Virtual reality is revolutionizing immersive experiences, yet the seamless integration of everyday devices, such as smartphones, remains a challenging frontier. This paper presents a method for dynamically integrating a live smartphone screen into the virtual reality pass-through view. Our approach leverages a lightweight convolutional neural network (CNN) to detect the smartphone in real time, accurately determining its position, scale, and orientation within the camera feed. By synchronizing live screen capture with inertial sensor data, our system computes precise affine transformations that ensure the overlay remains perfectly aligned with its physical counterpart, even during rapid movements. Experimental evaluations demonstrate that our solution achieves an average of 29.2 detection runs per second, delivering a stable and high-fidelity integration without the need for additional hardware. Evaluations also showed a 0.44 increase in detection F1 score during live comparisons to the baseline alternative, which does not use deep learning. This dynamic overlay enhances visual clarity and interaction in virtual reality and bridges the gap between virtual and real-world interfaces, empowering users to access notifications, messages, and productivity applications seamlessly.

Regular maintenance of heating, ventilation, and air conditioning (HVAC) systems is vital for building sustainability and energy efficiency, as neglect can lead to performance degradation, increased energy consumption, and reduced equipment lifespan. Fouling, the accumulation of unwanted material on surfaces, is a significant issue in HVAC heat exchangers, leading to efficiency losses and increased operational costs. While preventive maintenance is commonly employed, predictive maintenance offers a more effective approach, particularly when detecting fouling that requires visual data. However, the rarity of anomalies in such data complicates the training of deep learning models. This paper introduces an approach for synthetic fouling data generation for predictive maintenance designed to simulate fouling on a heat exchanger in a cooling tower. A synthetic image dataset is generated with two distinct types: continuous growth scenarios for training purposes and scheduled maintenance scenarios for evaluating model performance. Resulting in a collection of 4,260 images over a 60-day period. The effectiveness of the dataset is validated through experiments where a U-Net model is trained for semantic segmentation in fouling detection, achieving an average F1 score of 0.8595 across the test scenarios. These results confirm that the synthetic dataset is effective for training convolutional neural networks for fouling detection, laying the groundwork for integrating such models into a broader predictive maintenance strategy for cooling towers.

One branch of safety in reinforcement learning is through integrating risk sensitivity within the Markov Decision Process framework. The objective is to mitigate low-probability events that could lead to severe negative outcomes. Eliminating such risky events is usually done by incorporating a utility function on the expected return; therefore, reshaping the reward structures according to the risk levels associated with different outcomes. The temporal difference learning algorithm can be modified with a utility to capture risk. Notably, such utility functions are either convex or concave depending on the desired risk behavior. Given the outcome space and depending on the risk-sensitivity mode, concave utilities may promote risk-averse behavior and convex utilities may encourage risk-seeking strategies. Such function structure is demonstrated in Prospect Theory, and this motivates a novel formulation using the hyperbolic tangent function called PTanh. Using PTanh, experiments are performed to assess the effect of the diminishing marginal property on the risk-averse policies. It is concluded that there is a correlation between the marginal and selecting the risk-averse parameters. The marginals influence the effectiveness of the averse policies. When the marginals are considered, PTanh can demonstrate better results in terms of a ratio of average reward per prohibited state rate. Furthermore, using empirical evidence, the policy experiments shown with PTanh generalize to other utilities of the Prospect Shape. • Introduces PTanh utility function based on hyperbolic tangent for risk-sensitive RL. • Analyzes impact of diminishing marginals on risk-averse policy effectiveness. • Compares PTanh integrated with Q-learning and Expected SARSA against their base algorithms. • Demonstrates correlation between marginal effects and risk-averse policy parameters.

The number of electric vehicle (EV) owners continues to grow at a rate that makes it increasingly difficult to avoid overloading the capacity of charging stations. Existing solutions to balance this load primarily focus on solving parts of the problem and fail to consider a more holistic approach that can solve the issue of balancing the load across multiple stations by handling EV routing. This paper proposes a novel solution that routes EVs while considering both travel times and peak loads at charging stations. The approach integrates a reinforcement learning algorithm with a path-finding algorithm and a custom-built simulation environment. Compared with baseline methods, the solution showed improved performance in minimizing peak power loads across charging stations while increasing individual trip duration by less than 5%. This approach has the potential to significantly improve the efficiency of EV charging by reducing peak loads at charging stations.

Nowadays, electricity demand forecasting is critical for electric utility companies. Accurate residential load forecasting plays an essential role as an individual component for integrated areas such as neighborhood load consumption. Short-term load forecasting can help electric utility companies reduce waste because electric power is expensive to store. This paper proposes a novel method to evolve deep neural networks for time series forecasting applied to residential load forecasting. The approach centres its efforts on the neural network architecture during the evolution. Then, the model weights are adjusted using an evolutionary optimization technique to tune the model performance automatically. Experimental results on a large dataset containing hourly load consumption of a residence in London, Ontario shows that the performance of unadjusted weights architecture is comparable to other state-of-the-art approaches. Furthermore, when the architecture weights are adjusted the model accuracy surpassed the state-of-the-art method called LSTM one shot by 3.0%.