Search for: All records

The integration of the Internet of Things (IoT) and modern Artificial Intelligence (AI) has given rise to a new paradigm known as the Artificial Intelligence of Things (AIoT). In this survey, we provide a systematic and comprehensive review of AIoT research. We examine AIoT literature related to sensing, computing, and networking & communication, which form the three key components of AIoT. In addition to advancements in these areas, we review domain-specific AIoT systems that are designed for various important application domains. We have also created an accompanying GitHub repository, where we compile the papers included in this survey: https://github.com/AIoT-MLSys-Lab/AIoT-Survey. This repository will be actively maintained and updated with new research as it becomes available. As both IoT and AI become increasingly critical to our society, we believe that AIoT is emerging as an essential research field at the intersection of IoT and modern AI. It is our hope that this survey will serve as a valuable resource for those engaged in AIoT research and act as a catalyst for future explorations to bridge gaps and drive advancements in this exciting field. 

Cognitive Arousal, frequently elicited by environmental stressors that exceed personal coping resources, manifests in measurable physiological markers, notably in galvanic skin responses. This effect is prominent in cognitive tasks such as composition, where fluctuations in these biomarkers correlate with individual expressiveness. It is crucial to understand the nexus between cognitive arousal and expressiveness. However, there has not been a concrete study that investigates this inter-relation concurrently. Addressing this, we introduce an innovative methodology for simultaneous monitoring of these elements. Our strategy employs Bayesian analysis in a multi-state filtering format to dissect psychomotor performance (captured through typing speed), galvanic skin response or skin conductance (SC), and heart rate variability (HRV). This integrative analysis facilitates the quantification of expressive behavior and arousal states. At the core, we deploy a state-space model connecting one latent psychological arousal condition to neural activities impacting sweating (inferred through SC responses) and another latent state to expressive behavior during typing. These states are concurrently evaluated with model parameters using an expectation-maximization algorithms approach. Assessments using both computer-simulated data and experimental data substantiate the validity of our approach. Outcomes display distinguishable latent state patterns in expressive typing and arousal across different computer software used in office management, offering profound implications for Human-Computer Interaction (HCI) and productivity analysis. This research marks a significant advancement in decoding human productivity dynamics, with extensive repercussions for optimizing performance in telecommuting scenarios. 

IntroductionDecoding an individual's hidden brain states in responses to musical stimuli under various cognitive loads can unleash the potential of developing a non-invasive closed-loop brain-machine interface (CLBMI). To perform a pilot study and investigate the brain response in the context of CLBMI, we collect multimodal physiological signals and behavioral data within the working memory experiment in the presence of personalized musical stimuli. MethodsParticipants perform a working memory experiment called then-back task in the presence of calming music and exciting music. Utilizing the skin conductance signal and behavioral data, we decode the brain's cognitive arousal and performance states, respectively. We determine the association of oxygenated hemoglobin (HbO) data with performance state. Furthermore, we evaluate the total hemoglobin (HbT) signal energy over each music session. ResultsA relatively low arousal variation was observed with respect to task difficulty, while the arousal baseline changes considerably with respect to the type of music. Overall, the performance index is enhanced within the exciting session. The highest positive correlation between the HbO concentration and performance was observed within the higher cognitive loads (3-back task) for all of the participants. Also, the HbT signal energy peak occurs within the exciting session. DiscussionFindings may underline the potential of using music as an intervention to regulate the brain cognitive states. Additionally, the experiment provides a diverse array of data encompassing multiple physiological signals that can be used in the brain state decoder paradigm to shed light on the human-in-the-loop experiments and understand the network-level mechanisms of auditory stimulation. 

Federated learning (FL) has attracted increasing attention as a promising technique to drive a vast number of edge devices with artificial intelligence. However, it is very challenging to guarantee the efficiency of a FL system in practice due to the heterogeneous computation resources on different devices. To improve the efficiency of FL systems in the real world, asynchronous FL (AFL) and semi-asynchronous FL (SAFL) methods are proposed such that the server does not need to wait for stragglers. However, existing AFL and SAFL systems suffer from poor accuracy and low efficiency in realistic settings where the data is non-IID distributed across devices and the on-device resources are extremely heterogeneous. In this work, we propose FedSEA - a semi-asynchronous FL framework for extremely heterogeneous devices. We theoretically disclose that the unbalanced aggregation frequency is a root cause of accuracy drop in SAFL. Based on this analysis, we design a training configuration scheduler to balance the aggregation frequency of devices such that the accuracy can be improved. To improve the efficiency of the system in realistic settings where the devices have dynamic on-device resource availability, we design a scheduler that can efficiently predict the arriving time of local updates from devices and adjust the synchronization time point according to the devices' predicted arriving time. We also consider the extremely heterogeneous settings where there exist extremely lagging devices that take hundreds of times as long as the training time of the other devices. In the real world, there might be even some extreme stragglers which are not capable of training the global model. To enable these devices to join in training without impairing the systematic efficiency, Fed-SEA enables these extreme stragglers to conduct local training on much smaller models. Our experiments show that compared with status quo approaches, FedSEA improves the inference accuracy by 44.34% and reduces the systematic time cost and local training time cost by 87.02× and 792.9×. FedSEA also reduces the energy consumption of the devices with extremely limited resources by 752.9×.