Computational Memory Usage Research Articles

Efficient time-domain speech separation using short encoded sequence network

The key to single-channel time-domain speech separation lies in encoding the mixed speech into latent feature representations by encoder and obtaining the accurate estimation of the target speaker masks by the separation network. Despite the advanced separation network contribute to separate target speech, but due to the limitation of the time-domain encoder–decoder framework, these separation models commonly improve the separation performance by setting a small convolution kernel size of encoder to increase the length of the coded sequence, which will result in increased computational complexity and training costs for the model. Therefore, in this paper, we propose an efficient time-domain speech separation model using short-sequence encoder–decoder framework (ESEDNet). In this model, we construct a novel encoder–decoder framework to accommodate short encoded sequences, where the encoder consists of multiple convolution and downsampling operations to reduce length of high-resolution sequence, while the decoder utilizes the encoded features to reconstruct the fine-detailed speech sequence of the target speaker. Since the output sequence of the encoder is shorter, when combined with our proposed multi-temporal resolution Transformer separation network (MTRFormer), ESEDNet can efficiently obtains separation masks for the short encoded feature sequence. Experiments show that compared with previous state-of-the-art (SOTA) methods, ESEDNet is more efficient in terms of computational complexity, training speed and GPU memory usage, while maintaining competitive separation performance.

TransSMPL: Efficient Human Pose Estimation with Pruned and Quantized Transformer Networks

Existing Transformers for 3D human pose and shape estimation models often struggle with computational complexity, particularly when handling high-resolution feature maps. These challenges limit their ability to efficiently utilize fine-grained features, leading to suboptimal performance in accurate body reconstruction. In this work, we propose TransSMPL, a novel Transformer framework built upon the SMPL model, specifically designed to address the challenges of computational complexity and inefficient utilization of high-resolution feature maps in 3D human pose and shape estimation. By replacing HRNet with MobileNetV3 for lightweight feature extraction, applying pruning and quantization techniques, and incorporating an early exit mechanism, TransSMPL significantly reduces both computational cost and memory usage. TransSMPL introduces two key innovations: (1) a multi-scale attention mechanism, reduced from four scales to two, allowing for more efficient global and local feature integration, and (2) a confidence-based early exit strategy, which enables the model to halt further computations when high-confidence predictions are achieved, further enhancing efficiency. Extensive pruning and dynamic quantization are also applied to reduce the model size while maintaining competitive performance. Quantitative and qualitative experiments on the Human3.6M dataset demonstrate the efficacy of TransSMPL. Our model achieves an MPJPE (Mean Per Joint Position Error) of 48.5 mm, reducing the model size by over 16% compared to existing methods while maintaining a similar level of accuracy.

Laplacian Projection Based Global Physical Prior Smoke Reconstruction.

We present a novel framework for reconstructing fluid dynamics in real-life scenarios. Our approach leverages sparse view images and incorporates physical priors across long series of frames, resulting in reconstructed fluids with enhanced physical consistency. Unlike previous methods, we utilize a differentiable fluid simulator (DFS) and a differentiable renderer (DR) to exploit global physical priors, reducing reconstruction errors without the need for manual regularization coefficients. We introduce divergence-free Laplacian eigenfunctions (div-free LE) as velocity bases, improving computational efficiency and memory usage. By employing gradient-related strategies, we achieve better convergence and superior results. Extensive experiments demonstrate the effectiveness of our method, showcasing improved reconstruction quality and computational efficiency compared to existing approaches. We validate our approach using both synthetic and real data, highlighting its practical potential.

Hybrid Spatial–Spectral Autoencoder Models for Lossy Satellite Image Compression

The challenge of handling vast amounts of high-resolution satellite imagery is driven by onboard memory and bandwidth limitations. As spatial and spectral resolutions increase, image compression, particularly deep-learning-based methods, is essential to overcome these limitations. This paper presents hybrid autoencoder models that combine convolutional neural networks, long short-term memory networks, and attention mechanisms for spatial and spectral feature extraction. The proposed architectures, including sparse and variational autoencoder counterparts, form a comprehensive image compression framework with quantization, and various entropy coders are applied to the EuroSat dataset (RGB and multispectral). The experimental results show the models’ superiority over the JPEG family and recent state-of-the-art methods, achieving up to 3.3, 1.4, and 0.6% improvements in the peak signal-to-noise ratio, structural similarity index, and multiscale structural similarity index, respectively. Moreover, performance analysis in terms of computational complexity, processing time, and memory usage highlights the efficiency of the proposed models. A case study conducted on a real scene from the Sentinel-2 satellite further validates the compatibility of the proposed models with modern artificial intelligence chipsets.

