Computational Burden Research Articles

An improved particle filtering projectile trajectory estimation algorithm fusing velocity information

This study proposes an improved particle-filtering projectile trajectory estimation method that fuses velocity information to address the susceptibility to interference and large fluctuations in position and velocity measurements of a single-antenna-two-dimensional trajectory correction fuze. By considering the Doppler effect in satellite velocity measurements and the residuals between the model-derived velocity and velocity derived from the translational Doppler frequency shift, a sliding time window was established to generate velocity weight coefficients that dynamically adjust the weight of the velocity in filtering. By modifying the likelihood function, a particle-filtering algorithm was designed to achieve a fusion estimation of the projectile trajectory. Tests indicate that this method provides more accurate estimates of the position and velocity of the projectile compared to other existing methods, which can reduce the impact of velocity fluctuations to a certain extent. In addition, the computational burden is not increased and can directly replace existing mature algorithms in engineering.

A Combination of Attribute-Based Encryption and Blockchain Access Control Scheme in Smart Home Environment

In response to the problems of excessive decryption computation burden on users, inability to protect users' privacy information, and the inability of traditional cloud storage methods to meet users' faster file upload and download speed requirements and track malicious users, this paper proposes an attribute-based encryption and blockchain-based trusted data access control scheme for smart home environments. The scheme combines symmetric encryption algorithms and attribute-based encryption algorithms to achieve fine-grained access control of data. At the same time, it leverages edge computing technology to outsource most of the decryption and computation operations to edge computing nodes, reducing the user's decryption and computation burden. Furthermore, the introduction of blockchain technology enables the monitoring and auditing of users within the system, achieving full traceability of access control. Finally, the proposed scheme was analyzed and validated through simulation experiments, which showed that the scheme is safe and effective, protecting users' security and privacy, and enabling secure data sharing.

CP-RDM: a new object detection algorithm for casting and pouring robots

Abstract Automating the casting sector heavily relies on pivotal technology for object detection in pouring robots. A sophisticated algorithm designed to identify and locate target pouring holes in intricate casting workshops is crucial for advancing the intelligence of the casting process. However, the workshop environment for pouring is generally challenging, with uneven lighting, varying sizes of pouring holes, and significant occlusion in the target area, all impacting the accuracy of target detection tasks.
To overcome these challenges, this paper proposes enhancing the YOLOv8s algorithm for object detection in pouring robots. Firstly, to address the issue of different scales in pouring holes, a Multi-Scale Residual Channel and Spatial Information Fusion Module (MRCS) is designed to aggregate channel and spatial information, thereby enhancing the feature extraction capability of the model. The proposed enhancement is validated on the Pascal VOC dataset. Secondly, a SimAM attention mechanism is added at the end of the backbone network to focus the object detection network more on the positional region of the pouring hole. Importantly, this addition does not introduce extra parameters or computational burden to the model.
Finally, in the detection part of the model, the detection head from the RT-DETR model is introduced. This combination of real-time detection capability from YOLO and deep feature extraction capability from RT-DETR enhances the detection accuracy of the model while ensuring real-time performance. Experimental results on the updated pouring hole dataset reveal that, with only a slight increase in parameters, the proposed model achieves a 2.5% and 3.5% improvement in mAP@0.5 and F1-Score, respectively, compared to the baseline algorithm YOLOv8s. Precision (P) is enhanced by 1.8%, recall (R) by 3.5%, and PFS reaches 110, meeting the requirements for real-time pouring in pouring robots.

An improved sequential importance sampling method for structural reliability analysis of high dimensional problems

Reliability analysis for rare events has proven to be a significant challenge, particularly in non-linear and complex scenarios. Despite the effectiveness of Sequential Importance Sampling (SIS) and Subset Simulation (SUS) in addressing high-dimensional small failure probability problems, the computational burden associated with mechanical simulations for complex structures remains substantial. To address this issue, this paper introduces a novel approach referred to as SIS and Kriging Metamodel Integration (SISAK), designed for computing small failure probabilities in high dimensions. This method involves generating a small number of samples from the original distribution to construct an adaptive metamodel, which is then iteratively optimized using a series of intermediate distributions introduced by SIS. By substituting the function for intermediate distributions with a continuously optimized metamodel, the enhanced approach significantly reduces the computational load associated with mechanical model evaluations compared to the direct use of SIS. This approach does not depend on determining the most probable failure point and does not require consideration of the failure domain shape. Additionally, it inherits the advantages of SIS in addressing high-dimensional small failure probabilities, making it well-suited for structural reliability analysis of nonlinear systems, discontinuous failure domains, cascading functions, and high-dimensional problems.

Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility

This paper investigates the use of deep multi-agent reinforcement learning (MARL) for the coordination of residential energy flexibility. Particularly, we focus on achieving cooperation between homes in a way that is fully privacy-preserving, scalable, and that allows for the management of distribution network voltage constraints. Previous work demonstrated that MARL-based distributed control can be achieved with no sharing of personal data required during execution. However, previous cooperative MARL-based approaches impose an ever greater training computational burden as the size of the system increases, limiting scalability. Moreover, they do not manage their impact on distribution network constraints. We therefore adopt a deep multi-agent actor–critic method that uses a centralised but factored critic to rehearse coordination ahead of execution, such that homes can successfully cooperate at scale, with only first-order growth in computational time as the system size increases. Training times are thus 34 times shorter than with a previous state-of-the-art reinforcement learning approach without the factored critic for 30 homes. Moreover, experiments show that the cooperation of agents allows for a decrease of 47.2% in the likelihood of under-voltages. The results indicate that there is significant potential value for management of energy user bills, battery depreciation, and distribution network voltage management, with minimal information and communication infrastructure requirements, no interference with daily activities, and no sharing of personal data.

Simplified Finite Control Set Model Predictive Control for single-phase grid-tied inverters with twisted parameters

Large computational burden, time delay, and the necessity for precise modeling accuracy are the three main challenges for Finite Control Set-Model Predictive Control (FCS-MPC) in single-phase grid-tied inverters. To solve these issues, a twisted parameter scheme is proposed for the single-phase inverter in this article. Firstly, the law regarding the influence of the model parameter on the current total harmonic distortion (THD) is outlined, emphasizing that a decrease in the inductance parameter leads to a corresponding reduction in current THD. Second, a linear observer is constructed to identify the actual value of inductance and resistance, and an RBF-GA (Radial Basis Function neural network-Genetic Algorithm) scheme is used to obtain the optimal twisted parameter. Subsequently, the efficacy of the proposed methods was verified utilizing MATLAB/Simulink simulations, with further validation conducted through hardware-in-the-loop (HIL) experiments performed on Speedgoat performance real-time target machines. Simulation and experimental results demonstrate that within a specific range, decreasing the inductance parameter can significantly improve the quality of the current. Furthermore, the proposed method outperforms the traditional delay compensation method by reducing computational complexity, minimizing prediction error, and decreasing the number of switching transitions.

Hybrid CNN-Mamba network for single-pixel imaging

Recent progress in single-pixel imaging (SPI) has exhibited remarkable performance using deep neural networks, e.g., convolutional neural networks (CNNs) and vision Transformers (ViTs). Nonetheless, it is challenging for existing methods to well model object image from single-pixel detections that have a long-range dependency, where CNNs are constrained by their local receptive fields, and ViTs suffer from high quadratic complexity of attention mechanism. Inspired by the Mamba architecture, known for its proficiency in handling long sequences and global contextual information with enhanced computational efficiency as state space models (SSMs), we propose a hybrid network of CNN and Mamba for SPI, named CMSPI. The proposed CMSPI integrates the local feature extraction capability of convolutional layers with the abilities of SSMs for efficiently capturing the long-range dependency, and the design of complementary split-concat structure, depthwise separable convolution, and residual connection enhance learning power of network model. Besides, CMSPI adopts a two-step training strategy, which makes reconstruction performance better and hardware-friendly. Simulations and real experiments demonstrate that CMSPI has higher imaging quality, lower memory consumption, and less computational burden than the state-of-the-art SPI methods.

