Classification of breast cancer using a manta-ray foraging optimized transfer learning framework DOI Creative Commons
Nadiah A. Baghdadi, Amer Malki, Hossam Magdy Balaha

и другие.

PeerJ Computer Science, Год журнала: 2022, Номер 8, С. e1054 - e1054

Опубликована: Авг. 8, 2022

Due to its high prevalence and wide dissemination, breast cancer is a particularly dangerous disease. Breast survival chances can be improved by early detection diagnosis. For medical image analyzers, diagnosing tough, time-consuming, routine, repetitive. Medical analysis could useful method for detecting such Recently, artificial intelligence technology has been utilized help radiologists identify more rapidly reliably. Convolutional neural networks, among other technologies, are promising recognition classification tools. This study proposes framework automatic reliable based on histological ultrasound data. The system built CNN employs transfer learning metaheuristic optimization. Manta Ray Foraging Optimization (MRFO) approach deployed improve the framework's adaptability. Using Cancer Dataset (two classes) Ultrasound (three-classes), eight modern pre-trained architectures examined apply technique. uses MRFO performance of optimizing their hyperparameters. Extensive experiments have recorded parameters, including accuracy, AUC, precision, F1-score, sensitivity, dice, recall, IoU, cosine similarity. proposed scored 97.73% histopathological data 99.01% in terms accuracy. experimental results show that superior state-of-the-art approaches literature review.

Язык: Английский

Nature-inspired optimization algorithms and their significance in multi-thresholding image segmentation: an inclusive review DOI Open Access
Rebika Rai, Arunita Das, Krishna Gopal Dhal

и другие.

Evolving Systems, Год журнала: 2022, Номер 13(6), С. 889 - 945

Опубликована: Фев. 21, 2022

Язык: Английский

Процитировано

48
Improved Dwarf Mongoose Optimization for Constrained Engineering Design Problems DOI Open Access
Jeffrey O. Agushaka, Absalom E. Ezugwu,

Oyelade N. Olaide

и другие.

Journal of Bionic Engineering, Год журнала: 2022, Номер 20(3), С. 1263 - 1295

Опубликована: Дек. 13, 2022

Язык: Английский

Процитировано

45
Addressing Internet of Things security by enhanced sine cosine metaheuristics tuned hybrid machine learning model and results interpretation based on SHAP approach DOI Creative Commons
Miloš Dobrojević, Miodrag Živković, Amit Chhabra

и другие.

PeerJ Computer Science, Год журнала: 2023, Номер 9, С. e1405 - e1405

Опубликована: Июнь 30, 2023

An ever increasing number of electronic devices integrated into the Internet Things (IoT) generates vast amounts data, which gets transported via network and stored for further analysis. However, besides undisputed advantages this technology, it also brings risks unauthorized access data compromise, situations where machine learning (ML) artificial intelligence (AI) can help with detection potential threats, intrusions automation diagnostic process. The effectiveness applied algorithms largely depends on previously performed optimization, i.e., predetermined values hyperparameters training conducted to achieve desired result. Therefore, address very important issue IoT security, article proposes an AI framework based simple convolutional neural (CNN) extreme (ELM) tuned by modified sine cosine algorithm (SCA). Not withstanding that many methods addressing security issues have been developed, there is always a possibility improvements proposed research tried fill in gap. introduced was evaluated two ToN intrusion datasets, consist traffic generated Windows 7 10 environments. analysis results suggests model achieved superior level classification performance observed datasets. Additionally, conducting rigid statistical tests, best derived interpreted SHapley Additive exPlanations (SHAP) findings be used experts enhance systems.

Язык: Английский

Процитировано

42
Feature Extraction Using a Residual Deep Convolutional Neural Network (ResNet-152) and Optimized Feature Dimension Reduction for MRI Brain Tumor Classification DOI Creative Commons
Suganya Athisayamani,

Robert Singh Antonyswamy,

S. Velliangiri

и другие.

Diagnostics, Год журнала: 2023, Номер 13(4), С. 668 - 668

Опубликована: Фев. 10, 2023

One of the top causes mortality in people globally is a brain tumor. Today, biopsy regarded as cornerstone cancer diagnosis. However, it faces difficulties, including low sensitivity, hazards during treatment, and protracted waiting period for findings. In this context, developing non-invasive computational methods identifying treating cancers crucial. The classification tumors obtained from an MRI crucial making variety medical diagnoses. analysis typically requires much time. primary challenge that tissues are comparable. Numerous scientists have created new techniques categorizing cancers. due to their limitations, majority them eventually fail. work presents novel way classifying multiple types tumors. This also introduces segmentation algorithm known Canny Mayfly. Enhanced chimpanzee optimization (EChOA) used select features by minimizing dimension retrieved features. ResNet-152 softmax classifier then perform feature process. Python carry out proposed method on Figshare dataset. accuracy, specificity, sensitivity system just few characteristics evaluate its overall performance. According final evaluation results, our strategy outperformed, with accuracy 98.85%.

