Spatio-temporal air quality analysis and PM2.5 prediction over Hyderabad City, India using artificial intelligence techniques

Ecological Informatics, Journal Year: 2023, Volume and Issue: 76, P. 102067 - 102067

Published: March 13, 2023

Language: Английский

---

Ten years of generative adversarial nets (GANs): a survey of the state-of-the-art

Machine Learning Science and Technology, Journal Year: 2024, Volume and Issue: 5(1), P. 011001 - 011001

Published: Jan. 17, 2024

Abstract Generative adversarial networks (GANs) have rapidly emerged as powerful tools for generating realistic and diverse data across various domains, including computer vision other applied areas, since their inception in 2014. Consisting of a discriminative network generative engaged minimax game, GANs revolutionized the field modeling. In February 2018, GAN secured leading spot on ‘Top Ten Global Breakthrough Technologies List’ issued by Massachusetts Science Technology Review. Over years, numerous advancements been proposed, to rich array variants, such conditional GAN, Wasserstein cycle-consistent StyleGAN, among many others. This survey aims provide general overview GANs, summarizing latent architecture, validation metrics, application areas most widely recognized variants. We also delve into recent theoretical developments, exploring profound connection between principle underlying Jensen–Shannon divergence while discussing optimality characteristics framework. The efficiency variants model architectures will be evaluated along with training obstacles well solutions. addition, detailed discussion provided, examining integration newly developed deep learning frameworks transformers, physics-informed neural networks, large language models, diffusion models. Finally, we reveal several issues future research outlines this field.

Language: Английский

---

Four-way classification of Alzheimer’s disease using deep Siamese convolutional neural network with triplet-loss function

Brain Informatics, Journal Year: 2023, Volume and Issue: 10(1)

Published: Feb. 17, 2023

Alzheimer's disease (AD) is a neurodegenerative that causes irreversible damage to several brain regions, including the hippocampus causing impairment in cognition, function, and behaviour. Early diagnosis of will reduce suffering patients their family members. Towards this aim, paper, we propose Siamese Convolutional Neural Network (SCNN) architecture employs triplet-loss function for representation input MRI images as k-dimensional embeddings. We used both pre-trained non-pretrained CNNs transform into embedding space. These embeddings are subsequently 4-way classification disease. The model efficacy was tested using ADNI OASIS datasets which produced an accuracy 91.83% 93.85%, respectively. Furthermore, obtained results compared with similar methods proposed literature.

Language: Английский

---

Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review

Cognitive Computation, Journal Year: 2023, Volume and Issue: 16(1), P. 1 - 44

Published: Nov. 13, 2023

Abstract The unprecedented growth of computational capabilities in recent years has allowed Artificial Intelligence (AI) models to be developed for medical applications with remarkable results. However, a large number Computer Aided Diagnosis (CAD) methods powered by AI have limited acceptance and adoption the domain due typical blackbox nature these models. Therefore, facilitate among practitioners, models' predictions must explainable interpretable. emerging field (XAI) aims justify trustworthiness predictions. This work presents systematic review literature reporting Alzheimer's disease (AD) detection using XAI that were communicated during last decade. Research questions carefully formulated categorise into different conceptual approaches (e.g., Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, Global, Local etc.) frameworks (Local Interpretable Model-Agnostic Explanation or LIME, SHapley Additive exPlanations SHAP, Gradient-weighted Class Activation Mapping GradCAM, Layer-wise Relevance Propagation LRP, XAI. categorisation provides broad coverage interpretation spectrum from intrinsic Ante-hoc models) complex patterns Post-hoc taking local explanations global scope. Additionally, forms interpretations providing in-depth insight factors support clinical diagnosis AD are also discussed. Finally, limitations, needs open challenges research outlined possible prospects their usage detection.

Language: Английский

---

Revolutionizing heart disease prediction with quantum-enhanced machine learning

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

Published: March 29, 2024

Abstract The recent developments in quantum technology have opened up new opportunities for machine learning algorithms to assist the healthcare industry diagnosing complex health disorders, such as heart disease. In this work, we summarize effectiveness of QuEML disease prediction. To evaluate performance against traditional algorithms, Kaggle dataset was used which contains 1190 samples out 53% are labeled positive and rest 47% negative samples. evaluated terms accuracy, precision, recall, specificity, F1 score, training time algorithms. From experimental results, it has been observed that proposed approaches predicted around 50.03% an average 44.65% whereas could predict 49.78% 44.31% negative. Furthermore, computational complexity measured consumed 670 µs its consume 862.5 training. Hence, QuEL found be a promising approach prediction with accuracy rate 0.6% higher 192.5 faster than approaches.

