YOSEG Enhancing Instance Segmentation of Medical Small Targets DOI Creative Commons
Yifan Xia,

Dongqin Zhu,

Zhenao Mou

et al.

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: Dec. 19, 2023

Abstract Image segmentation stands as a pivotal pillar in the vast realm of computer vision. Nonetheless, formidable challenges endure, particularly when confronted with tasks necessitating precision delineating diminutive objects, evidenced context medical imaging for minute targets. Existing algorithms primarily cater to larger or medium-sized objects specific dimensions proportions. The persistent conundrum arises from trifecta minuscule target dimensions, feeble distinguishing features, and resultant subpar performance objects. In response these hurdles, our study introduces pioneering solution christened You only look one segment network (YOSEG), adeptly crafted tackle issues head-on. Our comprehensive investigations involve two datasets: proprietary collection comprising CT intracranial aneurysm data multiple centers publicly available CBIS-DDSM dataset, which Curated Breast Imaging Subset DDSM contains breast mass data. outcomes approach substantiate remarkable strides small object segmentation, marking significant advancement this critical field.

Language: Английский

Multi-objective RIME algorithm-based techno economic analysis for security constraints load dispatch and power flow including uncertainties model of hybrid power systems DOI Creative Commons
Sundaram B. Pandya, Kanak Kalita, Pradeep Jangir

et al.

Energy Reports, Journal Year: 2024, Volume and Issue: 11, P. 4423 - 4451

Published: April 18, 2024

In recent times, the landscape of power systems has undergone significant evolution, particularly with integration diverse renewable energy sources (RESs). This advancement presents an invaluable opportunity to enhance efficiency in modern grid, primarily by bolstering role stochastic RESs. The challenge lies optimal flow (OPF), a multifaceted and non-linear optimization that grows more complex inclusion RESs aims optimize allocation system resources minimize operational cost while maintaining stability security system. Addressing this, current study introduces innovative approach, Multi-Objective RIME (MORIME) algorithm. Drawing inspiration from physical phenomenon rime-ice, called RIME, MORIME seeks effectively tackle OPF issues. algorithm enhances solution accuracy smartly dividing non-dominated sorting crowding distance mechanism. proposed model incorporates three types RESs: solar photovoltaic, wind small-scale hydropower units. While uncertainties speed irradiation are managed through Monte Carlo simulations, small hydro unit is considered constant source. efficacy tested on IEEE 30 bus results indicate method identifies for multi-objective problem satisfying constraints, thereby proving its effectiveness superiority over MOWOA, MOGWO, MOALO, MOMRFO MOAGDE terms Hyper Volume (HV) reciprocal Pareto Sets Proximity (1/PSP) metrices. source code available at: https://github.com/kanak02/MORIME

Language: Английский

Citations

24
Automatic Generation Control of a Hybrid PV-Reheat Thermal Power System Using RIME Algorithm DOI Creative Commons
Serdar Ekinci, Özay Can, Mustafa Şinasi Ayas

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 26919 - 26930

Published: Jan. 1, 2024

This study focuses on the automatic generation control (AGC) system, which is crucial for maintaining balance between power and demand in systems. The implementation of AGC system needs to be more precise due increasing uncertainty surrounding renewable energy sources (RESs) changes demand. objective this investigate functions a two-area hybrid that combines PV with reheat thermal system. To improve performance, we utilize proportional-integral (PI) controller. We utilized recently developed optimization method, RIME, tuning controller parameters. technique has not been studied before processes. Furthermore, procedure utilizes modified version integral time-multiplied absolute error (ITAE) function. compares performance RIME-tuned PI under various scenarios, including load, load variations both areas, robustness considerations, well-known techniques literature, such as black widow algorithm (BWOA), salp swarm (SSA), shuffled frog leaping (SFLA), firefly (FA) genetic (GA). Our comparative demonstrates proposed outperforms state-of-the-art approaches terms overshoot values damping durations frequency tie-line changes. provides valuable information effectiveness controlling processes complex

Language: Английский

Citations

16
Hierarchical RIME algorithm with multiple search preferences for extreme learning machine training DOI Creative Commons
Rui Zhong, Chao Zhang, Jun Yu

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 110, P. 77 - 98

Published: Oct. 7, 2024

Language: Английский

Citations

7
Multi-strategy RIME optimization algorithm for feature selection of network intrusion detection DOI
Lan Wang,

Jialing Xu,

Liyun Jia

et al.

