A Lightweight Person Detector for Surveillance Footage Based on YOLOv8n by Qicheng Wang, Guoqiang Feng, Zongzhe Li

“…A series of experiments demonstrated that, due to these improvements, the proposed lightweight model achieved a reduction of nearly 10% in parameter size and 5% in the floating-point computational cost compared to the original YOLOv8n. …”
Get full text

LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips by Jie Zhang, Ning Chen, Mengyuan Li, Yifan Zhang, Xinyu Suo, Rong Li, Jian Liu

“…Experimental results demonstrate that LDDP-Net achieves an mIoU (mean Intersection over Union) of 90.29% on the chip dataset, with parameter numbers and FLOPs (Floating Point Operations) of 2.98 M and 2.24 G, respectively. …”
Get full text

A low functional redundancy-based network slimming method for accelerating deep neural networks by Zheng Fang, Bo Yin

“…In order to reduce the floating point operations (FLOPs) running DNNs and accelerate the inference speed, we start from the model pruning, and realize this goal by removing useless network parameters. …”
Get full text

TBF-YOLOv8n: A Lightweight Tea Bud Detection Model Based on YOLOv8n Improvements by Wenhui Fang, Weizhen Chen

“…The experimental results show that compared to the YOLOv8n model, the TBF-YOLOv8n model has a 3.7% increase in accuracy, a 1.1% increase in average accuracy, a 44.4% reduction in gigabit floating point operations (GFLOPs), and a 13.4% reduction in the total number of parameters included in the model. …”
Get full text

Improved insulator location and defect detection method based on GhostNet and YOLOv5s networks by Jianjun Huang, Xuhong Huang, Ronghao Kang, Zhihong Chen, Junhan Peng

“…First, the backbone feature extraction network of YOLOv5 was reconstructed with the lightweight GhostNet module to reduce the number of parameters and floating point operations of the model, so as to achieve the purpose of being lightweight. …”
Get full text

Neural-field-based image reconstruction for bioluminescence tomography by Xuanxuan Zhang, Xu Cao, Jiulou Zhang, Lin Zhang, Guanglei Zhang

“…Results of simulations and experiments show that the proposed NF-based method has similar performance to the photon density complement network and the two-stage network, while consuming fewer floating point operations with fewer model parameters.…”
Get full text

Leveraging transformer models to predict cognitive impairment: accuracy, efficiency, and interpretability by Kai Ma, Junzhi Zhang, Xinhang Huang, Mengyang Wang

“…Methods The Transformer integrates categorical (integer-encoded) and continuous (floating-point) data, using multi-head attention with four heads to capture complex relationships. …”
Get full text

Accelerated pseudo-transient method for elastic, viscoelastic, and coupled hydromechanical problems with applications by Y. Alkhimenkov, Y. Y. Podladchikov

“…With the advent of the memory-wall phenomenon around 2005, where memory access speed overtook floating-point operations as the bottleneck in high-performance computing, the APT method has gained prominence as a powerful tool for tackling various PDEs in geosciences. …”
Get full text

Time Complexity of Training DNNs With Parallel Computing for Wireless Communications by Pengyu Cong, Chenyang Yang, Shengqian Han, Shuangfeng Han, Xiaoyun Wang

“…As a metric of time complexity, the number of floating-point operations (FLOPs) for inference has been analyzed in the literature. …”
Get full text

FECI-RTDETR a Lightweight Unmanned Aerial Vehicle Infrared Small Target Detector Algorithm Based on RT-DETR by Renzheng Xue, Shijie Hua, Haiqiang Xu

“…Experimental results indicate that compared to RT-DETR, the FECI-RTDETR model reduces the number of parameters by 24.56% and floating-point operations by 19.12% on the HIT-UAV dataset. …”
Get full text

Textile Defect Detection Algorithm Based on the Improved YOLOv8 by Wenfei Song, Du Lang, Jiahui Zhang, Meilian Zheng, Xiaoming Li

“…The speed of textile defect detection has reached 257.38 frames per second (FPS) and the floating-point operation speed is 36.6 GFLOPS, ensuring the accuracy and speed of textile defect detection, with practical engineering application value.…”
Get full text

A novel FPGA‐Based Bi input‐reduced order extended Kalman filter for speed‐sensorless direct torque control of induction motor with constant switching frequency controller by Remzi Inan

