Reduction Of Computational Load Research Articles

Adaptive event‐triggered safety control for multiplayer mixed zero‐sum game with partial inputs delay

AbstractThis paper proposes an adaptive safety control method applicable to a multiplayer mixed zero‐sum (MZS) game of nonlinear systems with partial inputs delay. Firstly, a framework is introduced involving N players, where player 1 and player N form a zero‐sum (ZS) game, and player 1 and players 2 to N‐1 form nonzero‐sum (NZS) games, with some players experiencing time delays. Subsequently, the system's value function is augmented with a control barrier function (CBF) to ensure that the system's state remains within a safe region. Secondly, to approximate Nash equilibrium solutions, the study employs adaptive dynamic programming (ADP) and utilizes a critic‐only neural network (NN) to approximate optimal solutions. Diverging from traditional time‐trigger methods, computational and communication load reduction is achieved by introducing a state‐related event trigger condition. The stability of the system is then meticulously analyzed using the Lyapunov theorem. Finally, to validate the effectiveness of the proposed method, the study provides a simulation example demonstrating its performance. In summary, this research introduces an efficient adaptive safety control method for addressing multiplayer MZS games with partial inputs delay, incorporating CBFs, ADP, and state‐related event triggering.

A Method for Real-Time Recognition of Safflower Filaments in Unstructured Environments Using the YOLO-SaFi Model.

The identification of safflower filament targets and the precise localization of picking points are fundamental prerequisites for achieving automated filament retrieval. In light of challenges such as severe occlusion of targets, low recognition accuracy, and the considerable size of models in unstructured environments, this paper introduces a novel lightweight YOLO-SaFi model. The architectural design of this model features a Backbone layer incorporating the StarNet network; a Neck layer introducing a novel ELC convolution module to refine the C2f module; and a Head layer implementing a new lightweight shared convolution detection head, Detect_EL. Furthermore, the loss function is enhanced by upgrading CIoU to PIoUv2. These enhancements significantly augment the model's capability to perceive spatial information and facilitate multi-feature fusion, consequently enhancing detection performance and rendering the model more lightweight. Performance evaluations conducted via comparative experiments with the baseline model reveal that YOLO-SaFi achieved a reduction of parameters, computational load, and weight files by 50.0%, 40.7%, and 48.2%, respectively, compared to the YOLOv8 baseline model. Moreover, YOLO-SaFi demonstrated improvements in recall, mean average precision, and detection speed by 1.9%, 0.3%, and 88.4 frames per second, respectively. Finally, the deployment of the YOLO-SaFi model on the Jetson Orin Nano device corroborates the superior performance of the enhanced model, thereby establishing a robust visual detection framework for the advancement of intelligent safflower filament retrieval robots in unstructured environments.

Efficient Brain Tumor Segmentation with Lightweight Separable Spatial Convolutional Network

Accurate and automated segmentation of lesions in brain MRI scans is crucial in diagnostics and treatment planning. Despite the significant achievements of existing approaches, they often require substantial computational resources and fail to fully exploit the synergy between low-level and high-level features. To address these challenges, we introduce the Separable Spatial Convolutional Network (SSCN), an innovative model that refines the U-Net architecture to achieve efficient brain tumor segmentation with minimal computational cost. SSCN integrates the PocketNet paradigm and replaces standard convolutions with depthwise separable convolutions, resulting in a significant reduction in parameters and computational load. Additionally, our feature complementary module enhances the interaction between features across the encoder-decoder structure, facilitating the integration of multi-scale features while maintaining low computational demands. The model also incorporates a separable spatial attention mechanism, enhancing its capability to discern spatial details. Empirical validations on standard datasets demonstrate the effectiveness of our proposed model, especially in segmenting small and medium-sized tumors, with only 0.27M parameters and 3.68 GFlops. Our code is available at https://github.com/zzpr/SSCN .

Improved YOLOv8 Model for Lightweight Pigeon Egg Detection.

