Transformer Architecture and Attention Mechanisms in Genome Data Analysis: A Comprehensive Review

Biology, Год журнала: 2023, Номер 12(7), С. 1033 - 1033

Опубликована: Июль 22, 2023

The emergence and rapid development of deep learning, specifically transformer-based architectures attention mechanisms, have had transformative implications across several domains, including bioinformatics genome data analysis. analogous nature sequences to language texts has enabled the application techniques that exhibited success in fields ranging from natural processing genomic data. This review provides a comprehensive analysis most recent advancements transformer mechanisms transcriptome focus this is on critical evaluation these techniques, discussing their advantages limitations context With swift pace learning methodologies, it becomes vital continually assess reflect current standing future direction research. Therefore, aims serve as timely resource for both seasoned researchers newcomers, offering panoramic view elucidating state-of-the-art applications field. Furthermore, paper serves highlight potential areas investigation by critically evaluating studies 2019 2023, thereby acting stepping-stone further research endeavors.

Язык: Английский

---

Brain tumor segmentation based on optimized convolutional neural network and improved chimp optimization algorithm

Computers in Biology and Medicine, Год журнала: 2023, Номер 168, С. 107723 - 107723

Опубликована: Ноя. 19, 2023

Язык: Английский

---

Self-attention-based generative adversarial network optimized with color harmony algorithm for brain tumor classification

Electromagnetic Biology and Medicine, Год журнала: 2024, Номер 43(1-2), С. 31 - 45

Опубликована: Фев. 18, 2024

This paper proposes a novel approach, BTC-SAGAN-CHA-MRI, for the classification of brain tumors using SAGAN optimized with Color Harmony Algorithm. Brain cancer, its high fatality rate worldwide, especially in case tumors, necessitates more accurate and efficient methods. While existing deep learning approaches tumor have been suggested, they often lack precision require substantial computational time.The proposed method begins by gathering input MR images from BRATS dataset, followed pre-processing step Mean Curvature Flow-based approach to eliminate noise. The pre-processed then undergo Improved Non-Sub sampled Shearlet Transform (INSST) extracting radiomic features. These features are fed into SAGAN, which is Algorithm categorize different types, including Gliomas, Meningioma, Pituitary tumors. innovative shows promise enhancing efficiency classification, holding potential improved diagnostic outcomes field medical imaging. accuracy acquired identification 99.29%. BTC-SAGAN-CHA-MRI technique achieves 18.29%, 14.09% 7.34% higher 67.92%,54.04%, 59.08% less Computation Time when analyzed models, like diagnosis utilizing convolutional neural network transfer (BTC-KNN-SVM-MRI); M3BTCNet: multi model categorization under metaheuristic optimization (BTC-CNN-DEMFOA-MRI), depending upon hierarchical classifier tumour (BTC-Hie DNN-MRI) respectively.

Язык: Английский

---

ETACM: an encoded-texture active contour model for image segmentation with fuzzy boundaries

Soft Computing, Год журнала: 2023, Номер unknown

Опубликована: Июль 22, 2023

Язык: Английский

---

A deep learning model for ergonomics risk assessment and sports and health monitoring in self-occluded images

Signal Image and Video Processing, Год журнала: 2023, Номер 18(2), С. 1161 - 1173

Опубликована: Окт. 29, 2023

Язык: Английский

---

PRIS: Practical robust invertible network for image steganography

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108419 - 108419

Опубликована: Апрель 11, 2024

Язык: Английский

---

Mobile robot path planning based on bi-population particle swarm optimization with random perturbation strategy

Journal of King Saud University - Computer and Information Sciences, Год журнала: 2024, Номер 36(2), С. 101974 - 101974

Опубликована: Фев. 1, 2024

Path planning for mobile robots poses a challenging optimization problem, requiring the discovery of near-optimal path within diverse constraints. Conventional particle swarm (PSO) algorithms encounter limitations in solving constrained problems, vulnerability to local optima, and premature convergence. To address these challenges, this paper proposes bi-population PSO algorithm with random perturbation strategy (BPPSO), which divides particles into two subpopulations. The first subpopulation enhances global search capabilities by considering quality optimal solution randomly selected when updating velocities. second strengthens using linear cognitive coefficient adjustment strategy. Moreover, counter tracks iteration without improvement best position. Upon reaching predefined threshold, is added positions all both subpopulations, increasing diversity enhancing ability escape optima. performance BPPSO was experimentally validated across three benchmark functions four environment models. results have demonstrated that proposed outperforms existing other established terms running time, highlighting feasibility resolving challenge robot planning.

