Jaspreet Singh
Get in touch with us at info@new.com
Portfolio
Scroll to see projects or check out my resume or CV.
​
Jaspreet Singh
NEURAL ENGINEER
Nice to meet you.
I am a bioengineer with a deep passion for solving complex problems at the intersection of neuroscience, engineering, and data science. My goal is to create innovative solutions that improve patient outcomes and alleviate suffering through technology and creativity.
​
In 2024, I completed my Master of Science in Bioengineering (Neural Engineering track) at the University of Pittsburgh, where I specialized in Brain-Computer Interfaces (BCI) and Medical Devices. My background combines neuroscience, data science, and engineering—giving me a unique perspective on both the clinical needs of patients and the technical tools required to address them.
​
I am currently seeking full-time opportunities in data science, neural engineering, and medical device development, where I can contribute to building impactful technologies that advance healthcare and human well-being.
Portfolio Projects
01
Motion-Edge Detector
​Skills: numpy, cv2, openCV, python
Using numpy and cv2 in Python, I developed a black and white motion detection camera. The threshold detection can be altered in this as well. The video on the left displays a trial of this project.
​
​Event cameras, such as the Dynamic Vision Sensor (DVS), are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. They offer significant advantages over standard cameras, namely a very high dynamic range, no motion blur, and a latency in the order of microseconds
​​​Click here to go to my Github page and view more about this project.
02
MNIST Digit Classification with MLP
Skills: Python, NumPy, Keras, TensorFlow, artificial neural networks (ANN), activation functions (ReLU, Sigmoid), model tuning, overfitting/underfitting analysis, and image classification (MNIST).
In this project, I built a Multi-Layer Perceptron (MLP) using Python libraries like NumPy, Keras, and TensorFlow to classify handwritten digits (1–4) from the MNIST dataset, achieving ~95% accuracy. I experimented with different activation functions (ReLU vs. Sigmoid) and adjusted hidden layers and node counts to evaluate their effects on performance. This process deepened my understanding of how model architecture and complexity influence overfitting, underfitting, and overall generalization in neural networks.
Click to view the code and project on my GitHub portfolio.
03
1-D Cochlear Model
Skills: Python, Fast Fourier Transform (FFT), signal processing, spike encoding, bio-inspired design, audio sensor modeling
In this project, I developed a neuromorphic audio sensor that mimics a 1D cochlea using a microphone input. Spoken audio (digits) is processed in real-time using FFT to extract frequency bands, and spike events are generated based on power thresholds. This biologically inspired system simulates how the human cochlea converts sound into electrical signals, enabling efficient and low-power auditory processing.
This approach has practical applications in auditory prosthetics (e.g., cochlear implants) and real-time speech recognition systems, offering a compact and energy-efficient alternative to traditional digital signal processing.
Click here to view the code on GitHub.
04
Keyword Spotting Using Spiking Neural Networks
Skills: Spiking Neural Networks (SNNs), Leaky Integrate-and-Fire (LIF) neurons, neuromorphic computing, Intel Loihi Lava platform, PyTorch, Keras, audio preprocessing, keyword spotting, speech recognition.
Keyword Spotting, or using A.I to detect spoken words with increasing accuracy has a multitude of uses in today's day and age - beginning with Alexa, to translation, to accessibility. Spilking Neural Networks may offer an alternative approach with lower latency and higher computational power.
In this project, using Loihi's neuromorphic chip platform Lava, I created a Spiking Neural Network to perform keyword spotting for spoken digits (0-9) from a validated dataset. Additionally, Pytorch and keras were used to implement a LIF neuron model to perform keyword spotting.
​
I have not made my code or paper publicly available for privacy reasons. Please reach out to view this code, paper, or presentation and I would be happy to share more information.
05
Medical Device: Rotating Vial Holder
Skills: prototyping, prototyping
This project focuses on developing a rotating medication vial holder to improve the efficiency and safety of lumbar epidural injections. It addresses a critical clinical need: maintaining sterility while drawing medication from vials without requiring a second medical professional, thereby reducing procedure times and minimizing the risk of needlestick injuries for healthcare staff. The rotating holder is designed to secure vials, provide hands-free operation using a foot pump, and enhance workflow efficiency.
By applying ethnographic studies, the team observed the real-world challenges in clinical settings, particularly the reliance on medical assistants to hold vials, which prolongs procedure times and compromises sterility. The project aims to eliminate the need for an additional assistant, lowering the risks of needle sticks and infections, and reducing human error. The design underwent several iterations, incorporating feedback from clinicians and focusing on ease of use, sterility, and compactness.
​
The innovation has the potential to significantly impact healthcare workflows, increasing the number of patients seen per day and improving safety in high-risk needle procedures.
​
Explore more by clicking here.
