AI Learning Research Articles

Dominance of Artificial Intelligence and Machine Learning Algorithms in Real-Time Traffic Flow prediction and Route Optimization in Autonomous Vehicles

The evolution of autonomous vehicles has elicited significant interest in understanding how real-time data may be used to provide enhanced driving experiences. This research project explored AI and Machine Learning methodologies applied for traffic forecasting and route optimization, and their implications for autonomous vehicles and urban mobility. For this project, the road traffic flow Dataset was utilized from Kaggle, containing 48,000 records of the flow of traffic, each including the following key features. In our work, we deployed some credible and well-established machine learning models: linear regression and random forest. These algorithms were separately trained by using a part of preprocessed data. The MSE for the Random Forest model was significantly lower, which means that the Random Forest Regressor had much smaller errors in estimating the volume of traffic compared to the Linear Regression model. The Random Forest Model had a high R² score, proving that this model explains a great deal of variance in the volume of traffic. This means that the 'model of random forest regressors' excellently fitted the data, snatching most of the important patterns and relationships between input features and target variables.

Optimizing Quality Control on Electric Vehicle Production Lines with AI and Machine Learning

The study explores the use of AI and ML technologies to optimize quality control in EV production lines. By applying neural networks and machine learning algorithms, the research achieved significant improvements: a 74.4% reduction in torque deviation, a 75.9% enhancement in speed consistency, and a 70.8% decrease in defect rates. These gains also resulted in a 16.0% reduction in production cycle time and a 50.0% decrease in downtime, leading to an 8.4% increase in Overall Equipment Effectiveness (OEE). The methods employed included AI-driven predictive maintenance, real-time monitoring, and statistical process control (SPC). Despite the clear benefits, challenges such as integrating these technologies with existing systems and ensuring robust data infrastructure remain. Future research should focus on refining these approaches and extending their application across the automotive industry.

Evaluating AI's impact on self-regulated language learning: A systematic review

AI technology is reshaping language classrooms, prompting students to adopt flexible roles exhibiting linguistic competence and self-regulated learning (SRL) skills. Considerable studies explore the necessary integrated learning perspectives, emphasizing AI's adaptive role as a mind tool. In AI-mediated language learning, the technology's metacognitive importance enables students to learn with AI as a partner, encouraging independent critical thinking. Within Zimmerman's SRL model, AI as a mind tool is integrated for improving language students' strategic employment in a cyclical process. A systematic review, following PRISMA protocols, examines the intersection of AI and self-regulated language learning (SRLL) over 2000–2022. Findings highlight AI's evolving role, predominantly through algorithms and systems, aiming for micro and macro integration. Interactive AI has not fully engaged in two-way directions, despite a familiar process approach in reviewed studies. In the favored ESL/EFL research context, task-specific AI is utilized to encourage cyclical improvement with learner autonomy enhancement mainly among higher education students at intermediate level or above. Pedagogical values are possible when major SRL phases are fully practiced, even without highly autonomous AI. Future research is directed toward adaptive personalized technology by exploring the dynamic interplay between AI technologies and SRLL as educational practices under Education 4.0 principles.

Exploring Relationships Between Drought Indices and Ecological Drought Impacts Using Machine Learning and Explainable AI

Rangeland ecosystems in the United States hold great ecological, economic, and cultural value. However, the increasing frequency and severity of droughts pose potential threats to these ecosystems. This study used remotely sensed data, machine learning, and explainable artificial intelligence (XAI) to explore relationships between drought indices and vegetation health in the Cheyenne River Basin, USA. The study employed XGBoost Regressor and Extra Trees Regressor models in conjunction with SHapley Additive exPlanations (SHAP) to identify the most influential drought indices and environmental variables for predicting Normalized Difference Vegetation Index (NDVI), thereby uncovering indicators of vegetation stress in the basin. The XGBoost regressor was moderately successful at predicting NDVI, making the model suitable for subsequent XAI analysis using SHAP. SHAP results revealed that the Palmer Drought Severity Index (PDSI), the 90-day Standardized Precipitation Index (SPI), and snow water equivalent (SWE) were the most influential predictors of NDVI, indicating their strong association with changes in vegetation health in the Cheyenne River Basin. This study demonstrates the feasibility and value of applying XAI methods to investigate both the strength and directionality of ecological drought indicators—an approach that has been underutilized in drought research. These insights can inform future drought research, improve monitoring efforts, and help anticipate ecological drought impacts in the region.

