Artificial Intelligence Learning Research Articles

Artificial Intelligence for Prediction of Shunt Response in Idiopathic Normal Pressure Hydrocephalus: A Systematic Review

BackgroundIdiopathic normal pressure hydrocephalus (iNPH) is a reversible cause of dementia, typically treated with shunt surgery, although outcomes vary. Artificial intelligence (AI) advancements could improve predictions of shunt response (SR) by analyzing extensive data sets. MethodsWe conducted a systematic review to assess AI's effectiveness in predicting SR in iNPH. Studies using AI or machine learning (ML) algorithms for SR prediction were identified through searches in MEDLINE, EMBASE, and Web of Science up to September 2023, adhering to Synthesis Without Meta-Analysis reporting guidelines. ResultsOut of 3541 studies identified, 33 were assessed for eligibility, and 8 involving 479 patients were included. Study sample sizes varied from 28 to 132 patients. Common data inputs included imaging/radiomics (62.5%) and demographics (37.5%), with Support Vector Machine being the most frequently used ML algorithm (87.5%). Two studies compared multiple algorithms. Only four studies reported the Area Under the Curve (AUC) values, which ranged between 0.80 and 0.94. The results highlighted inconsistency in outcome measures, data heterogeneity, and potential biases in the models used. ConclusionsWhile AI shows promise for improving iNPH management, there is a need for standardized data and extensive validation of AI models to enhance their clinical utility. Future research should aim to develop robust and generalizable AI models for more effective diagnosis and management of iNPH.

Transforming Diagnostics: A Comprehensive Review of Advances in Digital Pathology.

Digital pathology has emerged as a revolutionary field, transforming traditional diagnostic practices by integrating advanced imaging technologies, computational tools, and artificial intelligence (AI). Adopting digital slides over conventional glass slides enables high-resolution imaging, facilitating remote consultations, second opinions, and telepathology. The digitalization of pathology laboratories enhances workflow efficiency and allows for large-scale data storage, retrieval, and analysis, paving the way for developing robust diagnostic algorithms. One of the most transformative aspects of digital pathology is its synergy with AI and machine learning (ML). These technologies have enabled the automation of repetitive processes, including diseased feature detection, biomarker quantification, and tissue segmentation. This has decreased inter-observer variability and increased diagnostic accuracy. AI-driven algorithms are particularly beneficial in complex cases, assisting pathologists in detecting subtle patterns that might be missed through manual examination. Furthermore, digital pathology plays a critical role in personalized medicine by enabling the precise characterization of tumors, which leads to targeted therapy decisions. Integrating digital pathology with genomics and other omics data holds promise for a more holistic understanding of diseases, driving innovation in diagnostics and treatment. However, the transition to digital pathology is challenging. Issues such as data standardization, regulatory compliance, and the need for robust IT infrastructure must be addressed to realize its full potential. This review provides a detailed examination of these advances, their clinical applications, and the challenges faced in the widespread adoption of digital pathology. As the field continues to evolve, it is poised to play a pivotal role in shaping the future of diagnostics, offering new possibilities for improving patient outcomes. This comprehensive review explores the significant advances in digital pathology, highlighting its impact on diagnostics, research, and patient care.

Development of in silico methodologies to predict the toxicity of novel proteins in the context of food and feed risk assessment

