Computational Speed Research Articles

A novel low-resource consumption and high-speed hardware implementation of HOG feature extraction on FPGA for human detection

In today’s increasingly complex traffic environment, pedestrian detection has become increasingly important. The Histogram of Oriented Gradients (HOG) algorithm has been proven to be highly efficient in pedestrian detection. This paper proposes a low-resource consumption, high-speed hardware implementation for HOG algorithm. In the case of a slight sacrifice in accuracy, it increases computational speed and reduces resource consumption. Experimental results demonstrate that the implementation achieves a speed of 0.933 pixels per clock cycle and consumes 4117 look-up tables and 4.5 Kbits of block RAMs while its accuracy decreases by 1.2% on the INRIA dataset and by 0.11% on the MIT dataset.

The gamma-variate in contrast-enhanced imaging: a unified view and method from computed to electrical impedance tomography

Objective. Modern medical imaging plays a vital role in clinical practice, enabling non-invasive visualization of anatomical structures. Dynamic contrast enhancement (DCE) imaging is a technique that uses contrast agents to visualize blood flow dynamics in a time-resolved manner. It can be applied to different modalities, such as computed tomography (CT) and electrical impedance tomography (EIT). This study aims to develop a common theoretical and practical hemodynamic extraction basis for DCE modelling across modalities, based on the gamma-variate function. Approach. The study introduces a framework to generate time-intensity curves for multiple DCE imaging modalities from user-defined hemodynamic parameters. Thus, extensive datasets were simulated for both DCE-CT and EIT, representing different hemodynamic scenarios. Additionally, gamma-variate extensions to account for several physiological effects were detailed in a modality-agnostic manner, and three corresponding fitting strategies, namely nonlinear, linear, and a novel hybrid approach, were implemented and compared on the basis of accuracy of parameter estimation, first pass reconstruction, speed of computation, and failure rate. Main results. As a result, we found the linear method to be the most modality-dependent, exhibiting the greatest bias, variance and failure rates, although remaining the fastest alternative. The hybrid method at least matches the state-of-the-art nonlinear method’s accuracy, while improving its robustness and speed by 10 times. Significance. Our research suggests that the hybrid method may bring noteworthy accuracy and efficiency improvements in handling the high-dimensionality of DCE imaging in general, being a step towards real-time processing. Moreover, our generative model presents a potential asset to produce benchmarking and data augmentation datasets across modalities.

Enhancing Speaker Recognition Models with Noise-Resilient Feature Optimization Strategies

This paper delves into an in-depth exploration of speaker recognition methodologies, with a primary focus on three pivotal approaches: feature-level fusion, dimension reduction employing principal component analysis (PCA) and independent component analysis (ICA), and feature optimization through a genetic algorithm (GA) and the marine predator algorithm (MPA). This study conducts comprehensive experiments across diverse speech datasets characterized by varying noise levels and speaker counts. Impressively, the research yields exceptional results across different datasets and classifiers. For instance, on the TIMIT babble noise dataset (120 speakers), feature fusion achieves a remarkable speaker identification accuracy of 92.7%, while various feature optimization techniques combined with K nearest neighbor (KNN) and linear discriminant (LD) classifiers result in a speaker verification equal error rate (SV EER) of 0.7%. Notably, this study achieves a speaker identification accuracy of 93.5% and SV EER of 0.13% on the TIMIT babble noise dataset (630 speakers) using a KNN classifier with feature optimization. On the TIMIT white noise dataset (120 and 630 speakers), speaker identification accuracies of 93.3% and 83.5%, along with SV EER values of 0.58% and 0.13%, respectively, were attained utilizing PCA dimension reduction and feature optimization techniques (PCA-MPA) with KNN classifiers. Furthermore, on the voxceleb1 dataset, PCA-MPA feature optimization with KNN classifiers achieves a speaker identification accuracy of 95.2% and an SV EER of 1.8%. These findings underscore the significant enhancement in computational speed and speaker recognition performance facilitated by feature optimization strategies.

TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations.

