Background: Fall detection is of great significance in safeguarding human health. By monitoring the motion data, a fall detection system (FDS) can detect a fall accident. Recently, wearable sensors–based FDSs have become the mainstream of research, which can be categorized into threshold-based FDSs using experience, machine learning–based FDSs using manual feature extraction, and deep learning (DL)–based FDSs using automatic feature extraction. However, most FDSs focus on the global information of sensor data, neglecting the fact that different segments of the data contribute variably to fall detection. This shortcoming makes it challenging for FDSs to accurately distinguish between similar human motion patterns of actual falls and fall-like actions, leading to a decrease in detection accuracy. Objective: This study aims to develop and validate a DL framework to accurately detect falls using acceleration and gyroscope data from wearable sensors. We aim to explore the essential contributing features extracted from sensor data to distinguish falls from activities of daily life. The significance of this study lies in reforming the FDS by designing a weighted feature representation using DL methods to effectively differentiate between fall events and fall-like activities. Methods: Based on the 3-axis acceleration and gyroscope data, we proposed a new DL architecture, the dual-stream convolutional neural network self-attention (DSCS) model. Unlike previous studies, the used architecture can extract global feature information from acceleration and gyroscope data. Additionally, we incorporated a self-attention module to assign different weights to the original feature vector, enabling the model to learn the contribution effect of the sensor data and enhance classification accuracy. The proposed model was trained and tested on 2 public data sets: SisFall and MobiFall. In addition, 10 participants were recruited to carry out practical validation of the DSCS model. A total of 1700 trials were performed to test the generalization ability of the model. Results: The fall detection accuracy of the DSCS model was 99.32% (recall=99.15%; precision=98.58%) and 99.65% (recall=100%; precision=98.39%) on the test sets of SisFall and MobiFall, respectively. In the ablation experiment, we compared the DSCS model with state-of-the-art machine learning and DL models. On the SisFall data set, the DSCS model achieved the second-best accuracy; on the MobiFall data set, the DSCS model achieved the best accuracy, recall, and precision. In practical validation, the accuracy of the DSCS model was 96.41% (recall=95.12%; specificity=97.55%). Conclusions: This study demonstrates that the DSCS model can significantly improve the accuracy of fall detection on 2 publicly available data sets and performs robustly in practical validation.

Background: Physical activity (PA) is vital for physical and mental health, but many college students fail to meet recommended levels. Artificial intelligence (AI)-powered gamification interventions through mobile app have the potential to improve PA levels among Chinese college students. Objective: This study aimed to assess the feasibility and usability of an AI-powered gamification intervention. Methods: A quasi-experimental study spanning 2 months was conducted on a sample of college students aged 18 to 25 years old from 18 universities in Beijing. PA data were recorded using the ShouTi Fitness app, and participant engagement was evaluated through surveys. User satisfaction was gauged through the System Usability Scale, while the intervention’s feasibility was assessed through Spearman rank correlation analysis, Mann-Whitney tests, and additional descriptive analyses. Results: As of July 2023, we enrolled 456 college students. In total, 18,073 PA sessions were recorded, with men completing 8068 sessions and women completing 10,055 sessions. The average PA intensity was 7 metabolic equivalent of energy (MET)s per session. Most participants preferred afternoon sessions and favored short-duration sessions, with men averaging 66 seconds per session and women 42 seconds. The System Usability Scale score for the intervention based on app is 65.2. Users responded positively to the integration of AI and gamification elements, including personalized recommendations, action recognition, smart grouping, dynamic management, collaborative, and competition. Specifically, 341 users (75%) found the AI features very interesting, 365 (80%) were motivated by the gamification elements, 364 (80%) reported that the intervention supported their fitness goals, and 365 (80%) considered the intervention reliable. A significant positive correlation was observed between the duration of individual PA and intervention duration for men (ρ=0.510, P<.001), although the correlation was weaker for women (ρ=0.258, P=.046). However, the frequency of PA declined after 35 days. Conclusions: This study provides pioneering evidence of the feasibility and usability of the AI-powered gamification intervention. While adherence was successfully demonstrated, further studies or interventions are needed to directly assess the impact on PA levels and focus on optimizing long-term adherence strategies and evaluating health outcomes.

The development of technology has strongly affected regional urbanization. With development of mobile communication technology, intelligent devices have become increasingly widely used in people’s lives. The application of big data in urban computing is multidimensional; it has been involved in different fields, such as urban planning, network optimization, intelligent transportation, energy consumption and so on. Data analysis becomes particularly important for wireless networks. In this paper, a method for analyzing cellular traffic data was proposed. Firstly, a method to extract trend components, periodic components and essential components from complex traffic time series was proposed. Secondly, we introduced causality data mining. Different from traditional time series causality analysis, the depth of causal mining was increased. We conducted causality verification on different components of time series and the results showed that the causal relationship between base stations is different in trend component, periodic component and essential component in urban wireless network. This is crucial for urban planning and network management. Thirdly, DIC-ST: a spatial temporal time series prediction based on decomposition and integration system with causal structure learning was proposed by combining GCN. Final results showed that the proposed method significantly improves the accuracy of cellular traffic prediction. At the same time, this method can play a crucial role for urban computing in network management, intelligent transportation, base station siting and energy consumption when combined with remote sensing map information.