Abstract This report is the outcome of an EFSA procurement (OC/EFSA/GMO/2021/02 – LOT1) aiming at developing an in silico strategy to predict the toxicity of (novel) proteins. Up‐to‐date, commercially available tools predicting protein toxicity based on primary structures were evaluated for their accuracy and usability, using a curated dataset of annotated toxins and non‐toxins from UniProt. ToxinPred2 and Toxify emerged as the top performers, showing both high accuracy and suitability for integration into an automated pipeline. Additional bioinformatics methods were explored, which provide sequence similarity‐based information rather than direct predictions (BLAST, InterPro HMM profiles). By converting their outputs into features for machine learning models, a high prediction accuracy was achieved, though there is potential for improvement to reduce overfitting risks. An Artificial Intelligence (AI)‐based consensus pipeline, integrating results from ToxinPred2, Toxify, and our machine learning models was developed. This consensus model reached a 95% accuracy rate in distinguishing toxins from non‐toxins. Noteworthy, our BLAST‐based machine learning model ‐ although performance‐wise comparable to BLAST ‐ offers higher sensitivity and specificity across diverse queries than BLAST; it relies on database‐based evolutionary relationships, which may significantly limit its applicability to novel or mutated toxins. Structure‐based prediction methods are deemed impractical due to their resource intensity and reliance on accurate structural data; AI‐driven structure prediction methods ‐ like Rosetta and AlphaFold ‐ are promising, however they are still under development and may not be suitable for the regulatory context yet. Recommendations are provided, including enhancement of the proposed consensus pipeline to create an independent open‐source, user‐friendly tool for evaluating the safety of (novel) proteins in food and feed; regular updates of the proposed databases and models; incorporation of 3D structures and in general validation of AI and machine learning models for regulatory uses.

Exploring the Artificial Intelligence and Its Impact in Pharmaceutical Sciences: Insights Toward the Horizons Where Technology Meets Tradition.

The technological revolutions in computers and the advancement of high-throughput screening technologies have driven the application of artificial intelligence (AI) for faster discovery of drug molecules with more efficiency, and cost-friendly finding of hit or lead molecules. The ability of software and network frameworks to interpret molecular structures' representations and establish relationships/correlations has enabled various research teams to develop numerous AI platforms for identifying new lead molecules or discovering new targets for already established drug molecules. The prediction of biological activity, ADME properties, and toxicity parameters in early stages have reduced the chances of failure and associated costs in later clinical stages, which was observed at a high rate in the tedious, expensive, and laborious drug discovery process. This review focuses on the different AI and machine learning (ML) techniques with their applications mainly focused on the pharmaceutical industry. The applications of AI frameworks in the identification of molecular target, hit identification/hit-to-lead optimization, analyzing drug-receptor interactions, drug repurposing, polypharmacology, synthetic accessibility, clinical trial design, and pharmaceutical developments are discussed in detail. We have also compiled the details of various startups in AI in this field. This review will provide a comprehensive analysis and outline various state-of-the-art AI/ML techniques to the readers with their framework applications. This review also highlights the challenges in this field, which need to be addressed for further success in pharmaceutical applications.

Artificial Intelligence for Sustainable Agribusiness: Innovations and Challenges

The integration of artificial intelligence (AI) in sustainable agribusiness is examined in this research, with particular attention paid to robots, supply chain management, and precision agriculture. AI analyzes a variety of datasets, maximizes resource utilization, forecasts pest outbreaks and production changes, and allows for data-driven decision-making. AI improves supply chain management by lowering food loss, streamlining logistics, and guaranteeing on-time delivery. Robotics powered by AI revolutionize labor-intensive processes, increasing output while reducing the need for chemicals. Notwithstanding its revolutionary potential, issues like data privacy and skill shortages still need to be resolved. Developing AI solutions that are inclusive and appropriate to a given context requires interdisciplinary collaboration. Improved equity and transparency are anticipated from developments in federated learning and explainable AI. All things considered, artificial intelligence (AI) presents hitherto unseen chances to advance sustainability along the agriculture value chain, building food system resilience and equity. Keywords: artificial intelligence, sustainability, efficiency, agribusiness, resilience, functionality

The wizard of artificial intelligence: Are physicians prepared?

