diff --git a/AI_models_pranav/guardian_monitor_models.py b/AI_models_pranav/guardian_monitor_models.py
new file mode 100644
index 000000000..d6f0fe43a
--- /dev/null
+++ b/AI_models_pranav/guardian_monitor_models.py
@@ -0,0 +1,449 @@
+# -*- coding: utf-8 -*-
+"""guardian monitor.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1cJmORhXpr_fDa_lXvVAtHtH6M-Z-dbXy
+"""
+
+
+
+"""**Reasoning**:
+To concatenate all DataFrames in `df_list` into a single DataFrame named `data`, I will use the `pd.concat()` function.
+
+
+"""
+
+import pandas as pd
+
+data = pd.concat(df_list, ignore_index=True)
+data.head()
+
+data = data[data[23] != 0]
+print("Missing values after removing activity label 0:\n", data.isnull().sum())
+
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+
+# Separate features (X) and activity labels (y)
+X = data.iloc[:, :-1].values
+y = data.iloc[:, -1].values
+
+# Normalize features using StandardScaler
+scaler = StandardScaler()
+X = scaler.fit_transform(X)
+
+print("Shape of X (features):", X.shape)
+print("Shape of y (labels):", y.shape)
+
+from sklearn.model_selection import train_test_split
+
+# Split data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+# Print the shapes of the resulting sets
+print("Shape of X_train:", X_train.shape)
+print("Shape of X_test:", X_test.shape)
+print("Shape of y_train:", y_train.shape)
+print("Shape of y_test:", y_test.shape)
+
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.svm import SVC
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.metrics import accuracy_score
+
+# 1. Random Forest Classifier
+print("Training Random Forest Classifier...")
+rf_classifier = RandomForestClassifier(random_state=42)
+rf_classifier.fit(X_train, y_train)
+y_pred_rf = rf_classifier.predict(X_test)
+accuracy_rf = accuracy_score(y_test, y_pred_rf)
+print(f"Random Forest Classifier Accuracy: {accuracy_rf:.4f}")
+
+# 2. Support Vector Machine (SVC)
+print("\nTraining Support Vector Machine (SVC)...")
+# For faster training, we can use a subset of the data or reduce C/gamma parameters
+# However, sticking to the instructions, we will use the full dataset for now.
+# Note: SVC can be computationally intensive on large datasets.
+svc_classifier = SVC(random_state=42)
+svc_classifier.fit(X_train, y_train)
+y_pred_svc = svc_classifier.predict(X_test)
+accuracy_svc = accuracy_score(y_test, y_pred_svc)
+print(f"Support Vector Machine (SVC) Accuracy: {accuracy_svc:.4f}")
+
+# 3. K-Nearest Neighbors (KNN) Classifier
+print("\nTraining K-Nearest Neighbors (KNN) Classifier...")
