Developing a brain inspired multilobar neural networks architecture for rapidly and accurately estimating concrete compressive strength DOI Creative Commons
Bashar Alibrahim, Ahed Habib, Maan Habib

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 15, 2025

Concrete compressive strength is a critical parameter in construction and structural engineering. Destructive experimental methods that offer reliable approach to obtaining this property involve time-consuming procedures. Recent advancements artificial neural networks (ANNs) have shown promise simplifying task by estimating it with high accuracy. Nevertheless, conventional ANNs often require deep achieve acceptable results cases large datasets where generalization required for variety of mixtures. This leads increased training durations susceptibility noise, causing reduced accuracy potential information loss networks. In order address these limitations, study introduces novel multi-lobar network (MLANN) architecture inspired the brain's lobar processing sensory information, aiming improve efficiency concrete strength. The MLANN framework employs various architectures hidden layers, referred as "lobes," each unique arrangement neurons optimize data processing, reduce expedite time. Within context, an developed, its performance evaluated predict concrete. Moreover, compared against two traditional cases, ANN ensemble learning (ELNN). indicated significantly improves estimation performance, reducing root mean square error up 32.9% absolute 25.9% while also enhancing A20 index 17.9%, ensuring more robust generalizable model. advancement model refinement can ultimately enhance design analysis processes civil engineering, leading cost-effective practices.

Язык: Английский

Crop monitoring using remote sensing land use and land change data: Comparative analysis of deep learning methods using pre-trained CNN models DOI
Min Peng, Yunxiang Liu, Asad Khan

и другие.

Big Data Research, Год журнала: 2024, Номер 36, С. 100448 - 100448

Опубликована: Март 20, 2024

Язык: Английский

Процитировано

24
A critical review of machine learning algorithms in maritime, offshore, and oil & gas corrosion research: A comprehensive analysis of ANN and RF models DOI
Md Mahadi Hasan Imran, Shahrizan Jamaludin, Ahmad Faisal Mohamad Ayob

и другие.

Ocean Engineering, Год журнала: 2024, Номер 295, С. 116796 - 116796

Опубликована: Янв. 30, 2024

Язык: Английский

Процитировано

20
Machine learning applications for electrospun nanofibers: a review DOI Creative Commons

Balakrishnan Subeshan,

Asonganyi Atayo,

Eylem Asmatulu

и другие.

Journal of Materials Science, Год журнала: 2024, Номер 59(31), С. 14095 - 14140

Опубликована: Июль 30, 2024

Abstract Electrospun nanofibers have gained prominence as a versatile material, with applications spanning tissue engineering, drug delivery, energy storage, filtration, sensors, and textiles. Their unique properties, including high surface area, permeability, tunable porosity, low basic weight, mechanical flexibility, alongside adjustable fiber diameter distribution modifiable wettability, make them highly desirable across diverse fields. However, optimizing the properties of electrospun to meet specific requirements has proven be challenging endeavor. The electrospinning process is inherently complex influenced by numerous variables, applied voltage, polymer concentration, solution flow rate, molecular weight polymer, needle-to-collector distance. This complexity often results in variations nanofibers, making it difficult achieve desired characteristics consistently. Traditional trial-and-error approaches parameter optimization been time-consuming costly, they lack precision necessary address these challenges effectively. In recent years, convergence materials science machine learning (ML) offered transformative approach electrospinning. By harnessing power ML algorithms, scientists researchers can navigate intricate space more efficiently, bypassing need for extensive experimentation. holds potential significantly reduce time resources invested producing wide range applications. Herein, we provide an in-depth analysis current work that leverages obtain target nanofibers. examining work, explore intersection ML, shedding light on advancements, challenges, future directions. comprehensive not only highlights processes but also provides valuable insights into evolving landscape, paving way innovative precisely engineered various Graphical abstract