Resource-efficient artificial intelligence for battery capacity estimation using convolutional FlashAttention fusion networks

Accurate battery capacity estimation is crucial for optimizing lifespan and monitoring health conditions. Deep learning has made notable strides in addressing long-standing issues in the artificial intelligence community. However, large AI models often face challenges such as high computational resource consumption, extended training times, and elevated deployment costs. To address these issues, we developed an efficient end-to-end hybrid fusion neural network model. This model combines FlashAttention-2 with local feature extraction through convolutional neural networks (CNNs), significantly reducing memory usage and computational demands while maintaining precise and efficient health estimation. For practical implementation, the model uses only basic parameters, such as voltage and charge, and employs partial charging data (from 80 % SOC to the upper limit voltage) as features, without requiring complex feature engineering. We evaluated the model using three datasets: 77 lithium iron phosphate (LFP) cells, 16 nickel cobalt aluminum (NCA) cells, and 50 nickel cobalt manganese (NCM) oxide cells. For LFP battery health estimation, the model achieved a root mean square error of 0.109 %, a coefficient of determination of 0.99, and a mean absolute percentage error of 0.096 %. Moreover, the proposed convolutional and flash-attention fusion networks deliver an average inference time of 57 milliseconds for health diagnosis across the full battery life cycle (approximately 1898 cycles per cell). The resource-efficient AI (REAI) model operates at an average of 1.36 billion floating point operations per second (FLOPs), with GPU power consumption of 17W and memory usage of 403 MB. This significantly outperforms the Transformer model with vanilla attention. Furthermore, the multi-fusion model proved to be a powerful tool for evaluating capacity in NCA and NCM cells using transfer learning. The results emphasize its ability to reduce computational complexity, energy consumption, and memory usage, while maintaining high accuracy and robust generalization capabilities.

Implementasi Fast Fourier Transform dalam Penyelesaian Persamaan Difusi Panas Satu Dimensi

The Fast Fourier Transform (FFT) method for solving the 1-D heat diffusion equation offers an efficient approach for resolving partial differential equations (PDEs) with various time steps . FFT is used to transform the 1-D heat diffusion equation into the frequency domain and back to the time domain through inverse FFT. Using mathematical modeling with initial and Dirichlet boundary conditions, the numerical solutions produced by FFT are compared with analytical solutions. The accuracy of the method is validated using MAE and MSE calculated in Matlab. At several time intervals , the obtained MAE and MSE values indicate a good agreement between the numerical and analytical solutions, with very small errors. Numerical stability analysis confirms the reliability of the FFT method across various The variation in time step has a significant impact on the accuracy and stability of the solution. Smaller time steps improve accuracy and stability but require longer computation times. The optimal time step selected in this study is Increasing the number of discretization points also enhances accuracy but implies an increase in computational load and memory usage. The FFT method demonstrates good numerical consistency with increasing

CNN-Informer: A hybrid deep learning model for seizure detection on long-term EEG

Timely detecting epileptic seizures can significantly reduce accidental injuries of epilepsy patients and offer a novel intervention approach to improve their quality of life. Investigation on seizure detection based on deep learning models has achieved great success. However, there still remain challenging issues, such as the high computational complexity of the models and overfitting caused by the scarce availability of ictal electroencephalogram (EEG) signals for training. Therefore, we propose a novel end-to-end automatic seizure detection model named CNN-Informer, which leverages the capability of Convolutional Neural Network (CNN) to extract EEG local features of multi-channel EEGs, and the low computational complexity and memory usage ability of the Informer to capture the long-range dependencies. In view of the existence of various artifacts in long-term EEGs, we filter those raw EEGs using Discrete Wavelet Transform (DWT) before feeding them into the proposed CNN-Informer model for feature extraction and classification. Post-processing operations are further employed to achieve the final detection results. Our method is extensively evaluated on the CHB-MIT dataset and SH-SDU dataset with both segment-based and event-based criteria. The experimental outcomes demonstrate the superiority of the proposed CNN-Informer model and its strong generalization ability across two EEG datasets. In addition, the lightweight architecture of CNN-Informer makes it suitable for real-time implementation.