In response to the high breakage rate of pigeon eggs and the significant labor costs associated with egg-producing pigeon farming, this study proposes an improved YOLOv8-PG (real versus fake pigeon egg detection) model based on YOLOv8n. Specifically, the Bottleneck in the C2f module of the YOLOv8n backbone network and neck network are replaced with Fasternet-EMA Block and Fasternet Block, respectively. The Fasternet Block is designed based on PConv (Partial Convolution) to reduce model parameter count and computational load efficiently. Furthermore, the incorporation of the EMA (Efficient Multi-scale Attention) mechanism helps mitigate interference from complex environments on pigeon-egg feature-extraction capabilities. Additionally, Dysample, an ultra-lightweight and effective upsampler, is introduced into the neck network to further enhance performance with lower computational overhead. Finally, the EXPMA (exponential moving average) concept is employed to optimize the SlideLoss and propose the EMASlideLoss classification loss function, addressing the issue of imbalanced data samples and enhancing the model's robustness. The experimental results showed that the F1-score, mAP50-95, and mAP75 of YOLOv8-PG increased by 0.76%, 1.56%, and 4.45%, respectively, compared with the baseline YOLOv8n model. Moreover, the model's parameter count and computational load are reduced by 24.69% and 22.89%, respectively. Compared to detection models such as Faster R-CNN, YOLOv5s, YOLOv7, and YOLOv8s, YOLOv8-PG exhibits superior performance. Additionally, the reduction in parameter count and computational load contributes to lowering the model deployment costs and facilitates its implementation on mobile robotic platforms.

Computation cost reduction in 3D shape optimization of nanophotonic components

Inverse design methodologies effectively optimize many design parameters of a photonic device with respect to a primary objective, uncovering locally optimal designs in a typically non-convex parameter space. Often, a variety of secondary objectives (performance metrics) also need to be considered before fabrication takes place. Hence, a large collection of optimized designs is useful, as their performance on secondary objectives often varies. For certain classes of components such as shape-optimized devices, the most efficient optimization approach is to begin with 2D optimization from random parameter initialization and then follow up with 3D re-optimization. Nevertheless, the latter stage is substantially time- and resource-intensive. Thus, obtaining a desired collection of optimized designs through repeated 3D optimizations is a computational challenge. To address this issue, a machine learning-based regression model is proposed to reduce the computation cost involved in the 3D optimization stage. The regression model correlates the 2D and 3D optimized structural parameters based on a small dataset. Using the predicted design parameters from this model as the initial condition for 3D optimization, the same optima are reached faster. The effectiveness of this approach is demonstrated in the shape optimization-based inverse design of TE0-TE1 mode converters, an important component in mode-division multiplexing applications. The final optimized designs are identical in both approaches, but leveraging a machine learning-based regression model offers a 35% reduction in computation load for the 3D optimization step. The approach provides a more effective means for sampling larger numbers of 3D optimized designs.

A study on expression recognition based on improved mobilenetV2 network

This paper proposes an improved strategy for the MobileNetV2 neural network(I-MobileNetV2) in response to problems such as large parameter quantities in existing deep convolutional neural networks and the shortcomings of the lightweight neural network MobileNetV2 such as easy loss of feature information, poor real-time performance, and low accuracy rate in facial emotion recognition tasks. The network inherits the characteristics of MobilenetV2 depthwise separated convolution, signifying a reduction in computational load while maintaining a lightweight profile. It utilizes a reverse fusion mechanism to retain negative features, which makes the information less likely to be lost. The SELU activation function is used to replace the RELU6 activation function to avoid gradient vanishing. Meanwhile, to improve the feature recognition capability, the channel attention mechanism (Squeeze-and-Excitation Networks (SE-Net)) is integrated into the MobilenetV2 network. Experiments conducted on the facial expression datasets FER2013 and CK + showed that the proposed network model achieved facial expression recognition accuracies of 68.62% and 95.96%, improving upon the MobileNetV2 model by 0.72% and 6.14% respectively, and the parameter count decreased by 83.8%. These results empirically verify the effectiveness of the improvements made to the network model.

