Hasil untuk "artificial intelligence"

Pierrick Pochelu, Hyacinthe Cartiaux, Julien Schleich

High-performance computing (HPC) centers consume substantial power, incurring environmental and operational costs. This review assesses how artificial intelligence (AI), including machine learning (ML) and optimization, improves the efficiency of operational HPC systems. Approximately 1,800 publications from 2019 to 2025 were manually screened using predefined inclusion/exclusion criteria; 74 "AI for HPC" papers were retained and grouped into six application areas: performance estimation, performance optimization, scheduling, surrogate modeling, fault detection, and language-model-based automation. Scheduling is the most active area, spanning research-oriented reinforcement-learning schedulers to production-friendly hybrids that combine ML with heuristics. Supervised performance estimation is foundational for both scheduling and optimization. Graph neural networks and time-series models strengthen anomaly detection by capturing spatio-temporal dependencies in production telemetry. Domain-specialized language models for HPC can outperform general-purpose LLMs on targeted coding and automation tasks. Together, these findings highlight integration opportunities such as LLM-based operating-system concepts and underscore the need for advances in MLOps, standardization of AI components, and benchmarking methodology.

Aisvarya Adeseye, Jouni Isoaho, Seppo Virtanen et al.

In today's artificial intelligence driven world, modern systems communicate with people from diverse backgrounds and skill levels. For human-machine interaction to be meaningful, systems must be aware of context and user expertise. This study proposes an agentic AI profiler that classifies natural language responses into four levels: Novice, Basic, Advanced, and Expert. The system uses a modular layered architecture built on LLaMA v3.1 (8B), with components for text preprocessing, scoring, aggregation, and classification. Evaluation was conducted in two phases: a static phase using pre-recorded transcripts from 82 participants, and a dynamic phase with 402 live interviews conducted by an agentic AI interviewer. In both phases, participant self-ratings were compared with profiler predictions. In the dynamic phase, expertise was assessed after each response rather than at the end of the interview. Across domains, 83% to 97% of profiler evaluations matched participant self-assessments. Remaining differences were due to self-rating bias, unclear responses, and occasional misinterpretation of nuanced expertise by the language model.

Dayun Jeong

The rapid evolution of technology characteristics has significantly influenced various sectors, including fashion, in which technology-enabled platforms have increasingly been utilized to enhance personalization and consumer engagement. This study investigates the effect of these characteristics on consumer behavior within fashion curation platforms. Integrating the task–technology fit and the unified theory of acceptance and use of technology models, this study examines key constructs using structural equation modeling. Data were collected via a week-long survey of 300 Korean consumers using fashion curation platforms. The findings reveal that technology characteristics exert a significant influence on task–technology fit and effort expectancy. Additionally, hedonic motivation, social influence, and facilitating conditions were pivotal in shaping behavioral intention. The novelty of this work lies in the fact that it extends the integrated model framework to a fashion curation context to offer a more nuanced understanding. Moreover, the findings provide practical insights for optimizing technology-enabled fashion platforms to boost user adoption and engagement.

Eleni Fotopoulou, Anastasios Zafeiropoulos, Eleftheria Arkadopoulou et al.

The positive impact of Social and Emotional Learning (SEL) activities in schools is widely recognized in various sectors, including mental health, social relationships, and academic performance of students. This impact can be efficiently realized and catalyzed based on the development of tools that help teachers to effectively and consistently apply SEL in classrooms. Such tools can leverage emerging Artificial Intelligence (AI) technologies, including Generative AI (GenAI) and Agentic AI, and Knowledge Graphs to enable their ease of adoption and use by teachers and provide accurate and context-aware guidance. In this perspective, this manuscript presents an Agentic Graph Retrieval-Augmented Generation (RAG) approach to support educators to apply methodologies for SEL. The approach is materialized through an agent, called MySELAgent, which synthesizes information and provides recommendations around SEL, taking advantage of GenAI and following an Agentic AI approach. MySELAgent is interoperable with third-party psychometric tools, enabling assessment and monitoring of the social and emotional competencies of students. It is able to suggest evidence-based targeted SEL activities and create holistic SEL intervention programs in the form of learning pathways, which are based on teachers’ pReferences and students’ emotional needs. A detailed evaluation of the implemented techniques is presented, analyzing the performance and effectiveness of MySELAgent on retrieving information and creating accurate responses based on the use of different Large Language Models (LLMs).