Fault3DNnet: A lightweight 3D seismic fault detection network with bidirectional decoding

Fault detection from seismic data is a critical component of hydrocarbon exploration and production. In recent years, deep-learning techniques have made tremendous achievements and breakthroughs in seismic fault detection. Especially U-nets, represented by FaultSeg3D and its variants, are a dominant method for 3D deep-learning-based seismic fault interpretation. The incorporation of state-of-the-art network modules or training strategies with U-nets continuously improves the performance of fault detection for field seismic data, usually at the cost of increased computational intensity and hardware consumption. We design a lightweight bidirectional decoding network, Fault3DNnet, for fault detection from 3D seismic data volume. To make it simple and concise, our Fault3DNnet is equipped with basic conventional convolution and regular operation modules. The two decoding branches in Fault3DNnet could provide complementary information and improve fault detection performance. The superiority of Fault3DNnet is verified using publicly available synthetic and four field seismic data sets. The experimental results indicate that the method predicts fault structures with improved completeness and continuity compared with FaultSeg3D. Meanwhile, the parameter and computational quantity of the network are only 1/7 and 1/5 of FaultSeg3D, respectively. With the same graphics processing unit memory consumption, Fault3DNnet can handle the size of approximately six times the volume of 3D seismic data during inferencing as that of FaultSeg3D. It helps to improve prediction stability and decrease discontinuous artifacts at the stitching boundaries when predicting the large field data in chunks. In general, our Fault3DNnet delivers superior fault detection results while greatly reducing computational intensity and memory usage.

Precise identification of delamination defect based on optimized deep learning method to understand mechanical property reduction

Ceramic matrix composites are advanced thermal structural materials used in aerospace and other fields due to their excellent performance. However, the common delamination defects in the interior can easily lead to material failure, posing significant threats to component reliability. Addressing this issue requires the development of precise and intelligent methodologies for the rapid identification of delamination defects and the evaluation of their impact on mechanical properties. In this study, delamination defects were intentionally introduced into SiCf/SiC composites to facilitate intelligent identification and quantitative analysis. We propose a novel network combining Mamba and Convolutional Neural Network, which surpasses existing models in defect segmentation by precisely capturing both global and local information, while optimizing computational efficiency and memory usage. Mechanical tests reveal that variations in delamination defects lead to an initial reduction followed by an increase in both tensile and compressive strengths. The minimum tensile and compressive strengths are 69.30 % and 74.30 % of those in non-defective control samples, respectively. Tensile strength is more sensitive to defect volume, as the reduced crack propagation path facilitates premature tensile fracture of the fibers, whereas compressive strength is more affected by defect depth due to compressive instability and stress concentration. This strategy provides a novel avenue for the intelligent identification and risk assessment of delamination defects in ceramic matrix composites.

EHNet: Efficient Hybrid Network with Dual Attention for Image Deblurring

The motion of an object or camera platform makes the acquired image blurred. This degradation is a major reason to obtain a poor-quality image from an imaging sensor. Therefore, developing an efficient deep-learning-based image processing method to remove the blur artifact is desirable. Deep learning has recently demonstrated significant efficacy in image deblurring, primarily through convolutional neural networks (CNNs) and Transformers. However, the limited receptive fields of CNNs restrict their ability to capture long-range structural dependencies. In contrast, Transformers excel at modeling these dependencies, but they are computationally expensive for high-resolution inputs and lack the appropriate inductive bias. To overcome these challenges, we propose an Efficient Hybrid Network (EHNet) that employs CNN encoders for local feature extraction and Transformer decoders with a dual-attention module to capture spatial and channel-wise dependencies. This synergy facilitates the acquisition of rich contextual information for high-quality image deblurring. Additionally, we introduce the Simple Feature-Embedding Module (SFEM) to replace the pointwise and depthwise convolutions to generate simplified embedding features in the self-attention mechanism. This innovation substantially reduces computational complexity and memory usage while maintaining overall performance. Finally, through comprehensive experiments, our compact model yields promising quantitative and qualitative results for image deblurring on various benchmark datasets.

