Posted on

Team Status Report for 02/22/2025

There were no major changes to the existing design.

Challenges & Mitigation:

  • Datasets for ML not having all necessary data: There were no single datasets that have all the data we needed for health detection, so multiple datasets were selected to be combined. 
  • Potential plant loss during training: We planned to let the system support three plants last time. In order to ensure a larger dataset and be ready for plant loss, we ordered 4 plants for each plant type. We are planning to set up the sensors and actuators as quickly as possible.
  • Increased costs: We ordered plants and additional components (blackout window film, liquid nutrients, soil, basil plants, hamalayamix foliage plants, flowering plants), which was a larger increase in costs than we expected. To mitigate this, we found the cheap but appropriate components to be purchased and minimized the amount of extra components like soil.

Progress:

  • Finalized and ordered plants and additional components for growing plants.
  • Assembled the greenhouse.
  • Worked on code that runs sensors.
  • Started working on the design review report. Split up sections of the report for each person.
  • Keep working on ML integration and web app.

Next Steps:

  • Keep setting up temperature/humidity sensors and start setting up a heater.
  • Finalize web app and user interface.
  • Establish initial training framework for the ML model.
  • Keep working on the design report.
Posted on

Jana’s Status Report for 02/22/2025

This week, I worked on my part of the design presentation which included defining the quantitative design requirements. I also chose and ordered the live plants for the project, which means we now have a clear direction for data collection and analysis.

For the plant health prediction ML model, I selected the datasets to be used in training, opting for images of entire plants instead of just leaves as originally planned. As many of the available datasets didn’t have all the necessary data, I chose to combine multiple datasets to include the required abiotic and biotic stress factors. Since the dataset consists of full plant images, the leaf detection step may not be necessary for now. Instead, I plan to train the ML model on these images directly and will only preprocess the images if needed, based on model performance.

I explored several potential models for plant detection and health classification. YOLOv8n/YOLOv8s stand out as suitable options for object detection. These models would allow the identification and labeling of multiple plants and their individual parts within the images, which is suitable for our 3 plant system. Additionally, I’m considering ResNet50 for better overall performance or MobileNet, which is more lightweight and better suited for deployment on an RPi 5. My plan is to train multiple models and evaluate which one performs the best.

I am on schedule.

Next Week’s Deliverables:

  • I will start labeling the datasets consistently, given that the images come from multiple sources. This will ensure that the training data is standardized. 
  • I will also perform data augmentation to create a larger training set.
  • I will also establish the initial training framework for the model.
Posted on

Zara’s Status Report for 02/15/2025

This week, I focused on ordering all the necessary parts for our project and ensuring that the components we selected are fully compatible with our Raspberry Pi 5. I spent time carefully planning how the sensors and actuators will connect to the Raspberry Pi on the pinout, including how they will be powered and controlled. Additionally, I researched various water pump systems to determine the best way to integrate one into our design.

With the upcoming design presentation, I also worked closely with my team to refine our slides. I finalized the block diagram to visually present how the system components will connect and interact. To address previous confusion about the role of our machine learning model, I created a detailed flow diagram to clearly outline its function and integration within our system. My goal was to ensure that our audience would fully understand how our data inputs contribute to plant health classification.

Currently, we are on schedule, and our progress aligns with our planned timeline. However, I am slightly concerned that some of our ordered components may take longer than expected to arrive, which could delay the integration of certain parts. Fortunately, none of these delays seem significant enough to disrupt our overall schedule. Another potential issue is the soil nutrient and pH sensor we selected, as it has limited reviews and its reliability is uncertain. Due to budget constraints, we opted for a more affordable sensor, but if testing reveals any issues, we will order an alternative model as soon as possible.

By next week, I hope to have the temperature and humidity sensor set up and fully integrated with the RPi 5 to establish a working model for collecting environmental data. Additionally, I plan to begin testing other hardware components as they arrive to ensure a smooth transition into the next phase of our project.

Posted on

Team Status Report for 02/15/2025

The most significant risk this week was potential plant loss during model training or system adjustments, which could disrupt data collection. We are managing this by scaling up the system to support three plants instead of one, ensuring a larger dataset and providing backup in case any plants die. Additionally, we are mitigating this risk by setting up the sensors as quickly as possible to begin data collection early. This was the most significant change to the design.

Challenges & Mitigation:

  • Conflicting sensor data: To ensure uniform readings, we placed all plants in a single large pot, allowing us to use one set of sensors and actuators for all plants.
  • Limited Raspberry Pi pins: We selected multi-function sensors (e.g., a 3-in-1 soil pH, nutrient, moisture sensor, and a 2-in-1 temperature/humidity sensor) to reduce the number of connections needed.
  • Increased costs: A larger greenhouse ($103.99) and increased water capacity were necessary to support three plants. To offset this, we are minimizing additional costs by reducing the number of sensors and opting for cost-effective components.

