Frontiers in Artificial Intelligence | New and Recent Articles

A binary decision tree (BDT) is stochastic and depth-dependent when inference is performed. The lower and upper bounds are derived from the minimum and maximum heights of the leaf nodes. The inherent randomness complicates BDT and random forest (RF) inference processes for fixed-rate streaming data. BDT is reformulated as a Boolean decision structure (BDS) in the proposed method to enable constan…

Two converging crises—uncontrolled operational expenditure and significant environmental hazards—have been aggravated by the exponential scaling of cloud infrastructure. This has led to a greater focus on the efficiency of Financial Operations (FinOps). Current monitoring methods exhibit a major flaw: passive dashboards require constant human monitoring and lead to alert fatigue, whereas deep lea…

IntroductionGraph data representation is widely applicable in numerous real-world scenarios, and recent advances in graph neural networks (GNNs) have enabled effective modeling of complex associations in graph-structured data. However, GNNs are often constrained by the over-smoothing problem, which reduces their ability to distinguish node representations. In contrast, large language models (LLMs…

Active learning (AL) is a central response to the annotation bottleneck in modern artificial intelligence: when labels are expensive, a learner should query for the most useful forms of supervision rather than indiscriminately acquiring labels. However, contemporary AL is no longer a unified field organized around a small set of stable query principles. It is fragmented across acquisition strateg…

Artificial Intelligence (AI) and Machine Learning (ML) have transformed the agricultural sector and will continue to do so. Adopting AI/ML technology has the potential to help meet global food, feed, and fiber demands while promoting sustainable farming practices. However, adoption depends on multiple dimensions of trust, particularly trust in system performance and trust in data governance. In t…

Autofluorescence (AF) imaging enables label-free visualization of tissue metabolism and microenvironmental alterations, while deep learning (DL) provides powerful tools to decode its complex optical signatures. Their integration has emerged as a promising framework for functional and biologically informed disease assessment. Recent studies demonstrate that AF-DL approaches improve lesion detectio…

BackgroundThe rapid integration of Generative Artificial Intelligence (GenAI) into education presents unique opportunities and challenges, particularly in developing nations. While research has explored factors influencing GenAI adoption, its subsequent impact on teachers’ core professional beliefs remains under-investigated. This study addresses this gap by examining the relationship between Gen…

This mini review surveys published work on automatic summarization of legal judgments. We focus on how natural language processing handles argument structure, discourse, and the role of citations and precedent when systems generate shorter versions of a case. The field began with extractive methods and classical machine learning, and moved through graph-based and neural models, and to recent tran…

The cognitive state modeling (CSM) problem is typically formulated as a classification problem, limiting the application of the CSM for adaptive real world applications, where the desired outputs are cognitive states to be desired and the inferred ones have to be used for decision making. While conventional methods classify states of the brain, they have not yet been able to connect the class to …

Pharmaceutical research and development has accumulated vast and heterogeneous archives of data. Much of this knowledge stems from discontinued programs, and reusing these archives is invaluable for reverse translation. However, in practice, such reuse is often infeasible. In this work, we introduce DiscoVerse, a multi-agent co-scientist designed to support pharmaceutical research and development…

The expansion of Internet of Things (IoT) and Internet of Medical Things (IoMT) infrastructures has increased the generation of multivariate sensor streams that reflect complex operational behaviors in industrial and clinical environments. Centralized anomaly detection approaches face limitations in IoMT due to privacy constraints, latency, and device heterogeneity. Federated learning (FL) enable…

The adoption of artificial intelligence (AI) in digital banking continues to increase as financial institutions seek to improve service efficiency, personalization, and customer experience. However, user acceptance of AI-enabled banking services remains a significant challenge, particularly in high-risk financial environments where trust, security, and perceived reliability are critical considera…

Large Language Models (LLMs) are being increasingly incorporated into decision-support systems. Nonetheless, a lack of clarity remains with reference to their reasoning processes, particularly in multilingual contexts. This uncertainty extends to cognitive biases - systematic errors in judgment, similar to those documented in human cognition. Existing research on cognitive biases in LLMs has focu…

IntroductionLiterary translation has recently gained attention as a distinct and complex task in machine translation research, yet translation by small open models remains an open problem, particularly for low-resource languages such as Romanian.MethodsWe introduce the TinyFabulist Translation Framework (TF2), a unified framework for dataset creation, fine-tuning, and evaluation in English → Roma…

Fluorodeoxyglucose (FDG) PET to evaluate patients with epilepsy is one of the most common applications for simultaneous PET/MRI, given the need to image both brain structure and metabolism but is suboptimal due to the radiation dose in this young population. Little work has been done synthesizing diagnostic quality PET images from MRI data or MRI data with ultralow-dose PET using advanced generat…

IntroductionThe Indian Lok Sabha generates a continuously expanding corpus of legislative records, predominantly archived as unstructured PDF files. Effective public access remains limited due to the shortcomings of keyword-based retrieval systems and the hallucination risks of general-purpose Large Language Models (LLMs).MethodsThis paper presents a domain-specific, resource-efficient Retrieval-…

IntroductionCancer is a leading cause of mortality worldwide. Anticancer peptides (ACPs) are promising therapeutic candidates due to their low toxicity, favorable biocompatibility, and selective anticancer activity; however, experimental ACP identification and screening remain labor-intensive, time-consuming, and costly.MethodsWe developed ProtT5-MSCRNet, an end-to-end deep learning framework for…

Rich and accurate medical image segmentation is poised to underpin the next generation of AI-defined clinical practice by delineating critical anatomy for pre-operative planning, guiding real-time intra-operative navigation, and supporting precise post-operative assessment. However, commonly used learning methods for medical and surgical imaging segmentation tasks penalize all errors equivalently…

The Internet of Medical Things (IoMT) environments face significant challenges in securely transmitting and storing medical images due to limited computational resources, multiple device types, and increasing cybersecurity threats. This paper describes a reversible RGB medical image encryption framework that employs deep reinforcement learning by combining adaptive policy learning with determinis…

IntroductionSafety supervision at power operation sites is critical for ensuring worker safety and maintaining a reliable electricity supply. However, existing safety violation detection methods are constrained by limited labeled data, poor performance on small-object detection tasks, and interference from complex backgrounds.MethodsTo overcome these challenges, this study proposes a framework th…