“…The full precision single floating point numbers in the IEEE 754 standard are used during the implementation of the HIL emulator which contains closed‐loop speed‐sensorless drive system of IM on the Xilinx Virtex XC5VLX‐110T ML506 FPGA board. …”
Get full text

MD-Unet for tobacco leaf disease spot segmentation based on multi-scale residual dilated convolutions by Zili Chen, Yilong Peng, Jiadong Jiao, Aiguo Wang, Laigang Wang, Wei Lin, Yan Guo

“…Furthermore, the model parameters, floating-point operations, and inference time per single image for MD-Unet were 4.65 × 107, 2.3392 × 1011, and 65.096 ms, respectively. …”
Get full text

Progressive Bitwidth Assignment Approaches for Efficient Capsule Networks Quantization by Mohsen Raji, Amir Ghazizadeh Ahsaei, Kimia Soroush, Behnam Ghavami

“…The proposed approaches include Post-Training Quantization (PTQ) strategies that minimize the dependence on floating-point operations and incorporates layer-specific integer bit-widths based on quantization error analysis. …”
Get full text

SSMM-DS: A semantic segmentation model for mangroves based on Deeplabv3+ with swin transformer by Zhenhua Wang, Jinlong Yang, Chuansheng Dong, Xi Zhang, Congqin Yi, Jiuhu Sun

“…Using GF-1 and GF-6 images, taking mean precision (mPrecision), mean intersection over union (mIoU), floating-point operations (FLOPs), and the number of parameters (Params) as evaluation metrics, we evaluate SSMM-DS against state-of-the-art models, including FCN, PSPNet, OCRNet, uPerNet, and SegFormer. …”
Get full text

Selective state models are what you need for animal action recognition by Edoardo Fazzari, Donato Romano, Fabrizio Falchi, Cesare Stefanini

“…By transforming the state-of-the-art MSQNet model with Mamba blocks, we achieve significant reductions in computational requirements: up to 90% fewer Floating point OPerations and 78% fewer parameters compared to MSQNet. …”
Get full text

An underground coal mine multi-target detection algorithm by FAN Shoujun, CHEN Xilin, WEI Liangyue, WANG Qingyu, ZHANG Shiyuan, DONG Fei, LEI Shaohua

“…The results showed that: ① The mAP@0.5 of the FEDSC-FFBD algorithm was 97.00%, the number of model parameters was 4.22×106, and the number of floating point operations per second was 21.7×109. ② The mAP@0.5 of the FEDSC-FFBD alorithm was 3.40% higher than the YOLOv8n algorithm, and the recognition accuracy of the helmet small target was 90.90%, 11% higher than the YOLOv8n algorithm. ③ Compared with other YOLO series algorithms, the FEDSC-FFBD algorithm achieved the highest mAP@0.5, which was 3.60%, 1%, 10.50%, and 6.40% higher than YOLOv5s, YOLOv9c, YOLOv10n, and YOLOv11n algorithms, respectively. ④ The FEDSC-FFBD algorithm improved the detection accuracy of multi-class targets and reduced missed detection and false detection of small targets under conditions of uneven light intensity distribution, complex target environments, and imbalanced target scale distribution in underground coal mine. …”
Get full text

The effect of depth data and upper limb impairment on lightweight monocular RGB human pose estimation models by Gloria-Edith Boudreault-Morales, Cesar Marquez-Chin, Xilin Liu, José Zariffa

“…Evaluation metrics include Mean per Joint Position Error (MPJPE), Floating Point Operations (FLOPs) and frame rates (frames per second). …”
Get full text

Accurate Sum and Dot Product with New Instruction for High-Precision Computing on ARMv8 Processor by Kaisen Xie, Qingfeng Lu, Hao Jiang, Hongxia Wang

“…We have redesigned and implemented accurate summation and the accurate dot product. The number of floating-point operations has been reduced from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7</mn><mi>n</mi><mo>−</mo><mn>5</mn></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>10</mn><mi>n</mi><mo>−</mo><mn>5</mn></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4</mn><mi>n</mi><mo>−</mo><mn>2</mn></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7</mn><mi>n</mi><mo>−</mo><mn>2</mn></mrow></semantics></math></inline-formula>, compared with the classic compensated precision algorithms. …”
Get full text

FCM Clustering Approach Optimization Using Parallel High-Speed Intel FPGA Technology by Abedalmuhdi Almomany, Amin Jarrah, Anwar Al Assaf

“…Also, its processing power reached 89 giga floating points operations per second (GFLOPs).…”
Get full text