Performance In Complex Environments Research Articles

Impact of public leadership on public service motivation and performance in complex environments

AbstractThis study empirically investigates the effects of public leadership (PL) on job performance (JP) and notes the mediating role of public service motivation (PSM) and the moderating role of environmental complexity (ENC) between PSM and JP. The research framework was tested using a survey of 211 civil servants working in Pakistan. The findings indicate significant positive effects of PL on JP. This relationship was partially mediated by PSM. Additionally, this study found that ENC negatively moderates the positive relationship of PSM and JP and dampens the effect of PSM on JP. The managerial implication of this study is to translate PSM into improved JP by reducing environmental complexities. Suggestions for future research are also presented.

Enhanced stability of perovskite CsPbBr3 QDs via Synergetic encapsulation with ZnO nanocrystals and commercial polymer

Lead halide perovskite nanocrystals with attractive optical properties and low-cost production have emerged as a reliable and promising candidate for next-generation display applications. However, the preparation of optical devices while maintaining high performance in complex environments poses a prominent challenge. Herein, a flexible, stretchable and stable nanocomposite was fabricated through embedding CsPbBr3 QDs (PeQDs) into ZnO nanocrystals and polymer, leading to the enhancements of both stability and luminescence efficiency. This simple approach allows PeQDs own a uniform size of ∼14 nm. Optical characterization showed that the PeQDs size did not change after embedding ZnO nanocrystals, while these QDs exhibit a distinct green emission, with emission centering at 518 nm and narrow bandwidth of ∼20 nm. It was also found that the PeQDs/ZnO/EPDM nanocomposite maintained sufficient stability even after being left in an outdoor environment for 27 days, soaked in water for 60 h, and placed on a hot plate at 90 °C for 60 min. Besides, nanocomposite still maintain good luminescent properties even when stretched four times its original length. Furthermore, using this PeQDs/ZnO/EPDM nanocomposite, the synthesized white light emitting diode (WLED) exhibits a color gamut coverage rate of 129 % under standard NTSC, and 97 % under standard Rec.2020. By using this PeQDs/ZnO/EPDM encapsulation adhesive film, the absolute efficiency of solar cell can be improved by 0.23 %. This work highlights a new insight into defect passivation techniques for PeQDs by the utilization of heterogeneous structures provided by metal oxides.

Design and application of bidirectional soft actuator with multiangle chambers

Purpose This study aims to introduce a novel bidirectional soft actuator as an enhancement to conventional pneumatic network actuators. This improvement involves integrating air chambers positioned at specific angles to improve stability, adaptability and grasping efficiency in various environments. Design/methodology/approach The design approach incorporates air chambers positioned at a 45° angle relative to the horizontal direction at the actuator's terminus, along with additional chambers at a 90° angle. Mathematical models are developed for longitudinal and transverse bending, as well as for obliquely connected cavities, based on the assumption of piecewise constant curvature. Analyses are conducted on output forces, bending characteristics and end contact areas for both transverse and longitudinal ends. Findings The proposed soft actuator surpasses traditional pneumatic network actuators in gripping area due to the inclusion of a diagonal air cavity and a transverse pneumatic network structure at the terminus. As a result, it provides torsion and gripping force in both directions. Testing on a dedicated platform with two variants of grippers demonstrates superior gripping force capability and performance in complex environments. Practical implications Through the design of multiangle chambers, the soft actuator exhibits diverse driving angles and morphological variations, offering innovative design perspectives for industrial grasping. Social implications The design of multiangle chambers facilitates personalized configurations of soft actuators by researchers, enabling tailored angles for specific interaction environments to achieve desired functionalities. This approach offers novel insights into soft actuator design, addressing more prevalent industrial grasping challenges. Originality/value This study introduces a novel soft actuator design that significantly enhances gripping capabilities in comparison to conventional pneumatic network actuators. The incorporation of specific air chamber configurations and mathematical modeling provides valuable insights for the development of adaptable and efficient robotic grippers for industrial and household applications.

