Occupancy State Prediction by Recurrent Neural Network (LSTM): Multi-Room Context.

The energy consumption of a building is significantly influenced by the habits of its occupants. These habits not only pertain to occupancy states, such as presence or absence, but also extend to more detailed aspects of occupant behavior. To accurately capture this information, it is essential to use tools that can monitor occupant habits without altering them. Invasive methods such as body sensors or cameras could potentially disrupt the natural habits of the occupants. In our study, we primarily focus on occupancy states as a representation of occupant habits. We have created a model based on artificial neural networks (ANNs) to ascertain the occupancy state of a building using environmental data such as CO2 concentration and noise level. These data are collected through non-intrusive sensors. Our approach involves rule-based a priori labeling and the use of a long short-term memory (LSTM) network for predictive purposes. The model is designed to predict four distinct states in a residential building. Although we lack data on actual occupancy states, the model has shown promising results with an overall prediction accuracy ranging between 78% and 92%.

Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks.

With the steep rise in the development of smart grids and the current advancement in developing measuring infrastructure, short term power consumption forecasting has recently gained increasing attention. In fact, the prediction of future power loads turns out to be a key issue to avoid energy wastage and to build effective power management strategies. Furthermore, energy consumption information can be considered historical time series data that are required to extract all meaningful knowledge and then forecast the future consumption. In this work, we aim to model and to compare three different machine learning algorithms in making a time series power forecast. The proposed models are the Long Short-Term Memory (LSTM), the Gated Recurrent Unit (GRU) and the Drop-GRU. We are going to use the power consumption data as our time series dataset and make predictions accordingly. The LSTM neural network has been favored in this work to predict the future load consumption and prevent consumption peaks. To provide a comprehensive evaluation of this method, we have performed several experiments using real data power consumption in some French cities. Experimental results on various time horizons show that the LSTM model produces a better result than the GRU and the Drop-GRU forecasting methods. There are fewer prediction errors and its precision is finer. Therefore, these predictions based on the LSTM method will allow us to make decisions in advance and trigger load shedding in cases where consumption exceeds the authorized threshold. This will have a significant impact on planning the power quality and the maintenance of power equipment.

Evaluation of a graphic interface to control a robotic grasping arm: a multicenter study.

UNLABELLED: Laffont I, Biard N, Chalubert G, Delahoche L, Marhic B, Boyer FC, Leroux C. Evaluation of a graphic interface to control a robotic grasping arm: a multicenter study. OBJECTIVE: Grasping robots are still difficult to use for persons with disabilities because of inadequate human-machine interfaces (HMIs). Our purpose was to evaluate the efficacy of a graphic interface enhanced by a panoramic camera to detect out-of-view objects and control a commercialized robotic grasping arm. DESIGN: Multicenter, open-label trial. SETTING: Four French departments of physical and rehabilitation medicine. PARTICIPANTS: Control subjects (N=24; mean age, 33y) and 20 severely impaired patients (mean age, 44y; 5 with muscular dystrophies, 13 with traumatic tetraplegia, and 2 others) completed the study. None of these patients was able to grasp a 50-cL bottle without the robot. INTERVENTIONS: Participants were asked to grasp 6 objects scattered around their wheelchair using the robotic arm. They were able to select the desired object through the graphic interface available on their computer screen. MAIN OUTCOME MEASURES: Global success rate, time needed to select the object on the screen of the computer, number of clicks on the HMI, and satisfaction among users. RESULTS: We found a significantly lower success rate in patients (81.1% vs 88.7%; chi(2)P=.017). The duration of the task was significantly higher in patients (71.6s vs 39.1s; P<.001). We set a cut-off for the maximum duration at 79 seconds, representing twice the amount of time needed by the control subjects to complete the task. In these conditions, the success rate for the impaired participants was 65% versus 85.4% for control subjects. The mean number of clicks necessary to select the object with the HMI was very close in both groups: patients used (mean +/- SD) 7.99+/-6.07 clicks, whereas controls used 7.04+/-2.87 clicks. Considering the severity of patients' impairment, all these differences were considered tiny. Furthermore, a high satisfaction rate was reported for this population concerning the use of the graphic interface. CONCLUSIONS: The graphic interface is of interest in controlling robotic arms for disabled people, with numerous potential applications in daily life.