Язык: Английский

Процитировано

39
Marine Predators Algorithm: A Review DOI Open Access
Mohammed Azmi Al‐Betar, Mohammed A. Awadallah, Sharif Naser Makhadmeh

и другие.

Archives of Computational Methods in Engineering, Год журнала: 2023, Номер 30(5), С. 3405 - 3435

Опубликована: Апрель 19, 2023

Язык: Английский

Процитировано

36
Recent advances in deep learning models: a systematic literature review DOI
Ruchika Malhotra, Priya Singh

Multimedia Tools and Applications, Год журнала: 2023, Номер 82(29), С. 44977 - 45060

Опубликована: Апрель 25, 2023

Язык: Английский

Процитировано

28
Optimization of CNN using modified Honey Badger Algorithm for Sleep Apnea detection DOI
Ammar Kamal Abasi, Moayad Aloqaily, Mohsen Guizani

и другие.

Expert Systems with Applications, Год журнала: 2023, Номер 229, С. 120484 - 120484

Опубликована: Май 20, 2023

Язык: Английский

Процитировано

27
Enhancing Robot Path Planning through a Twin-Reinforced Chimp Optimization Algorithm and Evolutionary Programming Algorithm DOI Creative Commons
Yang Zhang,

Hu Zhang

IEEE Access, Год журнала: 2023, Номер unknown, С. 1 - 1

Опубликована: Ноя. 30, 2023

The importance of efficient path planning (PP) cannot be overstated in the domain robots, as it involves utilization intelligent algorithms to determine optimal trajectory for robot navigate between two given points.The main target PP is potential trajectories operating a complex environment containing various obstacles.The implementation these movements should facilitate traversing without encountering any collisions, starting from its initial location and reaching intended destination.In order address challenges associated with PP, this study applies chimp optimization algorithm (CHOA) local searching (LS) technique evolutionary programming (EPA) enhance route discovered via collection LSs.In CHOA's tendency converge minima, new updating called twin-reinforced (TR) developed.In assess effectiveness TRCHOA, we conducted comparative analysis other widely used meta-heuristic that are typically employed solving problems.Additionally, included conventional probabilistic roadmap method (PRM) our evaluation.We evaluated performances on standardized set benchmark problems.Our findings indicate TRCHOA outperforms terms performance.The evaluation encompasses several key criteria, namely length, consistency scheduled paths, time complexity, rate success.The experiments provide evidence statistically significant value enhancements obtained through proposed method.The derived compelling capacity accurately most within specified test map.

Язык: Английский

Процитировано

25
Enhancing solar photovoltaic energy production prediction using diverse machine learning models tuned with the chimp optimization algorithm DOI Creative Commons
Sameer Al‐Dahidi, Mohammad Alrbai, Hussein Alahmer

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Авг. 10, 2024

Solar photovoltaic (PV) systems, integral for sustainable energy, face challenges in forecasting due to the unpredictable nature of environmental factors influencing energy output. This study explores five distinct machine learning (ML) models which are built and compared predict production based on four independent weather variables: wind speed, relative humidity, ambient temperature, solar irradiation. The evaluated include multiple linear regression (MLR), decision tree (DTR), random forest (RFR), support vector (SVR), multi-layer perceptron (MLP). These were hyperparameter tuned using chimp optimization algorithm (ChOA) a performance appraisal. subsequently validated data from 264 kWp PV system, installed at Applied Science University (ASU) Amman, Jordan. Of all 5 models, MLP shows best root mean square error (RMSE), with corresponding value 0.503, followed by absolute (MAE) 0.397 coefficient determination (R

Язык: Английский

Процитировано

14
Adapting transfer learning models to dataset through pruning and Avg-TopK pooling DOI Creative Commons
Cüneyt Özdemir

Neural Computing and Applications, Год журнала: 2024, Номер 36(11), С. 6257 - 6270

Опубликована: Фев. 19, 2024

Abstract This study focuses on efficiently adapting transfer learning models to address the challenges of creating customized deep for specific datasets. Designing a model from scratch can be time-consuming and complex due factors like complexity, size, dataset structure. To overcome these obstacles, novel approach is proposed using models. The method involves identifying relevant layers in removing unnecessary ones layer-based variance pruning technique. results creation new with improved computational efficiency classification performance. By streamlining through pruning, achieves enhanced accuracy faster computation. Experiments were conducted COVID-19 well-known models, including InceptionV3, ResNet50V2, DenseNet201, VGG16, Xception validate approach. Among variance-based layer technique was applied InceptionV3 yielding best results. When pruned combined pooling layer, Avg-TopK, achieved an outstanding image 99.3%. Comparisons previous literature studies indicate that outperforms existing methods, showcasing state-of-the-art high-performance provides great potential diagnosing monitoring disease progression, especially hardware-limited devices. leveraging efficient techniques, presents promising strategy tackling custom design, leading exceptional such as segmentation tasks. methodology holds yield outcomes across spectrum tasks, encompassing disciplines segmentation.

Язык: Английский

Процитировано

11