Advancements in artificial intelligence have propelled affective computing toward unprecedented accuracy and real-world impact. By leveraging the unique strengths of brain signals and ocular dynamics, we introduce a novel multimodal framework that integrates EEG and eye-movement (EM) features synergistically to achieve more reliable emotion recognition. First, our EEG Feature Encoder (EFE) uses a convolutional architecture inspired by the human visual cortex's eccentricity-receptive-field mapping, enabling the extraction of highly discriminative neural patterns. Second, our EM Feature Encoder (EMFE) employs a Kolmogorov-Arnold Network (KAN) to overcome the sparse sampling and dimensional mismatch inherent in EM data; through a tailored multilayer design and interpolation alignment, it generates rich, modality-compatible representations. Finally, the core Multimodal Iterative Attentional Feature Fusion (MIAFF) module unites these streams: alternating global and local attention via a Hierarchical Channel Attention Module (HCAM) to iteratively refine and integrate features. Comprehensive evaluations on SEED (3-class) and SEED-IV (4-class) benchmarks show that our method reaches leading-edge accuracy. However, our experiments are limited by small homogeneous datasets, untested cross-cultural robustness, and potential degradation in noisy or edge-deployment settings. Nevertheless, this work not only underscores the power of biomimetic encoding and iterative attention but also paves the way for next-generation brain-computer interface applications in affective health, adaptive gaming, and beyond.

Spiking neural networks (SNNs) can be operated in an event-driven manner to save energy consumption of artificial neural networks (ANNs), which has attracted enormous research interests for their high biological plausibility and powerful spatiotemporal information processing. However, representative studies only evaluated SNNs on static temporal tasks or short sequence tasks, which could not fully demonstrate the advantages of SNNs in spatiotemporal learning. In addition, we point out that the existing directly trained SNNs to face the problems of long-term memory, network degeneration, gradient saturation, and heterogeneity learning, these limit the performance of SNNs. In this article, we propose channelwise regional integrate and multiple firing (CRIMF) neuron to improve the spatiotemporal learning of SNNs. First, CRIMF neuron contains a new internal state of regional current that enhances the memory of spiking neurons and facilitates the learning of temporal information over long time steps. Second, CRIMF neuron is implemented with the multiple firing mechanisms; it is able to adjust the distribution of membrane potential and membrane potential gradient in the single firing mechanism, thus mitigating the underactivation and gradient saturation. Third, CRIMF neuron is trained with the channelwise learning strategy for the targeted learning of different types of temporal features, and an index of differentiation degree is proposed to visualize the effectiveness of the channelwise learning strategy. We also introduce the regional current reset equation and normalize the input of postsynaptic neurons in spatiotemporal dimension to avoid network degeneration. Finally, we select two emotion electroencephalogram (EEG) datasets and perform the evaluations based on manual features and raw signals. Experimental results show that CRIMF-based SNNs outperform the state-of-the-art methods in static temporal task, and CRIMF neurons are superior to the advanced spiking neurons and recurrent units of ANNs in dynamic temporal task, using low energy consumption.

Hand motion monitoring plays a crucial role in fields such as human-machine interaction and rehabilitation training. Currently, electronic sensors are commonly used for hand motion monitoring. However, they are confronted with issues such as susceptibility to electromagnetic interference and sweat stains. Fiber Bragg Grating (FBG) sensors are small in size, highly sensitive, and possess good biocompatibility. In this paper, a flexible distributed Fiber Bragg Grating sensor is introduced. Emphasis is laid on the optimization and fabrication of the sensor, and performance tests are carried out on the fabricated sensor. To verify the potential of the sensor in hand motion monitoring, experiments are conducted. In the gesture recognition experiment, the Vision Transformer (ViT) model is utilized to classify eight types of gestures, and the final accuracy reaches 96.5%. In the wrist joint angle measurement experiment, the Pearson correlation coefficient between the physical angle and the measured angle is 0.985. In the grasping experiment, individual differences are reflected by the standard deviation during the grasping process. The experiments have demonstrated that the proposed sensor has the potential for monitoring hand motions.

