Artificial Intelligence Review最新文献

Accurate estimation of a rigid object’s 6D pose and twist is a fundamental challenge for enabling autonomous systems operation and interaction with the environment. Monocular vision can mitigate the drift inherent in inertial methods and enables the estimation of non-cooperative target twist. However, the estimation accuracy of monocular vision is compromised by inherent depth ambiguity, a limitation that multi-camera systems can overcome. The lack of multi-view datasets with high-precision annotations hinders the development of robust perception algorithms. To address this, we present the first trinocular pose and twist estimation dataset for non-cooperative targets, comprising images of aircraft (7,824 for training, 4,710 for testing) and satellites (7683 for training, 4380 for testing), all manually annotated with sub-pixel-level keypoints and pose labels derived from optimization. We develop a neural network that predicts semantic keypoints for robust pose estimation. Combined with a multi-view optimization framework and twist estimation, our system achieves a mean angular velocity error of (0.1^{circ })/s and a mean linear velocity error of 0.3mm/s. Our open-source dataset and method provide a critical benchmark for future research in aerospace missions. We have open-sourced the dataset at the following https://www.kaggle.com/datasets/mingshiwuwjh/trinocular-pose-and-twist-estimation-dataset.

Structural engineering (SE) is a diverse field with numerous applications, including computational mechanics, structural simulation, and topology optimization, all governed by fundamental physical principles and typically addressed through classical numerical methods. These methods have delivered reliable and accurate solutions for forward problems within well-defined domains. However, they can become less effective when faced with high-dimensional spaces, complex geometries, irregular domains, or inverse problems with limited data. In parallel, data-driven models have gained popularity, but their dependence on large datasets and lack of physical interpretability restrict their generalization to unseen conditions. Physics-Informed Neural Networks (PINNs) have recently emerged as complementary tools that combine the strengths of numerical and data-driven approaches. By embedding governing physical laws directly into the learning process, PINNs reduce reliance on extensive datasets while improving interpretability and robustness. Although they may not yet rival classical solvers in terms of computational efficiency or accuracy for standard forward problems, PINNs offer unique advantages in scenarios where meshing is challenging, data and physics need to be integrated, or inverse problems require parameter identification and damage detection. This review provides a comprehensive overview of PINNs in SE, focusing on their theoretical framework, training strategies, computational implementations, and applications to both forward and inverse problems. The discussion highlights their advantages in accuracy, flexibility, and hybrid data-physics integration, while also outlining current limitations and future research directions to enhance their robustness and applicability for solving complex real-world SE problems.

Android is the most widely used operating system, making it a prime target for mobile malware, leading to data breaches and financial losses (e.g., Dark Herring). To address these issues, AI-based forensic tools are crucial for investigating security incidents, but their accuracy depends on high-quality mobile malware datasets. While dynamic analysis has limitations, recent research has shifted towards static analysis and AI-based methods for malware detection. However, there are three key challenges: lack of reproducibility, low dataset quality, and bias in AI datasets. This paper focuses on an overlooked bias—the incorrect API Level distribution in malware datasets. Such bias skews AI detection results, making them appear effective in tests but less applicable in real-world scenarios. To highlight the importance of dataset quality, three case studies on API Level Analysis were conducted, showing how biased datasets can distort detection results. To address this, the paper introduces methods and terms like Delayed Interception, Dataset of guaranteed quality, API Milestones, AndroBank, and Sample Unification, which aim to enhance dataset reliability and improve AI-based mobile malware detection.

Biofortified crops have gained significant attention as a sustainable solution to address malnutrition and under nutrition, particularly in developing countries. These crops are genetically enhanced to have higher levels of essential nutrients such as vitamins and minerals. It aims to improve the nutritional quality of staple foods and promote better health outcomes in populations that rely heavily on these crops. Biofortified crops play an important role in addressing global health challenges, providing a cost-effective and scalable approach to improving nutrition. But the selection of biofortified crops among various options is a complex task for decision-makers. Therefore, this paper introduces a novel approach called the feed-backward Double-hierarchy linguistic neural networks using double-hierarchy linguistic term fuzzy information to handle this issue. For this, we develop a series of weighted averaging Yager-Dombi aggregation operators and also discuss their desirable properties. The decision-making process becomes complex due to unknown weight vectors. Entropy distance measures are used to locate unknown weight vectors. The study addresses a real-world MADM problem by demonstrating that biofortified rice could potentially address vitamin A deficiency, a significant health concern in developing regions. The WASPAS approach is used to verify the proposed method, and its feasibility and efficacy are evaluated compared to other MADM techniques.

Reinforcement learning (RL), as an emerging interdisciplinary field formed by the integration of artificial intelligence and control science, is currently demonstrating a cross-disciplinary development trend led by artificial intelligence and has become a research hotspot in the field of optimal control. This paper systematically reviews the development context of RL, focusing on the intrinsic connection between single-agent reinforcement learning (SARL) and multi-agent reinforcement learning (MARL). Firstly, starting from the formation and development of RL, it elaborates on the similarities and differences between RL and other learning paradigms in machine learning, and briefly introduces the main branches of current RL. Then, with the basic knowledge and core ideas of SARL as the basic framework, and expanding to multi-agent system (MAS) collaborative control, it explores the coherence characteristics of the two in theoretical frameworks and algorithm design. On this basis, this paper reconfigures SARL algorithms into dynamic programming, value function decomposition and policy gradient (PG) type, and abstracts MARL algorithms into four paradigms: behavior analysis, centralized learning, communication learning and collaborative learning, thus establishing an algorithm mapping relationship from single-agent to multi-agent scenarios. This innovative framework provides a new perspective for understanding the evolutionary correlation of the two methods, and also discusses the challenges and solution ideas of MARL in solving large-scale MAS problems. This paper aims to provide a reference for researchers in this field, and to promote the development of cooperative control and optimization methods for MAS as well as the advancement of related application research.