Alex Glynn

The tendency of generative artificial intelligence (AI) systems to "hallucinate" false information is well-known; AI-generated citations to non-existent sources have made their way into the reference lists of peer-reviewed publications. Here, I propose a solution to this problem, taking inspiration from the Transparency and Openness Promotion (TOP) data sharing guidelines, the clash of generative AI with the American judiciary, and the precedent set by submissions of prior art to the United States Patent and Trademark Office. Journals should require authors to submit the full text of each cited source along with their manuscripts, thereby preventing authors from citing any material whose full text they cannot produce. This solution requires limited additional work on the part of authors or editors while effectively immunizing journals against hallucinated references.

Marie S. Bauer, Julia Gachot, Matthias Kerzel et al.

Within the context of human-robot interaction (HRI), Theory of Mind (ToM) is intended to serve as a user-friendly backend to the interface of robotic systems, enabling robots to infer and respond to human mental states. When integrated into robots, ToM allows them to adapt their internal models to users' behaviors, enhancing the interpretability and predictability of their actions. Similarly, Explainable Artificial Intelligence (XAI) aims to make AI systems transparent and interpretable, allowing humans to understand and interact with them effectively. Since ToM in HRI serves related purposes, we propose to consider ToM as a form of XAI and evaluate it through the eValuation XAI (VXAI) framework and its seven desiderata. This paper identifies a critical gap in the application of ToM within HRI, as existing methods rarely assess the extent to which explanations correspond to the robot's actual internal reasoning. To address this limitation, we propose to integrate ToM within XAI frameworks. By embedding ToM principles inside XAI, we argue for a shift in perspective, as current XAI research focuses predominantly on the AI system itself and often lacks user-centered explanations. Incorporating ToM would enable a change in focus, prioritizing the user's informational needs and perspective.

Jinhao Jiang, Changlin Chen, Shile Feng et al.

The ultimate goal of artificial intelligence (AI) is to achieve Artificial General Intelligence (AGI). Embodied Artificial Intelligence (EAI), which involves intelligent systems with physical presence and real-time interaction with the environment, has emerged as a key research direction in pursuit of AGI. While advancements in deep learning, reinforcement learning, large-scale language models, and multimodal technologies have significantly contributed to the progress of EAI, most existing reviews focus on specific technologies or applications. A systematic overview, particularly one that explores the direct connection between EAI and AGI, remains scarce. This paper examines EAI as a foundational approach to AGI, systematically analyzing its four core modules: perception, intelligent decision-making, action, and feedback. We provide a detailed discussion of how each module contributes to the six core principles of AGI. Additionally, we discuss future trends, challenges, and research directions in EAI, emphasizing its potential as a cornerstone for AGI development. Our findings suggest that EAI's integration of dynamic learning and real-world interaction is essential for bridging the gap between narrow AI and AGI.

