Previous research has shown that the temporal dynamics of human activity recorded by accelerometers share a similar structure with music. This opens the possibility to use musical sonification of motion data as a means of raising awareness of an individuals own daily physical activity and promote healthy activity behaviour, granted that human activity and music also share similar temporal structure. In this study a method was developed for quantifying the daily structure of human activity using multigranular temporal segmentation and applying it to produce musical sonifications. To that extent, two accelerometry recordings of physical activity were selected from a dataset, such that one shows more physical activity than the other. These data were segmented in different timescales so that segmentation boundaries at a given timescale have a corresponding boundary at a finer timescale, occurring at the same point in time. These properties are useful to display the hierarchical structure of daily events embedded in larger events, which is akin to musical structure. The segmented physical activity data for one day was mapped to musical sounds, resulting in two short musical pieces, one for each subject. A survey measured the extent to which people would identify the piece corresponding to the most active subject, resulting in a majority of correct answers. We propose that this method has potential to be a valuable and innovative technique for behavioural change. We discuss its potential to aid in interventions for behavioural change towards reducing sedentary behaviour and increasing physical activity.
相關內容
Large language models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted attention from the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a framework for large language models personification, including a strategy for constructing virtual characters' life stories from the ground up, a Multi-Agent Cognitive Mechanism capable of simulating human cognitive processes, and a psychology-guided evaluation method to assess human simulations from both self and observational perspectives. Experimental results demonstrate that our constructed simulacra can produce personified responses that align with their target characters. Our work is a preliminary exploration which offers great potential in practical applications. All the code and datasets will be released, with the hope of inspiring further investigations.
Adversarial examples in machine learning has emerged as a focal point of research due to their remarkable ability to deceive models with seemingly inconspicuous input perturbations, potentially resulting in severe consequences. In this study, we undertake a thorough investigation into the emergence of adversarial examples, a phenomenon that can, in principle, manifest in a wide range of machine learning models. Through our research, we unveil a new notion termed computational entanglement, with its ability to entangle distant features, display perfect correlations or anti-correlations regardless to their spatial separation, significantly contributes to the emergence of adversarial examples. We illustrate how computational entanglement aligns with relativistic effects such as time dilation and length contraction to feature pair, ultimately resulting in the convergence of their angle differences and distances towards zero, signifying perfect correlation, or towards maximum, indicating perfect anti-correlation.
We introduce a taxonomy of important factors to consider when designing interactions with an assistive robot in a senior living facility. These factors are derived from our reflection on two field studies and are grouped into the following high-level categories: primary user (residents), care partners, robot, facility and external circumstances. We outline how multiple factors in these categories impact different aspects of personalization, such as adjusting interactions based on the unique needs of a resident or modifying alerts about the robot's status for different care partners. This preliminary taxonomy serves as a framework for considering how to deploy personalized assistive robots in the complex caregiving ecosystem.
The study of regularity in signals can be of great importance, typically in medicine to analyse electrocardiogram (ECG) or electromyography (EMG) signals, but also in climate studies, finance or security. In this work we focus on security primitives such as Physical Unclonable Functions (PUFs) or Pseudo-Random Number Generators (PRNGs). Such primitives must have a high level of complexity or entropy in their responses to guarantee enough security for their applications. There are several ways of assessing the complexity of their responses, especially in the binary domain. With the development of analog PUFs such as optical (photonic) PUFs, it would be useful to be able to assess their complexity in the analog domain when designing them, for example, before converting analog signals into binary. In this numerical study, we decided to explore the potential of the disentropy of autocorrelation as a measure of complexity for security primitives as PUFs or PRNGs with analog output or responses. We compare this metric to others used to assess regularities in analog signals such as Approximate Entropy (ApEn) and Fuzzy Entropy (FuzEn). We show that the disentropy of autocorrelation is able to differentiate between well-known PRNGs and non-optimised or bad PRNGs in the analog and binary domain with a better contrast than ApEn and FuzEn. Next, we show that the disentropy of autocorrelation is able to detect small patterns injected in PUFs responses and then we applied it to photonic PUFs simulations.
