With the rising global energy consumption, the energy use of heating, ventilation, and air conditioning (HVAC) systems has become a critical concern. Existing deep reinforcement learning control methods for HVAC systems often exhibit slow convergence and poor adaptability to dynamic environments, resulting in significant indoor temperature fluctuations, inefficient temperature control strategies, and consequently, energy waste and failure to meet thermal comfort requirements. To address these challenges, this study proposes a novel HVAC control method based on the Soft Actor-Critic with Intrinsic Reward and Correlation-Aware CNN (SAC-IRCNet) model. The model incorporates cooling load prediction as a constraint to enable on-demand cooling supply. It integrates an Elliptical Dynamics Exploration intrinsic reward mechanism, which accelerates SAC convergence through elliptical exploration rewards and inverse dynamics models, thereby reducing energy waste. Additionally, the Correlation-Aware CNN enhances SAC’s feature extraction capability by leveraging state correlations to better understand contextual information, enabling more accurate responses to environmental changes and improved thermal comfort. Experimental results show that SAC-IRCNet achieves a 3.94% faster reward convergence and a 5.78% higher maximum cumulative reward within five episodes compared to SAC. It reduces energy consumption by up to 17.25% (21,837.58 kW) and lowers thermal discomfort violations by up to 6.44%, demonstrating excellent generalization ability across two datasets.

Audio-visual speech enhancement (AVSE) was shown to be superior over conventional audio-only counterpart for improving the speech quality. However, most existing AVSE models are heavyweight in the sense of parameter count, which is inappropriate for the deployment and practical applications. In this paper, we therefore present a lightweight AVSE approach (called M3Net) by incorporating several multi-modality, multi-scale and multi-branch strategies. Three multi-scale techniques are designed for the visual and audio streams, including multi-scale average pooling (MSAP), multi-scale ResNet (MSResNet) and multi-scale short time Fourier transform (MSSTFT). It is shown that each multi-scale module positively contributes to the performance. Also, we consider four skip connections for the audio-visual feature aggregation, which have a great complementary effect on the designed multi-scale techniques. Experimental results show that these techniques are flexible in combination with existing approaches, and more importantly obtain a comparable performance with a smaller model size compared to the heavyweight networks.

Human activity recognition (HAR) based on mobile sensors plays an important role in ubiquitous computing. However, the rise of data regulatory constraints precludes collecting private and labeled signal data from personal devices at scale. Thanks to the growth of computational power on mobile devices, federated learning has emerged as a decentralized alternative solution to model training, which iteratively aggregates locally updated models into a shared global model, therefore being able to leverage decentralized, private data without central collection. However, the effectiveness of federated learning for HAR is affected by the fact that each user has different activity types and even a different signal distribution for the same activity type. Furthermore, it is uncertain if a single global model trained can generalize well to individual users or new users with heterogeneous data. In this paper, we propose Meta-HAR, a federated representation learning framework, in which a signal embedding network is meta-learned in a federated manner, while the learned signal representations are further fed into a personalized classification network at each user for activity prediction. In order to boost the representation ability of the embedding network, we treat the HAR problem at each user as a different task and train the shared embedding network through a Model-Agnostic Meta-learning framework, such that the embedding network can generalize to any individual user. Personalization is further achieved on top of the robustly learned representations in an adaptation procedure. We conducted extensive experiments based on two publicly available HAR datasets as well as a newly created HAR dataset. Results verify that Meta-HAR is effective at maintaining high test accuracies for individual users, including new users, and significantly outperforms several baselines, including Federated Averaging, Reptile and even centralized learning in certain cases. Our collected dataset will be open-sourced to facilitate future development in the field of sensor-based human activity recognition.

Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently. However, the generalization ability of deep models on complex real-world HAR data is limited by the availability of high-quality labeled activity data, which are hard to obtain. In this article, we design a similarity embedding neural network that maps input sensor signals onto real vectors through carefully designed convolutional and Long Short-Term Memory (LSTM) layers. The embedding network is trained with a pairwise similarity loss, encouraging the clustering of samples from the same class in the embedded real space, and can be effectively trained on a small dataset and even on a noisy dataset with mislabeled samples. Based on the learned embeddings, we further propose both nonparametric and parametric approaches for activity recognition. Extensive evaluation based on two public datasets has shown that the proposed similarity embedding network significantly outperforms state-of-the-art deep models on HAR classification tasks, is robust to mislabeled samples in the training set, and can also be used to effectively denoise a noisy dataset.

Most current distributed machine learning systems try to scale up model training by using a data-parallel architecture that divides the computation for different samples among workers. We study distributed machine learning from a different motivation, where the information about the same samples, e.g., users and objects, are owned by several parities that wish to collaborate but do not want to share raw data with each other.

User action modeling and prediction has long been a topic of importance to recommender systems and user profiling. The quality of the model or accuracy of prediction plays a vital role in related applications like recommendation, advertisement displaying, searching, etc. For large scale systems with a massive number of users, beside the pure prediction performance, there are other practical factors like training and prediction latency, memory overhead, that must be optimized to ensure smooth operation of the system. We propose a fast linear computational framework to handle a vast number of second order crossed features with dimensionality reduction. By leveraging the training and serving system architecture, we shift heavy calculation burden from online serving to offline preprocessing, at the cost of a reasonable amount of memory overhead. The experiments on a 15-day data trace from Tencent MyApp shows that our proposed framework can achieve comparable prediction performance to much complex models like the field-aware factorization machine (FFM) while being served in 2 ms with a reasonable amount of memory overhead.