Efficiency and Privacy in Record Linkage: Evaluating a Novel Blocking Technique Implemented on Cryptographic Longterm Keys

Efficient privacy-preserving record linkage (PPRL) is essential for integrating data from different providers without exposing personally identifiable information (PII). This study investigates the effectiveness of a novel blocking technique, implemented on Bloom filters (a space-efficient probabilistic data structure), to enhance efficiency and maintain privacy in a real-world evaluation. This methodology involves the utilization of Anonlink, an open-source Python-based PPRL system which generates a type of Bloom filter, Cryptographic Longterm Keys (CLK), for secure record linkage. Initially, the relevant PII fields of the two datasets undergo anonymization into CLKs. Utilizing the CLK’s property of similarity preservation, we create manageable blocks of records based on bits in common within the Bloom filters. This allows us to reduce the number of comparisons of non-matching records to improve linkage efficiency. Finally, record linkage is performed to identify potential matches within the blocked datasets. This blocking technique for CLKs is evaluated in terms of efficiency and record matching precision, aiming to determine the optimal balance between the two factors. Preliminary results indicate a significant reduction in computational burden, with recall minimally affected. Moreover, the implemented blocking technique poses no additional risks of privacy breaches. Preliminary evaluation of the blocking technique shows a promising avenue for secure and efficient data integration, especially in datasets with PII, warranting further investigation for validation and wider application.

Assessment of data‐driven modeling approaches for chromatographic separation processes

AbstractChromatographic separation processes are described by nonlinear partial differential and algebraic equations, which may result in high computational cost, hindering further online applications. To decrease the computational burden, different data‐driven modeling approaches can be implemented. In this work, we investigate different strategies of data‐driven modeling for chromatographic processes, using artificial neural networks to predict pseudo‐dynamic elution profiles, without the use of explicit temporal information. We assess the performance of the surrogates trained on different dataset sizes, achieving good predictions with a minimum of 3400 data points. Different activation functions are used and evaluated against the original high‐fidelity model, using accuracy, interpolation, and simulation time as performance metrics. Based on these metrics, the best performing data‐driven models are implemented in a process optimization framework. The results indicate that data‐driven models can capture the nonlinear profile of the process and that can be considered as reliable surrogates used to aid process development.

DA-YOLOv7: A Deep Learning-Driven High-Performance Underwater Sonar Image Target Recognition Model

Affected by the complex underwater environment and the limitations of low-resolution sonar image data and small sample sizes, traditional image recognition algorithms have difficulties achieving accurate sonar image recognition. The research builds on YOLOv7 and devises an innovative fast recognition model designed explicitly for sonar images, namely the Dual Attention Mechanism YOLOv7 model (DA-YOLOv7), to tackle such challenges. New modules such as the Omni-Directional Convolution Channel Prior Convolutional Attention Efficient Layer Aggregation Network (OA-ELAN), Spatial Pyramid Pooling Channel Shuffling and Pixel-level Convolution Bilat-eral-branch Transformer (SPPCSPCBiFormer), and Ghost-Shuffle Convolution Enhanced Layer Aggregation Network-High performance (G-ELAN-H) are central to its design, which reduce the computational burden and enhance the accuracy in detecting small targets and capturing local features and crucial information. The study adopts transfer learning to deal with the lack of sonar image samples. By pre-training the large-scale Underwater Acoustic Target Detection Dataset (UATD dataset), DA-YOLOV7 obtains initial weights, fine-tuned on the smaller Smaller Common Sonar Target Detection Dataset (SCTD dataset), thereby reducing the risk of overfitting which is commonly encountered in small datasets. The experimental results on the UATD, the Underwater Optical Target Detection Intelligent Algorithm Competition 2021 Dataset (URPC), and SCTD datasets show that DA-YOLOV7 exhibits outstanding performance, with mAP@0.5 scores reaching 89.4%, 89.9%, and 99.15%, respectively. In addition, the model maintains real-time speed while having superior accuracy and recall rates compared to existing mainstream target recognition models. These findings establish the superiority of DA-YOLOV7 in sonar image analysis tasks.

Efficient EEG Feature Learning Model Combining Random Convolutional Kernel with Wavelet Scattering for Seizure Detection.

