https://www.jetqwang.com/home daily 1.0 2023-05-30 https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1597273038445-JUO39MW40CAPLT53ZBHO/DSC07443.jpg Home - I am Jet Wang! I’m a Software Engineer specializing in fintech. https://www.jetqwang.com/pastprojects daily 0.75 2023-07-13 https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/a001d0a8-00c2-469b-a8b0-a62d88fc8a49/Screenshot+2023-07-12+at+8.29.01+PM.png https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1626100014964-EQLJ6FLP753J9NDP6YIP/mouse_game.gif Past Projects https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1623341012856-D4LGX1O4SWYHLFYLS3IF/reworld_trimmed.gif Past Projects https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1610500336652-TIOXV18J3Y2MWZ7MKR26/Proj4PhaseCWaNG.gif Past Projects https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1610499790199-VO1ZIYOWVN105O11VYN9/Proj3PhaseC%2BWANG.gif Past Projects https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1597891766804-M3WB6WQPEH1S8ILSV144/ratViewCompressed.gif Past Projects - In the Pandarinath Lab, we train Long Evans rats to perform a protonation-supination task. In essence, we cue the rats to turn a knob either clockwise or counterclockwise. We intent to implant electrodes to measure neural activaty in the M1 cortex. By pairing this neural spiking data with muscle EMG data, we can find important information that may lead to a better understanding of muscle-neural communications and future brain machine interfaces. To facilitate this rodent training, I developed RatView, a graphical interface for real-time, simultaneous monitoring of up to four rodents during behavioral training. RatView presents useful, temporal information that allows for dynamic and responsive training. This project provided me an introduction to MATLAB GUI making as well as communication techniques between a script and a Raspberry Pi. https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1598310451076-TR1SGN3PFGO12HI6JL9Q/spacetraders.gif Past Projects - I believe that failures should be shown just as much as successes. SpaceTraders was the first video game I ever made. It was also a team project for my Object and Design class. Ironically, in a code design class, it was some of the worst code I had ever written. To me, it was a realization to how complicated and gritty video game creation can be, and it taught me to analyze every single aspect of a project. As you can see, there are many issues with SpaceTraders, namely a lack of art, window sizing, and any form of story telling. I often return to this project to remind myself the importance of understanding the bigger picture. ST is a prime example of when “done is better than perfect” is wrong. If a project is seen as modules, simply completing a module is not enough. Stress testing and a reconnection to the main project is absolutely necessary and should be considered at every step of the iterative design process. Despite all of that, I’m incredibly appreciative of its presence. By making so many mistakes, I’ve been able to intuit how to write better code. It’s taught me how to walk through the thought process in making design choices, and now I feel comfortable explaining all my coding decisions. https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1597779661885-SSNZEF349NTIIGO3GFAC/CoronaKing.gif Past Projects - You are a medieval doctor that was transported to America as the last line of defense after the coronavirus pandemic has destroyed much of the American infrastructure. It is up to you to defeat the huge viruses with your deadly syringes while dodging spewed RNA and spaces that go under quarantine. This game was largely an introduction to C as well as many low-level concepts such as DMA, VSync, Page-flipping, and Sound. I also utilized containerization and iterative design. Overall, it was an informative experience with control registers and the infrastructure of gaming engines. https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1597890008155-H0UM2AJQYM18DXPI9X0Y/PillReminderStoryBoard.png Past Projects - Accounting for over 125,000 deaths every year. medication non-adherence should not be a difficulty people have to experience. My team and I worked on a solution to streamline the medication taking process. Here, we embarked on a vertical project to create a pill-reminder app. Using Norman Principles and other principles of design, we created an intuitive and user-friendly interface to make the process of taking medication seamless. The entire project can be viewed here. We tested multiple interfaces to determine viability and conducted multiple user interviews, gaining real-world experience and information. https://www.jetqwang.com/currentprojects daily 0.75 2021-07-14 https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1597888880369-ZVJMW8K9VTQ3PMU4LMF3/LFADS.png Current Projects - LFADS (Latent Factor Analysis via Dynamical Systems) utilizes a sequential auto-encoder to recreate spiking data in single-trial neural populations. Previously, due to noise and single-trial variability, single-trial data analysis was infeasible. As demonstrated here, LFADS is able to accurately predict observed behavioral variables. In the Pandarinath Lab, I assist with further LFADS decomposition, creating additional functions to corroborate its usage with RDS (Reza’s Data Structure), a structure to hold neural data. I use these tools to further identify the underlying dynamical systems that govern the activity of neural populations. By identifying the latent factors that determine neural spiking, we can create intricate brain machine interfaces that can normalize the lives of paraplegics and amputees. https://images.squarespace-cdn.com/content/v1/5f3472f3814c9941ca37c770/1597459978994-35X49XC2IFKABT53Z1N1/DLC.gif Current Projects - Dystonia is a neurological disorder involving the basal ganglia and other brain regions that results in painful, involuntary muscle movements and affects over 250,000 people in the United States, making it the third most common movement disorder (Jinnah & Hess, 2017). M utant mice, known as DRD mice, which exhibit dystonic movements due to a lack of dopamine are used for calcium-imaging samples of population level neurons in the striatum, a region of the basal ganglia (Rose, 2015). However, a current complication is that due to concerns of phototoxicity, the calcium imaging can only be recorded for minutes at a time(Icha, 2017). This concern, combined with the infrequent, dystonic muscle contractions, results in poor and capricious data collection. I’m currently building a deep-learning computational model that is able to predict when these dystonic movements will occur. To create this model, the positions of the mice are estimated using DeepLabCut, a 3-D marker-less pose estimating tool that uses a deep-learning classifier to mark body segments at each frame of a video feed(Mathis, 2019). I then feed these position vectors to a trained LSTM (Long Short Term Memory Neural Network) so that it can make real-time predictions of dystonic movements. As the model predicts an oncoming episode of muscle flexion, an electronic signal is sent to the calcium-imaging implant that can then be turned on for a safe amount of time, greatly increasing data capturing abilities. This additional data could potentially lead to further discoveries regarding the nature of dystonia and form the infrastructure of a future cure. https://www.jetqwang.com/ceevee daily 0.75 2023-05-30 https://www.jetqwang.com/contact daily 0.75 2020-08-24