Calibrating Low-Cost Smart Insole Sensors with Recurrent Neural Networks for Accurate Prediction of Center of Pressure.

This paper proposes a scheme for predicting ground reaction force (GRF) and center of pressure (CoP) using low-cost FSR sensors. GRF and CoP data are commonly collected from smart insoles to analyze the wearer's gait and diagnose balance issues. This approach can be utilized to improve a user's rehabilitation process and enable customized treatment plans for patients with specific diseases, making it a useful technology in many fields. However, the conventional measuring equipment for directly monitoring GRF and CoP values, such as F-Scan, is expensive, posing a challenge to commercialization in the industry. To solve this problem, this paper proposes a technology to predict relevant indicators using only low-cost Force Sensing Resistor (FSR) sensors instead of expensive equipment. In this study, data were collected from subjects simultaneously wearing a low-cost FSR Sensor and an F-Scan device, and the relationship between the collected data sets was analyzed using supervised learning techniques. Using the proposed technique, an artificial neural network was constructed that can derive a predicted value close to the actual F-Scan values using only the data from the FSR Sensor. In this process, GRF and CoP were calculated using six virtual forces instead of the pressure value of the entire sole. It was verified through various simulations that it is possible to achieve an improved prediction accuracy of more than 30% when using the proposed technique compared to conventional prediction techniques.

An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination.

Most deep anomaly detection models are based on learning normality from datasets due to the difficulty of defining abnormality by its diverse and inconsistent nature. Therefore, it has been a common practice to learn normality under the assumption that anomalous data are absent in a training dataset, which we call normality assumption. However, in practice, the normality assumption is often violated due to the nature of real data distributions that includes anomalous tails, i.e., a contaminated dataset. Thereby, the gap between the assumption and actual training data affects detrimentally in learning of an anomaly detection model. In this work, we propose a learning framework to reduce this gap and achieve better normality representation. Our key idea is to identify sample-wise normality and utilize it as an importance weight, which is updated iteratively during the training. Our framework is designed to be model-agnostic and hyperparameter insensitive so that it applies to a wide range of existing methods without careful parameter tuning. We apply our framework to three different representative approaches of deep anomaly detection that are classified into one-class classification-, probabilistic model-, and reconstruction-based approaches. In addition, we address the importance of a termination condition for iterative methods and propose a termination criterion inspired by the anomaly detection objective. We validate that our framework improves the robustness of the anomaly detection models under different levels of contamination ratios on five anomaly detection benchmark datasets and two image datasets. On various contaminated datasets, our framework improves the performance of three representative anomaly detection methods, measured by area under the ROC curve.

Energy Trading among Power Grid and Renewable Energy Sources: A Dynamic Pricing and Demand Scheme for Profit Maximization.

With the technical growth and the reduction of deployment cost for distributed energy resources (DERs), such as solar photovoltaic (PV), energy trading has been recently encouraged to energy consumers, which can sell energy from their own energy storage system (ESS). Meanwhile, due to the unprecedented rise of greenhouse gas (GHG) emissions, some countries (e.g., Republic of Korea and India) have mandated using a renewable energy certificate (REC) in energy trading markets. In this paper, we propose an energy broker model to boost energy trading between the existing power grid and energy consumers. In particular, to maximize the profits of energy consumers and the energy provider, the proposed energy broker is in charge of deciding the optimal demand and dynamic price of energy in an REC-based energy trading market. In this solution, the smart agents (e.g., IoT intelligent devices) of consumers exchange energy trading associated information, including the amount of energy generation, price and REC. For deciding the optimal demand and dynamic pricing, we formulate convex optimization problems using dual decomposition. Through a numerical simulation analysis, we compare the performance of the proposed dynamic pricing strategy with the conventional pricing strategies. Results show that the proposed dynamic pricing and demand control strategies can encourage energy trading by allowing RECs trading of the conventional power grid.