Driver Abnormal Expression Detection Method Based on Improved Lightweight YOLOv5

The rapid advancement of intelligent assisted driving technology has significantly enhanced transportation convenience in society and contributed to the mitigation of traffic safety hazards. Addressing the potential for drivers to experience abnormal physical conditions during the driving process, an enhanced lightweight network model based on YOLOv5 for detecting abnormal facial expressions of drivers is proposed in this paper. Initially, the lightweighting of the YOLOv5 backbone network is achieved by integrating the FasterNet Block, a lightweight module from the FasterNet network, with the C3 module in the main network. This combination forms the C3-faster module. Subsequently, the original convolutional modules in the YOLOv5 model are replaced with the improved GSConvns module to reduce computational load. Building upon the GSConvns module, the VoV-GSCSP module is constructed to ensure the lightweighting of the neck network while maintaining detection accuracy. Finally, channel pruning and fine-tuning operations are applied to the entire model. Channel pruning involves removing channels with minimal impact on output results, further reducing the model’s computational load, parameters, and size. The fine-tuning operation compensates for any potential loss in detection accuracy. Experimental results demonstrate that the proposed model achieves a substantial reduction in both parameter count and computational load while maintaining a high detection accuracy of 84.5%. The improved model has a compact size of only 4.6 MB, making it more conducive to the efficient operation of onboard computers.

Trajectory optimization with hybrid probabilistic roadmap approach to achieve time efficient navigation of unmanned vehicles in unstructured environment

PurposeThis paper aims to focus on solving the path optimization problem by modifying the probabilistic roadmap (PRM) technique as it suffers from the selection of the optimal number of nodes and deploy in free space for reliable trajectory planning.Design/methodology/approachTraditional PRM is modified by developing a decision-making strategy for the selection of optimal nodes w.r.t. the complexity of the environment and deploying the optimal number of nodes outside the closed segment. Subsequently, the generated trajectory is made smoother by implementing the modified Bezier curve technique, which selects an optimal number of control points near the sharp turns for the reliable convergence of the trajectory that reduces the sum of the robot’s turning angles.FindingsThe proposed technique is compared with state-of-the-art techniques that show the reduction of computational load by 12.46%, the number of sharp turns by 100%, the number of collisions by 100% and increase the velocity parameter by 19.91%.Originality/valueThe proposed adaptive technique provides a better solution for autonomous navigation of unmanned ground vehicles, transportation, warehouse applications, etc.

Nonlinear Model Predictive Control for a Dynamic Positioning Ship Based on the Laguerre Function

In this paper, we present a novel nonlinear model predictive control (NMPC) algorithm based on the Laguerre function for dynamic positioning ships to solve the problems of input saturation, unknown time-varying disturbances, and heavy computation. The nonlinear model of a dynamic positioning ship is presented as a linear model, transformed from a standard affine nonlinear state-space model by precise feedback linearization. The environmental disturbance is overcome using an integrator. The time cost of the proposed nonlinear control algorithm is decreased by inducing the Laguerre function to describe the feedback-linearization system input increments. The Laguerre function reduces the matrix dimensions of the nonlinear optimization problem. The simulation results for a DP supply vessel showed that the novel algorithm maintained the effective control performance of the original nonlinear model predictive control algorithm and had a reduced computation load to satisfy the requirements of real-time operation.

Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators

The entry of electric bikes into elevators poses safety risks. This article proposes a lightweight object detection model for edge deployment in elevator environments specifically designed for electric bikes. Based on the YOLOv5s network, the backbone network replaces the original CSPDarknet53 with a lightweight multilayer ShuffleNet V2 convolutional neural network, achieving a lightweight backbone network. Swin Transformer modules are introduced between layers to enhance the feature expression capability of images, and a SimAM attention mechanism is applied at the end layer to further improve the feature extraction capability of the backbone network. In the neck network, lightweight and depth-balanced GSConv and VoV-GSCSP modules replace several Conv and C3 basic convolutional modules, reducing the parameter count while enhancing the cross-scale connection and fusion capabilities of feature maps. The prediction network uses the faster-converging and more accurate EIOU error function as the position loss function for iterative training. This article conducts various lightweighting comparison experiments and ablation experiments on the improved object detection model. The experimental results demonstrate that the proposed object detection model, with a model size of only 2.6 megabytes and 1.1 million parameters, achieves a frame rate of 106 frames per second and a detection accuracy of 95.5%. This represents an 84.8% reduction in computational load compared to the original YOLOv5s model. The model’s volume and parameter count are reduced by 81.0% and 84.3%, respectively, with only a 0.9% decrease in mAP. The improved object detection model proposed in this paper can meet the real-time detection requirements for electric bikes in elevator scenarios, providing a feasible technical solution for its deployment on edge devices within elevators.