Achieving a balance between computational speed, prediction accuracy, and universal applicability in molecular simulations has been a persistent challenge. This paper presents substantial advancements in TorchMD-Net software, a pivotal step forward in the shift from conventional force fields to neural network-based potentials. The evolution of TorchMD-Net into a more comprehensive and versatile framework is highlighted, incorporating cutting-edge architectures such as TensorNet. This transformation is achieved through a modular design approach, encouraging customized applications within the scientific community. The most notable enhancement is a significant improvement in computational efficiency, achieving a very remarkable acceleration in the computation of energy and forces for TensorNet models, with performance gains ranging from 2× to 10× over previous, nonoptimized, iterations. Other enhancements include highly optimized neighbor search algorithms that support periodic boundary conditions and smooth integration with existing molecular dynamics frameworks. Additionally, the updated version introduces the capability to integrate physical priors, further enriching its application spectrum and utility in research. The software is available at https://github.com/torchmd/torchmd-net.

Validation of a ray-tracing-based guided Lamb wave propagation methodology in aerostructures

Validation of a ray-tracing-based guided Lamb wave propagation methodology in aerostructures

Multi-Object Tracking Model Based on Detection Tracking Paradigm in Panoramic Scenes

Multi-Object Tracking (MOT) technology is dedicated to continuously tracking multiple targets of interest in a sequence of images and accurately identifying their specific positions at different times. This technology is crucial in key application areas such as autonomous driving and security surveillance. However, the application process often requires the coordination of cameras from multiple angles for tracking. Directly studying Multi-Object Tracking algorithms in panoramic scenes is an effective way to address this issue. The uniqueness of panoramic scenes causes target position changes at the boundaries and tracking difficulties due to continuous changes in target scales. To ensure the accuracy of target tracking, this study explores a detection-based tracking method using the newly improved YOLOx detector and the adjusted DeepSORT algorithm. Firstly, YOLOx_s was chosen as the detector because its simple network structure ensures a fast computational speed. During the feature extraction stage, we used the Polarized Self-Attention (PSA) mechanism to capture more feature information, thereby improving the tracking performance on small-scale targets. Secondly, the tracker was improved by adding a camera motion compensation module before predicting the target’s position to mitigate the impact of camera shake on tracking. Finally, to address the difficulty of continuously tracking targets in specific areas of panoramic scenes, this study proposes specific tracking strategies. These strategies effectively resolve the problem of tracking failure caused by target position changes at the boundaries. Experimental results show that improved algorithms have a superior performance on multiple evaluation metrics compared to other algorithms in the field. Compared to the original algorithm, the improved algorithm exhibits a 6% increase in the quantitative metric MOTA, a 7% increase in IDF1, and a 40% decrease in IDSWs, demonstrating its leading performance.

Focus-Attention Approach in Optimizing DETR for Object Detection from High-Resolution Images

Transformer-based detectors have recently achieved remarkable success in object detection, revolutionizing the field with their efficiency and accuracy. However, applying these models to high-resolution images presents significant challenges due to the increased computational demands and complexity of processing dense, high-resolution data. In this paper, we introduce a novel model specifically designed for object detection from high-resolution imagery. This model incorporates a multi-layer object-focus network along with a transformer encoder-decoder structure. Specifically, the model employs a dual-head strategy in the object-focus network to balance the detailed analysis of small objects with computational efficiency. This is achieved by leveraging data sparsity to reduce unnecessary computations in massive background regions. Additionally, to improve detection performance for small objects, we propose a method to effectively apply the transformer encoder-decoder structure combined with the object-focus network on the multi-layer feature maps of the feature pyramid. Our extensive evaluations of the VisDrone, MS-COCO, and UAVid datasets demonstrate that our model outperforms other DETR-based detectors in both detection accuracy and computational speed, highlighting its superior performance. These results indicate a significant advancement in the field of high-resolution object detection utilizing transformer architecture.

Graph‐based solution for smart grid real‐time operation and control

Graph‐based solution for smart grid real‐time operation and control

A novel unconstrained methodology for economic analysis of the level of repair with a case study of a multi-indenture and multi-echelon repair network

The multi-indenture and multi-echelon economic analysis of repair levels is commonly modelled as a constrained 0–1 programming problem. However, with the increase in the scale of the decision variables, the proportion of feasible solutions in the solution space sharply decreases, posing a challenge for traditional solution methods. In this paper, the transformation of the initial problem into an unconstrained integer programming problem is demonstrated. Specifically, the total number of feasible decisions can be solved analytically through a decision flow method, and a bijective relationship between decision sequence numbers and feasible decisions is established using a mixed-radix system, converting the optimization variables to feasible decision sequence numbers; in this way, the initial problem becomes unconstrained. The advantages of this approach include the following: (1) All the solutions in the transformed solution space are feasible, which significantly improves the efficiency of the solution and reduces the dimensionality of the decision variables; and (2) the proposed model is highly flexible in terms of considering additional variables, such as decision time, transportation modes, and repair locations. Furthermore, the sequence numbers of each feasible solution are transformed into binary sequences, and the binary particle swarm optimizer (BPSO) algorithm can be employed to solve the model. The proposed methodology is applied to the case of a three-indenture and three-echelon repair network considering multiple fault modes, and the results are compared with those of previous studies. The results validate the rationality and substantial advantages of the proposed methodology for economic analysis in terms of computational speed and convergence performance.