AI-optimized elliptic curve with Certificate-Less Digital Signature for zero trust maritime security

The proliferation of sensory applications has led to the development of the Internet of Things (IoT), which extends connectivity beyond traditional computing platforms and connects all kinds of everyday objects. Marine Ad Hoc Networks are expected to be an essential part of this connected world, forming the Internet of Marine Things (IoMaT). However, marine IoT systems are often highly distributed, and spread across large sparse areas which makes it challenging to implement and manage centralized security measures. Despite some ongoing efforts to establish network connectivity in such environment, securing these networks remains an unreached goal. The use of Certificate-Less Digital Signatures (CLDS) with Elliptic Curve Cryptography (ECC) shows great promise in providing secure communication in these networks and achieving zero trust IoMaT security. By eliminating the need for certificates and associated key management infrastructure, CLDS simplifies the key management process. ECC also enables secure communication with smaller key sizes and faster processing times, which is crucial for resource-limited IoMaT devices. In this paper, we introduce CLDS using ECC as a means of securing IoT networks in a marine environment, creating a zero trust security framework for Internet of Marine Things (IoMaT). To increase security and robustness of the framework, we optimize the ECC parameters using two vital artificial intelligence algorithms, namely Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Evaluation results demonstrate a reduction in ECC parameter generation time by over 40% with GA optimization and 20% with PSO optimization. Additionally, the computational cost and memory usage for major ECC attacks increased significantly by up to 40% and 67% for Rho attacks, 34% and 53% for brute-force attacks, and 30% and 67% for improved hybrid attacks, respectively.

MEDANet: More Efficient Dual Attention Network for Scene Segmentation

The dual attention module is a potent semantic segmentation technique renowned for its capabilities, yet it often faces significant computational demands and GPU memory usage. To tackle these challenges, we introduce an advanced dual perception network comprising two modules: A streamlined Multi-scale Efficient Position Attention Module (MEPAM) and an optimized Efficient Channel Attention Module (MECAM). MEPAM incorporates multi-scale global average pooling into the Position Attention Module (PAM), substantially cutting computational overhead and memory consumption without compromising performance. Meanwhile, MECAM integrates compressed convolutions into the Channel Attention Module (CAM), improving segmentation accuracy and inference speed compared to conventional methods like DANet. Our approach underwent comprehensive evaluation on a semantic segmentation benchmark dataset, showcasing superior performance. For instance, on the Cityscapes dataset, our method achieves an IoU of 82.2%. In terms of efficiency gains, MEPAM operates nearly 1.97 times faster than the standard PAM module on GPU, while requiring 7.55 times less memory with a [Formula: see text] input. Similarly, MECAM achieves approximately 2.2 times faster processing than CAM, while cutting GPU memory usage by 7.53 times. This innovative dual perception network not only enhances segmentation accuracy and speed but also addresses the computational challenges associated with traditional dual attention modules.

Fast computation of the spectral correlation via frequency-averaging

Spectral Correlation (SC) has become a critical analytical instrument for assessing the second-order cyclostationarity (CS) in signals, especially for mechanical vibration signals. Nonetheless, the computational demand for computing SC is considerable. Built upon the Smoothed Cyclic Periodogram (SCP), a consistent estimator named Fast Smoothed Cyclic Periodogram (FastSCP) is proposed to address this issue. FastSCP represents the computational process of SCP through the convolution of spectral components and incorporates the Overlap-Save algorithm for accelerating. Comparison results with other fast SC estimators, including Fast Spectral Correlation (FastSC) and Faster Spectral Correlation (FasterSC), indicate that the proposed method is competitive in terms of both computational cost and memory usage, particularly when dealing with wide cyclic frequency ranges.

Improving AI-assisted video editing: Optimized footage analysis through multi-task learning

In recent years, AI-assisted video editing has shown promising applications. Understanding and analyzing camera language accurately is fundamental in video editing, guiding subsequent editing and production processes. However, many existing methods for camera language analysis overlook computational efficiency and deployment requirements in favor of improving classification accuracy. Consequently, they often fail to meet the demands of scenarios with limited computing power, such as mobile devices. To address this challenge, this paper proposes an efficient multi-task camera language analysis pipeline based on shared representations. This approach employs a multi-task learning architecture with hard parameter sharing, enabling different camera language classification tasks to utilize the same low-level feature extraction network, thereby implicitly learning feature representations of the footage. Subsequently, each classification sub-task independently learns the high-level semantic information corresponding to the camera language type. This method significantly reduces computational complexity and memory usage while facilitating efficient deployment on devices with limited computing power. Furthermore, to enhance performance, we introduce a dynamic task priority strategy and a conditional dataset downsampling strategy. The experimental results demonstrate that achieved a comprehensive accuracy surpassing all previous methods. Moreover, training time was reduced by 66.33%, inference cost decreased by 59.85%, and memory usage decreased by 31.95% on the 2-task dataset MovieShots; on the 4-task dataset AVE, training time was reduced by 95.34%, inference cost decreased by 97.23%, and memory usage decreased by 61.21%.