Wiktor Stopyra, Oleksiy Voytsekhivskyy, Andrzej Grzybowski

<b>Purpose:</b> To compare the accuracy of seven artificial intelligence (AI)-based intraocular lens (IOL) power calculation formulas in medium-long Caucasian eyes regarding the root-mean-square absolute error (RMSAE), the median absolute error (MedAE) and the percentage of eyes with a prediction error (PE) within ±0.5 D. <b>Methods:</b> Data on Caucasian patients who underwent uneventful phacoemulsification between May 2018 and September 2023 in MW-Med Eye Center, Krakow, Poland and Kyiv Clinical Ophthalmology Hospital Eye Microsurgery Center, Kyiv, Ukraine were reviewed. Inclusion criteria, i.e., complete biometric and refractive data, were applied. Exclusion criteria were as follows: intraoperative or postoperative complications, previous eye surgery or corneal diseases, postoperative BCVA less than 0.8, and corneal astigmatism greater than 2.0 D. Prior to phacoemulsification, IOL power was computed using SRK/T, Holladay1, Haigis, Holladay 2, and Hoffer Q. The refraction was measured three months after cataract surgery. Post-surgery intraocular lens calculations for Hill-RBF 3.0, Kane, PEARL-DGS, Ladas Super Formula AI (LSF AI), Hoffer QST, Karmona, and Nallasamy were performed. RMSAE, MedAE, and the percentage of eyes with a PE within ±0.25 D, ±0.50 D, ±0.75 D, and ±1.00 were counted. <b>Results:</b> Two hundred fourteen eyes with axial lengths ranging from 24.50 mm to 25.97 mm were tested. The Hill-RBF 3.0 formula yielded the lowest RMSAE (0.368), just before Pearl-DGS (0.374) and Hoffer QST (0.378). The lowest MedAE was achieved by Hill-RBF 3.0 (0.200), the second-lowest by LSF AI (0.210), and the third-lowest by Kane (0.228). The highest percentage of eyes with a PE within ±0.50 D was obtained by Hill-RBF 3.0, LSF AI, and Pearl-DGS (86.45%, 85.51%, and 85.05%, respectively). <b>Conclusions:</b> The Hill-RBF 3.0 formula provided highly accurate outcomes in medium-long eyes. All studied AI-based formulas yielded good results in IOL power calculation.

Dino Petrosa, Pamela Haverkamp, Jana Gerta Backes et al.

Abstract The construction sector significantly contributes to environmental issues and often relies on Life Cycle Assessment (LCA) for the quantification and optimization of its environmental impacts. One of the most time- and labour-intensive tasks in LCA is matching real elements (e.g., construction elements and materials) to suitable environmental datasets to get an idea of the element’s sustainability performance (emissions). In this regard, this study presents an open-access software tool that leverages artificial intelligence (AI) to support the matching process between construction elements in Building Information Modelling (BIM) with corresponding environmental datasets in a semi-automatic manner. Developed in Python and using the GPT-4o mini model from OpenAI for its matching mechanism, the tool demonstrates how AI-driven digital innovation can improve efficiency, reduce manual effort, and enhance early-stage environmental assessment in construction planning, while integrating sustainability data into BIM workflows. Through a series of use cases, the software’s ability to address key challenges in the integration of BIM and LCA tools is demonstrated, showcasing a high degree of automation and interoperability. Moreover, the accessible design of the tool allows use without extensive technical knowledge. The conducted validation tests confirmed the tool’s potential for accurate LCA matching, highlighting opportunities for AI to enhance sustainability workflows while offering BIM experts a better understanding of the challenges in sustainability assessment.

Cuixia Liu, Meng Meng, Xian Luo

Based on the innovative mode driven by “data + artificial intelligence”, in this study, three methods, namely Gaussian noise (GAUSS Noise), the Generative Adversarial Network (GAN), and the optimized Generative Adversarial Network (GANPro), are adopted to expand and enhance the collected dataset of element contents and the hardness of the AlCoCrCuFeNi high-entropy alloy. Bayesian optimization with grid search is used to determine the optimal combination of hyperparameters, and two interpretability methods, SHAP and permutation importance, are employed to further explore the relationship between the element features of high-entropy alloys and hardness. The results show that the optimal data augmentation method is Gaussian noise enhancement; its accuracy reaches 97.4% under the addition of medium noise (σ = 0.003), and an optimal performance prediction model based on the existing dataset is finally constructed. Through the interpretability method, it is found that the contributions of Al and Ni are the most prominent. When the Al content exceeds 0.18 mol, it has a positive promoting effect on hardness, while Ni and Cu exhibit a critical effect of promotion–inhibition near 0.175 mol and 0.14 mol, respectively, revealing the nonlinear regulation law of element contents. This study solves the problem of revealing the mutual relationship between the element contents and hardness of high-entropy alloys in the case of a lack of alloy data and provides theoretical guidance for further improving the performance of high-entropy alloys.

Jinfang Ma, Mao Li, Lingxiao Yang et al.