Improving Hate Speech Classification Through Ensemble Learning and Explainable AI Techniques

Improving Hate Speech Classification Through Ensemble Learning and Explainable AI Techniques

대학생의 디지털 학습역량이 AI 지식수준과 중요도에 미치는 영향: AI 신념의 매개효과를 중심으로

Objectives The purpose of this study is to investigate the effect of digital learning capabilities on the level and importance of AI knowledge among university students, and to statistically analyze the mediating effect of AI beliefs in this process. Methods For this study, we surveyed 309 students at four-year universities across the country. SPSS 25.0 and AMOS 23.0 were used to analyze the trend and normality of the study variables and correlation by Pearson's correlation. The measurement model was examined through confirmatory factor analysis, while the structural model was examined through structural equation modeling. The mediating effects were tested for statistical significance using the bootstrapping method with a two-sided test at a 95% confidence level. Results The main results are as follows: First, The research variables all showed values above 3.0; however, their importance was higher compared to the level of AI knowledge. We found a positive correlation between digital learning capabilities and AI beliefs, knowledge and importance of AI. Second, digital learning capabilities have a statistically significant impact on AI beliefs, AI knowledge level, and AI knowledge importance. AI beliefs have a statistically significant impact on the importance of training and knowledge in AI. Third, we find that AI beliefs partially mediate the effects of digital learning capabilities on knowledge and importance of AI. Conclusions Based on the results of this study, we would like to propose ways to respond to the changing learning environment, including AI education policies and teaching and learning methods, as AI is expected to play a key role in the future society.

AI And Machine Learning For Optimizing Renewable Energy Systems In Engineering Management

AI And Machine Learning For Optimizing Renewable Energy Systems In Engineering Management

Toward the Integration of Machine Learning and Molecular Modeling for Designing Drug Delivery Nanocarriers.

The pioneering work on liposomes in the 1960s and subsequent research in controlled drug release systems significantly advances the development of nanocarriers (NCs) for drug delivery. This field is evolved to include a diverse array of nanocarriers such as liposomes, polymeric nanoparticles, dendrimers, and more, each tailored to specific therapeutic applications. Despite significant achievements, the clinical translation of nanocarriers is limited, primarily due to the low efficiency of drug delivery and an incomplete understanding of nanocarrier interactions with biological systems. Addressing these challenges requires interdisciplinary collaboration and a deep understanding of the nano-bio interface. To enhance nanocarrier design, scientists employ both physics-based and data-driven models. Physics-based models provide detailed insights into chemical reactions and interactions at atomic and molecular scales, while data-driven models leverage machine learning to analyze large datasets and uncover hidden mechanisms. The integration of these models presents challenges such as harmonizing different modeling approaches and ensuring model validation and generalization across biological systems. However, this integration is crucial for developing effective and targeted nanocarrier systems. By integrating these approaches with enhanced data infrastructure, explainable AI, computational advances, and machine learning potentials, researchers can develop innovative nanomedicine solutions, ultimately improving therapeutic outcomes.