The draw ratios allocation critically determines the final performance of carbon fiber. However, the stochastic nature in component fluxes and concentrations variations introduces uncertainty into draw ratios, causing frequent parameter fluctuations. Therefore, we propose a robust operation optimization framework that formulates a biobjective model to minimize linear density and maximize strength. Within this framework, a causal forest-guided partitioning for robust operation optimization algorithm is developed to solve the model. Specifically, the algorithm uses perturbations on individual decision variables to form treatment groups from an initial control population, enabling causal forests to infer the overall causal effects of each decision variable on the objectives. Next, the computed mean conditional average treatment effects are clustered via K-means to partition the variables by their robustness relevance. Then, a tailored optimization strategy, augmented by an external archiving mechanism, is performed on each group to efficiently search for the robust Pareto optimal set. Finally, adaptive utopian point-based decision making is used to determine the optimal setpoint. The proposed framework is validated on benchmark problems and in simulation study, achieves a 29.93% reduction in linear density and 99.41% increase in strength, thereby confirming its practical applicability.

Since digital spiking signals can carry rich information and propagate with low computational consumption, spiking neural networks (SNNs) have received great attention from neuroscientists and are regarded as the future development object of neural networks. However, generating the appropriate spiking signals remains challenging, which is related to the dynamics property of neurons. Most existing studies imitate the biological neurons based on the correlation of synaptic input and output, but these models have only one time constant, thus ignoring the structural differentiation and versatility in biological neurons. In this article, we propose the reconstruction of adaptive leaky integrate-and-fire (R-ALIF) neuron to perform complex behaviors similar to real neurons. First, a synaptic cleft time constant is introduced into the membrane voltage charging equation to distinguish the leakage degree between the neuron membrane and the synaptic cleft, which can expand the representation space of spiking neurons to facilitate SNNs to obtain better information expression way. Second, R-ALIF constructs a voltage threshold adjustment equation to balance the firing rate of output signals. Third, three time constants are transformed into learnable parameters, enabling the adaptive adjustment of dynamics equation and enhancing the information expression ability of SNNs. Fourth, the computational graph of R-ALIF is optimized to improve the performance of SNNs. Moreover, we adopt a temporal dropout (TemDrop) method to solve the overfitting problem in SNNs and propose a data augmentation method for neuromorphic datasets. Finally, we evaluate our method on CIFAR10-DVS, ASL-DVS, and CIFAR-100, and achieve top1 accuracy of 81.0%, 99.8%, and 67.83%, respectively, with few time steps. We believe that our method will further promote the development of SNNs trained by spatiotemporal backpropagation (STBP).

Upper limb rehabilitation robot can assist stroke patients to complete daily activities to promote the recovery of upper-limb motor functions. However, the robot uncertainty and the patient’s unconscious disturbance impose great difficulties on the high-performance trajectory tracking of the rehabilitation robot. In this paper, an uncertainty compensated high-order adaptive iterative learning controller (UCHAILC) is proposed to reduce the impact of uncertainty from inside and outside of the robot during the rehabilitation process. The nonlinear system is converted into a dynamic linearization model with uncertainty compensation, and the optimization criterion method is adopted to estimate the pseudo-partial derivative (PPD) parameters and the uncertainty respectively, then the previous iterations are used to update the current parameters through a high-order learning scheme. The convergence of UCHAILC is theoretically proved. Simulation and control experiments on a rehabilitation robot are given to validate the effectiveness of the proposed method, which is significant to improve the training security and physiotherapy effect of robot-assisted rehabilitation.Note to Practitioners—This paper was motivated by the need to assist stroke patients to restore motor function for executing daily activities. The inherent difficulties lie in reducing the tracking errors of rehabilitation robots caused by uncertainty and involuntary disturbance from patients to avoid secondary injury. The proposed UCHAILC can transform the complex nonlinear system into a dynamic linear model with uncertainty compensation, then the PPD parameters and uncertainty are estimated through high-order learning law. Theoretical analysis, simulation, and experiments verified the feasibility of the method. Furthermore, the proposed controller is not limited to the dynamic model and hardware driving mode of the robot system, which can be easily transplanted to other nonlinear control systems with uncertainties.