Unified control of diverse actions in a wastewater treatment activated sludge system using reinforcement learning for multi-objective optimization

The operation of modern wastewater treatment facilities is a balancing act in which a multitude of variables are controlled to achieve a wide range of objectives, many of which are conflicting. This is especially true within secondary activated sludge systems, where significant research and industry effort has been devoted to advance control optimization strategies, both domain-driven and data-driven. Among data-driven control strategies, reinforcement learning (RL) stands out for its ability to achieve better than human performance in complex environments. While RL has been applied to activated sludge process optimization in existing literature, these applications are typically limited in scope, and never for the control of more than three actions. Expanding the scope of RL control has the potential to increase the optimization potential while concurrently reducing the number of control systems that must be tuned and maintained by operations staff. This study examined several facets of the implementation of multi-action, multi-objective RL agents, namely how many actions a single agent could successfully control and what extent of environment data was necessary to train such agents. This study observed improved control optimization with increasing action scope, though control of waste activated sludge remains a challenge. Furthermore, agents were able to maintain a high level of performance under decreased observation scope, up to a point. When compared to baseline control of the Benchmark Simulation Model No. 1 (BSM1), an RL agent controlling seven individual actions improved the average BSM1 performance metric by 8.3%, equivalent to an annual cost savings of $40,200 after accounting for the cost of additional sensors.

RGG-PSO+: Random Geometric Graphs Based Particle Swarm Optimization Method for UAV Path Planning

Evolutionary algorithms, such as particle swarm optimization (PSO), are widely applied to UAV path planning problems. However, the fixed particle length of PSO, which may not be suitable for the scenario, will compromise the search efficiency. This paper proposes the RGG-PSO+ method, which adapts to scenarios by dynamically adjusting the number of waypoints. Random geometric graphs (RGG) and the divide-and-conquer paradigm are involved in improving the proposed method. Comparative analyses with established heuristic methods demonstrate RGG-PSO+’s superior performance in complex environments, particularly in terms of convergence speed and path length. The implementation of RGG significantly improves the F-Measure, indicating a shift from exploration to exploitation of PSO’s iterations, and the implementation of the divide-and-conquer paradigm is evident in the improved mean and variance of normalized path lengths.

Sulfur vacancy-rich bismuth sulfide nanowire derived from CAU-17 for radioactive iodine capture in complex environments: Performance and intrinsic mechanisms

Effective capture and immobilization of volatile radioiodine from the off-gas of post-treatment plants is crucial for nuclear safety and public health, considering its long half-life, high toxicity, and environmental mobility. Herein, sulfur vacancy-rich Vs-Bi2S3@C nanocomposites were systematically synthesized via a one-step solvothermal vulcanization of CAU-17 precursor. Batch adsorption experiments demonstrated that the as-synthesized materials exhibited superior iodine adsorption capacity (1505.8 mg g−1 at 200 °C), fast equilibrium time (60 min), and high chemisorption ratio (91.7%), which might benefit from the nanowire structure and abundant sulfur vacancies of Bi2S3. Furthermore, Vs-Bi2S3@C composites exhibited excellent iodine capture performance in complex environments (high temperatures, high humidity and radiation exposure). Mechanistic investigations revealed that the I2 capture by fabricated materials primarily involved the chemical adsorption between Bi2S3 and I2 to form BiI3, and the interaction of I2 with electrons provided by sulfur vacancies to form polyiodide anions (I3-). The post-adsorbed iodine samples were successfully immobilized into commercial glass fractions in a stable form (BixOyI), exhibiting a normalized iodine leaching rate of 3.81 × 10−5 g m−2 d−1. Overall, our work offers a novel strategy for the design of adsorbent materials tailed for efficient capture and immobilization of volatile radioiodine.

Mask-Wearing Detection in Complex Environments Based on Improved YOLOv7

Wearing masks is an effective protective measure for residents to prevent respiratory infectious diseases when going out. Due to issues such as a small target size, target occlusion leading to information loss, false positives, and missed detections, the effectiveness of face mask-wearing detection needs improvement. To address these issues, an improved YOLOv7 object detection model is proposed. Firstly, the C2f_SCConv module is introduced in the backbone network to replace some ELAN modules for feature extraction, enhancing the detection performance of small targets. Next, the SPPFCSPCA module is proposed to optimize the spatial pyramid pooling structure, accelerating the model convergence speed and improving detection accuracy. Finally, the HAM_Detect decoupled detection head structure is introduced to mitigate missed and false detections caused by target occlusion, further accelerating model convergence and improving detection performance in complex environments. The experimental results show that improved YOLOv7 achieved an mAP of 90.1% on the test set, a 1.4% improvement over the original YOLOv7 model. The detection accuracy of each category improved, effectively providing technical support for mask-wearing detection in complex environments.

