Introduction to Artificial Intelligence

Published: Dec. 28, 2024

---

A Novel Voltage Control System Based on Deep Neural Networks for MicroGrids Including Communication Delay as A Complex and Large-Scale System

ISA Transactions, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

---

SHARDA–ARAS: A Methodology for Prioritising Project Managers in Sustainable Development

Mathematics, Journal Year: 2024, Volume and Issue: 12(2), P. 219 - 219

Published: Jan. 9, 2024

In sustainable economic development, top-level human capital, especially project management, is paramount. This article integrates the Systematic Hierarchical Attribute Ratio Delphic Rating (SHARDA) method and Additive (ARAS) as a robust framework for identifying training managers. The research draws on diverse panel of experts against United Nations Sustainable Development Goals (SDGs) backdrop, emphasising stakeholder engagement transparency in decision-making processes. study investigates complexity multi-criteria (MCDM) methods focuses SWARA ARAS methods. These methodologies comprehensively improve process, considering range subjective criteria. extended modified hierarchical helps us understand each measure’s importance, while simplifies ranking selection based performance ratios. methodology seamlessly these to form SHARDA–ARAS that addresses challenging task selecting managers development. guarantees systematic inclusive incorporating perspectives aligned with global sustainability goals. studio’s innovation wrapped synthesis into methodology, presenting nuanced effective tool manager selection. Promoting an interconnected holistic approach contributes development emphasises methodology’s ability balance economic, environmental, social aspects. Thus, provides invaluable organisations seeking

Language: Английский

---

Mitigating Climate Change

Practice, progress, and proficiency in sustainability, Journal Year: 2024, Volume and Issue: unknown, P. 161 - 200

Published: Aug. 27, 2024

The existential threat presented by climate change demands an unprecedented response. Existing environmental regulations are insufficient for the pollution concerns that arise from our complicated and integrated global economy. AI has potential to completely revolutionize existing regulatory frameworks dramatically improve mitigation with superior data collection, modeling & new enforcement capabilities. Using a doctrinal approach, it studied both national international laws found best practices as well legal obstacles, such need privacy algorithmic bias concerns. It discovered health law regulation compliance of in public health. concluded artificial intelligence had vastly partially but theoretically, strict can curb worst impulses unscrupulous AI. recommended policymakers collaborate experts researchers ensure quality action.

Language: Английский

---

Recent Advancements in Artificial Intelligence in Battery Recycling

Batteries, Journal Year: 2024, Volume and Issue: 10(12), P. 440 - 440

Published: Dec. 11, 2024

Battery recycling has become increasingly crucial in mitigating environmental pollution and conserving valuable resources. As demand for battery-powered devices rises across industries like automotive, electronics, renewable energy, efficient is essential. Traditional methods, often reliant on manual labor, suffer from inefficiencies harm. However, recent artificial intelligence (AI) advancements offer promising solutions to these challenges. This paper reviews the latest developments AI applications battery recycling, focusing methodologies, challenges, future directions. technologies, particularly machine learning deep models, are revolutionizing sorting, classification, disassembly processes. AI-powered systems enhance efficiency by automating tasks such as identification, material characterization, robotic disassembly, reducing human error occupational hazards. Additionally, integrating with advanced sensing technologies computer vision, spectroscopy, X-ray imaging allows precise characterization real-time monitoring, optimizing strategies recovery rates. Despite advancements, data quality, scalability, regulatory compliance must be addressed realize AI’s full potential recycling. Collaborative efforts interdisciplinary domains essential develop robust, scalable AI-driven solutions, paving way a sustainable, circular economy materials.

