This project makes use of cutting-edge technologies, encompassing Artificial Intelligence (AI), Machine Learning (ML), Internet of Things (IOTs), and web3/blockchain solutions. Our central aim is to provide a data-centric proposition that substantially amplifies productivity and efficiency while simultaneously expanding market reach through data-driven insights. To validate our approach, we require a pilot program to serve as a proof of concept.
This pilot program is divided into two distinct phases:
Phase 1: Suitable for Electrical & Electronic Students. The job responsibilities are outlined as follows:
Collaborate in building a prototype
Execute detailed plans
Gain hands-on experience in assembling electronic components, flow controls, and breadboard
wiring
Work under supervision
For those eager to learn, we offer instruction in blockchain programming, along with the opportunity to participate in the design of a dashboard control system. This phase presents an excellent opportunity for individuals looking to apply their technical skills in a real-world project.
Phase 2: Geared towards Computer Science Students. The job description is structured as follows:
Execute detailed plans
Collaborate closely with the Phase 1 team
Optimize hydroponic vertical farming systems to enhance efficiency, productivity, and
sustainability
Implement various aspects of the workflow and setup, including:
o Data collection
o Data pre-processing
o Data storage (structured database or cloud storage)
o AI and ML model development (foundational level)
o Basic model training
o Real-time monitoring
o Decision support
o Automation
Work under supervision
Both Phase 1 and Phase 2 teams are expected to work collaboratively, reflecting the cooperative spirit of
this project.
AI & ML In The Context of Vertical Farming
Data is collected on various environmental parameters (temperature, humidity, light intensity), plant characteristics (color of leaf greens), and nutrient levels (EC, pH), as well as harvest-related data (weight at harvest) to predict the success of a harvest, can indeed be considered a machine learning problem. Specifically, it falls under the domain of supervised machine learning.
Here's how it works:
Data Collection: You collect a dataset consisting of historical records where you have measured these various parameters and noted whether the harvest was successful or not. These records become your labeled dataset.
Feature Selection: The parameters you collect, such as temperature, humidity, etc., become the features (input variables) for your machine learning model.
Labeling: The success or failure of each harvest becomes the target variable or label. In supervised learning, the model will learn to predict this label based on the input features.
Training: You split your dataset into a training set and a testing/validation set. The training set is used to train a machine learning model, such as a classifier (e.g., logistic regression, decision tree, neural network), to learn the patterns and relationships in the data.
Prediction: Once the model is trained, you can use it to make predictions on new, unseen data. For example, you can input the current environmental conditions and plant characteristics, and the model will predict whether the current harvest is likely to be successful or not.
Evaluation: You evaluate the model's performance on the testing/validation set to assess its accuracy and reliability in predicting harvest success.
Regarding the question about whether these datasets are a legitimate part of Large Language Models (LLMs), it's important to clarify that LLMs are typically used for natural language understanding and generation tasks and are not directly used for analyzing structured data like the one you mentioned. LLMs are pretrained on massive text corpora and are particularly suited for processing and generating text-based information.
However, LLMs can play a role in your vertical farming scenario in the following ways:
Natural Language Processing (NLP): LLMs can assist in analyzing textual data related to your vertical farming operations, such as maintenance logs, research reports, or user feedback.
Decision Support: LLMs can generate natural language reports or recommendations based on the predictions and insights generated by your machine learning models. They can help communicate the results to stakeholders in a more understandable and human-friendly format.
In summary, while LLMs are not directly used for analyzing structured data in the context of vertical farming, they can complement your machine learning efforts by assisting with natural language processing and report generation related to your farming operations. The primary tool for analyzing your structured data and predicting harvest success would be traditional machine learning models.