Machine Learning and Deep Learning for Big Data Analytics: a Review of Methods and Applications

SSRN Electronic Journal, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

The rapid expansion of data generation poses significant challenges and opportunities for data-driven innovation. This review explores the utilization machine learning (ML) deep (DL) methodologies in big analytics, emphasizing current advancements, techniques, practical implementations. We provide an in-depth examination ML methods large-scale data, encompassing supervised, unsupervised, reinforcement strategies. Additionally, we analyse various DL architectures such as convolutional neural networks (CNNs), recurrent (RNNs), transformers, which are adept at identifying complex patterns high-dimensional datasets. Data pre-processing feature engineering crucial enhancing quality utility; this discusses techniques managing noise, handling missing extracting relevant features. also highlight applications diverse fields healthcare, finance, retail, demonstrating their transformative impact. addresses scalability performance optimization essential effective deployment models contexts. Emerging trends automated ML, edge computing, potential integration quantum computing with discussed, offering a glimpse into future trajectory analytics. Ethical considerations, including issues privacy, bias, model interpretability, critically examined to ensure responsible application these technologies. paper aims be comprehensive resource researchers practitioners aiming harness advanced

Язык: Английский

---

Big data applications: overview, challenges and future

Artificial Intelligence Review, Год журнала: 2024, Номер 57(11)

Опубликована: Сен. 16, 2024

Язык: Английский

---

Unlocking the power of machine learning in big data: a scoping survey

Data Science and Management, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

Язык: Английский

---

Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection

Applied Sciences, Год журнала: 2025, Номер 15(2), С. 490 - 490

Опубликована: Янв. 7, 2025

The aging of power plant pipelines has led to significant leaks worldwide, causing environmental damage, human safety risks, and economic losses. Rapid leak detection is critical for mitigating these issues, but challenges such as varying characteristics, ambient noise, limited real-world data complicate their accurate model development. To address we propose a that integrates stepwise transfer learning an attention mechanism. proposed utilizes two-stage deep process. In Stage 1, one-dimensional convolutional neural networks (1D CNNs) are pre-trained extract root mean square (RMS) frequency-domain features from acoustic signals. 2, the classifier layers models removed, extracted fused processed using bidirectional long short-term memory (LSTM) network. An mechanism incorporated within LSTM prioritize features, enhancing ability distinguish signals noise. achieved accuracy 99.99%, significantly outperforming traditional methods considered in this study. By effectively addressing noise interference scarcity, robust approach demonstrates its potential enhance safety, reduce improve cost efficiency industrial infrastructure.

Язык: Английский

---

Blockchain-based digital twin management architecture for Internet of Medical Things Networks

Elsevier eBooks, Год журнала: 2025, Номер unknown, С. 313 - 335

Опубликована: Янв. 1, 2025

Язык: Английский

---

Cutting-Edge AI Approaches with MAS for PdM in Industry 4.0: Challenges and Future Directions

Journal of Applied Data Sciences, Год журнала: 2024, Номер 5(2), С. 455 - 473

Опубликована: Май 15, 2024

Integrating Artificial Intelligence (AI) within Industry 4.0 has propelled the evolution of fault diagnosis and predictive maintenance (PdM) strategies, marking a significant shift towards smarter paradigms in mechatronics sector. With advent 4.0, mechatronic systems have become increasingly sophisticated, highlighting critical need for advanced methodologies that are both efficient effective. This paper delves into confluence cutting-edge AI techniques, including machine learning (ML) deep (DL), with multi-agent (MAS) to enhance precision facilitate PdM context 4.0. Specifically, we explore use various ML models, Support Vector Machines (SVMs) Random Forests (RFs), DL architectures like Convolutional Neural Networks (CNNs) Recurrent (RNNs), which been effectively oriented analyses complex industrial data. Initially, study examines progress algorithms accelerate identification by leveraging data from system operations, sensors, historical trends. AI-enabled rapidly detects irregularities discerns fundamental causes, thereby minimizing downtime enhancing reliability efficiency. Furthermore, this underscores adoption AI-driven approaches, emphasizing prognostics predict Remaining Useful Life (RUL) machinery. capability allows strategic scheduling activities, optimizing resource use, prolonging lifespan expensive assets, refining management spare parts inventory. The tangible advantages employing showcased through case authentic implementations. highlights successful implementations, documenting real-world challenges such as integration issues interoperability, elaborates on strategies deployed navigate these obstacles. results demonstrate improved operational cost savings shed light pragmatic considerations solutions MAS applications. also navigates prospective research avenues applying domain setting stage ongoing innovation exploration transformative domain.