Despite the increasing use of artificial intelligence (AI) in medicine, research into the knowledge and attitudes of medical experts toward AI is limited. This study aimed to assess physicians' attitudes and perceptions of AI applications in healthcare. A cross-sectional study was conducted at the College of Medicine, King Abdulaziz University, Jeddah, Saudi Arabia between November 1 and December 20, 2023. Data was collected using a web-based validated self-administered questionnaire; information sought included demographics, familiarity with AI technology, attitudes towards AI applications in medicine, and perceived risks associated with its implementation. Data analysis performed using SPSS. Categorical variables were presented as frequencies and percentages, whereas mean and standard deviations were calculated for continuous variables. Four domains were used as study variables: familiarity, attitude, AI application, and possible risks. The domains were compared to the scored individual question using Pearson's correlation coefficient. A total of 128 academic staff participated (response rate 21.3%). About 41% reported being aware of AI as an emerging field and expressed desire to learn about AI. Concerns about the effect of AI on physicians' employability were not prominent. Instead, most (65.6%) agreed that new positions would be created and that the job market for those who embraced AI would increase. Thirty-two percent reported actively seeking out new technologies in their practice areas, and 24.2% would be willing to adapt AI to practice if its usefulness was published in scientific journals. Most participants (87.5%) agreed that dedicated courses would help them implement AI in their specialty. The most commonly reported problem of AI was its inability to provide opinions in unexpected scenarios. A quarter of participants believed that both AI creators and doctors should be liable for AI-caused medical errors. Physician's age, gender, or years of experience were not related to their familiarity with or attitudes toward AI. Doctors are open to learning about AI use in medicine. Including AI learning objectives or short courses in medical curricula would help physicians develop the necessary skills for an AI-augmented healthcare system.

The future of software development: integrating AI and machine learning into front-end technologies

This paper explores the integration of artificial intelligence (AI) and machine learning into front-end development, highlighting the transformative potential these technologies hold for the future of software development. By automating routine tasks, enhancing predictive capabilities, and improving user engagement, AI and machine learning are set to revolutionize how digital applications are created and experienced. However, this integration is accompanied by significant technical challenges, including the complexity of AI systems, performance concerns, and ethical issues such as data privacy and bias. The paper also discusses current applications and emerging trends in AI-powered front-end technologies, providing a comprehensive overview of the benefits and obstacles. It emphasizes the importance of ongoing research, innovation, and ethical considerations in maintaining the U.S. tech sector's competitive edge in this rapidly evolving field. The findings suggest that while AI and machine learning offer substantial opportunities for innovation, careful implementation is essential to ensure these technologies contribute positively to the future of software development.

인공지능 학습기 기반 멘토링이 취약계층 초등학생의 학습격차 해소에 미치는 효과

This study examines the impact of artificial intelligence (AI) learning devices and community-based mentoring on underprivileged elementary students to alleviate post COVID 19 pandemic educational disparities. 104 school-aged students engaged in self directed learning with AI devices and received mentoring for 8 months. Data included device usage, attendance, pre-and post-assessment scores in Korean language and math, and self-reported learning efficacy. Results showed significant improvements in Korean language and math scores for students in the mentoring program. A ‘high-utilization group’ displayed notable gains in math scores and learning efficacy. This study underscores the potential of EdTech and community-based mentoring in bridging educational gaps for underprivileged students, suggesting a viable alternative to traditional schooling.

Evaluating the impact of AI and blockchain on credit risk mitigation: A predictive analytic approach using machine learning

In recent years, the integration of artificial intelligence (AI), blockchain technology, and machine learning has transformed credit risk mitigation strategies in the financial industry. This paper explores the practical applications of these technologies in identifying, assessing, and managing credit risk, with a specific focus on predictive analytics and decentralized frameworks. Through a comprehensive literature review and case studies, the research demonstrates how AI-driven algorithms, blockchain's transparent and immutable ledger systems, and machine learning models have enhanced the precision and efficiency of credit risk evaluations. Additionally, the study investigates how these innovations are being adopted by financial institutions to create more accurate credit scoring systems, reduce fraud, and optimize operational risk management. While these technologies hold great promise, challenges such as data privacy, regulatory compliance, and implementation costs remain significant barriers. The paper concludes with recommendations for overcoming these challenges and maximizing the potential of AI, blockchain, and machine learning in credit risk mitigation.