Automatic seizure detection has significant value in epilepsy diagnosis and treatment. Although a variety of deep learning models have been proposed to automatically learn electroencephalography (EEG) features for seizure detection, the generalization performance and computational burden of such deep models remain the bottleneck of practical application. In this study, a novel lightweight model based on random convolutional kernel transform (ROCKET) is developed for EEG feature learning for seizure detection. Specifically, random convolutional kernels are embedded into the structure of a wavelet scattering network instead of original wavelet transform convolutions. Then the significant EEG features are selected from the scattering coefficients and convolutional outputs by analysis of variance (ANOVA) and minimum redundancy-maximum relevance (MRMR) methods. This model not only preserves the merits of the fast-training process from ROCKET, but also provides insight into seizure detection by retaining only the helpful channels. The extreme gradient boosting (XGboost) classifier was combined with this EEG feature learning model to build a comprehensive seizure detection system that achieved promising epoch-based results, with over 90% of both sensitivity and specificity on the scalp and intracranial EEG databases. The experimental comparisons showed that the proposed method outperformed other state-of-the-art methods for cross-patient and patient-specific seizure detection.

Advancing high-resolution remote sensing: a compact and powerful approach to semantic segmentation

ABSTRACT Deep learning (DL)-based approaches are notable for their ability to establish feature associations without relying on physical constraints, unlike traditional strategies that are complex and dependent on expert experience. However, three main challenges hinder the versatility of semantic segmentation models. First, the targets in these images are dense and exist at varying spatial scales, which imposes higher demands on the model for accurate segmentation across scales. Second, the segmentation of small targets in the images is often overlooked, leading to a compromise between fine segmentation and model efficiency. Lastly, the data-intensive nature of remote sensing images and the resource-intensive operations of large-scale networks impose significant communication and computation burdens on edge devices, which may not have sufficient resources to handle them effectively. To address these challenges, this paper proposes a lightweight semantic segmentation method for remote sensing images to achieve high-precision segmentation for multi-scale targets while maintaining low computational complexity. The main components include: (1) embedding the inverted residual block structure to minimize the number of model parameters and computational costs; (2) introducing the parallel irregular space pyramid pooling module to efficiently aggregate multi-scale contextual information for fine-grained recognition of small targets; and (3) embedding transfer learning into the encoder-decoder structure to speed up the convergence rate and improve multi-scale feature fusion capability, thereby reducing semantic information loss. The proposed lightweight method has been extensively tested on real-world high-resolution remote sensing datasets. It achieved PA, MPA, MIoU, and FWIoU scores of 87.90%, 75.76%, 66.29%, and 78.81% on the Vaihingen dataset; 87.03%, 85.31%, 74.85%, and 77.54% on the Potsdam dataset; and 95.37%, 83.33%, 75.70%, and 91.31% on the Aeroscapes dataset. Compared to other popular semantic segmentation models, the proposed method achieved the highest values in all four evaluation indicators, demonstrating its effectiveness and superiority.

Balancing Data Privacy and Compliance in Blockchain-Based Financial Systems

This study explores the balance between data privacy and regulatory compliance in blockchain-based financial systems, focusing on privacy-enhancing technologies (PETs) such as Zero-Knowledge Proofs (ZKPs) and multiparty computations (MPCs). Through a comprehensive methodology combining literature review, comparative analysis, and empirical testing on the Ethereum test network, the research reveals significant trade-offs. Implementing ZKPs increased transaction times from 5 seconds to 12 seconds and gas fees from 0.02 ETH to 0.05 ETH, while computational load rose by 60%, highlighting the impact on scalability and efficiency. Chi-Square tests and regression analysis uncovered notable algorithmic biases, with low-value accounts experiencing 15% fewer transaction approvals and small mining pools receiving 20% fewer rewards than larger counterparts. Additionally, MPCs, while offering robust privacy, increased communication overhead by 35%, posing scalability challenges. The study recommends adopting a tiered privacy approach, implementing basic privacy measures for low-sensitivity transactions, and advanced technologies like ZKPs for high-sensitivity transactions while optimizing ZKPs to reduce their computational burden and enhance transaction speeds, and integrating artificial intelligence to detect and mitigate algorithmic biases in blockchain systems. Future research should also explore hybrid privacy solutions that combine the strengths of different PETs, such as ZKPs and MPCs, to achieve both robust privacy and high efficiency. Furthermore, investigating quantum-resistant cryptographic methods is crucial to safeguarding blockchain systems against emerging threats. These insights provide valuable guidance for financial institutions, blockchain developers, and policymakers, promoting the development of blockchain-based financial systems that optimize data privacy while maintaining system performance and regulatory compliance.