Language: Английский

---

Optimizing Cancer Treatment: Exploring the Role of AI in Radioimmunotherapy

Diagnostics, Journal Year: 2025, Volume and Issue: 15(3), P. 397 - 397

Published: Feb. 6, 2025

Radioimmunotherapy (RIT) is a novel cancer treatment that combines radiotherapy and immunotherapy to precisely target tumor antigens using monoclonal antibodies conjugated with radioactive isotopes. This approach offers personalized, systemic, durable treatment, making it effective in cancers resistant conventional therapies. Advances artificial intelligence (AI) present opportunities enhance RIT by improving precision, efficiency, personalization. AI plays critical role patient selection, planning, dosimetry, response assessment, while also contributing drug design classification. review explores the integration of into RIT, emphasizing its potential optimize entire process advance personalized care.

Language: Английский

---

Performance Analysis of Machine Learning Approaches in Stroke Prediction

2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Journal Year: 2020, Volume and Issue: unknown, P. 1464 - 1469

Published: Nov. 5, 2020

Most of strokes will occur due to an unexpected obstruction courses by prompting both the brain and heart. Early awareness for different warning signs stroke can minimize stroke. This research work proposes early prediction diseases using machine learning approaches with occurrence hypertension, body mass index level, heart disease, average glucose smoking status, previous age. Using these high features attributes, ten classifiers have been trained, they are Logistics Regression, Stochastic Gradient Descent, Decision Tree Classifier, AdaBoost Gaussian Quadratic Discriminant Analysis, Multi layer Perceptron KNeighbors Boosting XGBoost Classifier predicting Afterwards, results base aggregated weighted voting approach reach highest accuracy. Moreover, proposed study has achieved accuracy 97%, where classifier performs better than classifiers. model gives best prediction. The area under curve value is also high. False positive rate false negative lowest compared others. As a result, almost perfect that be used physicians patients prescribe detect potential

Language: Английский

---

Social Group Optimization–Assisted Kapur’s Entropy and Morphological Segmentation for Automated Detection of COVID-19 Infection from Computed Tomography Images

Cognitive Computation, Journal Year: 2020, Volume and Issue: 12(5), P. 1011 - 1023

Published: Aug. 15, 2020

Abstract The coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared global pandemic. Due to its infection rate and severity, it emerged as one of the major threats current generation. To support combat against disease, this research aims propose machine learning–based pipeline detect COVID-19 using lung computed tomography scan images (CTI). This implemented consists number sub-procedures ranging from segmenting classifying segmented regions. initial part implements segmentation COVID-19–affected CTI social group optimization–based Kapur’s entropy thresholding, followed k-means clustering morphology-based segmentation. next feature extraction, selection, fusion classify infection. Principle component analysis–based serial technique is used in fusing features fused vector then employed train, test, validate four different classifiers namely Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, Decision Tree. Experimental results benchmark datasets show high accuracy (> 91%) for task; classification task, KNN offers highest among compared 87%). However, should be noted that method still awaits clinical validation, therefore not clinically diagnose ongoing

Language: Английский

---

3D DenseNet Ensemble in 4-Way Classification of Alzheimer’s Disease

Lecture notes in computer science, Journal Year: 2020, Volume and Issue: unknown, P. 85 - 96

Published: Jan. 1, 2020

Language: Английский

---

AI applications in functional genomics

Computational and Structural Biotechnology Journal, Journal Year: 2021, Volume and Issue: 19, P. 5762 - 5790

Published: Jan. 1, 2021

We review the current applications of artificial intelligence (AI) in functional genomics. The recent explosion AI follows remarkable achievements made possible by "deep learning", along with a burst "big data" that can meet its hunger. Biology is about to overthrow astronomy as paradigmatic representative big data producer. This has been huge advancements field high throughput technologies, applied determine how individual components biological system work together accomplish different processes. disciplines contributing this bulk are collectively known They consist studies of: i) information contained DNA (genomics); ii) modifications reversibly undergo (epigenomics); iii) RNA transcripts originated genome (transcriptomics); iv) ensemble chemical decorating types (epitranscriptomics); v) products protein-coding (proteomics); and vi) small molecules produced from cell metabolism (metabolomics) present an organism or at given time, physiological pathological conditions. After reviewing main genomics, we discuss important accompanying issues, including ethical, legal economic issues importance explainability.

Language: Английский

---