06
Regulatory Affairs Consultant for Spinal Cord Stimulator
Skills:
art of a dedicated team of engineers, I worked alongside Dr. Trent Emerick on the commercialization strategy for the Fella spinal cord stimulator. My role focused on regulatory affairs, guiding the device through FDA Class III approval processes and ensuring compliance with international medical device standards. I also contributed to clinical trial design, patent research, and developing market entry strategies to optimize the device’s impact on chronic pain management. This project deepened my passion for advancing medical technologies and applying regulatory and strategic insights to bring life-changing innovations to market.
07
Neural Data Analysis
Skills: MATLAB, signal processing, linear regression, spike sorting, Gabor filtering, time-lagged modeling, statistical testing (ANOVA), convolution, PSTH analysis, visualization (comet plots), and BCI decoder design.
I have applied these skills across several MATLAB-based projects focused on neural signal analysis and brain-computer interfaces. These include decoding hand movements in monkeys using linear regression models (94% accuracy), modeling visual perception via Gabor filters and convolution to simulate retinal/V1 activity, and analyzing behavioral data from delayed reaching tasks using PSTHs and ANOVA to identify neural tuning and response latency. I also implemented spike sorting pipelines to classify neuronal firing patterns from raw recordings. Together, these projects demonstrate proficiency in computational neuroscience, signal analysis, and the development of engineering solutions for neuroprosthetic and vision system applications.
08
Changemaker Scholar
Skills: Innovation strategy, interdisciplinary collaboration, entrepreneurial mindset, problem identification and framing, design thinking, systems-level thinking, leadership, stakeholder engagement, pitch development, and social impact analysis.
As part of my ongoing journey to become a changemaker scholar through the Big Idea Center, I have committed to exploring innovation and entrepreneurial concepts and what change-making in action and its impact looks like across various disciplines, professions, and areas of interest. This program combines students from a variety of disciplines, and ​​I joined the scholar series inaugural class. ​
Simulink code for robotic exoskeleton (KINARM)
09
Skills:
developed and implemented custom motor and collision tasks on the KINARM robotic exoskeleton using Simulink and Stateflow, integrating real-time tracking of hand kinematics such as position, velocity, and trajectory precision. My work included programming goal-directed reach tasks and pre-shot routines to study movement planning and sensorimotor integration. These tasks support research in neurorehabilitation by providing precise, quantitative assessments of motor function in individuals with neurological impairments.
10
Undergraduate Thesis & Publication
Skills: Neuroimaging analysis, resting-state functional connectivity (rsFC), statistical modeling, fMRI preprocessing (SPM/FSL/AFNI), region-of-interest (ROI) analysis, hypothesis testing, data visualization, literature synthesis, psychoneuroimmunology, developmental neuroscience, emotional regulation circuits (amygdala, BNST, sgACC), and trauma-informed research design.
According to the CDC, a majority of adults report experiencing at least one adverse childhood event (ACE), such as abuse, neglect, or resource deprivation. These early experiences can have lasting effects on adult mental health. My undergraduate thesis examined how childhood trauma and perceived socioeconomic standing influence adult stress reactivity, focusing on resting-state functional connectivity within a key emotional regulation circuit. The research found that trauma was linked to reduced connectivity between regions like the amygdala, BNST, and sgACC—suggesting long-term neural impacts—while perceived socioeconomic status showed no significant effect.
​
​
11
Machine Learning: Sale Prediction Model Using Ridge-Regression
​
Skills: Ridge regression, predictive modeling, time series forecasting, regularization, Python (NumPy, Pandas, Scikit-learn), data visualization, business analytics, and sales trend analysis.My mother often tells me to plan for the future - which is a handy tool for a business for a busy graduate student. Using ridge regression, I created a model for future predicted sales for Jeep Wrangler. I used a dataset containing car sales of Jeep wranglers, I created a prediction model for future sales of cars. This predictive model is a helpful way to forecast what future trends in a company may look like based on previous data.
​
See the model here.
​
​
12
Key Performance Indicator Pipeline Project
​​
Skills: Google Cloud Platform (workflows, dataform, cloud batch/run), ETL, sql, python, powerBI
​​​​​​
​
13
UI/UX Designs
​Skills: Wix, Client-focused design, market analysis, html, UI/UX Design principles
​
I developed a website for a client with a motel in the Poconos in Pennsylvania. Please note this project is currently under construction/development as of 10/28/25.
Check out more of the website and the design process here! ​​​​​​
14
CMS (Medicare) Dashboard Development
​Skills: Data analysis, SQL, PowerBI, story-telling
​
I used available Medicaid Data to perform statistical analysis using SQL and present a story with my findings on PowerBI. Note: This project is under development.
See more of that project here.
See the github here. ​​​​
15
Building a Financial Assistant: Using Retrieval Augmented Generator using Langchain
​Skills: Langchain, RAG, Python, Docker, APIs (used Plaid), LLMS
​
This project is currently under development. ​​​​
See github here.
MEDIA
TECH STACK
COURSEWORK
