An Efficient Cancer Classification Model Using Deep Neural Network with Arithmetic Optimization Algorithm-Based Optimal Gene Selection DOI

Shyamala Gowri B,

Sanjay Nair,

K. P. Sanal Kumar

et al.

2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Journal Year: 2023, Volume and Issue: unknown, P. 946 - 953

Published: Nov. 22, 2023

Cancers are the most disastrous and inevitable ailment that occurs in individuals. Due to hazardous effects of cancer, people get at death very early age. In today's date, cancer is categorized into many types, which affected by external internal parts body. general, cancers caused growth abnormal tissues where originates it gradually spread other parts. Therefore, medical industry struggles detect different types disorders without any loss people. Hence, automated detection system implemented predict its stages prevent gets worsening. Normally, collection individual data another challenging concern. Several methods have been yet they exist with constraints provide better results. Machine learning models also used, but does not tackle big process fail obtain relevant features. Henceforth, deep model has emerged for various processes like prediction, classification, recognition. So, a new improved classification framework classifying executed this paper. At first, gathered from benchmark database. From data, genes optimally selected using an Improved Arithmetic Optimization Algorithm (IAOA). Then, chosen given as input "Optimized Deep Neural Network (ODNN)" classification. The DNN optimized AOA. DNN, classified output obtained. Various experimentations carried out contrasting developed optimization algorithm enhanced verify efficient working suggested model. Throughout result analysis, accuracy precision rate designed method 93.42% 9363% all datasets.

Language: Английский

Optimizing energy Dynamics: A comprehensive analysis of hybrid energy storage systems integrating battery banks and supercapacitors DOI
Aykut Fatih Güven, Almoataz Y. Abdelaziz, Mohamed Mahmoud Samy

et al.

Energy Conversion and Management, Journal Year: 2024, Volume and Issue: 312, P. 118560 - 118560

Published: May 20, 2024

Language: Английский

Citations

62
A Literature Review and Critical Analysis of Metaheuristics Recently Developed DOI Creative Commons
Luis Velasco, Héctor Guerrero, Antonio Hospitaler

et al.

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 31(1), P. 125 - 146

Published: July 22, 2023

Abstract Metaheuristic algorithms have applicability in various fields where it is necessary to solve optimization problems. It has been a common practice this field for several years propose new that take inspiration from natural and physical processes. The exponential increase of controversial issue researchers criticized. However, their efforts point out multiple issues involved these practices insufficient since the number existing metaheuristics continues yearly. To know current state problem, paper analyzes sample 111 recent studies so-called new, hybrid, or improved are proposed. Throughout document, topics reviewed will be addressed general perspective specific aspects. Among study’s findings, observed only 43% analyzed papers make some mention No Free Lunch (NFL) theorem, being significant result ignored by most presented. Of studies, 65% present an version established algorithm, which reveals trend no longer based on analogies. Additionally, compilation solutions found engineering problems commonly used verify performance state-of-the-art demonstrate with low level innovation can erroneously considered as frameworks years, known Black Widow Optimization Coral Reef analyzed. study its components they do not any innovation. Instead, just deficient mixtures different evolutionary operators. This applies extension recently proposed versions.

Language: Английский

Citations

47
Gorilla optimization algorithm combining sine cosine and cauchy variations and its engineering applications DOI Creative Commons
Shuxin Wang, Li Cao,

Yaodan Chen

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: March 30, 2024

Abstract To address the issues of lacking ability, loss population diversity, and tendency to fall into local extreme value in later stage optimization searching, resulting slow convergence lack exploration ability artificial gorilla troops optimizer algorithm (AGTO), this paper proposes a search that integrates positive cosine Cauchy's variance (SCAGTO). Firstly, is initialized using refractive reverse learning mechanism increase species diversity. A strategy nonlinearly decreasing weight factors are introduced finder position update coordinate global algorithm. The follower updated by introducing Cauchy variation perturb optimal solution, thereby improving algorithm's obtain solution. SCAGTO evaluated 30 classical test functions Test Functions 2018 terms speed, accuracy, average absolute error, other indexes, two engineering design problems, namely, pressure vessel problem welded beam problem, for verification. experimental results demonstrate improved significantly enhances speed exhibits good robustness. demonstrates certain solution advantages optimizing verifying superior practicality

Language: Английский

Citations

18
ReTrackVLM: Transformer-Enhanced Multi-Object Tracking with Cross-Modal Embeddings and Zero-Shot Re-Identification Integration DOI Creative Commons
Ertuğrul Bayraktar

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 1907 - 1907

Published: Feb. 12, 2025

Multi-object tracking (MOT) is an important task in computer vision, particularly complex, dynamic environments with crowded scenes and frequent occlusions. Traditional methods often suffer from identity switches (IDSws) fragmented tracks (FMs), which limits their ability to maintain consistent object trajectories. In this paper, we present a novel framework, called ReTrackVLM, that integrates multimodal embedding visual language model (VLM) zero-shot re-identification (ReID) module enhance accuracy robustness. ReTrackVLM leverages the rich semantic information VLMs distinguish objects more effectively, even under challenging conditions, while ReID mechanism enables robust matching without additional training. The system also includes motion prediction module, powered by Kalman filtering, handle occlusions abrupt movements. We evaluated on several widely used MOT benchmarks, including MOT15, MOT16, MOT17, MOT20, DanceTrack. Our approach achieves state-of-the-art results, improvements of 1.5% MOTA reduction 10. 3% IDSws compared existing methods. excels precision, recording 91.7% precision MOT17. However, extremely dense scenes, framework faces challenges slight increases IDSws. Despite computational overhead using VLMs, demonstrates track effectively diverse scenarios.