Computers & Security, Journal Year: 2025, Volume and Issue: unknown, P. 104393 - 104393

Published: Feb. 1, 2025

Language: Английский

Citations

0
Prediction control of CO2 capture in coal‐fired power plants based on ERIME‐optimized CNN‐LSTM‐multi‐head‐attention DOI Open Access
Minan Tang, C.H. Kamesh Rao, Tong Yang

et al.

The Canadian Journal of Chemical Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 19, 2025

Abstract Predicting CO 2 concentration in post‐combustion carbon capture (PCC) systems is challenging due to complex operating conditions and multivariate interactions. This study proposes an enhanced RIME algorithm (ERIME) optimization‐based convolutional neural network (CNN)‐long short‐term memory (LSTM)‐multi‐head‐attention (ECLMA) model improve prediction accuracy. The local outlier factor (LOF) was used remove noise from the data, while mutual information (MI) determined time lags, smoothed clipped absolute deviation (SCAD) method optimized feature selection. CNN‐LSTM‐multi‐head‐attention extracts meaningful features series parameters are using ERIME algorithm. Using a simulated dataset 600 MW supercritical coal‐fired power plant, results showed that after LOF removal, root mean square error (RMSE) (MAE) improved by 10%–13%. Post‐MI delay reconstruction reduced RMSE 0.00999 MAE 11.6937, with R rising 0.9929. After variable selection, further 0.00907 9.9697, increasing 0.9983. optimization, ECLMA outperformed traditional models, reducing up 91.55% 84.94%, respectively, compared CNN, 85.91% 69.47%, LSTM. These confirm model's superior accuracy stability.

Language: Английский

Citations

0
IRIME: Mitigating exploitation-exploration imbalance in RIME optimization for feature selection DOI Creative Commons

Jinpeng Huang,

Yi Chen, Ali Asghar Heidari

et al.

iScience, Journal Year: 2024, Volume and Issue: 27(8), P. 110561 - 110561

Published: July 22, 2024

Rime optimization algorithm (RIME) encounters issues such as an imbalance between exploitation and exploration, susceptibility to local optima, low convergence accuracy when handling problems. This paper introduces a variant of RIME called IRIME address these drawbacks. integrates the soft besiege (SB) composite mutation strategy (CMS) restart (RS). To comprehensively validate IRIME's performance, IEEE CEC 2017 benchmark tests were conducted, comparing it against many advanced algorithms. The results indicate that performance is best. In addition, applying in four engineering problems reflects solving practical Finally, proposes binary version, bIRIME, can be applied feature selection bIRIMR performs well on 12 low-dimensional datasets 24 high-dimensional datasets. It outperforms other algorithms terms number subsets classification accuracy. conclusion, bIRIME has great potential selection.

Language: Английский

Citations

4
A fault identification method for cutting head of the roadheader based on parameter optimization VMD and RCMFDE DOI
Changpeng Li, Tianbing Ma, Rui Shi

et al.

Signal Image and Video Processing, Journal Year: 2025, Volume and Issue: 19(4)

Published: Feb. 21, 2025

Language: Английский

Citations

0
TERIME: An Improved RIME Algorithm With Enhanced Exploration and Exploitation for Robust Parameter Extraction of Photovoltaic Models DOI
Shi-Shun Chen, Yutong Jiang, Wenbin Chen

et al.

Journal of Bionic Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 9, 2025

Language: Английский

Citations

0
MWD Gyroscope Error Compensation Based on Equivalent Reverse Rotation DOI
Jinxian Yang, Saifei Wang

IEEE Sensors Journal, Journal Year: 2024, Volume and Issue: 24(9), P. 15588 - 15597

Published: March 18, 2024

Rotational modulation technology has been successfully applied in the field of aerospace and navigation. However, size measurements while drilling (MWD) is limited by environment rotation cannot be achieved adding a rotating mechanism. To improve attitude accuracy drilling, this article proposes method for identifying equivalent reverse rotary gyroscope error parameters based on frost ice optimizer (RFIO). First, inertial navigation analyzed. The objective function constructed using error. Then, acceleration, angular velocity, magnetic strength at stopping are used to construct constraints function. Furthermore, an RFIO proposed inverse property. solve under constraints. A dynamic upper lower bound strategy (DULBS) function's solution speed historical values, number iterations adaptive T-distribution, Lévy flight. In addition, rotational wandering (RWS) distance between current value optimal value. Finally, experimental results show that can accurately identify reverse-rotating three angles.

Language: Английский

Citations

2
A Novel Machine Learning Model for Efficacy Prediction of Immunotherapy-Chemotherapy in NSCLC Based on CT Radiomics DOI
Chengye Li, Zhifeng Zhou,

Lingxian Hou

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 178, P. 108638 - 108638

Published: May 21, 2024

Language: Английский

Citations

2