Intrusion Detection on Resource-Constrained IoT Devices with Hardware-Aware ML and DL

A new framework for explainable anomaly detection in Industrial IoT data streams has been introduced, addressing the challenges of real-time decision-making in maintenance under limited computational resources. This approach combines unsupervised anomaly detection with human-in-the-loop learning, utilizing an online Isolation Forest and enhancing interpretability through advanced visualization techniques.

A new ensemble-based machine learning model has been developed to enhance early diabetes prediction using the BRFSS dataset, which includes over 253,000 health records. The model employs techniques like SMOTE and Tomek Links to address class imbalance and achieves a strong ROC-AUC score of approximately 0.96 through various algorithms, including Random Forest and XGBoost.

Recent research benchmarks two chest X-ray (CXR) embedding models, CXR-Foundation (ELIXR v2.0) and MedImageInsight, using the publicly available MIMIC-CXR and NIH ChestX-ray14 datasets. The study employs a unified preprocessing pipeline and fixed classifiers to ensure reproducibility, revealing that MedImageInsight generally outperforms CXR-Foundation, which shows strong stability across datasets.

A recent study evaluates the sensitivity of Bidirectional Long Short-Term Memory (BiLSTM) forecasting models to input sequence length and noise, highlighting their effectiveness in time-series forecasting across various domains, including environmental monitoring and the Internet of Things (IoT).