Progress:

  • Finalized and ordered all system components.
  • Worked on the design presentation. 
  • Began planning the software, including machine learning integration and the web application.

Next steps:

  • Set up the Raspberry Pi 5, sensors, and camera once the components arrive.
  • Finalize the data collection pipeline for ML training.
  • Develop the web app framework and user interface.

We will include photos of the system setup once the components arrive.

 

Part A: Our automated greenhouse system enhances public health, safety, and welfare by providing an efficient, low-maintenance way to grow fresh produce, improving food security and reducing reliance on commercially farmed crops with chemical treatments. Safety is a top priority, and we are implementing physical dividers to separate water-sensitive electrical components from wet areas like the water tank, minimizing the risk of short circuits or electrical hazards. Additionally, the system automates irrigation and nutrient delivery, preventing overwatering, mold growth, and manual handling risks. With live monitoring and an intuitive control interface, the system reduces the need for constant supervision, making it safer and more accessible for users with limited mobility or time constraints. By offering an affordable and sustainable way to grow plants, our solution supports self-sufficiency and environmental sustainability while ensuring a safer, healthier growing environment.

Part B: In terms of social factors, our project is significant in that it promotes sustainable urban living by allowing easy indoor plant care. People who cannot be physically present at home to take care of the plants can take advantage of our solution. It is also especially impactful in communities that have limited access to green spaces, as people can grow their plants and form their personal gardens inside their houses. People that share the same sustainability goals regarding plant care can connect more, and educate each other with the plant information that our solution provides. Sproutly contributes to achieving more green-friendly and socially connected society.

Part C: Our goal is to create a mid-range product that balances affordability and advanced features. High-end competitors like AC Infinity ($699 for a 3 plant system) and Plant Hive ($984 for 1 plant) offer advanced sensing and automation but at a steep price. Our system provides similar capabilities at a more accessible cost of $385. This is comparable to Koru ($400), a lower-cost option that offers basic sensors and watering schedules but lacks control over external conditions. Unlike cheaper alternatives that support only one plant in an open environment, our system accommodates three or more plants in an enclosed space with real-time sensing, monitoring, camera feed, and ML-based plant health analysis. This makes our system a cost-effective alternative with premium features at a lower price point.

Part A was written by Zara, B was written by Yuna, and C was written by Jana.

 

Posted on

Jana’s Status Report for 02/15/2025

I researched and finalized the components required for the system, including all the sensors and the camera. I ensured that these components met the project’s durability and cost requirements and considered the pin requirements for connection to the Raspberry Pi 5.

I also worked on the design presentation, where I was responsible for updating the project schedule. Additionally, I researched the quantitative design requirements and linked them to the use case requirements wherever applicable.

I began researching potential plant health detection model datasets, including sensor and image datasets. While I found many datasets related to crop diseases and general health classification, I encountered a lack of suitable ones focused on household plants, specifically addressing conditions like over/under-watering, nutrient deficiencies, or excessive heat. Most datasets are centered on crop diseases or pest detection, which may not fully align with our needs.

I researched models that could be used for training the machine learning model, including pre-trained CNN models such as ResNet and MobileNet, as well as MLP models. I identified possible relevant works.

My progress is on schedule. I have completed the component research task and I am on track with my responsibilities for dataset research.

Next Week’s Deliverables:

  • Finalize dataset and model selection. If necessary, I will explore the option of training from my own dataset, though I am unsure if that is feasible.
  • Begin working on leaf detection using OpenCV.
  • Work on my assigned sections for the design report.
Posted on

Yuna’s Status Report for 02/15/2025

I looked up specific components to be ordered and made sure they met our project’s requirements. I specifically finalized actuator components like mini heater, humidifier, and LED lights.

For design presentation, I worked on listing solution approaches for hardware and software and testing and verification metrics.

I finished the initial setup with Django and React frameworks and made sure they work together correctly. Our original plan on the schedule was to first finish the backend portion and work on frontend later. However, while I was setting up the code I realized working on them together would be more efficient. I wrote basic code that can store plant database in Django. Currently, the database is based on sqlLite, but I’ll later use AWS DynamoDB to store data.

I did research about how I can use AWS Educate as a student. I applied to AWS Educate and got registered to the program. According to the website description, a student will get a credit of $35 in AWS Educate, which I believe will be enough for our project.

I am currently on schedule.

Next week, I will start implementing API calls for plant database and confirm API is being called correctly. I will also start working on basic UI of the app  (frontend).

Posted on

Yuna’s Status Report for 02/08/2025

This week, I worked with my teammates to work on proposal presentation. I specifically was in charge of Technical Challenges and Testing Metrics section.

For technical challenges, I researched and thought about possible challenges that we will face throughout the project. Based on our project requirements, I searched up different possible technical issues.  I took a look at the previous semester’s team who worked on a similar project to ours, and identified what similar challenges we might face and how we can be ready with backup plans. For Testing Metrics, I discussed with my team and looked up what metrics can be used to measure the success of the product. I referred to other past capstone projects and determined what numbers are appropriate for testing. It also helped me determine how specific I should be about testing. For example, measuring “accuracy” was vague – instead, I decided to use false positive and false negative rates.