Efficient lightweight cryptography for resource-constrained WSN nodes

In Wireless Sensor Networks (WSN), where resources are scarce, lightweight cryptography is crucial and difficult. The Constrained Application Protocol (CoAP), Field-Programmable Gate Array (FPGA) technology, and a modified RC5 algorithm are used in this study to achieve efficient encryption for WSN nodes. WSN are essential for monitoring temperature, humidity, vibrations, and seismic activity. However, processing capacity, memory, and energy constraints make data security difficult in these networks. CoAP, FPGA, and a modified RC5 algorithm provide security, computational load reduction, and energy efficiency in resource-limited WSN. This research is crucial because it creates cryptographic mechanisms that accommodate WSN unique needs. By protecting data integrity and confidentiality, these mechanisms ensure data transmission security and privacy. Data security and efficiency in WSN require innovative cryptographic, FPGA-based hardware acceleration, and protocol optimization solutions. These methods could improve these vital sensing networks. This research lays the foundation for protecting the accuracy and security of WSN node data collected and transmitted with limited resources while optimizing resource allocation.

Variable sample-size operator extrapolation algorithm for stochastic mixed variational inequalities

In this paper, we present a variable sample-size operator extrapolation algorithm for solving a class of stochastic mixed variational inequalities. One distinctive feature of our algorithm is that it updates a single search sequence by solving a prox-mapping subproblem and computing an evaluation of the expected mapping at each iteration and hence it may significantly reduce computation load. In particular, the iteration sequence generated by our algorithm always belongs to the feasible region. We show that, under some moderate conditions, the proposed algorithm can achieve O(1/T) ergodic convergence rate in terms of the expected restricted gap function, where T denotes the number of iterations. We derive some results related to the convergence rate of the Bregman distance between iterates and solutions, the iteration complexity, and the oracle complexity for the proposed algorithm when the sample size increases at a geometric rate. We also investigate the sublinear convergence rate in terms of the residual function under the generalized monotonicity condition. Numerical experiments on stochastic network game, stochastic sparse traffic assignment problems and sparse classification problem indicate that the proposed algorithm is promising compared with some existing algorithms.

Optimized Discrete-Time Current Control for IPMSM Drives

Designing the current controller directly in the discrete-time domain is essential to high-speed applications, mainly due to the delay inherent to the digital control system. Active-damping (AD) is usually included to improve the disturbance rejection. However, the continuous-time form of the AD element is normally followed simply in the discrete-time domain design, which causes the dynamic performance and the anti-disturbance performance cannot be taken into account well. To easy the confliction, a novel AD loop, dedicated to the discrete-time plant, is proposed. In this design, the AD element is no longer limited to be a single real gain, as commonly seen in the continuous-time domain representing the active resistance. Alternatively, it is designed with the feedback control theory, allowing both the tracking response and disturbance response to be designed as required respectively. As a result, the dynamic response and disturbance rejection can be determined independently, and the parameter robustness can also be designed intentionally to a great extent. Besides, to reduce computation load in practice, a discrete-time IPMSM’s model with low computation intensity and high accuracy is presented in this paper. Some experimental results are reported to demonstrate the performance of the discrete-time control designed in this paper.

Efficient Real-Time Whitening for Blind Eigenvalue-Based Detection in mmWave Full Duplex Cognitive Radio

Although combining Full Duplex (FD) and Cognitive Radio (CR) technologies can provide several benefits, the presence of the residual self-interference (RSI) at the FD transceiver may influence the spectrum sensing capabilities. In particular, focusing on the blind eigenvalue-based detectors (EVDs), this paper shows that operating at mmWave widebands, the RSI is a colored noise strongly affecting the detection performance even when it is characterized by low power. Consequently, we propose here a whitened detector whose novelty consists in the real-time computation of the whitening matrix, differently from previous works which employ an offline computation. The proposed whitening matrix computation uses a sample covariance matrix (SCM) regularization tailored for the FD scenario, instead of the conventional SCM estimator. Particularly, we prove that the proposed whitened detector is robust against RSI power uncertainty, attaining a constant false alarm rate under typical FD operating conditions. Finally, we show that our method provides computational load reduction and faster convergence to the theoretical false alarm probability characteristic of the white noise case. Numerical simulations validate the theoretical analysis confirming the better performance of the proposed whitening approach, particularly when applied to the sphericity test, in comparison to the offline-based approach.