+knn_classifier = KNeighborsClassifier(n_neighbors=5)
+knn_classifier.fit(X_train, y_train)
+y_pred_knn = knn_classifier.predict(X_test)
+accuracy_knn = accuracy_score(y_test, y_pred_knn)
+print(f"K-Nearest Neighbors (KNN) Classifier Accuracy: {accuracy_knn:.4f}")
+
+"""# Task
+```python
+from sklearn.metrics import classification_report, confusion_matrix
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Identify the best-performing model
+models = {
+    "Random Forest Classifier": accuracy_rf,
+    "Support Vector Machine (SVC)": accuracy_svc,
+    "K-Nearest Neighbors (KNN) Classifier": accuracy_knn
+}
+
+best_model_name = max(models, key=models.get)
+best_accuracy = models[best_model_name]
+
+print(f"The best-performing model is: {best_model_name} with an accuracy of {best_accuracy:.4f}\n")
+
+# Get predictions for the best model
+if best_model_name == "Random Forest Classifier":
+    best_y_pred = y_pred_rf
+    best_model = rf_classifier
+elif best_model_name == "Support Vector Machine (SVC)":
+    best_y_pred = y_pred_svc
+    best_model = svc_classifier
+else: # K-Nearest Neighbors (KNN) Classifier
+    best_y_pred = y_pred_knn
+    best_model = knn_classifier
+
+# Generate and print the classification report for the best model
+print(f"Classification Report for {best_model_name}:\n")
+print(classification_report(y_test, best_y_pred))
+
+# Generate and plot the confusion matrix for the best model
+cm = confusion_matrix(y_test, best_y_pred)
+
+plt.figure(figsize=(10, 8))
+sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', cbar=False)
+plt.title(f'Confusion Matrix for {best_model_name}')
+plt.xlabel('Predicted Label')
+plt.ylabel('True Label')
+plt.show()
+```
+"""
+
+import matplotlib.pyplot as plt
+import numpy as np
+from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
+
+# Accuracy bar chart
+model_names = ["Random Forest", "SVM", "KNN"]
+model_accuracies = [accuracy_rf, accuracy_svc, accuracy_knn]
+
+plt.figure(figsize=(8, 5))
+bars = plt.bar(model_names, model_accuracies)
+plt.title("Model Accuracy Comparison")
+plt.xlabel("Models")
+plt.ylabel("Accuracy")
+plt.ylim(0.98, 1.0)
+
+for bar, acc in zip(bars, model_accuracies):
+    plt.text(
+        bar.get_x() + bar.get_width() / 2,
+        bar.get_height(),
+        f"{acc:.4f}",
+        ha="center",
+        va="bottom"
+    )
+
+plt.show()
+
+# Confusion matrix for best model
+best_model_name = max(
+    {
+        "Random Forest": accuracy_rf,
+        "SVM": accuracy_svc,
+        "KNN": accuracy_knn
+    },
+    key={
+        "Random Forest": accuracy_rf,
+        "SVM": accuracy_svc,
+        "KNN": accuracy_knn
+    }.get
+)
+
+if best_model_name == "Random Forest":
+    best_predictions = y_pred_rf
+elif best_model_name == "SVM":
+    best_predictions = y_pred_svc
+else:
+    best_predictions = y_pred_knn
+
+cm = confusion_matrix(y_test, best_predictions)
+
+plt.figure(figsize=(10, 8))
+disp = ConfusionMatrixDisplay(confusion_matrix=cm)
+disp.plot(cmap="Blues", values_format="d")
+plt.title(f"Confusion Matrix - {best_model_name}")
+plt.show()
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+feature_importances = rf_classifier.feature_importances_
+feature_numbers = np.arange(1, len(feature_importances) + 1)
+
+plt.figure(figsize=(12, 6))
+plt.bar(feature_numbers, feature_importances)
+plt.title("Random Forest Feature Importance")
+plt.xlabel("Feature Number")
+plt.ylabel("Importance")
+plt.xticks(feature_numbers)
+plt.show()
+
+activity_labels_map = {
+    1: 'Standing',
+    2: 'Sitting',
+    3: 'Lying',
+    4: 'Walking',
+    5: 'Climbing Stairs',
+    6: 'Waist Bends Forward',
+    7: 'Frontal Elevation of Arms',
+    8: 'Knees Bending (Crouching)',
+    9: 'Cycling',
+    10: 'Jogging',
+    11: 'Running',
+    12: 'Jump'
+}
+
+target_names = [
+    'Standing',
+    'Sitting',
+    'Lying',
+    'Walking',
+    'Climbing Stairs',
+    'Waist Bends Forward',
+    'Frontal Elevation of Arms',
+    'Knees Bending (Crouching)',
+    'Cycling',
+    'Jogging',
+    'Running',
+    'Jump'
+]
+
+print("Activity labels map and target names created.")
+
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import classification_report
+import os
+
+# --- Start: Reconstructing 'data' from previous steps ---
+# List of data files expected
+file_names = [
+    "mHealth_subject1.log", "mHealth_subject2.log", "mHealth_subject3.log",
+    "mHealth_subject4.log", "mHealth_subject5.log", "mHealth_subject6.log",
+    "mHealth_subject7.log", "mHealth_subject8.log", "mHealth_subject9.log",
+    "mHealth_subject10.log"
+]
+
+# !!! IMPORTANT: Ensure these files are uploaded to your Colab environment.