Язык: Английский

---

Coati optimization algorithm for brain tumor identification based on MRI with utilizing phase-aware composite deep neural network

Electromagnetic Biology and Medicine, Год журнала: 2025, Номер unknown, С. 1 - 18

Опубликована: Янв. 21, 2025

Brain tumors can cause difficulties in normal brain function and are capable of developing various regions the brain. Malignant tumours develop quickly, pass through neighboring tissues, extend to further or central nervous system. In contrast, healthy typically slowly do not invade surrounding tissues. Individuals frequently struggle with sensory abnormalities, motor deficiencies affecting coordination, cognitive impairments memory focus. this research, Utilizing Phase-aware Composite Deep Neural Network Optimized Coati Algorithm for Tumor Identification Based on Magnetic resonance imaging (PACDNN-COA-BTI-MRI) is proposed. First, input images taken from tumour Dataset. To execute this, image pre-processed using Multivariate Fast Iterative Filtering (MFIF) it reduces occurrence over-fitting collected dataset; then feature extraction Self-Supervised Nonlinear Transform (SSNT) extract essential features like model, shape, intensity. Then, proposed PACDNN-COA-BTI-MRI implemented Matlab performance metrics Recall, Accuracy, F1-Score, Precision Specificity ROC analysed. Performance approach attains 16.7%, 20.6% 30.5% higher accuracy; 19.9%, 22.2% 30.1% recall 21.9% 30.8% precision when analysed existing techniques tumor identification MRI-Based Learning Approach Efficient Classification (MRI-DLA-ECBT), Detection Convolutional Methods Chosen Machine Techniques (MRI-BTD-CDMLT) Image CNN-Based Method (MRI-BTID-CNN) methods, respectively.

Язык: Английский

---

Spatial Attention Mechanism and Cascade Feature Extraction in a U-Net Model for Enhancing Breast Tumor Segmentation

Applied Sciences, Год журнала: 2023, Номер 13(15), С. 8758 - 8758

Опубликована: Июль 28, 2023

In the field of medical imaging, accurate segmentation breast tumors is a critical task for diagnosis and treatment cancer. To address challenges posed by fuzzy boundaries, vague tumor shapes, variation in size, illumination variation, we propose new approach that combines U-Net model with spatial attention mechanism. Our method utilizes cascade feature extraction technique to enhance subtle features tumors, thereby improving accuracy. addition, our incorporates mechanism enable network focus on important regions image while suppressing irrelevant areas. This combination techniques leads significant improvements accuracy, particularly challenging cases where have boundaries or shapes. We evaluate suggested Mini-MIAS dataset demonstrate state-of-the-art performance, surpassing existing methods terms sensitivity, specificity. Specifically, achieves an overall accuracy 91%, sensitivity specificity 93%, demonstrating its effectiveness accurately identifying tumors.

Язык: Английский

---

Dementia classification using a graph neural network on imaging of effective brain connectivity

Computers in Biology and Medicine, Год журнала: 2023, Номер 168, С. 107701 - 107701

Опубликована: Ноя. 15, 2023

Alzheimer's disease (AD) and Parkinson's (PD) are two of the most common forms neurodegenerative diseases. The literature suggests that effective brain connectivity (EBC) has potential to track differences between AD, PD healthy controls (HC). However, how effectively use EBC estimations for research diagnosis remains an open problem. To deal with complex networks, graph neural network (GNN) been increasingly popular in very recent years effectiveness combining GNN techniques unexplored field dementia diagnosis. In this study, a novel directed structure learning (DSL-GNN) was developed performed on imaging power spectrum density (PSD) features. comparison previous studies GNN, our proposed approach enhanced functionality processing directional information, which builds basis more efficiently performing EBC. Another contribution study is creation new framework applying univariate multivariate features simultaneously classification task. DSL-GNN validated four discrimination tasks exhibited best performance, against existing methods, highest accuracy 94.0% (AD vs. HC), 94.2% (PD 97.4% PD) 93.0% HC). word, provides robust analytical networks containing causal information implies promising conditions.

Язык: Английский

---