Robust Nonlinear MPC With Variable Prediction Horizon: An Adaptive Event-Triggered Approach

This paper investigates the event-triggered model predictive control (ETMPC) problem for nonlinear systems with the bounded disturbance. First, a novel adaptive event-triggered mechanism without Zeno behaviors, in which the triggering threshold can constantly be adjusted with the change of the system state, is proposed for computational load reduction. Then, an adaptive prediction horizon update strategy (APHUS) is proposed to further reduce the computational complexity of the optimization problem at each triggering instant. Moreover, a dual-mode ETMPC algorithm is developed, and sufficient conditions on the algorithm feasibility and the system robust stability are provided. Through a simulation example, the results show that the proposed scheme can use fewer computational resources and a shorter calculation time for solving the optimization problem while ensuring satisfactory system performances than the existing ones.

A machine-learning-based event-triggered model predictive control for building energy management

Model predictive control (MPC) for building energy management has exhibited a huge potential for largely cutting down energy use and improving human comfort. However, the high demand for computational power for solving the optimization is challenging the widespread deployment of MPC in real buildings. Typical MPC employs a time-triggered mechanism (TTM) that runs optimization recurrently at each time step without considering the necessity, which could cause excessive computation resource usage. This paper proposes an event-triggered mechanism (ETM) that only runs optimization when triggering events occur. Contrary to conventional ETMs that only considers the current information (e.g., room conditions), the ETM proposed is based on a cost function that covers the past, current, and future information. Based on the proposed ETM, a machine-learning-based event-triggered model predictive control (ETMPC) system that optimizes both building energy efficiency and thermal comfort is developed. The developed ETMPC system is then employed for air-conditioning control for performance evaluation through simulations. The control performance of the proposed ETMPC is compared to an MPC employing TTM and a common thermostat. Compared to the MPC employing TTM, the proposed ETMPC reduced the computational load in terms of the number of optimization runs by 77.6%–88.2%, meanwhile, achieving similar energy savings (more than 9.3% energy saving over the thermostat) as the MPC employing TTM does (9% energy saving over the thermostat). With the significant reduction of computational load, the ETMPC achieves similar thermal comfort performance as the MPC employing TTM does, and it is significantly better over the thermostat.

Information-Based Bit Allocation for Cooperative Visual Sensing in Vehicular Networks

Cooperative visual sensing among multiple vehicles has raised increasing concern with the development of connected vehicular systems. However, it remains challenging for effective cooperative sensing under communication constraints due to the lack of theoretic basis and efficient design for communication resource allocation in visual sensing networks. This paper establishes an information-based bit allocation framework for cooperative visual sensing in vehicular networks, where visual observations captured by on-board cameras are quantized before transmitted to the fusion center for 3D environment model estimation. Our aim is to allocate the quantization bits among observations in the network to minimize the overall estimation error. Specifically, we first design a Fisher information matrix (FIM)-based metric to evaluate the cooperative visual sensing error, and characterize the impact of quantization on sensing with geometric interpretations based on the relation among the 3D physical space, the quantization modulation space and the information eigenspace. Then we present closed-form investigations for the optimal bit allocation among observations in the network, and derive its dependence on network topology and communication constraints. Moreover, we propose a hierarchical bit allocation scheme and a convex relaxation-based scheme for cooperative visual sensing, and compare their performance with the generalized Breiman, Friedman, Olshen, and Stone (GBFOS) algorithm and the uniform allocation scheme. Numerical results validate that our schemes achieve near-optimal sensing performance under communication constraints with a significant reduction of computation load.