Language: Английский

Citations

1
Chinese Pangolin Optimizer: a novel bio-inspired metaheuristic for solving optimization problems DOI
Zhiqing Guo, Guangwei Liu, Feng Jiang

et al.

The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(4)

Published: Feb. 17, 2025

Language: Английский

Citations

1
Investigation of Recent Metaheuristics Based Selective Harmonic Elimination Problem for Different Levels of Multilevel Inverters DOI Open Access
Satılmış Ürgün, Halil Yiğit, Seyedali Mirjalili

et al.

Electronics, Journal Year: 2023, Volume and Issue: 12(4), P. 1058 - 1058

Published: Feb. 20, 2023

Multilevel inverters (MLI) are popular in high-power applications. MLIs generally configured to have switches reduced by switching techniques that eliminate low-order harmonics. The selective harmonic elimination (SHE) method, which significantly reduces the number of switching, determines optimal moments obtain desired output voltage and eliminates components. To solve SHE problem, classical methods primarily employed. disadvantages such high probability trapping locally solutions their dependence on initial controlling parameters. One solution overcome this problem is use metaheuristic algorithms. In study, firstly, 22 algorithms with different sources inspiration were used at levels MLIs, performances extensively analyzed. reveal method offers best solution, these first applied an 11-level MLI circuit, six determined as a result performance analysis. As evaluation, outstanding SPBO, BMO, GA, GWO, MFO, SPSA. application superior 7-, 11-, 15-, 19-level according IEEE 519—2014 standard, it has been shown BMO outperforms 7-level MLI, GA SPBO 15- terms THD, while quality, SPSA 15-level come forward.

Language: Английский

Citations

14
Optimization of Sliding Mode and Back-Stepping Controllers for AMB Systems Using Gorilla Troops Algorithm DOI Creative Commons
Huthaifa Al-Khazraji,

Rash M. Naji,

Mustafa K. Khashan

et al.

Journal Européen des Systèmes Automatisés, Journal Year: 2024, Volume and Issue: 57(2), P. 417 - 424

Published: April 28, 2024

An active magnetic bearing (AMB) is a frictionless used in high-speed motors and other electromechanical products.Due to its open loop instability, utilization of controller essential stabilize the system.In this paper, comparative study between sliding mode control (SMC) back-stepping (BSC) are presented for AMB systems.These two techniques have been applied various dynamical systems obtain stable systems.On basis avoiding chattering SMC design, power rate reaching introduced design action SMC.In terms BSC Lyapunov-stability theorem utilized derive low controller.A gorilla troops optimization (GTO) has tune adjustable parameters proposed controllers.According computer simulation based on MATLAB software, results indicate superior performance improved system response as compared controller.In addition, strategy good disturbance rejection capability strategy.

Language: Английский

Citations

5
An in-depth survey of the artificial gorilla troops optimizer: outcomes, variations, and applications DOI Creative Commons
Abdelazim G. Hussien, Anas Bouaouda, Abdullah Alzaqebah

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(9)

Published: Aug. 12, 2024

Abstract A recently developed algorithm inspired by natural processes, known as the Artificial Gorilla Troops Optimizer (GTO), boasts a straightforward structure, unique stabilizing features, and notably high effectiveness. Its primary objective is to efficiently find solutions for wide array of challenges, whether they involve constraints or not. The GTO takes its inspiration from behavior in world. To emulate impact gorillas at each stage search process, employs flexible weighting mechanism rooted concept. exceptional qualities, including independence derivatives, lack parameters, user-friendliness, adaptability, simplicity, have resulted rapid adoption addressing various optimization challenges. This review dedicated examination discussion foundational research that forms basis GTO. It delves into evolution this algorithm, drawing insights 112 studies highlight Additionally, it explores proposed enhancements GTO’s behavior, with specific focus on aligning geometry area real-world problems. also introduces solver, providing details about identification organization, demonstrates application scenarios. Furthermore, provides critical assessment convergence while limitation In conclusion, summarizes key findings study suggests potential avenues future advancements adaptations related

Language: Английский

Citations

5
Improved snake optimizer based on forced switching mechanism and variable spiral search for practical applications problems DOI
Yan‐Feng Wang, Baohua Xin, Zicheng Wang

et al.

Soft Computing, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 7, 2025

Language: Английский

Citations

0
NSGTO‐LSTM: Niche‐strategy‐based gorilla troops optimization and long short‐term memory network intrusion detection model DOI Creative Commons

Saritha Anchuri,

Arvind Ganesh,

Prathusha Perugu

et al.

ETRI Journal, Journal Year: 2025, Volume and Issue: unknown

Published: March 17, 2025

Abstract In recent decades, the rapid growth of Internet Things (IoT) has highlighted several network security problems. this study, an efficient intrusion detection (ID) system is implemented by using both machine learning and data mining concepts for detecting patterns. During initial phase, are collected from NSL‐KDD University New South Wales‐Network Based 15 (UNSW‐NB15) datasets. The then normalized/scaled employing a standard scaler technique. Next, informative feature values selected proposed optimization algorithm—that is, Niche‐Strategy‐based Gorilla Troops Optimization (NSGTO) algorithm. Finally, these transferred to Long Short‐Term Memory (LSTM) model classify types attacks on comparison existing ID systems, based NSGTO‐LSTM obtains classification accuracy 99.98% 99.90%

Language: Английский

Citations

0