ABSTRACT The pancreatic islets of Langerhans, which are composed of α, β, δ, ε, and PP cells, orchestrate systemic glucose homeostasis through tightly regulated hormone secretion. Although the precise mechanisms involving β cells in the onset and progression of diabetes have been elucidated and insulin replacement therapy remains the primary treatment modality, the regulatory processes, functions, and specific roles of other pancreatic islet hormones in diabetes continue to be the subject of ongoing investigation. At present, a comprehensive review of the secretion and regulation of pancreatic islet cell hormones as well as the related mechanisms of diabetes is lacking. This review synthesizes current knowledge on the secretion mechanisms of insulin, glucagon, somatostatin, ghrelin, and pancreatic polypeptides, emphasizing their functional crosstalk in diabetes. Emerging advances include CRISPR‐based β‐cell regeneration, bioengineered islet transplantation, and bioelectronic interventions aimed at restoring pancreatic function. Future research directions highlight artificial intelligence‐guided prediction of hormone dynamics, therapeutics targeting the gut microbiome–islet axis, and tissue‐engineered artificial islets. By integrating mechanistic insights, physiological roles, and translational innovations, this review outlines precision strategies for targeting islet hormone networks, offering a roadmap toward restoring metabolic equilibrium in diabetes.

Shahid Alam, Zeynep Altiparmak

With the rise of complex cyber devices Cyber Forensics (CF) is facing many new challenges. For example, there are dozens of systems running on smartphones, each with more than millions of downloadable applications. Sifting through this large amount of data and making sense requires new techniques, such as from the field of Artificial Intelligence (AI). To apply these techniques successfully in CF, we need to justify and explain the results to the stakeholders of CF, such as forensic analysts and members of the court, for them to make an informed decision. If we want to apply AI successfully in CF, there is a need to develop trust in AI systems. Some other factors in accepting the use of AI in CF are to make AI authentic, interpretable, understandable, and interactive. This way, AI systems will be more acceptable to the public and ensure alignment with legal standards. An explainable AI (XAI) system can play this role in CF, and we call such a system XAI-CF. XAI-CF is indispensable and is still in its infancy. In this paper, we explore and make a case for the significance and advantages of XAI-CF. We strongly emphasize the need to build a successful and practical XAI-CF system and discuss some of the main requirements and prerequisites of such a system. We present a formal definition of the terms CF and XAI-CF and a comprehensive literature review of previous works that apply and utilize XAI to build and increase trust in CF. We discuss some challenges facing XAI-CF. We also provide some concrete solutions to these challenges. We identify key insights and future research directions for building XAI applications for CF. This paper is an effort to explore and familiarize the readers with the role of XAI applications in CF, and we believe that our work provides a promising basis for future researchers interested in XAI-CF.

Xiangyu Wu, Hailiang Zhang, Yang Yang et al.

In this paper, we present our champion solution to the Global Artificial Intelligence Technology Innovation Competition Track 1: Medical Imaging Diagnosis Report Generation. We select CPT-BASE as our base model for the text generation task. During the pre-training stage, we delete the mask language modeling task of CPT-BASE and instead reconstruct the vocabulary, adopting a span mask strategy and gradually increasing the number of masking ratios to perform the denoising auto-encoder pre-training task. In the fine-tuning stage, we design iterative retrieval augmentation and noise-aware similarity bucket prompt strategies. The retrieval augmentation constructs a mini-knowledge base, enriching the input information of the model, while the similarity bucket further perceives the noise information within the mini-knowledge base, guiding the model to generate higher-quality diagnostic reports based on the similarity prompts. Surprisingly, our single model has achieved a score of 2.321 on leaderboard A, and the multiple model fusion scores are 2.362 and 2.320 on the A and B leaderboards respectively, securing first place in the rankings.

Jian Wang, Yujia Huo, Jinli Mahe et al.