Язык: Английский

Процитировано

17
Machine Learning and Deep Learning Paradigms: From Techniques to Practical Applications and Research Frontiers DOI Creative Commons
Kamran Razzaq, Mahmood Shah

Computers, Год журнала: 2025, Номер 14(3), С. 93 - 93

Опубликована: Март 6, 2025

Machine learning (ML) and deep (DL), subsets of artificial intelligence (AI), are the core technologies that lead significant transformation innovation in various industries by integrating AI-driven solutions. Understanding ML DL is essential to logically analyse applicability identify their effectiveness different areas like healthcare, finance, agriculture, manufacturing, transportation. consists supervised, unsupervised, semi-supervised, reinforcement techniques. On other hand, DL, a subfield ML, comprising neural networks (NNs), can deal with complicated datasets health, autonomous systems, finance industries. This study presents holistic view technologies, analysing algorithms application’s capacity address real-world problems. The investigates application which techniques implemented. Moreover, highlights latest trends possible future avenues for research development (R&D), consist developing hybrid models, generative AI, incorporating technologies. aims provide comprehensive on serve as reference guide researchers, industry professionals, practitioners, policy makers.

Язык: Английский

Процитировано

2
Predicting female pelvic tilt and lumbar angle using machine learning in case of urinary incontinence and sexual dysfunction DOI Creative Commons
Doaa A. Abdel Hady, Tarek Abd El‐Hafeez

Scientific Reports, Год журнала: 2023, Номер 13(1)

Опубликована: Окт. 20, 2023

Urinary incontinence (UI) is defined as any uncontrolled urine leakage. Pelvic floor muscles (PFM) appear to be a crucial aspect of trunk and lumbo-pelvic stability, UI one indication pelvic dysfunction. The evaluation tilt lumbar angle critical in assessing the alignment posture spine lower back region pelvis, both these variables are directly related female dysfunction floor. affects significant number women worldwide can have major impact on their quality life. However, traditional methods parameters involve manual measurements, which time-consuming prone variability. rehabilitation programs for (FSD) physical therapy often focus (PFMs), while other core overlooked. Therefore, this study aimed predict activity various multiparous with FSD using multiple scales instead relying Ultrasound imaging. Decision tree, SVM, random forest, AdaBoost models were applied train set. Performance was evaluated test set MSE, RMSE, MAE, R

Язык: Английский

Процитировано

40
Analysing Influential Factors in Student Academic Achievement: Prediction Modelling and Insight DOI Creative Commons

Fahmida Faiza Ananna,

Ruchira Nowreen,

Sakhar Saad Rashid Al Jahwari

и другие.

International Journal of Emerging Multidisciplinaries Computer Science & Artificial Intelligence, Год журнала: 2023, Номер 2(1)

Опубликована: Ноя. 25, 2023

The fascination with understanding student academic performance has drawn widespread attention from various stakeholders, including parents, policymakers, and businesses. 'Students Performance in Exams' dataset, available on platforms like Kaggle, stands as a treasure trove. It extends beyond test scores, encompassing diverse attributes ethnicity, gender, parental education, preparation, even lunch type. In our tech-driven age, predicting success become compelling pursuit. This study aims to delve deep into this utilizing data mining methods robust classification algorithms Logistic Regression Random Forest Jupyter Notebook environment. Rigorous model training, testing, fine-tuning strive for the utmost predictive accuracy. Data cleaning preprocessing play crucial role establishing reliable dataset accurate predictions. Beyond numbers, project emphasizes visualization's impact, transforming raw comprehensible insights effective communication. Model exhibits an impressive 87.6% accuracy, highlighting its potential performance. Moreover, excels remarkable 100% accuracy forecasting grades, showcasing effectiveness domain.

Язык: Английский

Процитировано

23
Artificial Intelligence in ESG investing: Enhancing portfolio management and performance DOI Creative Commons

Omotayo Bukola Adeoye,

Chinwe Chinazo Okoye,

Onyeka Chrisanctus Ofodile

и другие.