Advancing food safety standards through technology integration and policy development

Food safety is a critical global concern, directly impacting public health, economic stability, and international trade. With the complexity of modern food supply chains and the rising incidence of foodborne illnesses, traditional food safety measures are often insufficient to address the growing risks. This review explores how integrating advanced technologies and developing robust policies can significantly enhance food safety standards. Technological innovations, including the Internet of Things (IoT), blockchain, artificial intelligence (AI), and automation, offer promising solutions for real-time monitoring, traceability, and predictive analytics in food production and distribution. IoT and sensors enable constant monitoring of environmental conditions like temperature and humidity, while blockchain ensures transparency and traceability across supply chains. AI and machine learning are transforming food safety by predicting contamination risks and optimizing inspection processes, while robotics and automation reduce human error in food processing plants. Alongside technological advancements, policy development plays a crucial role in reinforcing food safety standards. Global harmonization of food safety regulations, stronger enforcement mechanisms, and public-private partnerships are essential for ensuring widespread compliance. Incorporating technology into regulatory frameworks is key to addressing new challenges and maintaining food safety across borders. Governments must also prioritize consumer education and awareness through policies that leverage technology platforms to promote food safety knowledge. Case studies demonstrate the successful application of these technologies in sectors like dairy and meat processing, showcasing the potential for broader industry adoption. However, challenges such as high implementation costs, regulatory lag, and data security concerns remain. This review argues that a synergistic approach combining technological integration with forward-thinking policy development is essential for advancing global food safety standards and safeguarding public health in the future.

Combating terrorist financing in cryptocurrency platforms: The role of AI and machine learning

This study addresses the critical issue of terrorist financing through cryptocurrency platforms, a growing concern due to digital currencies' pseudonymous nature and global reach. The research explores the strategic role of Artificial Intelligence (AI) and Machine Learning (ML) in identifying, preventing, and disrupting the flow of illicit funds used to finance terrorism. Employing a mixed-methods approach, the study integrates qualitative case studies of documented instances of cryptocurrency-based terrorist financing with quantitative data analysis from significant cryptocurrency exchanges. Advanced AI and ML algorithms, including supervised learning models such as decision trees and neural networks, were applied to detect suspicious transactions indicative of terrorist activities. The findings reveal that AI and ML technologies significantly enhance the ability to identify patterns of terrorist financing within large and complex datasets, with models achieving precision and recall rates exceeding 90%. However, challenges remain, particularly regarding the quality and standardization of data across platforms, algorithmic biases, and the need for continuous updates to counter evolving tactics used by terrorist organizations. The study concludes that AI and ML present powerful tools for enhancing financial security. However, their successful implementation requires overcoming these challenges through collaborative efforts among stakeholders, including financial institutions, regulators, and technology providers. This research contributes to the growing field of economic crime prevention by offering a robust framework for integrating AI-driven solutions into the fight against terrorist financing on cryptocurrency platforms.

Brain-computer Interaction in the Smart Era.

The brain-computer interface (BCI) system serves as a critical link between external output devices and the human brain. A monitored object's mental state, sensory cognition, and even higher cognition are reflected in its electroencephalography (EEG) signal. Nevertheless, unprocessed EEG signals are frequently contaminated with a variety of artifacts, rendering the analysis and elimination of impurities from the collected EEG data exceedingly challenging, not to mention the manual adjustment thereof. Over the last few decades, the rapid advancement of artificial intelligence (AI) technology has contributed to the development of BCI technology. Algorithms derived from AI and machine learning have significantly enhanced the ability to analyze and process EEG electrical signals, thereby expanding the range of potential interactions between the human brain and computers. As a result, the present BCI technology with the help of AI can assist physicians in gaining a more comprehensive understanding of their patients' physical and psychological status, thereby contributing to improvements in their health and quality of life.