Direct integration of measured viscoelastic relaxation data in time-domain finite element simulations

The current approach to modeling viscoelastic materials in most commercial finite element packages is based on the General Maxwell Model, which views these materials as combinations of spring and dashpot elements. However, the data can be incorporated more directly into a transient finite element study by direct interpolation of the relaxation function. This work explores a linear interpolation scheme to the inclusion of viscoelastic relaxation functions on an example problem. The results show several benefits over the General Maxwell Model for transient studies. Included in the analysis are displacement solutions utilizing both approaches, relaxation function error calculations for both approaches, and parametric runtime studies comparing speed of calculation. The variation in computational flop counts is considered and an argument is made for the preference of the proposed approach.

A differentiable programming framework for spin models

We introduce a novel framework for simulating spin models using differentiable programming, an approach that leverages the advancements in machine learning and computational efficiency. We focus on three distinct spin systems: the Ising model, the Potts model, and the Cellular Potts model, demonstrating the practicality and scalability of our framework in modeling these complex systems. Additionally, this framework allows for the optimization of spin models, which can adjust the parameters of a system by a defined objective function. In order to simulate these models, we adapt the Metropolis-Hastings algorithm to a differentiable programming paradigm, employing batched tensors for simulating spin lattices. This adaptation not only facilitates the integration with existing deep learning tools but also significantly enhances computational speed through parallel processing capabilities, as it can be implemented on different hardware architectures, including GPUs and TPUs.

Deep learning-based inverse design of multi-functional metasurface absorbers.

A novel approach-integrating a simulated annealing (SA) algorithm with deep learning (DL) acceleration-is presented for the rapid and accurate development of terahertz perfect absorbers through forward prediction and backward design. The forward neural network (FNN) effectively deduces the absorption spectrum based on metasurface geometry, resulting in an 80,000-fold increase in computational speed compared to a full-wave solver. Furthermore, the absorber's structure can be precisely and promptly derived from the desired response. The incorporation of the SA algorithm significantly enhances design efficiency. We successfully designed low-frequency, high-frequency, and broadband absorbers spanning the 4 to 16 THz range with an error margin below 0.02 and a remarkably short design time of only 10 min. Additionally, the proposed model in this Letter introduces a novel, to our knowledge, method for metasurface design at terahertz frequencies such as the design of metamaterials across optical, thermal, and mechanical domains.

Insights from the 2nd China intelligent sleep staging competition.

Artificial intelligence (AI) is quickly advancing in the field of sleep medicine, which bodes well for the potential of actual clinical use. In this study, an analysis of the 2nd China Intelligent Sleep Staging Competition was conducted to gain insights into the general level and constraints of AI-assisted sleep staging in China. The outcomes of 10 teams from the children's track and 13 teams from the adult track were investigated in this study. The analysis included overall performance, differences between five different sleep stages, variations across subjects, and performance during stage transitions. The adult track's accuracy peaked at 80.46%, while the children's track's accuracy peaked at 88.96%. On average, accuracy rates stood at 71.43% for children and 68.40% for adults. All results were produced within a mere 5-min timeframe. The N1 stage was prone to misclassification as W, N2, and R stages. In the adult track, significant differences were apparent among subjects (p < 0.05), whereas in the children's track, such differences were not observed. Nonetheless, both tracks experienced a performance decline during stage transitions. The computational speed of AI is remarkably fast, simultaneously holding the potential to surpass the accuracy of physicians. Improving the machine learning model's classification of the N1 stage and transitional periods between stages, along with bolstering its robustness to individual subject variations, is imperative for maximizing its ability in assisting clinical scoring.

Efficient pulse sequence design framework for high-dimensional MR fingerprinting scans using systematic error index.