Graph neural networks (GNNs) have been demonstrated to be a powerful algorithmic model in broad application fields for their effectiveness in learning over graphs. To scale GNN training up for large-scale and ever-growing graphs, the most promising solution is distributed training which distributes the workload of training across multiple computing nodes. However, the workflows, computational patterns, communication patterns, and optimization techniques of distributed GNN training remain preliminarily understood. In this paper, we provide a comprehensive survey of distributed GNN training by investigating various optimization techniques used in distributed GNN training. First, distributed GNN training is classified into several categories according to their workflows. In addition, their computational patterns and communication patterns, as well as the optimization techniques proposed by recent work are introduced. Second, the software frameworks and hardware platforms of distributed GNN training are also introduced for a deeper understanding. Third, distributed GNN training is compared with distributed training of deep neural networks, emphasizing the uniqueness of distributed GNN training. Finally, interesting issues and opportunities in this field are discussed.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data available in sequential order. Similar to the human learning process with the ability of learning, fusing, and accumulating new knowledge coming at different time steps, continual learning is considered to have high practical significance. Hence, continual learning has been studied in various artificial intelligence tasks. In this paper, we present a comprehensive review of the recent progress of continual learning in computer vision. In particular, the works are grouped by their representative techniques, including regularization, knowledge distillation, memory, generative replay, parameter isolation, and a combination of the above techniques. For each category of these techniques, both its characteristics and applications in computer vision are presented. At the end of this overview, several subareas, where continuous knowledge accumulation is potentially helpful while continual learning has not been well studied, are discussed.
Deep neural networks have revolutionized many machine learning tasks in power systems, ranging from pattern recognition to signal processing. The data in these tasks is typically represented in Euclidean domains. Nevertheless, there is an increasing number of applications in power systems, where data are collected from non-Euclidean domains and represented as the graph-structured data with high dimensional features and interdependency among nodes. The complexity of graph-structured data has brought significant challenges to the existing deep neural networks defined in Euclidean domains. Recently, many studies on extending deep neural networks for graph-structured data in power systems have emerged. In this paper, a comprehensive overview of graph neural networks (GNNs) in power systems is proposed. Specifically, several classical paradigms of GNNs structures (e.g., graph convolutional networks, graph recurrent neural networks, graph attention networks, graph generative networks, spatial-temporal graph convolutional networks, and hybrid forms of GNNs) are summarized, and key applications in power systems such as fault diagnosis, power prediction, power flow calculation, and data generation are reviewed in detail. Furthermore, main issues and some research trends about the applications of GNNs in power systems are discussed.
For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve computational efficiency). In this paper, we propose an efficient method to train a deep thin network with a theoretic guarantee. Our method is motivated by model compression. It consists of three stages. In the first stage, we sufficiently widen the deep thin network and train it until convergence. In the second stage, we use this well-trained deep wide network to warm up (or initialize) the original deep thin network. This is achieved by letting the thin network imitate the immediate outputs of the wide network from layer to layer. In the last stage, we further fine tune this well initialized deep thin network. The theoretical guarantee is established by using mean field analysis, which shows the advantage of layerwise imitation over traditional training deep thin networks from scratch by backpropagation. We also conduct large-scale empirical experiments to validate our approach. By training with our method, ResNet50 can outperform ResNet101, and BERT_BASE can be comparable with BERT_LARGE, where both the latter models are trained via the standard training procedures as in the literature.
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implicitly learn to suppress irrelevant regions in an input image while highlighting salient features useful for a specific task. This enables us to eliminate the necessity of using explicit external tissue/organ localisation modules of cascaded convolutional neural networks (CNNs). AGs can be easily integrated into standard CNN architectures such as the U-Net model with minimal computational overhead while increasing the model sensitivity and prediction accuracy. The proposed Attention U-Net architecture is evaluated on two large CT abdominal datasets for multi-class image segmentation. Experimental results show that AGs consistently improve the prediction performance of U-Net across different datasets and training sizes while preserving computational efficiency. The code for the proposed architecture is publicly available.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191