Unveiling Uncertainty: Exploring the Potential of Neutrosophic Statistics for Artificial Intelligence

Artificial intelligence (AI) has revolutionized various fields, but its effectiveness can hampered by limitations in handling uncertainty inherent in real-world data. Traditional statistical methods often rely on binary logic (true/false) and may not adequately capture the nuances of uncertainty present in real-world data. This paper explores neutrosophic statistics (NS) as a novel approach to address uncertainty in AI applications. NS, introduced by Smarandache (1998), generalizes classical set theory by incorporating three truth-values: truth (T), indeterminacy (I), and falsity (F). This allows for a more nuanced representation of uncertainty compared to traditional binary methods. We discuss the limitations of classical statistics and how NS can overcome them. The paper explores the potential of NS for AI in areas like machine learning, data fusion, and Explainable AI (XAI). We propose research questions and methodology to investigate the effectiveness of NS integration with AI frameworks. The expected outcome is to contribute to the development of more robust and reliable AI systems by demonstrating the effectiveness of NS in handling uncertainty. Finally, we discuss future research directions to further explore the potential of NS for AI.

Strategic insights: mapping the terrain of artificial intelligence (AI) in banking through mixed method approach

Purpose The purpose of this paper is to supplement and update previously published articles about artificial intelligence (AI) instruments and operations in banking sectors with the following objectives in mind: to understand the role of AI in banking sectors; to explore the themes and context in this area based on keywords, co-citations and co-words; and to identify future research direction by evaluating the trend and direction of previous research. Design/methodology/approach This study adopts a semi-inductive approach with the convolution of bibliometrics and literature review. This study used bibliometrics for the identification of literature across multiple databases and systematic literature review on identified articles to explore heterogeneous sectors within AI in banking and finance. Findings This study contributes a literature-based model that accounts for both the broadly in AI application in banking and finance: predictive modeling in risk assessment and detection; financial decision-making; client service delivery; and emerging FinTech applications of AI and machine learning. Originality/value This study is among the few to address the literature of tools and application of AI in banking through mixed-methods approach and produce a synthesized model for the same.

Integrating the 6Cs in Moroccan Higher Education: A Framework for Inclusive AI Learning Design

Aligning market demands with the knowledge, competencies, and skills provided by higher education is a significant challenge and often falls primarily on the shoulders of educators. This study aims to explore the concept of inclusive AI learning design and its intersection with the integration of the 6Cs framework in higher education. In other words, it delves into the multifaceted role of Artificial Intelligence in the classroom, focusing primarily on the integration of the 6Cs (communication, collaboration, critical thinking, creativity, character education/ connectivity, and culture/ citizenship) in Moroccan higher education institutions, Artificial Intelligence literacy, and the cultivation of digital humanities techniques. The main research question guiding the study was “How to integrate the 6Cs at the tertiary level using inclusive Artificial Intelligence learning design? ». The study held significance in contributing to the existing literature by providing new insights and filling gaps in knowledge. To achieve the objectives of the study, the researcher relied on an exploratory descriptive approach through an interview and a self-developed questionnaire involving 15 ESP teachers. The results indicated that teachers face several challenges when integrating the 6C of 21st-century education into ESP classes, including engineering students’ low motivation, difficulties in combining multiple competencies, limitations in teaching materials, and time management issues. Hence, establishing a framework for inclusive Artificial Intelligence learning design that encompasses the 6 Cs is compulsory.

Artificial intelligence: An empirical survey of student and staff perspectives

There has been a recent upsurge in debates about the role and potential of artificial intelligence (AI) in transforming traditional learning environments globally, and more recently, these discussions have expanded to include developing countries. While proponents of AI praise it as a new normal that educators must embrace or risk falling behind, sceptics caution that AI poses significant risks to academic endeavours, often citing ethical dilemmas and widely reported misuse of these technologies. This study employed an explanatory sequential mixed methods design to explore student and staff perspectives on AI in teaching and learning. Data were collected from 375 students and 187 staff via a quantitative questionnaire, as well as from 30 students and 18 staff through follow-up semi-structured interviews. The findings revealed that although students and staff largely agreed on AI's potential to transform university teaching, learning, and research, there were significant differences regarding feedback enhancement, personalisation of learning, critical thinking, and the efficiency and accuracy of data analysis in research. The study recommends that stakeholders engage in ongoing dialogue, research, and professional development to navigate the opportunities and challenges presented by AI in education.

