FeFETs hold strong potential for advancing memory and logic technologies, but their inherent randomness arising from both operational cycling and fabrication variability poses significant challenges for accurate and reliable modeling. Capturing this variability is critical, as it enables designers to predict behavior, optimize performance, and ensure reliability and robustness against variations in manufacturing and operating conditions. Existing deterministic and machine learning-based compact models often fail to capture the full extent of this variability or lack the mathematical smoothness required for stable circuit-level integration. In this work, we present an enhanced probabilistic modeling framework for FeFETs that addresses these limitations. Building upon a Mixture Density Network (MDN) foundation, our approach integrates C-infinity continuous activation functions for smooth, stable learning and a device-specific embedding layer to capture intrinsic physical variability across devices. Sampling from the learned embedding distribution enables the generation of synthetic device instances for variability-aware simulation. With an R2 of 0.92, the model demonstrates high accuracy in capturing the variability of FeFET current behavior. Altogether, this framework provides a scalable, data-driven solution for modeling the full stochastic behavior of FeFETs and offers a strong foundation for future compact model development and circuit simulation integration.

Consumer Internet of things research often involves collecting network traffic sent or received by IoT devices. These data are typically collected via crowdsourcing or while researchers manually interact with IoT devices in a laboratory setting. However, manual interactions and crowdsourcing are often tedious, expensive, inaccurate, or do not provide comprehensive coverage of possible IoT device behaviors. We present a new method for generating IoT network traffic using a robotic arm to automate user interactions with devices. This eliminates manual button pressing and enables permutation-based interaction sequences that rigorously explore the range of possible device behaviors. We test this approach with an Arduino-controlled robotic arm, a smart speaker, and a smart thermostat, using machine learning to demonstrate that collected network traffic contains information about device interactions that could be useful for network, security, or privacy analyses. We also provide source code and documentation allowing researchers to easily automate IoT device interactions and network traffic collection in future studies.

Britannica describes artificial intelligence as the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings. The trouble in this definition is the term intelligent. How do you define intelligence? How do you measure intelligence? You can say something is intelligent if it can do descriptive, diagnostic, predictive, and prescriptive analytics at the same time or within a short timeframe.

ONE Tech, an AI and ML-driven company specializing in Internet of Things (IoT) solutions for network operators, enterprises, and more, has announced new capabilities of its MicroAI Atom product. MicroAI Atom is part of ONE Tech's Micro AI product line, and it now has the ability to train and run AI models at the edge, enabling a variety of individuals and entities to "reduce the costs of bringing intelligence to the edge and endpoint by at least 80 percent." According to ONE Tech's press release, MicroAI is a machine learning algorithm that is embedded into microcontroller units and operates a recursive analysis of device behavior. More specifically, MicroAI collects data from internal device sensors and utilizes a semi-supervised learning approach to come up with a complete view of device behavior. Semi-supervised learning refers to a machine learning method that makes use of some labeled data with a much larger amount of unlabeled data during the model's training phase. Other machine learning methods can either employ a fully supervised approach that would consist of using only labeled training data or a fully unsupervised approach that would consist of using only unlabeled training data.