The motor synergy pattern is an intrinsic characteristic found in natural human movements, particularly in the upper limb. It is essential to improve the multijoint coordination ability for stroke patients by integrating the synergy pattern into rehabilitation tasks and trajectory design. However, current robot-assisted rehabilitation systems tend to overlook the incorporation of a multijoint synergy model. This article proposes postural synergistic kernelized movement primitives (PSKMP) method for the human-like trajectory planning of robot-assisted upper limb rehabilitation. First, the demonstrated trajectory obtained from the motion capture system is subject to principal component analysis to extract postural synergies. Then, the PSKMP is proposed by kernelizing the postural synergistic subspaces with the kernel treatment to preserve human natural movement characteristics. Finally, the rehabilitation trajectory accord with human motion habits can be generated based on generalized postural synergistic subspaces. This approach has undergone practical validation on an upper limb rehabilitation robot, and the experimental results show that the proposed method enables the generation of human-like trajectories adapted to new task points, in accordance with the natural movement style of human. This method holds great significance in promoting the recovery of coordination ability of stroke patients.

Non-terrestrial wireless communications have evolved into a technology enabler for seamless connectivity and ubiquitous computing services in the beyond fifth-generation (B5G) and sixth-generation (6G) networks, aiming to provision reliable and energy efficient communications among aerial platforms and ground mobile users. This paper considers intelligent reflecting surface (IRS)-assisted unmanned aerial vehicle (UAV)-empowered wireless communication, which exploits both the high mobility of UAV and passive beamforming gain brought by IRS. The energy minimization of rotary-wing UAV is formulated by jointly considering numerous quality of service (QoS) constraints with intricately coupled variables. To tackle the formulated challenging problem, a heuristic algorithm is proposed. First, we decouple it into several subproblems. Moreover, we jointly investigate offloading decisions of Internet of Thing (IoT) devices by the proposed enhanced differential evolution algorithm. Then, minorization-maximization algorithm (MMA) is utilized to solve the optimization of IRS phase shift-vector. Moreover, ant colony optimization (ACO) algorithm is proposed to optimize UAV flight route indicator matrix. Numerical results validate the effectiveness of the proposed algorithm. The results show that the proposed solution can remarkably decrease UAV flight distance while improving the network energy efficiency in comparison with numerous advanced algorithms.

Abstract Studying representation learning and generative modelling has been at the core of the 3D learning domain. By leveraging the generative adversarial networks and convolutional neural networks for point‐cloud representations, we propose a novel framework, which can directly generate 3D objects represented by point clouds. The novelties of the proposed method are threefold. First, the generative adversarial networks are applied to 3D object generation in the point‐cloud space, where the model learns object representation from point clouds independently. In this work, we propose a 3D spatial transformer network, and integrate it into a generation model, whose ability for extracting and reconstructing features for 3D objects can be improved. Second, a point‐wise approach is developed to reduce the computational complexity of the proposed network. Third, an evaluation system is proposed to measure the performance of our model by employing various categories and methods, and the error, considered as the difference between synthesized objects and raw objects are quantitatively compared, is less than 2.8%. Extensive experiments on benchmark dataset show that this method has a strong ability to generate 3D objects in the point‐cloud space, and the synthesized objects have slight differences with man‐made 3D objects.

During robot-assisted rehabilitation, failure to detect muscle fatigue in time may cause severe damage to human muscles. Surface electromyography (sEMG) signals are widely used in muscle fatigue analysis, but the dynamic fatigue classification is rarely reported and the accuracy is not satisfactory. In this article, an accurate classification model incorporating support vector machine (SVM) is established to accommodate the muscle fatigue prediction in dynamic conditions by proposing an improved whale optimization algorithm (WOA). Multidomain sEMG features are extracted and then fused to effectively classify the muscle fatigue statuses. WOA’s global optimization capability is able to find out the optimal parameters for SVM, but it will be greatly affected by the initial population. The differential evolution (DE) algorithm is adopted here to generate a more appropriate initial population. Experiments were carried out to distinguish the normal and fatigue status by using sEMG signals only. Results demonstrate the effectiveness and feasibility of the proposed method in dynamic muscle fatigue prediction with an average accuracy of 85.50% in ankle dorsiflexion (DF) and 84.75% in ankle plantarflexion (PF).