Enhancing early Parkinson’s disease detection through multimodal deep learning and explainable AI: insights from the PPMI database

Parkinson’s is the second most common neurodegenerative disease, affecting nearly 8.5M people and steadily increasing. In this research, Multimodal Deep Learning is investigated for the Prodromal stage detection of Parkinson's Disease (PD), combining different 3D architectures with the novel Excitation Network (EN) and supported by Explainable Artificial Intelligence (XAI) techniques. Utilizing data from the Parkinson’s Progression Markers Initiative, this study introduces a joint co-learning approach for multimodal fusion, enabling end-to-end training of deep neural networks and facilitating the learning of complementary information from both imaging and clinical modalities. DenseNet with EN outperformed other models, showing a substantial increase in accuracy when supplemented with clinical data. XAI methods, such as Integrated Gradients for ResNet and DenseNet, and Attention Heatmaps for Vision Transformer (ViT), revealed that DenseNet focused on brain regions believed to be critical to prodromal pathophysiology, including the right temporal and left pre-frontal areas. Similarly, ViT highlighted the lateral ventricles associated with cognitive decline, indicating their potential in the Prodromal stage. These findings underscore the potential of these regions as early-stage PD biomarkers and showcase the proposed framework's efficacy in predicting subtypes of PD and aiding in early diagnosis, paving the way for innovative diagnostic tools and precision medicine.

The Cloud Security Revolution: Unlocking the Potential of AI and Machine Learning to Stay Ahead of Threats

As we navigate the digital world, cybersecurity has become a top priority. With each technological advancement, new vulnerabilities emerge, making robust defenses essential. The fusion of machine learning and artificial intelligence has become a game-changer in the fight against cyber threats. This paper delves into the latest applications of these technologies in network security, shedding light on their critical roles in addressing pressing concerns and identifying areas for further exploration. We also examine the ethical and legal implications of implementing these technologies. Our research highlights current challenges and open questions, with a focus on recent breakthroughs in network security leveraging AI and ML. The findings are promising, suggesting that further innovation in integrating AI and ML into network security frameworks holds significant potential. Exciting applications include bolstering network security, detecting malware, and responding to intrusions. Interestingly, while 45% of organizations recognize the need to adopt these technologies, half have already done so, while 5% remain hesitant.

Ensuring Security and Compliance in Agile Cloud Infrastructure Projects

Purpose: This research paper investigates strategies for ensuring security and compliance in agile cloud infrastructure projects. Methodology: The study synthesizes current literature, industry reports, and expert insights to provide a comprehensive overview of the topic. Findings: Key challenges identified include rapid deployment cycles, shared responsibility models, and data sovereignty concerns. The research proposes strategies such as shift-left security approaches, continuous compliance monitoring, and automated security testing. The importance of organizational culture shifts and the evolving role of cloud service providers in shared security responsibilities are highlighted. Unique Contribution to Theory, Policy and Practice: The paper offers recommendations for practitioners navigating the complex landscape of security and compliance in agile cloud projects. It provides insights into integrating security and compliance into agile methodologies, leveraging cloud-native security tools, and the potential impact of AI and machine learning on cloud security.

Forensic Perspective on Voice Biometrics and AI : A Review

Modern internet has given rise to various voice related crimes worldwide, notably deepfake voice scams where the perpetrators utilize artificial intelligence to deceive victims by the means of forgery of voice. This review article aims to discuss the advancements and challenges in voice biometrics, particularly focusing on the impact of AI and deep learning on this field. It underscores the evolution of voice biometrics from early methods to modern AI enhanced techniques, by highlighting the significant improvements in accuracy, security, and adaptability etc. The key findings of the article have highlighted that while AI-driven advancements have addressed many challenges including voice robustness and multilingual recognition, new threats like deep fake audio require ongoing innovation. The integration of various methods like deep learning, neural networks and advanced feature extraction has shown incredible potential in enhancing the system resilience. But challenges such as voice variability, privacy concerns and the forensic applications of these technologies remain critical issue to be addressed by the future researchers. This review article recommends multidisciplinary research to bridge the gap between this field and forensic science, emphasizing the need for continued development to address and prevent emerging threats very efficiently.

