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

Chaotic opposition learning with mirror reflection and worst individual disturbance grey wolf optimizer for continuous global numerical optimization DOI Creative Commons
Oluwatayomi Rereloluwa Adegboye, Afi Kekeli Feda, Opeoluwa Seun Ojekemi

и другие.

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

Опубликована: Фев. 26, 2024

The effective meta-heuristic technique known as the grey wolf optimizer (GWO) has shown its proficiency. However, due to reliance on alpha for guiding position updates of search agents, risk being trapped in a local optimal solution is notable. Furthermore, during stagnation, convergence other wolves towards this results lack diversity within population. Hence, research introduces an enhanced version GWO algorithm designed tackle numerical optimization challenges. incorporates innovative approaches such Chaotic Opposition Learning (COL), Mirror Reflection Strategy (MRS), and Worst Individual Disturbance (WID), it's called CMWGWO. MRS, particular, empowers certain extend their exploration range, thus enhancing global capability. By employing COL, diversification intensified, leading reduced improved precision, overall boost accuracy. integration WID fosters more information exchange between least most successful wolves, facilitating exit from optima significantly potential. To validate superiority CMWGWO, comprehensive evaluation conducted. A wide array 23 benchmark functions, spanning dimensions 30 500, ten CEC19 three engineering problems are used experimentation. empirical findings vividly demonstrate that CMWGWO surpasses original terms accuracy robust capabilities.

Язык: Английский

Процитировано

11
AttGRU-HMSI: enhancing heart disease diagnosis using hybrid deep learning approach DOI Creative Commons

G. M. Narasimha Rao,

Dharavath Ramesh, Vandana Sharma

и другие.

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

Опубликована: Апрель 3, 2024

Abstract Heart disease is a major global cause of mortality and public health problem for large number individuals. A issue raised by regular clinical data analysis the recognition cardiovascular illnesses, including heart attacks coronary artery disease, even though early identification can save many lives. Accurate forecasting decision assistance may be achieved in an effective manner with machine learning (ML). Big Data, or vast amounts generated sector, assist models used to make diagnostic choices revealing hidden information intricate patterns. This paper uses hybrid deep algorithm describe visualization approach detection. The proposed intended use big systems, such as Apache Hadoop. An extensive medical collection first subjected improved k-means clustering (IKC) method remove outliers, remaining class distribution then balanced using synthetic minority over-sampling technique (SMOTE). next step forecast bio-inspired mutation-based swarm intelligence (HMSI) attention-based gated recurrent unit network (AttGRU) model after recursive feature elimination (RFE) has determined which features are most important. In our implementation, we compare four algorithms: SAE + ANN (sparse autoencoder artificial neural network), LR (logistic regression), KNN (K-nearest neighbour), naïve Bayes. experiment results indicate that 95.42% accuracy rate model's suggested prediction attained, effectively outperforms overcomes prescribed research gap mentioned related work.

Язык: Английский

Процитировано

10
IoT Workflow Scheduling Using Intelligent Arithmetic Optimization Algorithm in Fog Computing DOI Creative Commons
Mohamed Abd Elaziz, Laith Abualigah, Rehab Ali Ibrahim

и другие.

Computational Intelligence and Neuroscience, Год журнала: 2021, Номер 2021(1)

Опубликована: Янв. 1, 2021

Instead of the cloud, Internet things (IoT) activities are offloaded into fog computing to boost quality services (QoSs) needed by many applications. However, availability continuous resources on servers is one restrictions for IoT applications since transmitting large amount data generated using devices would create network traffic and cause an increase in computational overhead. Therefore, task scheduling main problem that needs be solved efficiently. This study proposes energy‐aware model enhanced arithmetic optimization algorithm (AOA) method called AOAM, which addresses computing’s job maximize users’ QoSs maximizing makespan measure. In proposed we conventional AOA searchability marine predators (MPA) search operators address diversity used solutions local optimum problems. The AOAM validated several parameters, including various clients, centers, hosts, virtual machines, tasks, standard evaluation measures, energy makespan. obtained results compared with other state‐of‐the‐art methods; it showed promising effectively comparative methods.

Язык: Английский

Процитировано

56
A boosted chimp optimizer for numerical and engineering design optimization challenges DOI Open Access

Ch. Leela Kumari,

Vikram Kumar Kamboj,

S. K. Bath

и другие.

Engineering With Computers, Год журнала: 2022, Номер 39(4), С. 2463 - 2514

Опубликована: Март 24, 2022

Язык: Английский

Процитировано

34
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

Процитировано

33