Update README.md

README.md

@@ -68,14 +68,14 @@ This model is not intended for general-purpose natural image classification (lik
 ---
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-While the model demonstrates an accuracy of $99.6\%$, performance is strictly dependent on the consistency of the input data compared to the training set. Users should evaluate the model for bias if applying it to datasets with significantly different lighting or sensor noise profiles.
+While the model demonstrates an accuracy of *99.6\%*, performance is strictly dependent on the consistency of the input data compared to the training set. Users should evaluate the model for bias if applying it to datasets with significantly different lighting or sensor noise profiles.
 
 ### Recommendations
 
 Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. Specifically:
 
 * **Domain Verification:** Since EinsteinNet is optimized for scientific and engineering imaging (as detailed in [EinsteinNet and state-of-the-art ML models for android-based orange classification: Integration, evaluation, and deployment](https://doi.org/10.1016/j.atech.2025.101072)), users should perform domain-specific validation before deploying it for critical decision-making.
-* **Edge Deployment:** Given its small footprint ($2.54$ MB), the model is highly recommended for mobile and IoT applications. However, ensure the target hardware supports the Keras/LiteRT runtime to maintain the reported $99.6\%$ accuracy.
+* **Edge Deployment:** Given its small footprint (*2.54* MB), the model is highly recommended for mobile and IoT applications. However, ensure the target hardware supports the Keras/LiteRT runtime to maintain the reported *99.6\%* accuracy.
 * **Input Consistency:** To minimize bias and risk, ensure input images are preprocessed to match the training resolution and normalization parameters used during development.
 * **Human-in-the-loop:** This model should complement, not replace, expert analysis in high-stakes environments like medical diagnostics or thermal structural safety.
 
@@ -112,7 +112,7 @@ The model was trained on the [Orange Fruit Image Dataset for Classification](htt
 
 #### Preprocessing
 
-- **Resolution:** All images were resized to $224 \times 224$ pixels.
+- **Resolution:** All images were resized to *224 x 224* pixels.
 - **Splitting:** The dataset was partitioned using stratified sampling:
   - **Training:** 70% (10,500 images)
   - **Validation:** 15% (2,250 images)
@@ -133,7 +133,7 @@ The model was trained on the [Orange Fruit Image Dataset for Classification](htt
 - **Total Training Time:** 13,033.01 Seconds.
 - **Model Size:** 2.54 MB.
 - **Quantized Size:** 254 KB (Optimized for mobile/IoT deployment via LiteRT).
-- **Inference Performance:** Real-world on-device accuracy remains $>95\%$ despite variability in lighting and backgrounds.
+- **Inference Performance:** Real-world on-device accuracy remains *>95\%* despite variability in lighting and backgrounds.
 
 ## Evaluation
 ---
@@ -192,7 +192,6 @@ The model architecture was specifically optimized to reduce the number of traina
 
 ## Environmental Impact
 ---
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
 - **Hardware Type:** GPU (Benchmarked for Mobile deployment on Google Pixel 6)
 - **Hours used:** ~3.62 hours (13,033 seconds)