Explainable Artificial Intelligence for Crowd Forecasting Using Global Ensemble Echo State Networks by Chamod Samarajeewa, Daswin De Silva, Milos Manic, Nishan Mills, Prabod Rathnayaka, Andrew Jennings

“…Crowd forecasting is typically achieved using deep learning models that learn the evolving nature of data streams. The computational complexity, execution time, and opaqueness are inherent challenges of deep learning models that also overlook the latent relationships between multiple real-time data streams for improved accuracy. …”
Get full text

Tensor-based approach to the co-prime planar array signal processing by Wei RAO, Yufeng GUI, Dan LI

“…For the co-prime planar array (CPPA) consisting of two sparse uniform rectangular array (URA),a new processing method based on tensor algebra was proposed to enhance the degrees of freedom (DoF).By dividing each URA into some overlapping subarrays,the received signals of two URAs were expressed as two tensors.And then the cross-correlation between such two tensors was processed into a received signal tensor of the virtual array.Analysis show that by the new method,the CPPA with 2 ²L -1 physical elements can be transformed into a virtual sparse non-uniform planar array with<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mfrac> <mrow> <msup> <mrow> <mo stretchy="false">(</mo><mi>L</mi><mo>+</mo><mn>1</mn><mo stretchy="false">)</mo></mrow> <mrow> <mtext> </mtext><mn>4</mn></mrow> </msup> </mrow> <mrow> <mn>16</mn></mrow> </mfrac> </math></inline-formula>elements.For the virtual array,the tensor decomposition-based approach for estimating the two-dimensional (2-D) direction of arrival (DoA) of the incident signal is also proposed,which means 2-D spectral peak searching is avoided.Compared with the co-prime planar signal processing methods reported in the literature,the proposed method can increase the DoF from L ²to<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML"> <mfrac> <mrow> <msup> <mrow> <mo stretchy="false">(</mo><mi>L</mi><mo>+</mo><mn>1</mn><mo stretchy="false">)</mo></mrow> <mrow> <mtext> </mtext><mn>4</mn></mrow> </msup> </mrow> <mrow> <mn>16</mn></mrow> </mfrac> <mo>+</mo><mn>1</mn> </math></inline-formula>,and has the better performance of the 2-D DoA estimation and lower computational complexity.Simulation results demonstrate the efficiency of the proposed method.…”
Get full text

Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics by Shuhao Ma, Yu Cao, Ian D. Robertson, Chaoyang Shi, Jindong Liu, Zhi-Qiang Zhang

“…Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. …”
Get full text

Uniform Quantization for Multi-Antenna Amplify&#x2013;Quantize&#x2013;Forward Relay by Gangsan Jeong, Xianglan Jin

“…Subsequently, we introduce neural network-based deep learning methods to mitigate computational complexity. Specifically, we present supervised learning (SL) and unsupervised learning (USL) methodologies, with the latter employing a novel loss function designed to avoid the need for extensive training data collection. …”
Get full text

A Three-Vector Fast Model Predictive Control Method for Steady State Performance Improvement by Yongzhen Zhang, Pu Cheng, Kai Shen, Weiming He, Di Nian, Jun Pan

“…Results show that the proposed method effectively prevents common-mode voltage spikes caused by dead-time, reduces torque and flux ripples, and minimizes current harmonic content while lowering computational complexity.…”
Get full text

An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction by Song Zhou, Jing Chen, Zao Wang, Yuhao Wang, Pin Wen

“…However, due to the computation of the large-scale matrix, the optimal searching in an iterative manner will involve tremendous computational complexity with slow convergence, which will prevent deep learning algorithms from being efficiently applied for SAR imaging. …”
Get full text

IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition by George Karantaidis, Athanasios Pantsios, Ioannis Kompatsiaris, Symeon Papadopoulos

“…Additionally, we explore the use of TinyViT to reduce computational complexity and propose an attention mechanism to dynamically enhance feature representation. …”
Get full text

A Differential Evolution-Oriented Pruning Neural Network Model for Bankruptcy Prediction by Yajiao Tang, Junkai Ji, Yulin Zhu, Shangce Gao, Zheng Tang, Yuki Todo

“…The EPNN can reduce the computational complexity by removing the superfluous and ineffective synapses and dendrites in the structure and is simultaneously able to achieve a competitive classification accuracy. …”
Get full text

Nonlinear Dynamic Response Analysis of Cable–Buoy Structure Under Marine Environment by Qiufu Xie, Binghan Liu, Junxian Zhang, Yaobing Zhao