Artificial intelligence (AI) ethics has emerged as a global discourse within both academic and policy spheres. However, translating these principles into concrete, real-world applications for AI development remains a pressing need and a significant challenge. This study aims to bridge the gap between principles and practice from a regulatory government perspective and promote best practices in AI governance. To this end, we developed the Ethical Regulatory Framework for AI (ERF-AI) to guide regulatory bodies in constructing mechanisms, including role setups, procedural configurations, and strategy design. The framework was developed through a systematic review, thematic analysis, and the integration of interdisciplinary concepts. A comprehensive search was conducted across four electronic databases (PubMed, IEEE Xplore, Web of Science, and Scopus) and four additional sources containing AI standards and guidelines from various countries and international organizations, focusing on studies published from 2014 to 2024. Thematic analysis identified and refined key themes from the included literature and integrated concepts from process control theory, computer science, organizational management, information technology, and behavioral psychology. This study adhered to the PRISMA guidelines and employed NVivo for thematic analysis. The resulting framework encompasses 23 themes, particularly emphasizing three feedback-loop processes: the ethical review process, the incentive and penalty process, and the mechanism improvement process, offering theoretical guidance for the construction of ethical regulatory mechanisms. Based on this framework, a seven-step process and case examples for mechanism design are presented, enhancing the practicality of ERF-AI in developing ethical regulatory mechanisms. Future research is expected to explore customization of the framework to remain responsive to emerging AI trends and challenges, supported by empirical studies and rigorous testing for further refinement and expansion.

Isha Duggal, Tulika Tripathi

In the current technological era, dental practitioners are faced with various ethical challenges, highlighting the importance of bioethics in this healthcare discipline. The rise of artificial intelligence has recently sparked a debate regarding the privacy of patient data. While the advancements may offer innovative treatment options, their long-term effects may not be fully understood, raising questions about the responsible implementation of such methods. Thus, conscientious and ethical AI use in dentistry encompasses that patients be notified about how their data is used and also about the involvement of AI-based decision-making. This paper explores the key bioethical considerations in dental healthcare, with a focus on evidence-based AI development and use. The framework of ethical principles and guidelines provided would foster trust between the clinician and patients, while promoting the highest standards of care.

Jiayun Xin, Mohammad Khishe, Diyar Qader Zeebaree et al.

Deep Convolutional Neural Networks (DCNNs) have shown remarkable success in image classification tasks, but optimizing their hyperparameters can be challenging due to their complex structure. This paper develops the Adaptive Habitat Biogeography-Based Optimizer (AHBBO) for tuning the hyperparameters of DCNNs in image classification tasks. In complicated optimization problems, the BBO suffers from premature convergence and insufficient exploration. In this regard, an adaptable habitat is presented as a solution to these problems; it would permit variable habitat sizes and regulated mutation. Better optimization performance and a greater chance of finding high-quality solutions across a wide range of problem domains are the results of this modification's increased exploration and population diversity. AHBBO is tested on 53 benchmark optimization functions and demonstrates its effectiveness in improving initial stochastic solutions and converging faster to the optimum. Furthermore, DCNN-AHBBO is compared to 23 well-known image classifiers on nine challenging image classification problems and shows superior performance in reducing the error rate by up to 5.14%. Our proposed algorithm outperforms 13 benchmark classifiers in 87 out of 95 evaluations, providing a high-performance and reliable solution for optimizing DNNs in image classification tasks. This research contributes to the field of deep learning by proposing a new optimization algorithm that can improve the efficiency of deep neural networks in image classification.

Hyun Park, Xiaoli Yan, Ruijie Zhu et al.

Metal-organic frameworks (MOFs) exhibit great promise for CO2 capture. However, finding the best performing materials poses computational and experimental grand challenges in view of the vast chemical space of potential building blocks. Here, we introduce GHP-MOFassemble, a generative artificial intelligence (AI), high performance framework for the rational and accelerated design of MOFs with high CO2 adsorption capacity and synthesizable linkers. GHP-MOFassemble generates novel linkers, assembled with one of three pre-selected metal nodes (Cu paddlewheel, Zn paddlewheel, Zn tetramer) into MOFs in a primitive cubic topology. GHP-MOFassemble screens and validates AI-generated MOFs for uniqueness, synthesizability, structural validity, uses molecular dynamics simulations to study their stability and chemical consistency, and crystal graph neural networks and Grand Canonical Monte Carlo simulations to quantify their CO2 adsorption capacities. We present the top six AI-generated MOFs with CO2 capacities greater than 2 $m mol/g$, i.e., higher than 96.9% of structures in the hypothetical MOF dataset.