Revolutionizing flame detection: Novelization in flame detection through transferring distillation for knowledge to pruned model

Traditional flame sensors have demonstrated suboptimal detection performance in complex environments, prompting researchers to integrate deep neural network algorithms into these sensors to enhance detection accuracy. However, these algorithms usually rely on sizeable neural networks, resulting in excessive parameterization, which limits their adaptability to different devices. To effectively compress models, this study proposes an effective flame detection framework where the distillation for knowledge is transferred to pruned model (DK-TPM) for the purpose of reducing model parameters. This framework integrates CFasterNet (CFN) and RepConv as foundational components within the base model called YO-CR to accomplish comprehensive feature learning while ensuring better compatibility with devices. Subsequently, structured pruning is applied to the base model to construct a student model. Finally, a new technique called feature distillation with smoothing (FDS) is employed to transfer flame features from the teacher model into the student model. We conducted experiments using three V100 GPUs on five public datasets, demonstrating the generalization capability of the algorithm. Moreover, systematic experiments on flame datasets yielded significant results, achieving an average precision (AP0.5) of 81.5% and frames per second (FPSGPU) of 1048.6, surpassing the requirements of existing devices. Therefore, the proposed DK-TPM is able to provide reliable prediction accuracy and speed for flame detection tasks.

An investigation into the correlation between visual performance in simulated complex environments and academic attainment among primary school students

Traditional vision screenings in schools are limited to simple visual tasks, yet students in their daily learning face more complex visual environments. Binocular rivalry tasks can partially simulate the visual challenges of real visual environments and activate advanced visual processing mechanisms that simple visual tasks cannot. Therefore, by superimposing binocular rivalry-state tasks onto simple visual tasks, we have developed an innovative vision screening program to rapidly and extensively assess students’ visual performance in complex environments. This is a cross-sectional study in which we investigated the performance of 1126 grade 1–6 students from a primary school in Wuxi, China, in rivalry-state stereoscopic vision tasks. The correlation between the screening results of 1044 students and their academic achievements was also statistically analyzed. The study results revealed pass rates of 53.5–60.5% across various visual tests. Specifically, for first-grade students, there was a statistically significant difference in standardized Chinese scores between the group that failed and the group that passed the rivalry-state stereoscopic vision test (− 0.49 ± 3.42 vs. 0.22 ± 0.58, t = − 2.081, P = 0.04). This result underscores the importance of focusing on the visual adaptability of first graders in complex environments.Trail registration: Ethics Committee of Affiliated Children’s Hospital of Jiangnan University-Certificate number: WXCH2022-04-027

A symmetric low-rank subspace clustering method for cooperative spectrum sensing in complex environments

A new cooperative spectrum sensing (CSS) method based on low-rank symmetric subspace clustering is proposed to improve spectrum sensing performance in complex environments. To align with the evolution of cellular networks and leverage spatial observations, a CSS model with multiple primary users and antennas is considered. To address the asymmetric weighting issue of data pairs, a low-rank representation with a symmetric constraint is proposed that reduces the signal dimensions. Finally, features are extracted from the symmetric coefficient matrix and clustered using the K-means algorithm. Through simulation, the effectiveness of the novel algorithm is numerically validated through comparative experiments.

Blink-Related Oscillations Provide Naturalistic Assessments of Brain Function and Cognitive Workload within Complex Real-World Multitasking Environments.