+# Typically, files can be uploaded to the '/content/' directory.
+# If your files are in a different directory (e.g., '/content/my_data/'),
+# please update the `data_directory` variable below.
+data_directory = "/content/" # <--- Adjust this path if your files are elsewhere!
+
+df_list = []
+for file in file_names:
+    try:
+        file_path = os.path.join(data_directory, file)
+        df = pd.read_csv(file_path, sep=r'\s+', header=None)
+        df_list.append(df)
+    except FileNotFoundError:
+        print(f"Warning: File {file_path} not found. Skipping.")
+
+# Combine all dataframes into a single one
+if df_list:
+    data = pd.concat(df_list, ignore_index=True)
+else:
+    # Raise a more informative error message
+    raise ValueError(f"No data files were loaded from '{data_directory}'. "
+                     "Please ensure 'mHealth_subject*.log' files are uploaded "
+                     "to the correct directory or adjust `data_directory` variable.")
+
+# Remove rows where the last column (activity label) is 0
+data = data[data.iloc[:, -1] != 0]
+
+# --- End: Reconstructing 'data' ---
+
+# Define activity labels map and target names (from cell 26078274 to ensure they are available)
+activity_labels_map = {
+    1: 'Standing',
+    2: 'Sitting',
+    3: 'Lying',
+    4: 'Walking',
+    5: 'Climbing Stairs',
+    6: 'Waist Bends Forward',
+    7: 'Frontal Elevation of Arms',
+    8: 'Knees Bending (Crouching)',
+    9: 'Cycling',
+    10: 'Jogging',
+    11: 'Running',
+    12: 'Jump'
+}
+
+target_names = [
+    'Standing',
+    'Sitting',
+    'Lying',
+    'Walking',
+    'Climbing Stairs',
+    'Waist Bends Forward',
+    'Frontal Elevation of Arms',
+    'Knees Bending (Crouching)',
+    'Cycling',
+    'Jogging',
+    'Running',
+    'Jump'
+]
+
+# Separate features (X) and activity labels (y)
+X = data.iloc[:, :-1].values
+y = data.iloc[:, -1].values
+
+# Normalize features using StandardScaler
+scaler = StandardScaler()
+X = scaler.fit_transform(X)
+
+# Split data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+# Train Random Forest Classifier and make predictions
+rf_classifier = RandomForestClassifier(random_state=42)
+rf_classifier.fit(X_train, y_train)
+y_pred_rf = rf_classifier.predict(X_test)
+
+# Assign to best_y_pred for consistency with the original code structure
+best_y_pred = y_pred_rf
+
+# Generate and print the classification report using target_names
+print("Classification Report for Random Forest Classifier (with activity names):\n")
+print(classification_report(y_test, best_y_pred, target_names=target_names))
+
+import matplotlib.pyplot as plt
+from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
+
+# Compute the confusion matrix
+cm = confusion_matrix(y_test, y_pred_rf)
+
+# Create a ConfusionMatrixDisplay object
+disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=target_names)
+
+# Initialize a figure
+plt.figure(figsize=(12, 10))
+
+# Plot the confusion matrix
+disp.plot(cmap='Blues', values_format='d', ax=plt.gca())
+
+# Add a title
+plt.title('Confusion Matrix - Random Forest Classifier with Activity Names')
+
+# Rotate x-axis labels for better readability
+plt.xticks(rotation=90)
+plt.yticks(rotation=0)
+
+# Display the plot
+plt.show()
+
+import matplotlib.pyplot as plt
+import numpy as np
+from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay, accuracy_score
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.svm import SVC
+from sklearn.neighbors import KNeighborsClassifier
+
+# --- Re-execute model training and prediction to ensure variables are defined ---
+# This section is taken from cell f1ceae06 to ensure accuracy and prediction variables exist.