A novel framework for developing a machine learning-based forecasting model using multi-stage sensitivity analysis to predict the energy consumption of PCM-integrated building

Accurate machine learning (ML) predictions for the early stages of the building design are crucial to construct energy-efficient buildings utilizing limited resources. Several studies have employed ML methods for energy consumption (EC) prediction without considering the utmost crucial PCM-integrated building design parameters. In addition, reducing the dataset by considering only the most significant building design parameters before applying the ML-based method would be beneficial for reducing the computational power and memory usage of the system as well as utilizing less time in the modelling process. To this end, this research presents a novel framework to establish the most robust and reliable ML-based prediction model with less complexity, considering only the most influential PCM-integrated building design parameters. These parameters were identified for future scenarios of hot semi-arid (BSh) climate zones using multi-stage sensitivity analysis. Afterward, a reduced EC database based on the most significant building's early-design-stage parameters (EDSPs) was utilized to formulate several multi-expression programming (MEP) and support vector machines (SVM)-based forecasting models, considering the variations in their hyperparameter values. Formulated prediction models have shown less time utilization through the training and testing phases for the EC evaluations of selected PCM-integrated building compared to the physical-modelling process. Several statistical parameters were used to test and validate the performance of the formulated prediction models. The acquired model evaluation and validation results demonstrated that the MEP-based prediction model (MEP15) exhibited the highest level of reliability and accuracy, showing an R2 value of >95% for both the training and testing phases. The model's interpretability showed that, throughout the parametric analysis, the developed prediction model adhered to the system's physical boundary constraints. Also, the best-performing prediction model showed energy savings of up to 12% for building integrated with PCM having a melting temperature of 28 °C. Conclusively, this research demonstrated that the developed MEP-based prediction model could be employed to precisely forecast the EC for selected PCM-incorporated building in the whole BSh climate, considering important EDSPs while utilizing minimal resources.

Efficient Numerical Implementation of the Time-Fractional Stochastic Stokes–Darcy Model

This paper presents an efficient numerical method for the fractional-order generalization of the stochastic Stokes–Darcy model, which finds application in various engineering, biomedical and environmental problems involving interaction between free fluid flow and flows in porous media. Unlike the classical model, this model allows taking into account the hereditary properties of the process under uncertainty conditions. The proposed numerical method is based on the combined use of the sparse grid stochastic collocation method, finite element/finite difference discretization, a fast numerical algorithm for computing the Caputo fractional derivative, and a cost-effective ensemble strategy. The hydraulic conductivity tensor is assumed to be uncertain in this problem, which is modeled by the reduced Karhunen–Loève expansion. The stability and convergence of the deterministic numerical method have been rigorously proved and validated by numerical tests. Utilizing the ensemble strategy allowed us to solve the deterministic problem once for all samples of the hydraulic conductivity tensor, rather than solving it separately for each sample. The use of the algorithm for computing the fractional derivatives significantly reduced both computational cost and memory usage. This study also analyzes the influence of fractional derivatives on the fluid flow process within the fractional-order Stokes–Darcy model under uncertainty conditions.

A novel efficient calculation method for rotor aeroacoustic characteristics based on multiple aerodynamic surfaces source model

Based on the simplified acoustic source model of multiple aerodynamic surfaces, an efficient calculation method for rotor aeroacoustic characteristics has been established. Firstly, the aerodynamic characteristics database of the airfoil is obtained based on the Computational Fluid Dynamics (CFD) method. The inflow environment of each blade element is calculated using the free wake method, and the distribution of chord-wise loading is obtained by combining the established database. Subsequently, based on the F1A equation, a simplified formula for loading noise with pressure difference as a parameter is derived. The thickness noise is obtained from the blade shape and operating conditions, and the blade surface mesh is constructed by using the adaptive curvature distribution strategy of airfoil points. The validation is carried out by comparing with experimental values in the hover and forward flight states. Then, A hybrid weighted interpolation scheme is proposed based on inverse distance weighted interpolation (IDW) and bidirectional linear interpolation method, which is suitable for capturing blade/vortex interaction (BVI) noise. A set of parameters suitable for engineering applications is obtained through the parametric sensitivity analysis. The computational time and memory usage are reduced to 1/47 and 1/4 of the original amount, respectively. Finally, Using the above method, the influence of rotational speeds (ω) on rotor aeroacoustic characteristics are studied. The results show that ω and sound pressure level (SPL) are linearly related and the SPL decreases by approximately 5 dB for every 0.1 Ω decrease in ω. The rotational speed ω≈90 %Ω can effectively suppress rotor aeroacoustic levels, benefiting the stealth design of helicopters.