There is a significant need to monitor human cognitive performance in complex environments, with one example being pilot performance. However, existing assessments largely focus on subjective experiences (e.g., questionnaires) and the evaluation of behavior (e.g., aircraft handling) as surrogates for cognition or utilize brainwave measures which require artificial setups (e.g., simultaneous auditory stimuli) that intrude on the primary tasks. Blink-related oscillations (BROs) are a recently discovered neural phenomenon associated with spontaneous blinking that can be captured without artificial setups and are also modulated by cognitive loading and the external sensory environment-making them ideal for brain function assessment within complex operational settings. Electroencephalography (EEG) data were recorded from eight adult participants (five F, M = 21.1 years) while they completed the Multi-Attribute Task Battery under three different cognitive loading conditions. BRO responses in time and frequency domains were derived from the EEG data, and comparisons of BRO responses across cognitive loading conditions were undertaken. Simultaneously, assessments of blink behavior were also undertaken. Blink behavior assessments revealed decreasing blink rate with increasing cognitive load (p < 0.001). Prototypical BRO responses were successfully captured in all participants (p < 0.001). BRO responses reflected differences in task-induced cognitive loading in both time and frequency domains (p < 0.05). Additionally, reduced pre-blink theta band desynchronization with increasing cognitive load was also observed (p < 0.05). This study confirms the ability of BRO responses to capture cognitive loading effects as well as preparatory pre-blink cognitive processes in anticipation of the upcoming blink during a complex multitasking situation. These successful results suggest that blink-related neural processing could be a potential avenue for cognitive state evaluation in operational settings-both specialized environments such as cockpits, space exploration, military units, etc. and everyday situations such as driving, athletics, human-machine interactions, etc.-where human cognition needs to be seamlessly monitored and optimized.

Research on Coal Volume Detection and Energy-Saving Optimization Intelligent Control Method of Belt Conveyor Based on Laser and Binocular Visual Fusion

Real-time coal flow monitoring is crucial for efficient coal mine transportation. Traditional vision acquisition devices generate two-dimensional images that are not accurately identified in the complex underground coal mine environment, such as dust, water mist, and low light. In this paper, we propose a conveyor belt coal flow detection method that integrates laser scanning and binocular vision to address this problem. Our proposed method has several advantages over traditional approaches. Firstly, we calibrate the binocular camera using Zhang’s calibration method to enhance the accuracy of the system. Secondly, we extract the centerline of the laser stripe using the grayscale center of gravity method, which improves the system’s performance in complex environments. Thirdly, we calculate the cross-sectional area of the material accurately using the trapezoidal area accumulation method, and visualize it in two dimensions based on a single frame, while the point cloud data from multiple consecutive frames are visualized in a 3D model at a realistic scale. Finally, we use the continuous multi-frame cross-sectional area to calculate the current conveyor flow, and apply the BP neural network to establish an energy-saving optimization model for the belt conveyor. We also design a PLC fuzzy controller based on fuzzy control algorithms to adjust the belt’s operating speed intelligently according to the coal flow size, achieving energy-saving operation and intelligent control of the belt conveyor. Our experiments show that our method can accurately obtain coal volume and control the belt speed of the conveyor in real-time, making it an innovative and practical solution for coal flow detection and energy-saving operation in underground coal mines.

Boosting Reinforcement Learning via Hierarchical Game Playing With State Relay.

Due to its wide application, deep reinforcement learning (DRL) has been extensively studied in the motion planning community in recent years. However, in the current DRL research, regardless of task completion, the state information of the agent will be reset afterward. This leads to a low sample utilization rate and hinders further explorations of the environment. Moreover, in the initial training stage, the agent has a weak learning ability in general, which affects the training efficiency in complex tasks. In this study, a new hierarchical reinforcement learning (HRL) framework dubbed hierarchical learning based on game playing with state relay (HGR) is proposed. In particular, we introduce an auxiliary penalty to regulate task difficulty, and one training mechanism, the state relay mechanism, is designed. The relay mechanism can make full use of the intermediate states of the agent and expand the environment exploration of low-level policy. Our algorithm can improve the sample utilization rate, reduce the sparse reward problem, and thereby enhance the training performance in complex environments. Simulation tests are carried out on two public experiment platforms, i.e., MazeBase and MuJoCo, to verify the effectiveness of the proposed method. The results show that HGR significantly benefits the reinforcement learning (RL) area.