+# X_train, X_test, y_train, y_test are assumed to be defined from previous steps (e.g., cell 58c97233).
+
+# 1. Random Forest Classifier
+print("Re-training Random Forest Classifier...")
+rf_classifier = RandomForestClassifier(random_state=42)
+rf_classifier.fit(X_train, y_train)
+y_pred_rf = rf_classifier.predict(X_test)
+accuracy_rf = accuracy_score(y_test, y_pred_rf)
+print(f"Random Forest Classifier Accuracy: {accuracy_rf:.4f}")
+
+# 2. Support Vector Machine (SVC)
+print("\nRe-training Support Vector Machine (SVC)...")
+svc_classifier = SVC(random_state=42)
+svc_classifier.fit(X_train, y_train)
+y_pred_svc = svc_classifier.predict(X_test)
+accuracy_svc = accuracy_score(y_test, y_pred_svc)
+print(f"Support Vector Machine (SVC) Accuracy: {accuracy_svc:.4f}")
+
+# 3. K-Nearest Neighbors (KNN) Classifier
+print("\nRe-training K-Nearest Neighbors (KNN) Classifier...")
+knn_classifier = KNeighborsClassifier(n_neighbors=5)
+knn_classifier.fit(X_train, y_train)
+y_pred_knn = knn_classifier.predict(X_test)
+accuracy_knn = accuracy_score(y_test, y_pred_knn)
+print(f"K-Nearest Neighbors (KNN) Classifier Accuracy: {accuracy_knn:.4f}")
+
+# --- End of re-execution of model training ---
+
+# Gather the accuracy scores (now guaranteed to be available)
+print(f"\nRandom Forest Classifier Accuracy: {accuracy_rf:.4f}")
+print(f"Support Vector Machine (SVC) Accuracy: {accuracy_svc:.4f}")
+print(f"K-Nearest Neighbors (KNN) Classifier Accuracy: {accuracy_knn:.4f}")
+
+# Create lists for plotting
+model_names = ["Random Forest", "SVM", "KNN"]
+model_accuracies = [accuracy_rf, accuracy_svc, accuracy_knn]
+
+print("\nModel names for plotting:", model_names)
+print("Model accuracies for plotting:", [f'{acc:.4f}' for acc in model_accuracies])
+
+# Accuracy bar chart
+plt.figure(figsize=(8, 5))
+bars = plt.bar(model_names, model_accuracies)
+plt.title("Model Accuracy Comparison")
+plt.xlabel("Models")
+plt.ylabel("Accuracy")
+plt.ylim(0.98, 1.0)
+
+for bar, acc in zip(bars, model_accuracies):
+    plt.text(
+        bar.get_x() + bar.get_width() / 2,
+        bar.get_height(),
+        f"{acc:.4f}",
+        ha="center",
+        va="bottom"
+    )
+
+plt.show()
+
+# Confusion matrix for best model (retained for completeness of original cell)
+best_model_name = max(
+    {
+        "Random Forest": accuracy_rf,
+        "SVM": accuracy_svc,
+        "KNN": accuracy_knn
+    },
+    key={
+        "Random Forest": accuracy_rf,
+        "SVM": accuracy_svc,
+        "KNN": accuracy_knn
+    }.get
+)
+
+if best_model_name == "Random Forest":
+    best_predictions = y_pred_rf
+elif best_model_name == "SVM":
+    best_predictions = y_pred_svc
+else:
+    best_predictions = y_pred_knn
+
+cm = confusion_matrix(y_test, best_predictions)
+
+plt.figure(figsize=(10, 8))
+disp = ConfusionMatrixDisplay(confusion_matrix=cm)
+disp.plot(cmap="Blues", values_format="d")
+plt.title(f"Confusion Matrix - {best_model_name}")
+plt.show()
\ No newline at end of file
diff --git a/AI_models_pranav/report.pdf b/AI_models_pranav/report.pdf
new file mode 100644
index 000000000..004924894
Binary files /dev/null and b/AI_models_pranav/report.pdf differ