Compensation control of commercial vehicle platoon considering communication delay and response lag

The real-time accurate control of vehicle is of great significance for the stability of platoon driving. To address the impact of random time-varying communication delays, communication packet loss, data disorder, and significant response lag of commercial vehicle on platoon control performance in non-ideal communication environment, a novel compensation control method for commercial vehicle platoon is proposed to overcome the abovementioned issues. The proposed method significantly improves the impact of communication issues and vehicle response lag on platoon control, ensuring platoon safety while reducing inter-vehicle spacing and spacing error, and maintaining platoon stability. In addition, this method combines the comprehensive compensation mechanism with the Distributed Model Predictive Controller (DMPC), avoiding the establishment of additional compensation control modules and effectively reducing the computational burden. The results under emergency braking condition show that, compared with the method without compensation, the proposed method significantly reduces inter-vehicle spacing and spacing error, reducing the average maximum spacing error from 29.25 m to 1.44 m, shortening the error convergence time of the platoon by 28 %, and ensuring platoon stability. Additionally, compared to the compensation method based on Kalman Filtering (KF) and Smith predictor, the proposed method can reduce the average maximum spacing error by 60 % while maintaining similar convergence time and platoon stability.

An enhanced traceable access control scheme based on multi-authority CP-ABE for cloud-assisted e-health system

Due to the inherent openness of the Internet of Things (IoT), e-health systems that utilize this technology on a broad scale are susceptible to network attacks. The propose black and white box traceable multi-authority ciphertext policy attribute-based encryption scheme (BWMABE) that combines black and white box accountability with ciphertext policy attribute-based encryption (CP-ABE) to improve data security in e-health systems. The proposed BWMABE scheme enhances security by enabling traceable permissions leakage and employs distributed attribute and key management across multiple authorities. By outsourcing the decryption process to cloud service providers, the proposed BWMABE significantly reduces the computational burden on end-users, making it suitable for lightweight IoT devices with limited computing power. Compared to previous traceable CP-ABE methods, the proposed BWMABE requires less computational effort while supporting both black box and white box traceability. By means of thorough security analysis and performance assessment, the proposed BWMABE has been validated to provide robust security and high efficiency, demonstrating its effectiveness in protecting e-health systems.

Event-triggered model-free adaptive sliding-mode heading control for unmanned surface vehicles under DoS attacks

This article investigates event-triggered model-free adaptive sliding-mode heading control issues for unmanned surface vehicles with dual-channel denial of service (DoS) attacks and bounded disturbances. Initially, we establish a redefined output. Meanwhile, we establish a virtual linear data model based on the redefined output and pseudo-partial-derivative technology. In addition, to reduce the effects of the external disturbance, we introduce the sliding mode control method to enhance the system’s robustness against disturbances. Then, an event-triggered communication scheme is developed to reduce the waste of communication resources. Two compensation schemes are formulated to eliminate the effects of dual-channel DoS attacks. So, the main contributions of the presented method are the enhancement of accuracy, reduction of computational burden, and increased robustness, all of which are demonstrated in the simulation section.

A framework for model maintenance using kernel-based forward propagating neural networks

Deep learning models possess limited flexibility in computational burden in model adaptation owing to the conventional use of backpropagation for model training. To address this problem, we propose an alternate training methodology inspired by the forward–forward algorithm originally designed for classification tasks. We extend this concept through a kernel-based modification, enabling its application to regression tasks, which are commonly encountered in process system modeling. Our proposed Kernel-based Forward Propagating Neural Network (K-FP-NN) eliminates backpropagation, using layer-wise updates for better adaptability. We introduce a real-time (RT) updating framework, RT-K-FP-NN, to continuously refine model parameters with new data. Results indicate that when applied to model predictive control of a continuous stirred tank reactor (CSTR) system, our approach updates the model within 100 s, achieving better performance metrics compared to backpropagation-based real-time models, which require 326 s. This framework can be applied to various dynamic systems, enhancing real-time decision-making by improving predictive accuracy and system adaptability.

