SMART PATIENT CARE: A SPONTANEOUS INTELLIGENCE APPROACH TO IOT-ENABLED CONDITION MONITORING VIA ANDROID APP

---

Dr. Rajendra Singh Kushwah, Vankani Manish Jitendrabhai

Vol 18, No 11 ( 2023 )   |  Licensing: CC 4.0   |   Pg no: 355-362   |   Published on: 30-11-2023

---

Abstract
This paper presents a comparative analysis of scalability and interpretability among three prominent machine learning algorithms: Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and the novel combination of Online Gradient Descent and Online Random Forest (OGD + RF). Through a meticulous evaluation, OGD + RF emerges as the most scalable algorithm, exhibiting robustness in handling extensive datasets and computational demands, closely followed by SVM. Conversely, LSTM demonstrates superior interpretability, providing clearer insights into its decision-making processes compared to SVM and OGD + RF. These findings offer valuable guidance for algorithm selection, with OGD + RF favored for scalability and LSTM for interpretability, catering to diverse requirements and constraints in practical applications. Overall, this study contributes to enhancing understanding and decision-making in the adoption of machine learning algorithms for various real-world scenarios.

Keywords:
Support Vector Machine (SVM), Long Short-Term Memory (LSTM), Online Gradient Descent and Online Random Forest (OGD + RF)

---

Download Full Article PDF