The integration of Micro Electronic Mechanical Systems (MEMS) sensor technology in smartphones has greatly improved the capability for Human Activity Recognition (HAR). By utilizing Machine Learning (ML) techniques and data from these sensors, various human motion activities can be classified. This study performed experiments and compiled a large dataset of nine daily activities, including Laying Down, Stationary, Walking, Brisk Walking, Running, Stairs-Up, Stairs-Down, Squatting, and Cycling. Several ML models, such as Decision Tree Classifier, Random Forest Classifier, K Neighbors Classifier, Multinomial Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine, were trained on sensor data collected from accelerometer, gyroscope, and magnetometer embedded in smartphones and wearable devices. The highest test accuracy of 95% was achieved using the random forest algorithm. Additionally, a custom-built Bidirectional Long-Short-Term Memory (Bi-LSTM) model, a type of Recurrent Neural Network (RNN), was proposed and yielded an improved test accuracy of 98.1%. This approach differs from traditional algorithmic-based human activity detection used in current wearable technologies, resulting in improved accuracy.

Identifying correct human postures is crucial in areas like patient care in hospitals. However, the traditional vision-based methods widely used for this purpose raise privacy concerns for the subject, and the other wearable sensor-based approaches are impractical for real-world scenarios. In this paper, we propose a contactless, privacy-conscious, and memory-efficient posture classification system based on millimeter wave (mmWave) radar. This system utilizes three-dimension(3D) point-cloud data captured using Texas Instrument’s IWR1843BOOST Frequency Modulated Continuous Wave (FMCW) radar module to classify the posture of the subject. Two types of datasets are extracted from this radar data: ( i ) image dataset derived from the isometric view of the point-cloud data, and ( ii ) spatial coordinates dataset also extracted from the point-cloud data. A low-computational Tiny Machine Learning (TinyML) model is employed on the datasets for efficient implementation on embedded hardware, Raspberry Pi 3 B+. The proposed model’s parameters were quantized to 8 bits (int8), which accurately classify four postures, i.e., standing, sitting, lying, and bending, with an accuracy of 98.97% for the image data. However, to make it more computationally efficient, the int8 quantized TinyML model was trained on the spatial coordinates dataset, giving an accuracy of 96.12%. This highlights the efficiency and effectiveness of our proposed lightweight model that can be deployed on edge devices for real-world applications.

Breast Cancer is a global health concern, emphasizing the crucial importance of its early detection in improving patient treatment. This is especially true for the most frequently diagnosed type of breast cancer, Invasive Ductal Carcinoma (IDC), which has a high risk of spreading and significant mortality. Automation provides an opportunity to streamline the detection, improving efficiency and minimizing diagnostic errors. In this research paper, we proposed a low-computational Tiny Machine Learning (TinyML) model for the classification of IDC. Conventional methods for IDC classification, such as histopathological analysis and mammography, are time-consuming, costly, and subjective. Therefore, there is a need for an automated and accurate method for IDC classification that can be applied in a resource-limited environment. Our proposed TinyML model takes digital images of whole-mount breast cancer slide specimens and extracts the features necessary to classify them as IDC-(-ve) or IDC-(+ve). The TinyML model is evaluated using a publicly available dataset of Breast Histopathology Images and compared to the other Deep Learning (DL) models based on accuracy and computational complexity. The results show that our model achieved a high accuracy of 89.3% while maintaining limited processing power and memory. The successful deployment of the model on an embedded system like Raspberry Pi demonstrates that our TinyML model can be used in hardware resource- constrained environments, promising improved cancer diagnosis.

The alternating current (AC) optimal power flow (AC-OPF) problem is crucial for efficient power system operation, yet it remains challenging due to its nonlinear, nonconvex structure and numerous operational constraints. This paper introduces a Physics-guided Graph Safe Reinforcement Learning (PGSRL) framework that provides accurate, scalable, and physically consistent solutions to AC-OPF. The proposed PGSRL framework first models the power system as a weighted graph, encoding voltage magnitudes, load demands, and transmission line impedances to capture existing spatiotemporal correlations among power system buses. A Graph Mamba encoder with selective State Space Modeling extracts spatiotemporal correlations, which are used to define the system states within a constrained Markov Decision Process (CMDP). To solve this CMDP, we design a physics-guided safe Twin Delayed Deep Deterministic Policy Gradient (TD3) architecture containing twin critics and deterministic actors, guided by physics-informed reward functions that promote feasibility through penalty-based soft constraints. By interacting with a simulated power system environment, the introduced PGSRL learns optimal generator dispatch strategies in continuous action spaces while honoring AC-OPF constraints. Experimental results on six test benchmarks demonstrate the superiority of PGSRL compared with traditional numerical solution and supervised data-driven baselines, rather than RL methods, in terms of estimation accuracy of AC-OPF setpoints.