Disassembly is a core procedure in remanufacturing. Disassembly is currently carried out mainly by human operators. It is important to reduce the labor content of disassembly through automation, to make remanufacturing more economically attractive. Threaded fastener removal is one of the most difficult disassembly tasks to be fully automated. This article presents a new method developed for automating the unfastening of screws. An electric nutrunner spindle with a geared offset adapter was fitted to the end of a collaborative robot. The position of a hexagonal headed screw in a fitted stage was known only approximately, and its orientation in the hole was unknown. The robot was programed to perform a spiral search motion to engage the tool onto the screw. A control strategy combining torque and position monitoring with active compliance was implemented. An existing robot cell was modified and utilized to demonstrate the concept and to assess the feasibility of the solution using a turbocharger as a disassembly case study. Note to Practitioners-Remanufacturing is known to generate substantial economic, social, and environmental benefits. Disassembly is the first operation in a remanufacturing process chain. Unfastening threaded parts (“unscrewing”) is a common disassembly task accounting for approximately 40% of all disassembly activity. Like other disassembly tasks, often, unscrewing has to be carried out manually in remanufacturing due to difficulties caused by the variable and unpredictable condition of the end-of-life (EoL) products to be remanufactured. Automating unscrewing operations should reduce the labor content of disassembly, thus lowering remanufacturing costs and promoting the adoption of remanufacturing. This article proposes the use of a collaborative robot to perform autonomous unfastening of hexagonal headed screws. Collaborative robots have built-in force sensors and can be programed to carry out operations involving not only position but also active force and compliance control. They can work safely alongside human operators, enabling the latter to focus on jobs requiring high cognitive or manipulation abilities. The article presents a novel spiral search technique developed to improve the rate of successful engagement between the robot end effector and the screw heads despite uncertainties in the location of the screws. The technique was successfully demonstrated on the dismantling of a turbocharger but can readily be applied to other EoL products with hexagonal headed screws. It can also be used with other kinds of screws (e.g., Phillips screws and slotted-head screws) simply by changing the tool and tuning the robot control parameters. A limitation of the proposed technique is that it can only deal reliably with undamaged screws. In our future research, we will consider screws that are in imperfect conditions through usage and develop appropriate solutions for their removal by robots.

To solve the poor compliance and safety problems in current rehabilitation robots, a novel two-degrees-of-freedom (2-DOF) soft ankle rehabilitation robot driven by pneumatic muscles (PMs) is presented, taking advantages of the PM's inherent compliance and the parallel structure's high stiffness and payload capacity. However, the PM's nonlinear, time-varying and hysteresis characteristics, and the coupling interference from parallel structure, as well as the unpredicted disturbance caused by arbitrary human behavior all raise difficulties in achieving high-precision control of the robot. In this paper, a multi-input-multi-output disturbance compensated sliding mode controller (MIMO-DCSMC) is proposed to tackle these problems. The proposed control method can tackle the un-modeled uncertainties and the coupling interference existed in multiple PMs' synchronous movement, even with the subject's participation. Experiment results on a healthy subject confirmed that the PMs-actuated ankle rehabilitation robot controlled by the proposed MIMO-DCSMC is able to assist patients to perform high-accuracy rehabilitation tasks by tracking the desired trajectory in a compliant manner.

Image annotation is always an easy task for humans but a tough task for machines. Inspired by human's thinking mode, there is an assumption that the computer has double systems. Each of the systems can handle the task individually and in parallel. In this paper, we introduce a new hierarchical model for image annotation, based on constructing a novel, hierarchical tree, which consists of exploring the relationships between the labels and the features used, and dividing labels into several hierarchies for efficient and accurate labeling.