For effective optimization of MR fingerprinting (MRF) pulse sequences, estimating and minimizing errors from actual scan conditions are crucial. Although virtual-scan simulations offer an approximation to these errors, their computational demands become expensive for high-dimensional MRF frameworks, where interactions between more than two tissue properties are considered. This complexity makes sequence optimization impractical. We introduce a new mathematical model, the systematic error index (SEI), to address the scalability challenges for high-dimensional MRF sequence design. By eliminating the need to perform dictionary matching, the SEI model approximates quantification errors with low computational costs. The SEI model was validated in comparison with virtual-scan simulations. The SEI model was further applied to optimize three high-dimensional MRF sequences that quantify two to four tissue properties. The optimized scans were examined in simulations and healthy subjects. The proposed SEI model closely approximated the virtual-scan simulation outcomes while achieving hundred- to thousand-times acceleration in the computational speed. In both simulation and in vivo experiments, the optimized MRF sequences yield higher measurement accuracy with fewer undersampling artifacts at shorter scan times than the heuristically designed sequences. We developed an efficient method for estimating real-world errors in MRF scans with high computational efficiency. Our results illustrate that the SEI model could approximate errors both qualitatively and quantitatively. We also proved the practicality of the SEI model of optimizing sequences for high-dimensional MRF frameworks with manageable computational power. The optimized high-dimensional MRF scans exhibited enhanced robustness against undersampling and system imperfections with faster scan times.

Multi-User Detection Based on Improved Cheetah Optimization Algorithm

Targeting the issues of slow speed and inadequate precision of optimal solution calculation for multi-user detection in complex noise environments, this paper proposes a multi-user detection algorithm based on a Hybrid Cheetah Optimizer (HCO). The algorithm first optimizes the control parameters and individual update mechanism of the Cheetah Optimizer (CO) algorithm using a nonlinear strategy to improve the uniformity and discretization of the individual search range, and then dynamically introduces a differential evolutionary algorithm into the improved selection mechanism of the CO algorithm, which is utilized to fine-tune the solution space and maintain the local diversity during the fast search process. Simulation results demonstrate that this detection algorithm not only realizes fast convergence with a very low bit error rate (BER) at eight iterations but also has obvious advantages in terms of noise immunity, resistance to far and near effects, communication capacity, etc., which greatly improves the speed and accuracy of optimal position solving for multi-user detection and can achieve the purpose of accurate solving in complex environments.

Research on Multi-Objective Flexible Job Shop Scheduling Problem with Setup and Handling Based on an Improved Shuffled Frog Leaping Algorithm

Flexible job shop scheduling problem (FJSP), widely prevalent in many intelligent manufacturing industries, is one of the most classic problems of production scheduling and combinatorial optimization. In actual manufacturing enterprises, the setup of machines and the handling of jobs have an important impact on the scheduling plan. Furthermore, there is a trend for a cluster of machines with similar functionalities to form a work center. Considering the above constraints, a new order-driven multi-equipment work center FJSP model with setup and handling including multiple objectives encompassing the minimization of the makespan, the number of machine shutdowns, and the number of handling batches is established. An improved shuffled frog leading algorithm is designed to solve it through the optimization of the initial solution population, the improvement of evolutionary operations, and the incorporation of Pareto sorting. The algorithm also combines the speed calculation method in the gravity search algorithm to enhance the stability of the solution search. Some standard FJSP data benchmarks have been selected to evaluate the effectiveness of the algorithm, and the experimental results confirm the satisfactory performance of the proposed algorithm. Finally, a problem example is designed to demonstrate the algorithm’s capability to generate an excellent scheduling plan.

Radial basis point interpolation for strain field calculation in digital image correlation

In order to extract smooth and accurate strain fields from the noisy displacement fields obtained by digital image correlation (DIC), a point interpolation meshless (PIM) method with a radial basis function (RBF) is introduced for full-field strain calculation, which overcomes the problems of slow calculation speed and unstable matrix inverse calculation of the element-free Galerkin method (EFG). The radial basis point interpolation method (RPIM) with three different radial basis functions and the moving least squares (MLS) and pointwise least squares (PLS) methods are compared by analyzing and validating the strain fields with high-strain gradients in simulation experiments. The results indicate that the RPIM is nearly 80% more computationally efficient than the MLS method when a larger support domain is used, and the efficiency of the RPIM is nearly 26% higher than that of the MLS method when a smaller support domain is used; the strain calculation accuracy is slightly lower than that of the MLS method by 0.3–0.5%, but the stability of the calculation is significantly improved. In contrast with the PLS method, which is easily affected by the noise and the size of the strain calculation window, the RPIM is insensitive to the displacement noise and the size of the support domain and can obtain a similar calculation accuracy. The RPIM with multiquadric (MQ) radial basis functions performs well in balancing the computational accuracy and efficiency and is insensitive to shape parameters. The application cases show that the method can effectively compute the strain field at the crack tip, validating its applicability to the study of the plastic region at the crack tip. In conclusion, the proposed RPIM-based method provides an accurate, practical, and robust approach for full-field strain measurements.

