Smart Soil Analyzer and Crop Guidance System
| dc.contributor.author | Boukhezna , Marwa | |
| dc.contributor.author | Hazmoune , Samira | |
| dc.contributor.author | Bala , Sahima | |
| dc.date.accessioned | 2025-11-05T09:35:01Z | |
| dc.date.available | 2025-11-05T09:35:01Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract | This study aims to develop an intelligent crop recommendation system based on soil characteristics using artificial intelligence techniques. The core objective is to classify the most suitable crop for cultivation in a specific soil based on various features such as nitrogen (N), phosphorus (P), potassium (K) levels, pH value, moisture, rainfall, soil type, and other environmental factors. To achieve this, we applied a set of machine learning and deep learning algorithms, including Naïve Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), Logistic Regression (LR), as well as LSTM and GRU neural networks. The models were trained using a specialized agricultural dataset collected from Kaggle, with consistent preprocessing and splitting methods to ensure fair performance comparison. A thorough hyperparameter tuning process was carried out to identify the optimal settings for each algorithm. The experimental results showed that deep learning models (LSTM and GRU) achieved strong classification performance, while the Decision Tree model provided good accuracy with lower computational requirements, making it a suitable option for resource constrained applications. | |
| dc.identifier.uri | http://dspace.univ-skikda.dz:4000/handle/123456789/5330 | |
| dc.language.iso | en | |
| dc.publisher | Faculty of Science | |
| dc.title | Smart Soil Analyzer and Crop Guidance System | |
| dc.title.alternative | Artificial Intelligence | |
| dc.type | Masters degree thesis |