This study examined how different sequences of concurrent training impacted physical activity (PA), body composition, and physical fitness in young obese males. We also investigated whether the effectiveness of these interventions in reducing body fat percentage (BF%) was influenced by PA levels. A 12-week randomized controlled trial involving a cohort of 45 obese young males (mean age: 22.42 ± 1.96 years, mean BMI: 29.78 ± 3.37) was conducted. Participants were randomly assigned to three groups: the CRE group (Resistance Training (RT) followed by Endurance Training (ET)), the CER group (ET followed by RT), and the control group (Con). The training sessions were held three times a week. Measurements, including PA level, body composition, bone density, VO2max, and muscle strength, were assessed before and after the intervention. Compared to those at baseline, following the intervention, both the CRE and CER groups showed significant improvements in various parameters, including PA level, body composition, bone density, VO_2max, and muscle strength (p < 0.05), whereas no significant changes were observed in the Con group (p > 0.05). Specifically, the CRE group demonstrated remarkable progress, as evidenced by an increase in MVPA level (η²_p = 0.37, p < 0.001), a reduction in fat mass (η²_p = 0.28, p < 0.001), BF% (η²_p = 0.28, p < 0.001), android fat (%) (η²_p = 0.21, p < 0.001), gynoid fat (%) (η²_p = 0.30, p < 0.001), and various physical fitness indices, such as maximum strength (η²_p = 0.20, p = 0.008), explosive strength (η²_p = 0.38, p < 0.001), and muscular endurance (η²_p = 0.55, p < 0.001), surpassing the improvements observed in the CER and Con groups. Changes in PA levels during the intervention influence the efficacy of CT in reducing BF%. CT, particularly when RT precedes ET, had the potential to improve PA levels, overall physical fitness, body composition, and bone health in obese young males. Moreover, changes in PA levels during the intervention impacted the effectiveness of CT in reducing BF%. ChiCTR, ChiCTR2200063892.

In this article, we consider a single unmanned aerial vehicle (UAV)-assisted heterogeneous network in a disaster area, which includes a UAV, ground cellular users, and ground sensor users. The cellular data and sensing data are transmitted to UAVs by cellular users and sensor users, due to the outage of the ground wireless network caused by the disaster. In this scenario, we aim to minimize the energy consumption of all the users, to extend their communication time and facilitate rescue. At the same time, cellular users and sensor users have different rate requirements, hence the quality of service (QoS) of the users should be guaranteed. To solve these challenges, we propose an energy-effective relay selection and resource-allocation algorithm. First, to solve the problem of insufficient coverage of the single UAV network, we propose to perform multi-hop transmission for the users outside the UAV’s coverage by selecting suitable relays in an energy-effective manner. Second, for the cellular users and sensor users inside the coverage of the UAV but with different QoS requirements, we design a non-orthogonal multiple access (NOMA)-based transmission scheme to improve spectrum efficiency. Deep reinforcement learning is exploited to dynamically adjust the power level and allocated sub-bands for inside users to reduce energy consumption and improve QoS satisfaction. The simulation results show that the proposed NOMA transmission scheme can achieve 9–17% and 15–32% performance gain on the reduction of transmit power and the improvement of QoS satisfaction, respectively, compared with state-of-the-art NOMA transmission schemes and orthogonal multiple access scheme.

Unmanned Aerial Vehicle (UAV) has been widely used in various applications of wireless network. A system of UAVs has the function of collecting data, offloading traffic for ground Base Stations (BSs) and illuminating coverage holes. However, inter-UAV interference is easily introduced because of the huge number of LoS paths in the air-to-ground channel. In this paper, we propose an interference management framework for UAV-assisted networks, consisting of two main modules: power control and UAV clustering. The power control is executed first to adjust the power levels of UAVs. We model the problem of power control for UAV networks as a non-cooperative game which is proved to be an exact potential game and the Nash equilibrium is reached. Next, to further improve system user rate, coordinated multi-point (CoMP) technique is implemented. The cooperative UAV sets are established to serve users and thus transforming the interfering links into useful links. Affinity propagation is applied to build clusters of UAVs based on the interference strength. Simulation results show that the proposed algorithm integrating power control with CoMP can effectively reduce the interference and improve system sum-rate, compared to Non-CoMP scenario. The law of cluster formation is also obtained where the average cluster size and the number of clusters are affected by inter-UAV distance.