Integrating GRU with a Kalman Filter to Enhance Visual Inertial Odometry Performance in Complex Environments

To enhance system reliability and mitigate the vulnerabilities of the Global Navigation Satellite Systems (GNSS), it is common to fuse the Inertial Measurement Unit (IMU) and visual sensors with the GNSS receiver in the navigation system design, effectively enabling compensations with absolute positions and reducing data gaps. To address the shortcomings of a traditional Kalman Filter (KF), such as sensor errors, an imperfect non-linear system model, and KF estimation errors, a GRU-aided ESKF architecture is proposed to enhance the positioning performance. This study conducts Failure Mode and Effect Analysis (FMEA) to prioritize and identify the potential faults in the urban environment, facilitating the design of improved fault-tolerant system architecture. The identified primary fault events are data association errors and navigation environment errors during fault conditions of feature mismatch, especially in the presence of multiple failure modes. A hybrid federated navigation system architecture is employed using a Gated Recurrent Unit (GRU) to predict state increments for updating the state vector in the Error Estate Kalman Filter (ESKF) measurement step. The proposed algorithm’s performance is evaluated in a simulation environment in MATLAB under multiple visually degraded conditions. Comparative results provide evidence that the GRU-aided ESKF outperforms standard ESKF and state-of-the-art solutions like VINS-Mono, End-to-End VIO, and Self-Supervised VIO, exhibiting accuracy improvement in complex environments in terms of root mean square errors (RMSEs) and maximum errors.

Constructed "sandwich" structure to obtain recyclability and high rejection rate high-flux CA@HMSN@h-BN/PDA membrane for efficient treatment of dye wastewater

It is necessary to develop a nanofiltration membrane that can remove dye molecules efficiently and is not easily polluted for the treatment of textile industry wastewater. A novel high-flux CA@HMSN@h-BN/PDA membrane with a "sandwich" structure was obtained by assembling the support layer of the Hollow mesoporous silica nanoparticles (HMSN), and the isolation layer of the h-BN/PDA on the Cellulose acetate (CA) membrane. HMSN was synthesized using ZIF-8 as a self-sacrificial template to provide improved permeability. h-BN/PDA obtained by modifying hexagonal boron nitride (h-BN) with polydopamine (PDA) brought higher hydrophilicity, rejection rate, and stability to the membrane. The study solved the problem that the membrane separation process requires sacrificing flux and recyclability for high rejection rates. CA@HMSN@h-BN/PDA membrane has a super-hydrophilic property (water contact angle of 22.5°) and high pure water flux (4419.4 L·m−2·h−1·bar−1). Meanwhile, the CA@HMSN@h-BN/PDA membrane achieves a high rejection rate (over 99.5%) due to the special "sandwich" structure. Through cycling experiments, CA@HMSN@h-BN/PDA membranes exhibit recyclability. More importantly, CA@HMSN@h-BN/PDA membranes maintain stable performance in complex environments, such as extremely acidic/alkaline or inorganic salt interference environments. Thus the CA@HMSN@h-BN/PDA membrane has the potential for future wastewater treatment.

Tough and Stretchable Phenolic‐Reinforced Double Network Deep Eutectic Solvent gels for Multifunctional Sensors with Environmental Adaptability

AbstractConductive gels are perfect for various sensor applications due to their inherent stretchability, flexibility, and electrical conductivity. However, their poor environmental adaptability and low fracture toughness restrict their potential applications. In this study, resorcinol‐formaldehyde resin (RF) is used for the first time as a rigid network compounded with a flexible polyacrylic acid (PAA) network to successfully prepare a double network (DN) deep eutectic solvent gel (RF/PAA DN gel). The gel has high stress strength (1.04 MPa), compressive strength (10.63 MPa), and toughness (1.07 MJ m−3). The addition of RF significantly improves the mechanical properties and gives the RF/PAA DN gel certain photothermal effects, swelling resistance, and flame retardancy, broadening the scope of use and application of the gel. Importantly, as a multifunctional sensor, it can combine deformation sensing, temperature sensing, optical sensing, humidity sensing, and underwater sensing into one, with a wide range of stimuli responses and excellent sensing properties. Excellent environmental suitability also allows its use in a wide range of temperatures (−20−90 °C), humidity (55%−90% RH), underwater, and in fire conditions. The work provides new ideas for choosing rigid networks and a novel strategy for developing multifunctional sensors with excellent performance in complex environments.