Automated intelligent design of modified uni-traveling carrier photodectors

This paper introduces an automatic intelligent design method for the modified uni-traveling carrier photodetector (MUTC-PD). The conventional photodetector design process often relies on the numerical solution of complex nonlinear partial differential equations to simulate and optimize device performance, which is not only computationally intensive but also inefficient. To overcome this challenge, we apply the charge control principle to calculate the photodetector bandwidth, which improves the computational speed by a factor of approximately 1800 compared to the numerical solution of nonlinear partial differential equations. To further optimize the structure of the photodetector, we incorporate the Velocity Varying Climbing Particle Swarm Optimization (VVCPSO) algorithm. This is an improved algorithm based on the traditional particle swarm algorithm, which is able to quickly find the optimal solution in a complex parameter space. By applying the VVCPSO algorithm, we successfully fine-tuned the photodetector structure and obtained structural parameters with optimal performance. Our thorough verification process confirms that the proposed method is consistent with the results of ATLAS simulation software. Automated design has resulted in a high-performance MUTC-PD with a responsivity of 0.52A/W and a bandwidth of 60 GHz (@-3 V) at a mesa diameter of 16µm. Compared to the pre-optimized device, the bandwidth is increased to three times the original. By reducing the mesa diameter to 4µm, the bandwidth can be further increased to 82 GHz (@-3 V). The proposed method's calculation speed is fast enough, enabling extensive parameter studies to optimize device performance.

A comparison between physics-based Li-ion battery models

Physics-based electrochemical battery models, such as the Doyle-Fuller-Newman (DFN) model, are valuable tools for simulating Li-ion battery behavior and understanding internal battery processes. However, the complexity and computational demands of such models limit their applicability for battery management systems and long-term aging simulations. Reduced-order models (ROMs), such as the Extended Single Particle Model (ESPM), Single Particle Model (SPM) and Polynomial and Padé approximations, here all referred to as simplifications, lead to faster computational speeds. Choosing the appropriate simplification method for a specific cell type and operating condition is a challenge. This study investigates the simulation accuracy and calculation speed of various simplifications for high-energy (HE) and high-power (HP) batteries at different current loading conditions and compares those to the full-order DFN model. The results indicate that among the ROMs, the ESPM consistently offers the best combination of high computational speed and relatively good accuracy in most conditions in comparison to the full-order DFN model. Among the approximations, higher-order polynomial approximation, third and fourth-order Padé approximation perform the best in terms of accuracy. The higher-order polynomial approximation shows an advantage in terms of computing speed, while the fourth-order Padé approximation achieves the highest overall accuracy among the different approximations.

Rapid calculation for avalanche maps by GPGPU-based snow avalanche model

The required time for producing snow avalanche maps is influenced by computation speed of simulations. Commonly, integrating terrain assessment with dynamic flow simulation aids in mapping dangerous areas for human and structural threats. This approach enables the evaluation of avalanche paths, as well as the assessment of flow rate and thickness during avalanche movement. However, the substantial computational cost of the simulation results in long calculation times when using the Central Processing Unit (CPU). In this study, a new rapid snow avalanche simulator was developed by applying massively parallel computation with the General-Purpose computing on Graphics Processing Unit (GPGPU) technique. By avoiding slower data transfer and utilizing faster memory, computational speed could be accelerated up to 80 times faster than conventional simulation using a CPU. Additionally, the rapid calculation models were validated based on the Mt. Nasu event in 2017, and pilot studies of the avalanche map of Mt. Nasu in Japan demonstrated the usefulness of the developed model for vulnerability evaluation. A total of 123 simulations were conducted for each susceptible source area, and all simulations were completed within only 6.5 h. This high-performance calculation can significantly reduce the time cost of producing and expanding conventional avalanche maps.