V. I. Yukalov

The review analyzes the fundamental principles which Artificial Intelligence should be based on in order to imitate the realistic process of taking decisions by humans experiencing emotions. Two approaches are compared, one based on quantum theory and the other employing classical terms. Both these approaches have a number of similarities, being principally probabilistic. The analogies between quantum measurements under intrinsic noise and affective decision making are elucidated. It is shown that cognitive processes have many features that are formally similar to quantum measurements. This, however, in no way means that for the imitation of human decision making Affective Artificial Intelligence has necessarily to rely on the functioning of quantum systems. Appreciating the common features between quantum measurements and decision making helps for the formulation of an axiomatic approach employing only classical notions. Artificial Intelligence, following this approach, operates similarly to humans, by taking into account the utility of the considered alternatives as well as their emotional attractiveness. Affective Artificial Intelligence, whose operation takes account of the cognition-emotion duality, avoids numerous behavioural paradoxes of traditional decision making. A society of intelligent agents, interacting through the repeated multistep exchange of information, forms a network accomplishing dynamic decision making. The considered intelligent networks can characterize the operation of either a human society of affective decision makers, or the brain composed of neurons, or a typical probabilistic network of an artificial intelligence.

Bilel Benjdira, Anis Koubaa, Ahmad Taher Azar et al.

Smart traffic engineering and intelligent transportation services are in increasing demand from governmental authorities to optimize traffic performance and thus reduce energy costs, increase the drivers' safety and comfort, ensure traffic laws enforcement, and detect traffic violations. In this paper, we address this challenge, and we leverage the use of Artificial Intelligence (AI) and Unmanned Aerial Vehicles (UAVs) to develop an AI-integrated video analytics framework, called TAU (Traffic Analysis from UAVs), for automated traffic analytics and understanding. Unlike previous works on traffic video analytics, we propose an automated object detection and tracking pipeline from video processing to advanced traffic understanding using high-resolution UAV images. TAU combines six main contributions. First, it proposes a pre-processing algorithm to adapt the high-resolution UAV image as input to the object detector without lowering the resolution. This ensures an excellent detection accuracy from high-quality features, particularly the small size of detected objects from UAV images. Second, it introduces an algorithm for recalibrating the vehicle coordinates to ensure that vehicles are uniquely identified and tracked across the multiple crops of the same frame. Third, it presents a speed calculation algorithm based on accumulating information from successive frames. Fourth, TAU counts the number of vehicles per traffic zone based on the Ray Tracing algorithm. Fifth, TAU has a fully independent algorithm for crossroad arbitration based on the data gathered from the different zones surrounding it. Sixth, TAU introduces a set of algorithms for extracting twenty-four types of insights from the raw data collected. The code is shared here: https://github.com/bilel-bj/TAU. Video demonstrations are provided here: https://youtu.be/wXJV0H7LviU and here: https://youtu.be/kGv0gmtVEbI.

Lukas Stappen, Jeremy Dillmann, Serena Striegel et al.

This paper aims to serve as a comprehensive guide for researchers and practitioners, offering insights into the current state, potential applications, and future research directions for generative artificial intelligence and foundation models within the context of intelligent vehicles. As the automotive industry progressively integrates AI, generative artificial intelligence technologies hold the potential to revolutionize user interactions, delivering more immersive, intuitive, and personalised in-car experiences. We provide an overview of current applications of generative artificial intelligence in the automotive domain, emphasizing speech, audio, vision, and multimodal interactions. We subsequently outline critical future research areas, including domain adaptability, alignment, multimodal integration and others, as well as, address the challenges and risks associated with ethics. By fostering collaboration and addressing these research areas, generative artificial intelligence can unlock its full potential, transforming the driving experience and shaping the future of intelligent vehicles.