A New Virtual Tracking Sub-Algorithm Based Hybrid Active Control System for Narrowband Noise With Impulsive Interference

Mechanical noise is usually a mixture of narrowband and impulsive noise which needs complex active noise control (ANC) algorithms to improve the de-noising performance. But the ANC algorithm with a high computation load will reduce the real-time performance of an ANC system, thus decreasing the attenuation performance and even leading to divergence. To alleviate this contradiction in narrowband ANC systems, a new virtual filtered-x L0 norm discrete Fourier cancellation (FxL0DFC) based hybrid FxNLMS(filtered-x normalized least mean square)-FxDFC framework is proposed to decrease the total computing load and keep good attenuation performance. For a fast-changing noise, the FxNLMS algorithm is employed. The new virtual FxL0DFC algorithm serves to prepare parameters for steady-state, and when this happens, the FxDFC algorithm with the parameters provided by FxL0DFC is applied. Compared to using the FxNLMS algorithm to attenuate narrowband periodical noise, the FxDFC algorithm has nearly the same tracking performance while having a low computational load. As a result, the FxL0DFC-based FxNLMS-FxDFC algorithm leads to a reduction of the total computational load. Moreover, the proposed method performs excellently in terms of tracking in simulations and experiments on actual data, particularly in environments with rapid power changes and impulsive noise.

Smart Water Meter Based on Deep Neural Network and Undersampling for PWNC Detection

Having become aware of how limited all natural resources are, the water leakage problem in piping systems has become a stimulating topic. This problem increased over the last few years even though innovative tools and techniques appeared in the literature and in the consumer market. Identifying water leaks at the nearest point, the household level, is still an unsolved problem because most water meters are mechanical and, therefore, cannot detect leaks. While the issue is not important for water service providers since consumption is charged to the user, the resolution is crucial due to the increasingly relevant concern of saving natural resources. The detection of small but continuous leaks of drinking water in domestic systems is addressed in this work. Machine learning approaches enabled image processing techniques also in uncontrolled environments, overcoming the classical methods but introducing new challenges like power consumption. Using a combination of Convolutional Neural Networks (CNNs) and Long Short–Term Memory Networks (LSTM) within an adaptive under–sampling strategy, it is possible to process the images captured from the mechanical water meter dial and identify the Period With Null Consumption (PWNC) or the consumption class. The presented solution can classify the water flow into four different classes, and, in the case of absence or small flow, its function becomes to detect leakages. Analyzing images from a mechanical water meter quadrant, it has been possible to identify PWNC and detect small water leakages in the domestic environment under common consumer flow profiles. In addition to the confusion matrices, the synthetic parameters of Sørensen–Dice coefficient (DSC) and Jaccard Index have been utilized and presented to quantify the performance of the proposed DNN. The conducted experiments on static and dynamic water flow demonstrated the applicability of this approach and the possibility of an increase in PWNC identification thanks to the adaptative increase in the sampling time. Moreover, the reduction of sampling time allows for the reduction of computational load and power consumption in embedded scenarios where limited energy is available.

Overcoming challenges in crash prediction modeling using discretized duration approach: An investigation of sampling approaches

Until recently, statistical approaches used for real-time crash prediction modeling were limited to case-control design and “sampling of alternatives” approaches. A recent study has developed a duration-based real-time crash prediction model capable of incorporating dynamic (time-varying) covariates within its framework. The modeling approach discretizes the duration between crashes into equal time intervals which can be modeled as alternatives in a multinomial logit framework. The approach, however, requires a reformulation of the original crash dataset to fit its modeling framework which results in considerably large data making model estimation computationally demanding. Additionally, validation of the model in the original study is based on crash data from just one interstate, I-405, assuming homogenous highway segments each 5 miles in length. This study improves upon the original study by investigating sampling techniques that can be applied to the reformulated data to reduce computational load using 2019 crash data from two interstates, I-40 and I-55, in Memphis, Tennessee. Furthermore, discretization of inter-crash duration is undertaken following non-homogenous segmentation of the interstates that is based on highway geometry, terrain, and posted speed limit. To accomplish the study objectives, a relatively small future window of 1 h with 15-minute time intervals is used to discretize the inter-crash duration and obtain the reformulated data. Sampling of crashes for model estimation is then done at the crash, epoch, and segment levels to answer the question of which sampling technique (by crash, epoch, or segment) would result in reasonable accuracy when compared with the complete (100%) data. Results show that 25% of samples drawn at the epoch level can result in a considerable reduction of computational load while providing reasonably consistent estimates.