Artificial intelligence in the diagnostics and treatment of inflammatory bowel diseases (review)

Currently scientists from different countries are exploring the possibilities of using machine learning methods to improve the accuracy of endoscopic and radiation diagnostics in patients with inflammatory bowel diseases (IBD) both to reduce the time spent by doctors on describing the results and to reduce the time needed to verify the diagnosis. Predicting the course of IBD based on artificial intelligence (AI) with the creation of predictive scenarios (models) is another promising area in gastroenterology. This review analyzes the main directions of scientific projects on the introduction of AI and machine learning methods in the diagnosis and prediction of the course of IBD. The article pays special attention to the problems faced by specialists in the application of AI methods, ways to solve them, as well as the prospects for using AI in patients with IBD. The possibilities of using AI for colorectal cancer screening and analysis of medical records are presented.

AI and Machine Learning in International Diplomacy and Conflict Resolution

The role of incorporating Artificial Intelligence (AI) and Machine Learning (ML) in International Diplomacy and conflict resolution has the ability to revolutionize the current processes. The current paper aims at reviewing the future responsibilities of these technologies in improving diplomacy and forecasting wars. Thus, scrutinizing selected successful cases of AI use in diplomacy, and the possibilities of ML in conflict areas. The paper also covers the ethical issues and the possible developments of Artificial Intelligence in the sphere of diplomacy of various states. The conclusions stress the essential role of AI and ML in creating a more favorable external environment in order to reduce conflicts.

Prediction of flashover time in a compartment fire by CNN-LSTM based deep neural network considering wearable data collection equipment

Real-time prediction of flashover in a compartment fire is of great significance for rescue. This paper investigated a CNN-LSTM neural network to predict the flashover based on the temperature and radiative heat flux in 24 compartment fire cases simulated with FDS. Multiple conditions affecting compartment fires have been taken into account, like room size, room height, fire source location, opening size, number of vents, and fire load. Radiative heat flux meters and thermocouples were positioned at specific heights, to simulate sensors worn by firefighters entering a fire scene. The proposed model consisted of a convolutional layer and three LSTM layers. After training, the deep learning model effectively identified the flashover in compartment fires, with an average relative error of 4.1 % for temperature prediction and 11.2 % for radiative heat flux prediction. In addition, the model was validated on other simulated fire cases and full-scale experimental data, and the results showed good performance. In this paper, the sensitivity of the model to lead time was analyzed, and the application range of the model was determined. The model performed well within the lead time of 25s. In view of the strong performance of the proposed deep learning model in predicting flashover based on wearable sensors (temperature and radiative heat flux), it is believed that this model holds potential for application in a broader range of fire scenarios. This demonstrates the feasibility of using deep learning artificial intelligence models to predict compartment fire development, providing scientific guidance for smart firefighting technology.

Advancements in Electronic Component Assembly: Real-Time AI-Driven Inspection Techniques

This study presents an advanced methodology for improving electronic assembly quality through real-time, inline inspection utilizing state-of-the-art artificial intelligence (AI) and deep learning technologies. The primary goal is to ensure compliance with stringent manufacturing standards, notably IPC-A-610 and IPC-J-STD-001. Employing the existing infrastructure of pick-and-place machines, this system captures high-resolution images of electronic components during the assembly process. These images are analyzed instantly by AI algorithms capable of detecting a variety of defects, including damage, corrosion, counterfeit, and structural irregularities in components and their leads. This proactive approach shifts from conventional reactive quality assurance methods by integrating real-time defect detection and strict adherence to industry standards into the assembly process. With an accuracy rate exceeding 99.5% and processing speeds of about 5 ms per component, this system enables manufacturers to identify and address defects promptly, thereby significantly enhancing manufacturing quality and reliability. The implementation leverages big data analytics, analyzing over a billion components to refine detection algorithms and ensure robust performance. By pre-empting and resolving defects before they escalate, the methodology minimizes production disruptions and fosters a more efficient workflow, ultimately resulting in considerable cost reductions. This paper showcases multiple case studies of component defects, highlighting the diverse types of defects identified through AI and deep learning. These examples, combined with detailed performance metrics, provide insights into optimizing electronic component assembly processes, contributing to elevated production efficiency and quality.