International Journal of Science and Research Archive, Год журнала: 2024, Номер 11(1), С. 2194 - 2205

Опубликована: Фев. 20, 2024

Artificial Intelligence (AI) has emerged as a transformative force in Environmental, Social, and Governance (ESG) investing, significantly enhancing portfolio management performance. This paper investigates the integration of AI technologies within ESG investment strategies, elucidating their profound impact on decision-making processes financial outcomes. By leveraging advanced data analytics machine learning algorithms, empowers investors to analyze extensive ESG-related datasets, extract actionable insights, identify opportunities aligned with sustainability objectives. The application AI-driven analysis enables construct well-structured portfolios that not only aim for success but also adhere ethical sustainable principles. Through utilization AI, can systematically evaluate environmental impact, social responsibility, corporate governance practices potential investments. approach facilitates identification risks greater precision efficiency, leading more informed decisions. Moreover, dynamically adjust response changing market conditions emerging trends. continuously monitoring factors predictive analytics, proactively manage seize enhance performance over long term. proactive mitigates positions capitalize trends shifts consumer preferences. Furthermore, investing fosters transparency, accountability, stakeholder engagement ecosystem. AI-powered tools facilitate dissemination information, enabling make decisions align values goals. harnessing capabilities drive positive while achieving competitive returns. In conclusion, represents paradigm shift management, offering unprecedented navigate complex challenges achieve success.

Язык: Английский

Процитировано

10
Applications of machine learning and deep learning in medical diagnosis DOI
Shailendra Chouhan, Hemant Khambete, Sanjay Jain

и другие.

Elsevier eBooks, Год журнала: 2025, Номер unknown, С. 47 - 82

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
Advances and applications of artificial intelligence in breast reconstruction surgery: a systematic review DOI

Juan E. Ospina-Gómez,

Juan M. Molano-Diaz,

María C. Rojas-Gómez

и другие.

European Journal of Plastic Surgery, Год журнала: 2025, Номер 48(1)

Опубликована: Янв. 24, 2025

Язык: Английский

Процитировано

1
CART-ANOVA-Based Transfer Learning Approach for Seven Distinct Tumor Classification Schemes with Generalization Capability DOI Creative Commons
Shazia Afzal, Muhammad Rauf, Shahzad Ashraf

и другие.

Diagnostics, Год журнала: 2025, Номер 15(3), С. 378 - 378

Опубликована: Фев. 5, 2025

Background/Objectives: Deep transfer learning, leveraging convolutional neural networks (CNNs), has become a pivotal tool for brain tumor detection. However, key challenges include optimizing hyperparameter selection and enhancing the generalization capabilities of models. This study introduces novel CART-ANOVA (Cartesian-ANOVA) tuning framework, which differs from traditional optimization methods by systematically integrating statistical significance testing (ANOVA) with Cartesian product values. approach ensures robust precise parameter evaluating interaction effects between hyperparameters, such as batch size learning rate, rather than relying solely on grid or random search. Additionally, it implements seven distinct classification schemes tumors, aimed at improving diagnostic accuracy robustness. Methods: The proposed framework employs ResNet18-based knowledge (KTL) model trained primary dataset, 20% allocated testing. Hyperparameters were optimized using analysis, validation ensured selection. model’s robustness evaluated an independent second dataset. Performance metrics, including precision, accuracy, sensitivity, F1 score, compared against other pre-trained CNN Results: achieved exceptional 99.65% four-class 98.05% seven-class source 1 It also maintained high capabilities, achieving accuracies 98.77% 96.77% 2 datasets same tasks. incorporation further enhanced variability capability, surpassing performance Conclusions: combined KTL approach, significantly improves robustness, generalization. These advancements demonstrate strong potential precision informing effective treatment strategies, contributing to in medical imaging AI-driven healthcare solutions.

Язык: Английский

Процитировано

1