The Internet of Things (IoT) enables us to gain access to a wide range of data from the physical world that can be analyzed for deriving critical state information. In this regard, machine learning (ML) is a valuable tool that can be used to develop models based on observed physical data, leading to efficient analytical decisions, including anomaly detection. In this work, we address some key challenges for applying ML in IoT applications that include maintaining privacy considerations of user data that are needed for developing ML models and minimizing the communication cost for transmitting the data over the IoT network. We consider a representative application of the anomaly detection of ECG signals that are obtained from a set of low-cost wearable sensors and transmitted to a central server using LoRaWAN, which is a popular and emerging low-power wide-area network (LPWAN) technology. We present a novel framework utilizing federated learning (FL) to preserve data privacy and appropriate features for uplink and downlink communications between the end devices and the gateway to optimize the communication cost. Performance results obtained from computer simulations demonstrate that the proposed framework leads to a 98% reduction in the volume of data that is required to achieve the same level of performance as in traditional centralized ML.

This paper presents an enhanced Ant Colony Optimization (ACO) algorithm tailored for optimizing CMOS physical design in VLSI circuits. As device complexity escalates, traditional placement techniques struggle with multiobjective goals such as minimizing layout area, wirelength, and achieving effective aspect ratios. The proposed ACO framework simulates artificial ant colonies exploring layout configurations and reinforcing promising solutions through a pheromone-guided heuristic. Evaluated on a benchmark containing ten typical logic blocks—Adder, Multiplier, Shifter, MUX, Register, ALU, Decoder, Control, Cache, and Buffer—the ACO method achieves a maximum layout area reduction of 27.27% (from 1760 to 1280 units²) and improves the aspect ratio from 3.64 to 5.0 compared to traditional layouts. The mean area reduction observed across different parameter settings is approximately 20%. The system also includes a fully configurable and modular automation tool designed for flexible parameter tuning and the rapid benchmarking of the ACO algorithm. This tool enables users to easily adjust key parameters such as number of ants, iteration count, pheromone evaporation rate, and heuristic influences, allowing for a comprehensive exploration of the optimization space. Experimental results demonstrate ACO’s scalability, adaptability, and effectiveness, establishing it as a viable approach for automation in complex physical designs. Future work will focus on hybrid algorithms and multi-objective optimization extensions.