• WandaVision Platform: Developed a new sensor testing and debugging platform, WandaVision, enabling real-time data visualization and analysis for sensor data.
• Dewey Duct Project: Designed a mini wind tunnel using Solidworks to facilitate air flow sensor testing. Achieved a 15% improvement in integration with the WandaVision platform.
• Data Platform: Contributed to the development of a data pipeline for camera vision-based modeling of wound imagery, utilizing U-Net for improved accuracy and efficiency.
• Collaborated across diverse teams to conduct iterative testing and deployment of various technologies. Engaged in brainstorming sessions to devise innovative solutions for a range of challenges.
• Developed a U-Net-based pipeline for wound imagery modeling, achieving improved accuracy.
• Streamlined project tracking and agile processes using Jira and Smartsheets.

• Projects: CAN-based GPS Tagger, CAN-based Third-party Implement integrator, Satellite-Based Farming Prediction, Code first SQL Data Integration, Camera Image Acquisition App
• Programming and Implementing MRS Embedded Modules for Off-road vehicular CAN-based controller for specialized research products.
• Scripting custom process automation code for Data analytics and SQL Uploads with Backup protocols.
• Setting up and providing in-house support for VM-based products and file transfers with ext4 file format support.
• Designed a custom Android App for more efficient documentation in image capture for Project records.
• Embedded solutions to improve data collection capability in the research of the Agricultural Bio-systems Domain.
• MATLAB-based automation for visualizing and processing Satellite Imagery data to predict crop production and growth loss using NDVI.

• Projects: Sensing Objects in Multiple Terrain, Advanced Machinery Data logger Units
• Implementing vision systems and mapping tools to achieve the required goals for the research group using tools such as MATLAB and LabVIEW.
• Sort out the Technological Challenges the Agricultural segment face and find ways to solve and improve overall efficiency.
• Working on supporting Linux-based data logging systems at the hardware level.
• Program Embedded products to suit the required client and internal needs of the research group.

• Projects: In-Line Camera Test System, Embedded Inventory control label system.
• Controls and Test Co-op Engineer in the Advanced Manufacture Engineering group.
• Prototype new test modules or procedures to improve manufacturing efficiency using python and proprietary software codes.
• Maintain and rectify the test sequence for new builds.
• Create a custom part tracker for the electronics flashing stations to backtrack uploaded software and inventory.

• Project: Long Range Irrigation Monitoring System
• Research: Long Range Low Power IoT devices data collection and power analysis.
• Research Assistant on the Internet of Things (IoT) Research Group developing a Wireless Sensor Network for Precision Agricultural Domain. (Smart Farming).
• Design custom data logger with wireless capability at a generic level. Using Python at the high-level post-processing and C++ at the firmware level.
• Enable future technologies to include temporary storage and additional sensor option for the specific farming application.

• Research: ISO15118 Protocols and deployment for car charging stations.
• Developed Display driver for ISO15118-based Car Charging Station written in C case structure.
• Led a three-member team, with a specific focus on back-end drivers for the display unit.

• Requirement: Design a cost-effective and accurate data logger for IoT-based information gathering and prediction for the horticulture department.
• Developed the prototype Data logger at stage 4 with a power management cycle perfected to run an entire crop season.
• The end product allows a layman to visualize and measure data of the field as a part of Smart Farming.

We propose a deep learning methodology for multivariate regression that is based on pattern recognition that triggers fast learning over sensor data. We used a conversion of sensors-to-image, which enables us to take advantage of Computer Vision architectures and training processes. In addition to this data preparation methodology, we explore the use of state-of-the-art architectures to generate regression outputs to predict agricultural crop continuous yield information. Finally, we compare with some top models reported in MLCAS2021. We found that using a straightforward training process, we were able to accomplish an MAE of 4.394, RMSE of 5.945, and R^2 of 0.861.