessary. The majority of individuals who experience the symptoms of Alzheimer’s are 65 years or older. Starting from the age of 65 years, the risk of succumbing to Alzheimer's significantly increases - doubling every 5 years. There is an evident overlap between the high-risk age groups of COVID-19 and Alzheimer’s Disease. Thus, the demand for digital prediction tools has unquestionably increased. The purpose of conducting this research is to employ digital and physically contact-free technology to construct an artificial intelligence model to identify early symptoms of Alzheimer’s Disease. Data was collected from fluency data from UCSD. The machine learning algorithm that was most effective at predicting the advancement of Alzheimer’s Disease in patients who are able to function cognitively normally has an accuracy percentage of 93%. Further research into this area of building digital Alzheimer’s Disease prediction tools will help aid the early diagnosis of dementia, lower the burden on medical professionals, and assist in meeting the rising healthcare needs of countries with underdeveloped healthcare systems.
 

Neuroscience of Learning and Memory, Computational Neuroscience, Data science, Artificial Intelligence

Award-Winning Machine Learning Predictive Algorithm of Alzheimer's Disease from the Analysis of Semantics and Early Linguistic Variables

We are going to explore breast cancer development and metastasis and look into the mechanism of action via tumor suppressors. Ideally, we will research p53 (a tumor suppressor/others) and see how that influences ROS production. ROS is influential in tumorigenesis and leads to microenvironment that facilitates favorable factors for cancer. Our research will explore how this suppression leads to ROS production and if this in turn influences migration of cancer cells. We will explore if ROS is a direct influence on the migration or just a byproduct of tumor suppressor mutations and how that plays in leading to the migration of cancer to other tissues. 

Meet Polygence Scholars and explore their projects