Recently, tremendous utilization of wireless networks has led to sever scarcity of radio spectrum resources. TV White Spaces (TVWSs) as novel bands enabling Cognitive Radio (CR) technology to improve spectrum resources utilization, have attracted significant standardisation efforts such as IEEE 802.11af, IEEE 802.16h and 802.22. As these heterogeneous networks may operate on the same channels of TVWSs, network coexistence problem cannot be avoided and is particularly challenging given the heterogeneous MAC/PHY layer protocols and operation parameters (e.g., tx power) employed in coexisting networks. In this paper, we develop a coexistence mechanism called ecological Species Competition based HEterogeneous networks coexistence MEchanism (SCHEME). Inspired by ecology based species competition model, SCHEME uses an ecological spectrum allocation method to assign available spectrums. Through both theoretical and simulation analysis, we demonstrate that SCHEME can achieve stable and fair spectrum allocation among coexisting networks.

For those shortcomings of current methods in fault diagnosis knowledge representation, it is necessary to use an efficient knowledge model to improve the accuracy of fault diagnosis and to realize the reusing and sharing of machinery fault knowledge. In this paper, an ontology-based fault diagnosis model is established. Focusing on fault diagnosis of rotating machinery, the domain-ontology knowledge base and structure definition of the fault diagnosis are demonstrated in detail. The protégé is used to construct the model of ontology-based fault diagnosis. Furthermore, rules are added and Jena is used to realize the knowledge reasoning. The result indicates that the model of fault diagnosis based on ontology is intuitive and efficient.

Faults in mechanical equipment could cause breakdown of time-critical production systems, which is very expensive in terms of production losses and re-commissioning costs. In cloud manufacturing, the scattered distribution of mechanical equipment and fault diagnosis resources, such as experts and specialist instruments, etc., could hinder the development of fault diagnosis systems. The idea of resource servitisation, aimed at resource sharing and collaboration, will lead fault diagnosis systems toward integration, low cost and high efficiency. This paper focuses on the servitisation of fault diagnosis for mechanical equipment in cloud manufacturing. A new service-oriented fault diagnosis system framework for mechanical equipment is proposed, together with a new servitisation method of fault diagnosis for mechanical equipment. Moreover, enabling technologies, e.g. XML, Web Services Definition Language (WSDL), Axis2, are also analysed. Finally, a prototype system is presented that demonstrates the feasibility and effectiveness of the developed architecture and servitisation method in a cloud manufacturing environment.

The authors consider a cognitive radio network overlaying on top of a legacy primary network in which a secondary user is allowed to access primary channel by overhearing feedback signals over the primary channels. Each channel is assumed to be a two state Makovian process. Aiming at maximising the expected accumulated discounted network throughput, the considered sequential decision‐making problem can be cast into a restless multi‐armed bandit (RMAB) problem which is well‐known to be PSPACE‐hard, and thus a natural alternative approach is to seek a simple myopic policy. This study presents a theoretical study on the optimality of the proposed myopic policy for the special RMAB problem by considering four different cases: negatively correlated homogeneous channels, heterogeneous channels, positively correlated heterogeneous channels and negatively correlated heterogeneous channels. More specifically, the authors establish the closed‐form conditions to guarantee the optimality of the myopic policy for the four cases, respectively, which, combined with the case of positively correlated homogeneous channels, constitute a complete paradigm for the optimality of the myopic policy.

In this paper, we consider the probing order and stopping problem arising from the identification of spectrum holes in multi-channel cognitive radio networks, in which a secondary user (SU) seeks to maximize the probability of finding an available channel while minimizing the related probing cost within a long time horizon. This problem can be casted into a restless multi-armed bandit problem, which is proved to be PSPACE-hard. The key point of this problem is the trade-off between exploitation, in which the SU stops probing once an available channel is identified, and exploration, in which the SU continues to probe new channels even after identifying an available channel in order to learn the system state to reduce probing cost in the future. To strike a desirable balance between the two conflicting objectives, we develop a heuristic channel probing policy, termed the v-step lookahead policy, in which the SU makes its decision based on the prediction of system state within the future v steps, with v being a tunable parameter. We conduct an analytical study on the structure of the proposed v-step lookahead policy and demonstrate how the policy can be implemented with linear complexity with respect to the number of channels in the system via a detailed analysis on the 1-step lookahead policy. Numerical experiments between the v-step lookahead policy and myopic probing policy on two representative network scenarios demonstrate the effectiveness of the proposed v-step lookahead policy.