Job crafting and entrepreneurial innovativeness: the moderated mediation roles of dynamic capabilities and self-initiated AI learning

PurposeThis paper investigates the moderated mediation roles of dynamic capabilities and self-initiated AI learning between job crafting and entrepreneurial innovativeness among owner-managers of family craft businesses in Ghana.Design/methodology/approachA convenience sampling technique was used in the selection of 498 family craft business owner-managers in Ghana. The paper deployed regression analysis to examine the hypothesized paths.FindingsUsing hierarchical regression, job crafting was found to have a positive effect on entrepreneurs’ innovativeness. Further, dynamic capabilities moderate the mediated link between self-initiated AI learning and entrepreneurial innovativeness.Research limitations/implicationsThe current study assesses self-initiated learning for work adjustment from a cross-sectional design perspective. Though, this research design is effective in the assessment of opinions and attitudes of persons, it is limited in its capacity to reflect changing opinions and attitudes overtime. This study recommends future studies to conduct a longitudinal survey on the phenomenon.Originality/valueThis study is one of the first to deploy AI affordances to extend empirical literature on the novel SIWAL concept for work adjustment among craft family business owner-managers in Africa.

Optimized Tiny Machine Learning and Explainable AI for Trustable and Energy-Efficient Fog-Enabled Healthcare Decision Support System

The Internet of things (IoT)-based healthcare decision support system plays a crucial role in modern medicine, especially with the rise in chronic illnesses and an aging population necessitating continuous remote health monitoring. Current healthcare decision support systems struggle to deliver timely and accurate decisions with minimal latency due to limited real-time healthcare data and inefficient computational resources. There is a critical need for an optimized, energy-efficient machine learning model that reliably supports remote health monitoring within IoT and fog computing environments. Our study proposes an Optimized Tiny Machine Learning (TinyML) and Explainable AI (XAI) binary classification model for a trustable and energy-efficient healthcare decision support system, leveraging fog computing to optimize performance. The fog-based approach improves response times and enhances bandwidth usage, addressing critical needs such as reduced latency, higher bandwidth utilization, and decreased packet loss. To further improve efficiency, we incorporate the innovative mLZW data compression technique, significantly enhancing data communication efficiency and reducing response time to critical health alerts. However, limited real-time healthcare data records challenge machine learning classification performance. By implementing a TinyML algorithm, our system demonstrates superior performance to other machine learning models. The proposed optimized TinyML model achieves an impressive F1 score of 0.93 for health abnormalities detection, emphasizing its robustness and effectiveness. This paper highlights the potential of TinyML and XAI in delivering robust, trustworthy, and energy-aware healthcare solutions, making significant contributions toward effective remote health monitoring and decision support in fog-enabled IoT networks.Graphical abstract

Transforming air pollution management in India with AI and machine learning technologies

A comprehensive approach is essential in India's ongoing battle against air pollution, combining technological advancements, regulatory reinforcement, and widespread societal engagement. Bridging technological gaps involves deploying sophisticated pollution control technologies and addressing the rural–urban disparity through innovative solutions. The review found that integrating Artificial Intelligence and Machine Learning (AI&ML) in air quality forecasting demonstrates promising results with a remarkable model efficiency. In this study, initially, we compute the PM2.5 concentration over India using a surface mass concentration of 5 key aerosols such as black carbon (BC), dust (DU), organic carbon (OC), sea salt (SS) and sulphates (SU), respectively. The study identifies several regions highly vulnerable to PM2.5 pollution due to specific sources. The Indo-Gangetic Plains are notably impacted by high concentrations of BC, OC, and SU resulting from anthropogenic activities. Western India experiences higher DU concentrations due to its proximity to the Sahara Desert. Additionally, certain areas in northeast India show significant contributions of OC from biogenic activities. Moreover, an AI&ML model based on convolutional autoencoder architecture underwent rigorous training, testing, and validation to forecast PM2.5 concentrations across India. The results reveal its exceptional precision in PM2.5 prediction, as demonstrated by model evaluation metrics, including a Structural Similarity Index exceeding 0.60, Peak Signal-to-Noise Ratio ranging from 28–30 dB and Mean Square Error below 10 μg/m3. However, regulatory challenges persist, necessitating robust frameworks and consistent enforcement mechanisms, as evidenced by the complexities in predicting PM2.5 concentrations. Implementing tailored regional pollution control strategies, integrating AI&ML technologies, strengthening regulatory frameworks, promoting sustainable practices, and encouraging international collaboration are essential policy measures to mitigate air pollution in India.