Deep Robot Sketching: An application of Deep Q-Learning Networks for human-like sketching

The current success of Reinforcement Learning algorithms for its performance in complex environments has inspired many recent theoretical approaches to cognitive science. Artistic environments are studied within the cognitive science community as rich, natural, multi-sensory, multi-cultural environments. In this work, we propose the introduction of Reinforcement Learning for improving the control of artistic robot applications. Deep Q-learning Neural Networks (DQN) is one of the most successful algorithms for the implementation of Reinforcement Learning in robotics. DQN methods generate complex control policies for the execution of complex robot applications in a wide set of environments. Current art painting robot applications use simple control laws that limits the adaptability of the frameworks to a set of simple environments. In this work, the introduction of DQN within an art painting robot application is proposed. The goal is to study how the introduction of a complex control policy impacts the performance of a basic art painting robot application. The main expected contribution of this work is to serve as a first baseline for future works introducing DQN methods for complex art painting robot frameworks. Experiments consist of real world executions of human drawn sketches using the DQN generated policy and TEO, the humanoid robot. Results are compared in terms of similarity and obtained reward with respect to the reference inputs.

Polyphenol‐Mediated Synthesis of Superparamagnetic Magnetite Nanoclusters for Highly Stable Magnetically Responsive Photonic Crystals

AbstractAchieving high stability and excellent optical performance in complex environments is crucial for practical applications of magnetically responsive photonic crystals (MRPCs). It, however, remains a great challenge. This study demonstrates a polyphenol‐mediated strategy for synthesizing size‐controllable superparamagnetic magnetite (Fe3O4) colloid nanocrystal clusters (CNCs) that can be stably dispersed in various polar solvents to form MRPCs with brilliant structural colors for a long term. As tannic acid (TA) functions as a linker to robustly bind polyvinylpyrrolidone (PVP) chains to Fe3O4 surfaces, the MRPCs can maintain nearly constant diffraction wavelength and high reflectance for up to 4 years. The strong coordination between TA and Fe3+ inhibits crystal growth, ensuring the small primary crystal size and superparamagnetism of Fe3O4@TA‐PVP CNCs. Partial oxidation of TA accelerates the crystal nucleation and growth, reducing the overall CNC particle size, which can be utilized for controlling the particle size. Additionally, enhancing the dissolution of PVP before the solvothermal reaction improves the size monodispersity of the products, making the as‐constructed MRPCs ideal for practical applications in color display, sensors, anti‐counterfeiting, and camouflage. The Fe3O4@TA‐PVP CNCs with high stability and versatility for surface‐functionalization are also promising for magnetic resonance imaging, targeting drug delivery, recyclable catalysis, and magnetic nanomotors.

Recent Developments of Actuation Mechanisms for Continuum Robots: A Review.

Traditional rigid robots face significant challenges in congested and tight environments, including bulky size, maneuverability, and safety limitations. Thus, soft continuum robots, inspired by the incredible capabilities of biological appendages such as octopus arms, starfish, and worms, have shown promising performance in complex environments due to their compliance, adaptability, and safety. Different actuation techniques are implemented in soft continuum robots to achieve a smoothly bending backbone, including cable-driven actuators, pneumatic actuators, and hydraulic actuation systems. However, designing and developing efficient actuation mechanisms, motion planning approaches, and control algorithms are challenging due to the high degree of redundancy and non-linearity of soft continuum robots. This article profoundly reviews the merits and drawbacks of soft robots' actuation systems concerning their applications to provide the readers with a brief review reference to explore the recent development of soft robots' actuation mechanisms technology. Moreover, the authors have surveyed the recent review studies in controller design of continuum robots as a guidance for future applications.

An Efficient and Unified Recognition Method for Multiple License Plates in Unconstrained Scenarios

License plate recognition is an important research topic in image recognition, which plays a vital role in helping the government effectively manage vehicles. At present, most license plate recognition methods focus on a single category and specific scenes. The requirements on distance, illumination, angle and other conditions are pretty high, which are not conducive to the application in practice. This paper proposes a real-time and accurate automatic license plate recognition (ALPR) method to overcome these challenges. The ALPR method contains a license plate detection network (LPDNet) and character recognition network (CRNet). LPDNet is based on the anchor-free method to detect the bounding box and four corners of license plates in an unconstrained environment. The proposed Rotating Gaussian Kernel and centrality loss enable LPDNet to improve performance in complex environments. CRNet is composed of a full convolution network, which can identify many kinds of license plates. In this network, feature extraction and compression technology have been proposed, effectively identifying multiple license plates in combination with a Character Classification module. Experiments on multiple public datasets show that the method outperforms existing methods in speed and accuracy, especially in complex and challenging environments.