Assistive mobile robots are a transformative technology that helps persons with disabilities regain the ability to move freely. Although autonomous wheelchairs significantly reduce user effort, they still require human input allow users maintain control and adapt changing environments. Brain Computer Interface (BCI) stands out as highly user-friendly option does not physical movement. Current BCI systems can understand whether want accelerate or decelerate, but implement these changes in...

Building autonomous mobile robots (AMRs) with optimized efficiency and adaptive capabilities-able to respond changing task demands dynamic environments-is a strongly desired goal for advancing construction robotics. Such can play critical role in enabling automation, reducing operational carbon footprints, supporting modular processes. Inspired by the autonomy of living organisms, we introduce interoception, which centers on robot's internal state representation, as foundation developing...

Background Timely percutaneous coronary intervention (PCI) is crucial for restoring myocardial blood supply in ST-segment elevation infarction (STEMI) patients, with the first 72 h being a critical period early ventricular remodelling. The association between heart rate trajectories within this and after hospital discharge outcomes STEMI patients post-PCI remains unclear.

Monitoring brain activity is a novel development for hazard recognition in the construction industry. However, very few empirical studies have investigated causal connections within brain. This study aimed to explore connectivity of workers during recognition. Electroencephalogram data were collected from perform image-based tasks. The Granger causality-based adaptive directed transfer function was used simulate and time-variant information flow across observed perspective cognitive...

Human–machine collaboration is a promising approach to improve on-site hazard inspection because it can complement the inherent limitations of human cognitive functions. Nevertheless, research on effective integration opinions from humans and machines form optimal group decision-making lacking. Prior work suggests that confidence-weighted voting strategy superior, but self-reported decision confidence often unreliable. Thus, this study proposes an innovative methodological framework predict...

The study aimed to reinvestigate psychological mechanisms of the influence construction workers' experience on hazard recognition performance, with signal detection theory (SDT) and electroencephalogram (EEG) readings.

The mobile edge computing (MEC) technology can provide users (MU) with high reliability and low time-delay communication services. imbalanced cloud deployment better adapt to the non-uniform spatial-time distribution of tasks reduce cost servers. For multi-user multi-task offloading decision based on cloud, a new criteria, tradeoff among time delay-energy consumption-cost, is designed quantify user experience task be optimization target decision. Both problems minimizing sum costs for all...

Automated vision-based hazard detection algorithms are being rapidly developed to provide alerts for construction workers. However, these alerting systems often apply a fixed low-beta threshold, which can cause excessive false alarms, followed by distractions and human distrust in automation. In this study, we propose novel adaptive automated system capable of adjusting alert threshold levels based on environmental scenarios workers’ recognition performance evaluated using wearable...

Abstract Machine vision technologies have the potential to revolutionize hazard inspection, but training machine learning models requires large labeled datasets and is susceptible biases. The lack of robust perception capabilities in systems for construction inspection poses significant safety concerns. To address this, we propose a novel method that leverages human knowledge extracted from electroencephalogram (EEG) recordings enhance through transfer learning. By pretraining convolutional...

Vulnerable Road Users (VRUs) present a significant challenge for road safety due to the frequent unpredictability of their behaviors. In typical Intelligent Transportation Systems, vision-based approaches supported by networked cameras are often used anticipate VRUs motion intentions and trajectories. However, several limitations posed occlusions distractions set boundary efficacy such methods. To address these challenges, this study introduces framework that leverages data collected using...

<title>Abstract</title> Background and Hypothesis: Chronic Kidney Disease (CKD) Cardiovascular (CVD) are significant public health concerns with high morbidity mortality rates. the relationship between CKD CVD comorbidities their influencing factors in Chinese middle-aged elderly people remains underexplored. We hypothesize that some socio-demographic factors, lifestyle physical condition significantly influence prevalence comorbidity of CVD. Methods Data from China Health Retirement...

<title>Abstract</title> Background and aims: Chronic Kidney Disease (CKD) Cardiovascular (CVD) are significant public health concerns with high morbidity mortality. The relationship between CKD CVD their influencing factors in Chinese middle-aged elderly people remains underexplored. We hypothesize that some socio-demographic factors, lifestyle physical condition significantly influence the prevalence comorbidity of CVD. Methods used data from China Health Retirement Longitudinal Study...

Classifying brain signals collected by wearable Internet of Things (IoT) sensors, especially brain-computer interfaces (BCIs), is one the fastest-growing areas research. However, research has mostly ignored secure storage and privacy protection issues personal neurophysiological data. Therefore, in this article, we try to bridge gap propose a privacy-preserving protocol for implementing BCI applications. We first transformed into images used generative adversarial network generate synthetic...

Computer-vision technologies have emerged to assist security surveillance. However, automation alert/alarm systems often apply a low-beta threshold avoid misses and generates excessive false alarms. This study proposed an adaptive hazard diagnosis alarm system with adjustable alert levels based on environmental scenarios operator's recognition performance. We recorded electroencephalogram (EEG) data during tasks. The linear ballistic accumulator model was used decompose the response time...

Purpose: Human-machine collaboration is a promising strategy to improve hazard inspection. However, research on the effective integration of opinions from humans with machines for optimal group decision making lacking. Hence, considering benefits brain-computer interface (BCI) enable intuitive commutation, this study proposes novel method predict human response choices and confidence brain activities superior confidence-weighted voting strategy. Methodology: First, we developed Bayesian...

The sandstone test of uniaxial compression acoustic emission (AE) has been studied, the HHT analysis is applied to AE signal processing, and through reveal process rock fracture. results show that a method based on principal component time-frequency analysis. can very convenient deal singular signal; it be determine main composition signal. instantaneous frequency used describe precisely characteristics important significance EMD decomposed into 8 IMF components in failure sound. IMF1 ~ IMF4...

This paper simulated 7 kinds of rock uniaxial compression fracture under different homogeneity (each sample size is 3) by RFPA.According to the results numerical simulation, failure analyzed as follow.The study indicate that with increase degree, precursory information main significantly reduced, and stronger brittle fracture, macroscopic mode performance a concentrated shape.On contrary, then it will show some diffusivity.Under same degree conditions, macro-strength certain statistical law,...

The increasing frequency of extreme weather events poses ever greater challenges to urban resilience and residents' quality life. Despite a growing trend towards advocating for human-centered approach resilience, there remains an inadequate understanding human needs their temporal fluctuations during multi-wave disasters. This knowledge gap results in significant shortcomings how government emergency responses city infrastructure repairs can effectively cater needs. article seeks bridge this...

A transfer learning paradigm is proposed for "knowledge" between the human brain and convolutional neural network (CNN) a construction hazard categorization task. Participants' activities are recorded using electroencephalogram (EEG) measurements when viewing same images (target dataset) as CNN. The CNN pretrained on EEG data then fine-tuned scene images. results reveal that EEG-pretrained achieves 9 % higher accuracy compared with architecture but randomly initialized parameters three-class...