Musculoskeletal models have been widely used for detailed biomechanical analysis to characterise various functional impairments given their ability estimate movement variables (i.e., muscle forces and joint moments) which cannot be readily measured in vivo. Physics-based computational neuromusculoskeletal can interpret the dynamic interaction between neural drive muscles, dynamics, body kinematics kinetics. Still, such set of solutions suffers from slowness, especially complex models,...

In recent years, WiFi-based device-free localization (DFL) has attracted attentions due to the rapid development of location-based applications. The performance data-driven DFL models highly relies on quality fingerprint. However, it is difficult obtain high-quality fingerprints in cluttered environments various uncertainties, such as environmental dynamics. To mitigate effects this article proposes a variance-constrained local–global modeling method enhance performance. be specific,...

Past decades have witnessed the extension of Wi-Fi signals as a useful tool sensing human activities. One common assumption behind it is that there one-to-one mapping between activities and received signal patterns. However, this does not hold when user conducts in different locations orientations. Actually, patterns same activity would become inconsistent relative location orientation with respect to transceivers change, leading unstable performance. This problem known position-dependent...

Purpose Efficient traffic incident management is needed to alleviate the negative impact of incidents. Accurate and reliable estimation duration great importance for management. Previous studies have proposed models prediction; however, most these focus on total could not update prediction results in real-time. From a traveler’s perspective, relevant factor residual incident. Besides, few (if any) used dynamic flow parameters models. This paper aims propose framework fill gaps....

Vital signs, such as respiration rate (RR) and heart (HR), are essential for human health status assessment. The radar could detect RR HR in a noncontact manner by sensing the repetitive chest wall movement caused cardiopulmonary activity, which is attractive due to more comfortable experience better privacy protection. However, displacement heartbeat much smaller than that respiration, weak component may be easily overwhelmed harmonics, noise, clutter, making it difficult achieve accurate...

Gas utilization ratio (GUR) is an important indicator used to measure the operating status and energy consumption of blast furnaces (BFs). In this paper, we present a soft-sensor approach, i.e., novel online sequential extreme learning machine (OS-ELM) named DU-OS-ELM, establish data-driven model for GUR prediction. firstly, old collected data are discarded gradually newly acquired given more attention through dynamic forgetting factor (DFF), depending on estimation errors enhance tracking...

In this paper, an intelligent data-driven optimization scheme is proposed for finding the proper burden surface distribution, which exerts large influences on keeping blast furnace running smoothly in energy-efficient state. scheme, production indicators prediction models are first developed using a kernel extreme learning machine algorithm. To heel, decision presented as multiobjective problem time and solved by modified two-stage strategy to generate initial setting values of surface....

Ubiquitous WiFi signals not only provide fundamental communications for a large number of Internet Things devices, but also enable to estimate target's location in contactless manner. However, most the existing device-free localization (DFL) methods utilize time dynamics received signals, leading inaccurate DFL cluttered indoor environments. Because different layouts environments and deployments devices cause mathematical distributions data collected from In this article, multiple kernel...

Recent advances in WiFi-based device-free localization (DFL) mainly focus on stationary scenarios and ignore the environmental dynamics, hindering large-scale implementation of DFL technique. In order to enhance performance nonstationary environments, this article, a novel multidomain collaborative extreme learning machine (MC-ELM)-based framework is proposed. Specifically, whole environment first divided into several subdomains depending distributions collected data using clustering...

Recent advances in wireless sensing techniques have made it possible to recognize hand gestures using channel state information (CSI) commodity WiFi devices. Existing WiFi-based gesture recognition systems mainly use learning-based pattern methods different gestures, however, these fail work well when the locations of transceivers, relative location and orientation with respect and/or gesturing size change, leading inconsistent signal patterns caused by those factors. Although some recent...

Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals provide timely intervention promote health well-beings, such mental chronic cares. As the objectives of mobile sensing could be either \emph{(a) personalized medicine for individuals} or \emph{(b) public populations}, in this work we review design these apps, propose categorize apps/systems two paradigms -- \emph{(i) Personal Sensing} \emph{(ii) Crowd...

Device-free localization (DFL) is becoming one of the new technologies in wireless field, due to its advantage that target be localized does not need attached any electronic device. In radio-frequency (RF) DFL system, radio transmitters (RTs) and receivers (RXs) are used sense collaboratively, location can estimated by fusing changes received signal strength (RSS) measurements associated with links. this paper, we will propose an extreme learning machine (ELM) approach for DFL, improve...

Traffic flow prediction plays an important role in intelligent transportation systems. To accurately capture the complex non-linear temporal characteristics of traffic flow, this paper adopts a Bi-directional Gated Recurrent Unit (Bi-GRU) model prediction. Compared to (GRU), which can memorize information from previous sequence, both and subsequent sequence. demonstrate model's performance, set real case data at 1-hour intervals 5 working days was used, wherein dataset separated into...

Map matching is a fundamental component for location-based services (LBSs), such as vehicle mobility analysis, navigation services, traffic scheduling, etc. In this paper, we investigate federated learning augmented map based on heterogeneous cellular moving trajectories from different operator systems, the goal of which to improve accuracy without violating user privacy. First, develop data collection platform with one Android-based application, and conduct rigorous campaigns. Second,...

Retinal disease detection and diagnosis relying solely on artificial retinal diseases will bring great pressure to doctors increase the rate of misdiagnosis. Therefore, development computer vision technology has brought possibility for ophthalmologists use computer-aided diagnosis. In recent years, most models recognition have been based deep learning, which disadvantage requiring large amounts data training time. It is also partly broad learning its disadvantages are that feature extraction...

Computational biomechanical analysis plays a pivotal role in understanding and improving human movements physical functions. Although physics-based modeling methods can interpret the dynamic interaction between neural drive to muscle dynamics joint kinematics, they suffer from high computational latency. In recent years, data-driven have emerged as promising alternative due their fast execution speed, but label information is still required during training, which not easy acquire practice....

Device-free localization (DFL) is becoming one of the attractive techniques in wireless sensing field, due to its advantage that target does not need be attached any electronic device. However, most existed approaches for DFL can only obtain satisfactory performance specific small area, they cannot function well when implemented complex and large area. In order tackle this issue, article, a hierarchical framework developed large-scale based on data knowledge twin driven integration, which...

There has been no systematic research on the effect of plant growth regulators and silver nitrate treatments control sex expression in watermelon. In this study, we tested responses four watermelon forms (monoecism, gynoecism, andromonoecism, hermaphrodite) to gibberellin, ethephon treatments. Results have shown that, monoecious plants, gibberellins (GA3) reduced percentage female flowers delayed occurrence first flower, while induced formation bisexual flowers. gynoecious both transformed...

Wearable sensor-based human activity recognition has been widely used in many fields. Considering that a multi-sensor based system is not suitable for practical applications and long-term monitoring, this paper proposes single wearable accelerometer-based approach. In order to improve the reliability of remove redundant features have no effect on accuracy, wavelet energy spectrum novel feature selection method are introduced. For each sample, acceleration signal extracted represented by set...