“…The absolute velocity model incorporates flow velocity coupling terms, offering higher accuracy but at the expense of increased computational complexity. In contrast, the relative velocity model is computationally simpler and therefore more widely adopted. …”
Get full text

Prediction of the Bending Strength of Boltless Steel Connections in Storage Pallet Racks: An Integrated Experimental-FEM-SVM Methodology by Zhi-Jun Lyu, PeiCai Zhao, Qi Lu, Qian Xiang, HongLiang Li

“…Despite the fact that the finite element method (FEM) and physical experiment have been used to obtain the mechanical performance of beam-to-column connections (BCCs), those methods have the disadvantages of high computational complexity and test cost. Taking, for example, the boltless steel connections, this paper proposes a data-driven simulation model (DDSM) that combines the experimental test, FEM, and support vector machine (SVM) techniques to determine the bending strength of BCCs by means of data mining from the engineering database. …”
Get full text

Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds by Joarder Jafor Sadique, Imtiaz Nasim, Ahmed S. Ibrahim

“…Remarkably, unlike other ML-based models that require extensive training data, both models only need 30 training samples to achieve over 99% of the sum rate while maintaining similar computational complexity relative to the benchmark.…”
Get full text

Improved Binary Grey Wolf Optimization Approaches for Feature Selection Optimization by Jomana Yousef Khaseeb, Arabi Keshk, Anas Youssef

“…Finally, the results revealed that the best approach in terms of classification accuracy, fitness value, and number of selected features had the highest computational complexity.…”
Get full text

Adaptive Resource Allocation and Mode Switching for D2D Networks With Imperfect CSI in AGV-Based Factory Automation by Safiu A. Gbadamosi, Gerhard P. Hancke, Adnan M. Abu-Mahfouz

“…The ARAMS scheme integrates mode switching (MS), channel-quality factor (CQF), and power control (PC) within a bi-phasic resource-sharing (RS) algorithm to lower the computational complexity. In the initial phase, the operational mode for each D2D user (DU) per cell is adaptively selected based on the channel gain ratio (CGR). …”
Get full text

Research on Feature Extracted Method for Flutter Test Based on EMD and CNN by Hua Zheng, Zhenglong Wu, Shiqiang Duan, Jiangtao Zhou

“…The method allows for real-time, online prediction with low computational complexity.…”
Get full text

A novel arc detection and identification method in pantograph-catenary system based on deep learning by Yue Yan, Hu Liu, Linfeng Gan, Runtong Zhu

“…Traditional arc detection methods, while functional, often suffer from low detection accuracy and high computational complexity, especially in complex operational environments. …”
Get full text

A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR by Zongtai Li, Gangsheng Li, Ling Zhang, Lanjun Liu, Q. M. Jonathan Wu

“…Subsequently, the improved TFA algorithm is applied to adjacent range cells of suspicious targets to generate multiframe TF images, forming a three-dimensional data block structured as time-RD frequency. To reduce computational complexity, a TFA method using multisynchrosqueezing transform is employed, enhancing detection accuracy for targets within cluttered regions. …”
Get full text

A Real-Time Road Scene Semantic Segmentation Model Based on Spatial Context Learning by Xiaomei Xiao, Jialiang Tang, Xiaoyan Lu, Zhengyong Feng, Yi Li

“…To address the issues of high computational complexity and insufficient aggregation of global and local information in existing image segmentation methods, this paper proposes an efficient segmentation model based on Spatial Context Learning, named SCLSeg. …”
Get full text

ν-point energy correletors with FastEEC: Small-x physics from LHC jets by Ankita Budhraja, Hao Chen, Wouter J. Waalewijn

“…Originally, the computational complexity of evaluating ν-correlators for M particles scaled as 22M, making it impractical for real-world analyses. …”
Get full text

Least Square Estimation-Based Different Fast Fading Channel Models in MIMO-OFDM Systems by Walaa Hussein, Kamil Audah, N. K. Noordin, Habib Kraiem, Aymen Flah, Mohd Fadlee, Alyani Ismail

“…However, existing massive MIMO systems face challenges with their high computational complexity and intricate spatial structures, preventing efficient utilization of channel and sparsity features in these multiantenna systems. …”
Get full text

ECC-Based Authentication Protocol for Military Internet of Drone (IoD): A Holistic Security Framework by Hyeon Choe, Dongsu Kang

“…The employed Elliptic Curve Cryptography security technology provides robust encryption with minimal computational complexity, making it suitable for resource-constrained IoD environments. …”
Get full text