Identification of genetic basis of brain imaging by group sparse multi-task learning leveraging summary statistics

Brain imaging genetics is an evolving neuroscience topic aiming to identify genetic variations related to neuroimaging measurements of interest. Traditional linear regression methods have shown success, but their reliance on individual-level imaging and genetic data limits their applicability. Herein, we proposed S-GsMTLR, a group sparse multi-task linear regression method designed to harness summary statistics from genome-wide association studies (GWAS) of neuroimaging quantitative traits. S-GsMTLR directly employs GWAS summary statistics, bypassing the requirement for raw imaging genetic data, and applies multivariate multi-task sparse learning to these univariate GWAS results. It amalgamates the strengths of conventional sparse learning methods, including sophisticated modeling techniques and efficient feature selection. Additionally, we implemented a rapid optimization strategy to alleviate computational burdens by identifying genetic variants associated with phenotypes of interest across the entire chromosome. We first evaluated S-GsMTLR using summary statistics derived from the Alzheimer's Disease Neuroimaging Initiative. The results were remarkably encouraging, demonstrating its comparability to conventional methods in modeling and identification of risk loci. Furthermore, our method was evaluated with two additional GWAS summary statistics datasets: One focused on white matter microstructures and the other on whole brain imaging phenotypes, where the original individual-level data was unavailable. The results not only highlighted S-GsMTLR's ability to pinpoint significant loci but also revealed intriguing structures within genetic variations and loci that went unnoticed by GWAS. These findings suggest that S-GsMTLR is a promising multivariate sparse learning method in brain imaging genetics. It eliminates the need for original individual-level imaging and genetic data while demonstrating commendable modeling and feature selection capabilities.

CFD-based shape optimization of flashing converging-diverging nozzles in pelton turbines for domestic carbon dioxide heat pumps including off-design conditions

A path to enhance the coefficient of performance (COP) of domestic heat pumps is to replace the throttling valve with a turboexpander. Designing this component requires addressing supersonic flashing flows localized within the nozzle. In particular, two-phase flows prevent the application of the method of characteristics to design efficient converging–diverging shapes. To overcome this issue, we propose a shape optimization combined with a homogeneous equilibrium flow model as a design tool. Kriging models are used as surrogates of the objective function and constraint to reduce the overall computational burden associated with shape optimization. The infilling criterion to improve surrogate accuracy involves the maximization of the constrained expected improvement. A multi-point optimization is formulated, including design and off-design conditions in both objective and constraint, for a total of four relevant operating conditions. The off-design conditions are derived from system analysis, accounting for variations in the evaporator temperature and outlet gas-cooler temperature. The optimized nozzle results in a COP improvement of 7.6%, compared to a 6.6% increase when replacing the throttling valve with a baseline geometry designed as recommended by the literature. The adoption of a multi-point optimization strategy ensures that this enhancement in design conditions is not offset by off-design performance decay, which is 0.3 percentage points over the three off-design conditions. Overall, replacing the throttling valve with the optimized expander leads to an average COP improvement of 8.6%.

A Comparison of Model Predictive Control Architectures for Application to Electrified Aircraft Propulsion Systems

Abstract As electrified aircraft propulsion (EAP) systems continue to mature, more sophisticated hardware and software are being developed to balance operations among electric machines and gas-turbine engines. In hybrid-electric propulsion systems, the increased complexity resulting from integrating turbine-engine shafts with electric machines necessitates control methodologies to account for various physical domains. Ideal controllers for hybrid-electric engines manage systems, subsystems, and their interactions in a coordinated fashion, able to account for safety and performance goals while being computationally efficient. In a previous work, linear model predictive control (MPC) schemes were implemented in centralized and distributed frameworks on a nonlinear turbofan engine model as a proof of concept. However, these schemes were not evaluated for computational complexity, prompting further study. The research presented here develops hierarchical MPC schemes to reduce the computational burden of the previous MPC schemes. A two-tier framework is implemented, where a slower sampling MPC controls electric machines and determines fan-speed tracking goals for a faster sampling controller, which is either a MPC or a proportional-integral (PI) controller. The proposed designs are compared to the centralized MPC investigated previously, and performance is measured via fan speed tracking error, energy storage state-of-charge, and computation time. Results reveal that the hierarchical MPC scheme employing a lower-level PI controller improves computation time while maintaining comparable tracking and state-of-charge regulation to the centralized scheme.