Language: Английский

---

NRGCNMDA: Microbe-Drug Association Prediction Based on Residual Graph Convolutional Networks and Conditional Random Fields

Interdisciplinary Sciences Computational Life Sciences, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 7, 2025

Language: Английский

---

Vehicle structural road noise prediction based on an improved Long Short-Term Memory method

Sound&Vibration, Journal Year: 2025, Volume and Issue: 59(1), P. 2022 - 2022

Published: Jan. 9, 2025

The control of vehicle interior noise has become a critical metric for assessing noise, vibration, and harshness (NVH) in vehicles. During the initial phases development, accurately predicting impact road on is essential reducing levels expediting product development cycle. In recent years, data-driven methods based machine learning have gained significant attention due to their robust capability navigating complex data mapping relationships. Notably, surrogate models demonstrated exceptional performance this domain. Numerous researchers integrated diverse intelligent algorithms into study leveraging advantages such as elimination precise modeling requirements, extensive solution space exploration, continuous from data, algorithmic versatility. However, NVH engineering applications, face inherent limitations, particularly interpretability stability. To address these issues, paper introduces an improved Long Short-Term Memory (LSTM) network that combines knowledge data. Inspired by physical information neural concept, approach incorporates values calculated through empirical formulas constraints. Comparative assessments with traditional LSTM networks highlight deep model. By integrating constraints, model not only enhances but also achieves generalization fewer samples. proposed method validated specific model, showing improvements prediction accuracy efficiency.

Language: Английский

---

Artificial intelligence-based decision support systems: Integration, adaptation, and performance evaluation

Economics and Management, Journal Year: 2025, Volume and Issue: 30(12), P. 1521 - 1534

Published: Feb. 6, 2025

Aim. The work aimed to conduct a comprehensive analysis of decision support systems (DSS) based on artificial intelligence (AI) technologies, with an emphasis their integration into business processes and performance evaluation. Objectives. seeks study the main stages AI-based DSS development, determine key indicators for assessing financial, operational, strategic impact, select challenges in such implementations long-term effects systems, as well formulate recommendations improving interpretability adaptability. Methods. employed methods system analysis, generalization practical experience, research. article considers modern trends use AI, successful cases from practice large companies (JPMorgan Chase, General Electric, Amazon), concept J-curve productivity analyzing effects. Results. AI provides best potential increasing efficiency, reducing costs, quality management decisions. A efficiency assessment model has been developed, which includes both quantitative qualitative indicators. Conclusions. can be used not only increase accuracy rate decisions, but also optimize resource utilization adapt fast-paced market environment. However, requires solving number problems, including improvement data quality, enhancement algorithms, adapting personnel new technologies. Hybrid models that combine capabilities cognitive open up promising direction capable adaptability under conditions uncertainty. implementation proposed approaches leads increased competitiveness sustainability companies.

Language: Английский

---

An expert system for modeling skill levels for corporate power relations in an entropy-based environment using SPIRIT

Decision Analytics Journal, Journal Year: 2025, Volume and Issue: 14, P. 100556 - 100556

Published: Feb. 22, 2025

Language: Английский

---

Development of an Intelligent Tablet Press Machine for the In-Line Detection of Defective Tablets Using Machine Learning and Deep Learning Models

Pharmaceutics, Journal Year: 2025, Volume and Issue: 17(4), P. 406 - 406

Published: March 24, 2025

Objectives: This study aims to develop a tablet press machine (TPM) integrated with learning (ML) and deep (DL) models for in-line detection of defective tablets as Process Analytical Technology (PAT) tool. aimed predict defects, including capping occurrence inappropriate breaking force (TBF), using real-time processing data. Methods: Free-flowing metformin HCl (MF) granules produced the granulation method were compressed into TPM. Commercial-scale experiments conducted determine MF tablets’ defect criteria. Random Forest (RF) Artificial Neural Network (ANN) designed trained sensed data, compression force, ejection speed, quality defects. Subsequently, TPM was manufactured PAT an RF model. The verified by sorting pretrained defect-detection algorithm. Results: model demonstrated highest predictive accuracy at 93.7% Area Under Curve (AUC) 0.895, while ANN achieved 92.6% AUC 0.878. successfully sorted in real time, achieving 99.43% 93.71%. Conclusions: These results suggest that ML-based applied during tableting process can detect defects non-destructively scale-up wet granulation. In particular, it serve base produces small batches multiple products, thereby reducing additional labor, API consumption, decreasing environmental pollution.

Language: Английский

---