Hybrid Filtering and Probabilistic Techniques for Privacy-Preserving Community Detection in OSNs

Online Social Networks (OSNs) face the major challenge of protecting participant's privacy, due to the high dimensionality and volume of the data. In real-time social networks, where hundreds of personal details of people are shared every day, there remains a significant threat to privacy. Privacy preservation is challenging for a community detection problem due to the high computational complexity and memory requirements, especially in larger real-world OSN graphs. Although weighted nodes provide better results, as they allow capturing the frequencies of the values, the privacy preservation of sensitive attributes such as specific profiles becomes harder compared to these models. This problem can result in queries and subsequent learnings from social network profiles of specific individuals, which may be of personal, political or otherwise concern. Online social networks (OSNs) grapple with significant privacy challenges due to the extensive dimensions and vast quantities of data involved. This research fills the void in current privacy-preserving community detection methodologies, which face problems in computational complexity and memory usage in large-scale OSNs. The proposed framework seeks to bolster privacy preservation through a comprehensive multi-step process. Data filtering uses a blended data filter system to remove outliers and irrelevant data, thus enhancing the quality of the input data. Density-Oriented Clustering phase employs a density-oriented clustering model to identify communities, with each cluster representing a distinct community. Privacy Preservation component introduces a new privacy preservation technique for sensitive OSN attributes, surpassing existing k-anonymization methods. The developed density-based social network community detection model and its novel privacy-preserving scheme are evaluated using the datasets Yelp, Football, Zachary and Dolphin from the SNAP dataset. Experimental results on these datasets embed a comprehensive evaluation based on the order of each node and the graph-based networks, where each node is laden with weights as proximity values, indicating the semantic proximity between communities and individuals. The proposed framework employs the normalized mutual information (NMI), modularity (Q), Rand index and runtime measurements to demonstrate widespread advantages in the multi-dimensional functional space, including greater accuracy, cluster compatibility, and computational tractability over the existing prominent traditional models for OSNs.

Momentum recursive DARTS

DARTS has emerged as a popular method for neural architecture search (NAS) owing to its efficiency and simplicity. It employs gradient-based bi-level optimization to iteratively optimize the upper-level architecture parameters and lower-level super-network weights. The key challenge in DARTS is the accurate estimation of gradients for two-level object functions, leading to significant errors in gradient approximation. To address this issue, we propose a new approach, MR-DARTS, that incorporates a momentum term and a recursive scheme to improve gradient estimation. Specifically, we leverage historical information by using a running average of past observed gradients to enhance the quality of current gradient estimation in both upper-level and lower-level functions. Our theoretical analysis shows that the variance of our estimated gradient decreases with each iteration. By utilizing momentum and a recursive scheme, MR-DARTS effectively controls the error in stochastic gradient updates that result from inaccurate gradient estimation. Furthermore, we utilize the Neumann series approximation and Hessian Vector Product scheme to reduce computational requirements and memory usage. We evaluate our proposed method on several benchmarks and demonstrate its effectiveness through comprehensive experiments.

Adaptive member adding for truss topology optimization: application to elastic design

This paper provides a rigorous and computationally efficient means of identifying compliance-based optimal truss topologies from high-resolution ground structures—problems involving over 30 million potential elements can be solved in under 1 h on a typical laptop. The adaptive ‘member adding’ approach is shown to provide significant savings in computational time and memory usage compared to directly solving the full optimization problem, whilst obtaining the same optimal solution; this paper presents the first application of this powerful principle to the well-known linear-elastic design problem. The computational advantages are particularly notable for multiple load-case problems, as the numerical structure of these cannot be effectively exploited without understanding of the physical nature of the problem. For such cases, the member adding process reduces the computational time required from approximately O(m2)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(m^2)$$\\end{document} to O(m), where m is the number of potential elements; here, the time required is reduced by a factor of up to 60 for the relatively small problems that could be solved with both approaches. By using the member adding approach, compliance-optimized structures are obtained at a significantly higher resolution than has previously been possible. The findings of this paper have the potential to deliver a step change in the size of problems that can be solved in compliance-based truss topology optimization, and an accompanying Python code is provided to facilitate this.