Harnessing Machine Learning and Generative AI: A New Era in Online Tutoring Systems

Discover how the convergence of machine learning and generative AI is revolutionizing online tutoring, enabling systems that evolve to become better teachers--continuously refining their instructional methods based on student data and feedback.

Snn and sound: a comprehensive review of spiking neural networks in sound.

The rapid advancement of AI and machine learning has significantly enhanced sound and acoustic recognition technologies, moving beyond traditional models to more sophisticated neural network-based methods. Among these, Spiking Neural Networks (SNNs) are particularly noteworthy. SNNs mimic biological neurons and operate on principles similar to the human brain, using analog computing mechanisms. This capability allows for efficient sound processing with low power consumption and minimal latency, ideal for real-time applications in embedded systems. This paper reviews recent developments in SNNs for sound recognition, underscoring their potential to overcome the limitations of digital computing and suggesting directions for future research. The unique attributes of SNNs could lead to breakthroughs in mimicking human auditory processing more closely.

Deep SVBRDF Acquisition and Modelling: A Survey

AbstractHand in hand with the rapid development of machine learning, deep learning and generative AI algorithms and architectures, the graphics community has seen a remarkable evolution of novel techniques for material and appearance capture. Typically, these machine‐learning‐driven methods and technologies, in contrast to traditional techniques, rely on only a single or very few input images, while enabling the recovery of detailed, high‐quality measurements of bi‐directional reflectance distribution functions, as well as the corresponding spatially varying material properties, also known as Spatially Varying Bi‐directional Reflectance Distribution Functions (SVBRDFs). Learning‐based approaches for appearance capture will play a key role in the development of new technologies that will exhibit a significant impact on virtually all domains of graphics. Therefore, to facilitate future research, this State‐of‐the‐Art Report (STAR) presents an in‐depth overview of the state‐of‐the‐art in machine‐learning‐driven material capture in general, and focuses on SVBRDF acquisition in particular, due to its importance in accurately modelling complex light interaction properties of real‐world materials. The overview includes a categorization of current methods along with a summary of each technique, an evaluation of their functionalities, their complexity in terms of acquisition requirements, computational aspects and usability constraints. The STAR is concluded by looking forward and summarizing open challenges in research and development toward predictive and general appearance capture in this field. A complete list of the methods and papers reviewed in this survey is available at computergraphics.on.liu.se/star_svbrdf_dl/.

Development and Application of AI Teaching and Learning Model based on Backward Design for using AI Digital Textbook

Development and Application of AI Teaching and Learning Model based on Backward Design for using AI Digital Textbook

SCADA Systems in Oil and Gas: Driving Innovation and Efficiency in the Digital Age

Abstract: In the oil and gas sector, supervisory control and data acquisition (SCADA) systems have become a revolutionary force that are transforming operations throughout the whole value chain. This in-depth analysis looks at the development, design, and various uses of SCADA systems in the upstream, middle, and downstream domains. It projects that the global SCADA market for oil and gas will grow to $4.52 billion by 2026. Real-time well monitoring, production optimization, and remote operations are made possible by SCADA systems in upstream operations, which greatly increase output and efficiency. The goal of midstream applications is to increase pipeline efficiency and safety by using predictive maintenance, enhanced leak detection, and flow optimization. By streamlining quality assurance, energy management, and process control, SCADA systems can completely transform refinery operations. SCADA deployments are not without difficulties, though, including data management complications, cybersecurity threats, and legacy system interoperability. In addition to addressing these problems, the study looks at new developments that could improve SCADA capabilities, such as edge computing, digital twins, AI and machine learning integration, and 5G technology. According to the research, SCADA is essential for promoting efficiency, safety, and innovation in the oil and gas industry. Businesses that successfully integrate SCADA technologies while overcoming implementation obstacles will be best positioned to prosper in the complicated and fiercely competitive energy market.