This paper proposes an electromyography (EMG)-based method for online force prediction and control of a lower limb rehabilitation robot. Root mean square (RMS) features of EMG signals from four muscles of the lower limb are used as the inputs to a support vector regression (SVR) model to estimate the human-robot interaction force. The autoregressive algorithm is utilized to construct the relationship between EMG signals and the impact force. Combining the force prediction model with the position-based impedance controller, the robot can be controlled to track the desired force of the lower limb, and so as to achieve an adaptive and active rehabilitation mode, which is adaptable to the individual muscle strength and movement ability. Finally, the method was validated through experiments on a healthy subject. The results show that the EMG-based SVR model can predict the lower limb force accurately and the robot can be controlled to track the estimated force by using simplified impedance model.

We consider the channel access problem in a multi-channel opportunistic communication system with imperfect channel sensing, where the state of each channel evolves as an independent and identically distributed Markov process. The considered problem can be cast into a restless multi-armed bandit (RMAB) problem that is of fundamental importance in decision theory. It is well-known that the optimal policy of RMAB problem is intractable for its exponential computation complexity. A natural alternative is to consider the easily implementable myopic policy that maximizes the immediate reward but ignores the impact of the current strategy on the future reward. In this paper, we perform an analytical study on the optimality of the myopic policy under imperfect sensing for the considered RMAB problem. Specifically, for a family of generic and practically important utility functions, we establish the closed-form conditions to guarantee the optimality of the myopic policy even under imperfect sensing. Despite our focus on the opportunistic channel access, the obtained results are generic in nature and are widely applicable in a wide range of engineering domains.

In this study, the authors consider the restless multi-armed bandit problem, which is one of the most well-studied generalisations of the celebrated stochastic multi-armed bandit problem in decision theory. However, it is known to be PSPACE-Hard to approximate to any non-trivial factor. Thus, the optimality is very difficult to obtain because of its high complexity. A natural method is to obtain the greedy policy considering its stability and simplicity. However, the greedy policy will result in the optimality loss for its intrinsic myopic behaviour generally. In this study, by analysing one class of so-called standard reward function, the authors establish the closed-form condition about the discounted factor β such that the optimality of the greedy policy is guaranteed under the discounted expected reward criterion, especially, the condition β=1 indicating the optimality of the greedy policy under the average accumulative reward criterion. Thus, this kind of standard reward function can easily be used to judge the optimality of the greedy policy without any complicated calculation. Some examples in cognitive radio networks are presented to verify the effectiveness of the mathematical result in judging the optimality of the greedy policy.

Cyber-physical system (CPS) is a multi-dimensional complex system in which physical world operations are monitored and controlled using the communication and computing components, and they interact with each other in order to achieve a global optimization of such system operation. Dynamic response to the emergencies in a public environment not only requires the perception capability that obtains such useful information, but also needs the optimum operation methods to handling them. With the tight integration of communication, computing and control, a CPS can be used to address the aforementioned goals. In this paper, a framework of the CPS for public environment perception and emergency handling is developed, and its requirements to each component in the framework are analyzed in detail. Furthermore, a task allocation mechanism and a hybrid path planning approach are also presented for a set of robots in the CPS to handle uncertain emergencies collaboratively. Finally, we demonstrate the system using a case study in which mobile robots are equipped with multiple sensors to handle fires with different cases in a scenario of public environment, and the simulation results show the effectiveness of the proposed approaches and the feasibility of such system.

A joint project of a Web-based remote service platform is introduced in the paper. First the architecture of the platform is offered. Then key technologies, such as remote maintenance and operation, remote monitoring based on multi-media, management of virtual device and user files, after-sale service and technical supports, and security considerations for remote communication etc, are described in detail. In the end, the remote operation and inspection prototype interface of the platform is provided. Key technologies described in the paper have important values and application prospects for manufacturing enterprises to set up their remote service system