Wetlands are critical ecosystems supporting biodiversity and providing essential environmental services. With increasing threats to wetlands, efficient classification techniques are essential for effective conservation. Several researchers have contributed to wetland classification across reputable journals. However, some challenges (data scarcity, noisy labels, and model generalisability) still exist. Therefore, this paper presents a comprehensive survey of recent advancements in machine learning (ML) and deep learning (DL) for wetland classification, focusing on developments from 2018 to 2025. Key methodologies, including convolutional neural networks, transformers, and generative adversarial networks, are critically reviewed, highlighting their strengths, limitations, and applications in remote sensing. Unlike previous reviews, this work emphasises underexplored techniques such as few-shot learning and Mamba networks, offering practical recommendations for handling limited training data and improving model generalisability. The study also identifies promising research directions, such as test-time training and hybrid loss functions, to address challenges in wetland classification. This survey aims to guide researchers and practitioners in advancing state-of-the-art wetland classification through ML and DL technologies.

Effective communication is essential for human touch, and it’s especially crucial for those who rely on sign language because they have speech or hearing difficulties. Communication between deaf and normal people is restricted by the inability of current technology to automatically create flexible Bangla Sign Language (BdSL) animations from Bangla text or voice. This work introduces a revolutionary computer graphics-based system that takes voice or text input in Bangla and uses it to create BdSL animations. The system uses a HamNoSys to Gesture Markup Language (SiGML) conversion to dynamically translate input into gestures. With the use of 94 classes in the dataset that cover Bangla numbers, alphabets, and word motions, the model can generate any word or phrase in Bangla. Additionally, the system creates gestures for inputs that aren’t in the dataset by spelling out the letters. The system converts Bangla text into three-dimensional animated BdSL movements by parsing it based on Linguistic principles. According to performance evaluations, each input has a processing cost of 79.57 ms, and the average accuracy for text and voice input is 97.50% and 94.75%, respectively. The method ensures fluency and naturalness by taking into consideration crucial elements of sign language, such as hand shape, palm orientation, and non-manual messages. By reducing communication barriers between the sign and non-sign populations, this study significantly advances accessibility. Visit this GitHub repository link for further details on the implementation of the suggested system and the SiGML dataset: https://gitlab.com/devarifkhan/bdsl-3d-animation

The decline of bee and wind-based pollination systems in greenhouses due to controlled environments and limited access has boosted the importance of finding alternative pollination methods. Robot-based pollination systems have emerged as a promising solution, ensuring adequate crop yield even in challenging pollination scenarios. This paper presents a comprehensive review of the current robotic-based pollinators employed in agriculture. The review categorizes pollinator technologies into major categories such as air-jet, water-jet, linear actuator, ultrasonic wave, and air-liquid spray, each suitable for specific crop pollination requirements. However, these technologies are often tailored to particular crops, limiting their versatility. The advancement of science and technology has led to the integration of automated pollination technology, encompassing information technology, automatic perception, detection, control, and operation. This integration not only reduces labor shortage problem but also fosters the ongoing progress of modern agriculture by refining technology, enhancing automation, and promoting intelligence in agricultural practices. Finally, the challenges encountered in the design of robot-based pollinators are addressed, and a forward-looking perspective is taken towards future developments, aiming to contribute to the sustainable advancement of this technology.

Transfer Learning (TL) has gained significant traction in machine learning, especially in deep learning contexts. However, its integration with Nature-Inspired Algorithms (NIAs) remains fragmented, with limited understanding of strategies, challenges, and outcomes. This paper presents the first systematic review focused exclusively on the use of TL in NIAs, excluding deep learning approaches. Major challenges include dealing with domain/task similarity, avoiding negative transfer, selecting what and when to transfer, and adapting TL mechanisms to population-based search paradigms. To address these issues, we conducted a structured analysis of 47 primary studies, categorizing them by TL strategies, learning paradigms, and algorithmic goals. Our findings reveal recurring patterns, highlight open research gaps, and propose future directions for developing robust TL-based NIAs. This review provides a foundation for researchers interested in designing adaptive, efficient, and knowledge-guided metaheuristics for complex optimization tasks.

The challenge of unanswerable questions in Machine Reading Comprehension (MRC) has drawn considerable attention, as current MRC systems are typically designed under the assumption that every question has a valid answer within the provided context. However, these systems often encounter real-world situations where no valid answer is available. This paper provides a comprehensive review of existing methods for addressing unanswerable questions in MRC systems, categorizing them into model-agnostic and model-specific approaches. It explores key strategies, examines relevant datasets, and evaluates commonly used metrics. This work aims to provide a comprehensive understanding of current techniques and identify critical gaps in the field, offering insights and key challenges to direct future research toward developing more robust MRC systems capable of handling unanswerable questions.