I conducted research on how I can specifically use tech stacks we planned to use for web application. We are set on using Django for backend, since Django works well with ML/OpenCV, can integrate with MQTT, and I have experience in using it.

Our project is currently on schedule.

Next week’s goals are to order all the components needed, work on design presentation slides, and begin setting up the Django framework.

Posted on

Jana’s Status Report for 02/08/2025

This week, I worked on the proposal presentation, including use cases, use case requirements, testing, task division, and schedule (Gantt chart). Since I was responsible for presenting, I dedicated additional time to practicing and refining the presentation.

I researched existing products to build a well-informed feature set, identifying their strengths and limitations. I conducted informal surveys with friends, both plant owners and non-owners, to understand what features they would find most useful. Based on this feedback, I determined key use case requirements. Furthermore, I investigated the quantitative specifications these features should meet. For instance, I analyzed how much water capacity is required for a plant to remain self-sufficient for up to two weeks.

Additionally, I worked on defining testing and verification requirements with my teammates. I researched various sensors and methods for measuring their accuracy and precision in real-world conditions. I also spent significant time structuring the project schedule. I broke down tasks and submission deadlines into manageable phases, ensuring sufficient integration time and allocating buffer periods for unexpected events such as spring break and potential unforeseen challenges before the final demo.

I also began exploring suitable datasets for the machine learning application. I searched for publicly available plant sensor data and identified a Kaggle dataset that aligns well with our objectives. This dataset includes sensor data that we plan on measuring, along with ground truth labels for plant health status. Moreover, I looked into image datasets for plant health detection and found that most of them focus on leaf analysis. This insight led me to conclude that we will need to preprocess plant images using OpenCV to detect leaves before passing them into the model.

We are currently on schedule.

Next Week’s Deliverables:

  • Finalize the sensors to make the purchases.
  • Finalize the sensor and image datasets for the machine learning model.
  • Explore different machine learning models suitable for plant health detection.
  • Begin working on my assigned sections of the design presentation slides.
Posted on

Team Status Report for 02/08/2025

One of the most significant risks to our project is ensuring that we have enough time to train a machine learning model on sensor input data. If we do not set up our data collection system early, we may not have sufficient training data, which could result in an underdeveloped model that does not perform as expected. To mitigate this risk, our approach is to prioritize setting up the fundamental hardware and software components as soon as possible. This includes setting up the Raspberry Pi 5 with an initial sensor and the camera module, establishing a data collection and storage system to begin logging sensor and camera input, and implementing the initial machine learning pipeline so we can start training models early in the development process. By doing this, we ensure that data collection and ML training can happen concurrently with other parts of the project, minimizing delays.

There were no major changes to the design of the system. However, we made one key adjustment by switching from the Raspberry Pi 4B to the Raspberry Pi 5. This decision was made because the Raspberry Pi 5 offers better performance, which will help with machine learning training and real-time processing. Additionally, we were able to secure one for free from the ECE inventory, reducing project costs. This change does not introduce additional expenses but improves our system’s capability and allows us to work with newer hardware.

At this point, there are no major schedule updates. Our current focus is on ordering components and beginning initial setup. Once our parts arrive, we will start hardware integration and software development.

So far, we have finalized our project proposal and user case requirements, researched communication protocols for sensor and camera data transfer, ordered our first Raspberry Pi 5 unit, and finalized the initial list of parts to order next week. Our next steps include ordering all remaining parts and beginning hardware setup, setting up the Raspberry Pi 5 with essential sensors and the camera, and establishing the data collection and machine learning training pipeline. We will include photos of our hardware setup in future updates as we begin assembling components.

Posted on

Zara’s Status Report for 02/08/2025

This week, I collaborated with my team to finalize the proposal presentation slides. This included refining our user case requirements and engaging in an in-depth discussion on testing methodologies for different project components. We ensured that each aspect of our design was well-justified and accounted for potential testing strategies.

Additionally, I conducted further research into the communication protocols we will be using between the Raspberry Pi (RPI) and our Django-based web application. This involved understanding how we will handle data transmission for the sensors and the camera module.

To ensure we received the necessary hardware on time, I placed an early order for our first Raspberry Pi 5 unit. This will allow us to begin setup as soon as possible and secure the hardware before free units run out from inventory. As a team, we also finalized the list of initial components we plan to order for the base system.

Our project is currently on track. The planning phase is progressing well, and we expect to move into the implementation phase soon.

Our goals for next week include finalizing and placing the order for all remaining required components, specifically, the sensors we want to start on including temperature and light. We also want to begin setting up and testing the Raspberry Pi 5 to ensure compatibility with our planned system architecture.