Язык: Английский

---

Utilizing a Hybrid Approach to Identify the Importance of Factors That Influence Consumer Decision-Making Behavior in Purchasing Sustainable Products

Sustainability, Год журнала: 2024, Номер 16(11), С. 4432 - 4432

Опубликована: Май 23, 2024

Consumer decision-making behaviors play a pivotal role in the realm of purchasing sustainable products. It is crucial for businesses to understand key factors that influence consumers’ choices this context, especially if they aim align with eco-friendly trends. Conventional methods are inadequate accurately and successfully identifying importance products stem from lack holistic consideration. methods, like AHP, surveys, questionnaires, interviews, focus groups, often do not fully consider many aspects consumer behavior related sustainability. To address gap, our study aims (1) employ hybrid approach, integrating conventional cutting-edge machine-learning technology predicting consumer’s products; (2) demonstrate practical application approach through example green furniture; (3) provide guide influencing This will map out implications future The studying decision making product purchases, combining quantitative AI methods. methodology provides comprehensive analysis environmentally friendly choices, fostering awareness informed making. Businesses can use these insights tailor strategies, enhance offerings, meet rising demand products, contributing responsible promoting economies scale innovation. understanding creating socially marketplace.

Язык: Английский

---

Proposing an Efficient Deep Learning Algorithm Based on Segment Anything Model for Detection and Tracking of Vehicles through Uncalibrated Urban Traffic Surveillance Cameras

Electronics, Год журнала: 2024, Номер 13(14), С. 2883 - 2883

Опубликована: Июль 22, 2024

In this study, we present a novel approach leveraging the segment anything model (SAM) for efficient detection and tracking of vehicles in urban traffic surveillance systems by utilizing uncalibrated low-resolution highway cameras. This research addresses critical need accurate vehicle monitoring intelligent transportation (ITS) smart city infrastructure. Traditional methods often struggle with variability complexity environments, leading to suboptimal performance. Our harnesses power SAM, an advanced deep learning-based image segmentation algorithm, significantly enhance accuracy robustness. Through extensive testing evaluation on two datasets 511 cameras from Quebec, Canada NVIDIA AI City Challenge Track 1, our algorithm achieved exceptional performance metrics including precision 89.68%, recall 97.87%, F1-score 93.60%. These results represent substantial improvement over existing state-of-the-art such as YOLO version 8 single shot detector (SSD), region-based convolutional neural network (RCNN). advancement not only highlights potential SAM real-time applications, but also underscores its capability handle diverse dynamic conditions scenes. The implementation technology can lead improved management, reduced congestion, enhanced mobility, making it valuable tool modern cities. outcomes pave way future advancements remote sensing photogrammetry, particularly realm management.

Язык: Английский

---

A review of deep learning techniques for enhancing spectrum sensing and prediction in cognitive radio systems: approaches, datasets, and challenges

International Journal of Computers and Applications, Год журнала: 2024, Номер unknown, С. 1 - 25

Опубликована: Окт. 21, 2024

Язык: Английский

---

Layered Data-Centric AI to Streamline Data Quality Practices for Enhanced Automation

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 128 - 142

Опубликована: Янв. 1, 2025

Язык: Английский

---