Artificial Intelligence Review最新文献

Worldwide lung cancer is a significant reason for death resulting from cancer with early diagnosis crucial for enhancing patient results. This comprehensive survey looks at the most recent developments in methods for detecting lung cancer by using chest CT scan images. The study describes a broad variety of approaches includes methods for machine learning such random forests support vector machines logistic regression and k-nearest neighbors in addition to deep learning frameworks such as variational autoencoders recurrent neural networks convolutional neural networks and generative adversarial networks. Additionally the survey explores hybrid models that combine deep learning and machine learning with nature-inspired optimization techniques to enhance performance. All the techniques discussed in this paper mainly focus on the diagnosis of NSCLC i.e. non-small cell lung cancer as it is more prevalent. The paper also reviews multiple advanced techniques used in diagnosis of lung cancer, including 3D-CNN i.e. Convolutional Neural Networks, multimodal logistic regression models and Cyclic Variational Autoencoders. It highlights key publicly available datasets frequently used in this research area such as LIDC-IDRI (Lung Image Database Consortium and Image Database Resource Initiative), LUNA16 (Lung Nodule Analysis 2016), the Kaggle lung cancer dataset, NSCLC Radiogenomics and the NIH (National Institutes of Health) chest X-ray database. This survey provides a detailed comparison of each technique, describing their advantages, limitations, and reported performance metrics, especially in terms of classification accuracy. Transfer learning with Vision Transformer achieves the highest accuracy of 94.6%, while 3D Convolutional Neural Network (3D -CNN) achieves an accuracy of 93.7%, both of which are showcasing highest performance on applicable datasets. Furthermore, the research demonstrates the potential of emerging techniques like federated learning and explainable AI in addressing challenges pertaining to data privacy and model interpretability. This survey paper reviews several techniques and finds that deep learning is the most extensively researched area in lung cancer diagnosis. This approach is not only widely used but also exhibits notable success in identifying and categorizing lung cancer with a high degree of accuracy.

A novel metaheuristic optimization algorithm, namely the Farthest better or Nearest worse Optimizer (FNO) algorithm, is proposed in this paper. The idea behind the FNO algorithm is derived from the qualities and distances between agents’ positions in a search space. The process of searching in the FNO includes two phases. During the first phase of the FNO, it jumps over the nearest regions with lower potential to avoid local optima. In the second phase, the algorithm tries to explore the farthest positions with higher potential to reach or explore the global optimum. These operations aim to enhance population diversity and provide the FNO with opportunities to discover high-quality regions while avoiding low-quality regions. A structural component within FNO, called Dynamic Focus Strategy (DFS), is also presented for controlling the exploration ratio. The DFS applies a random vector as a coefficient to shrink the area around the farthest better positions throughout the search process. Several experimental studies have been conducted on well-known benchmark suites, comprising 45 benchmarks, to assess the efficacy of the FNO algorithm. Additionally, five engineering problems were used to evaluate the practical applicability of the proposed FNO algorithm. The Wilcoxon test, as a well-known non-parametric statistical test, is conducted to fairly compare results. The findings indicate that the FNO algorithm performs competitively against other state-of-the-art population-based metaheuristic algorithms on the tested problems.

In this paper, we study a collaborative optimization scheduling approach for high-proportion renewable energy smart microgrids to achieve multi-energy management in a distributed execution framework with centralized training. First, we construct a multi-agent distributed microgrid optimization model for this optimization problem based on different types of renewable energy sources, energy storage, power exchange with the upper grid, and time-of-use electricity prices. Then, multiple long-term optimization objectives are designed to transform the cooperative optimization scheduling problem into a multi-agent multi-objective optimization problem, addressing the challenges of dynamic optimization. To enhance the correlation of policy sampling, we propose a novel multi-objective generalized normal distribution optimization (MGNDO) algorithm. By updating the covariance matrix, the policy correlations between different agents are better captured, resulting in more cooperative action sequences. Compared to traditional action sampling methods, this approach can better accommodate complex dynamic constraints and multi-objective requirements. Finally, a smart distribution network connected to three microgrids is taken as an example to realize the cooperative optimal scheduling problem by using the proposed algorithm, MADDPG algorithm and PSO algorithm, respectively. Operational cost and new energy consumption are compared separately to further illustrate the effectiveness of the proposed approach.

This review systematically summarizes the research progress of Large Language Models (LLMs) as meta-optimizers in the field of automated intelligent optimization algorithm design, aiming to establish a unified framework for this emerging research direction. The study first defines the core paradigm and research scope of LLM-driven meta-optimization, explaining how it overcomes the limitations of traditional optimization algorithms in terms of parameter sensitivity and cross-domain generalization. It then systematically summarizes representative methodological frameworks and typical methods for key stages such as algorithm auto-generation, dynamic selection, parameter configuration, and mutation control using LLMs, revealing the potential for synergies between generative AI and gradient-free optimization heuristics. Additionally, this paper integrates relevant performance evaluation metrics and benchmarking problems, providing practical references for researchers. Finally, the paper discusses the main challenges in this field and outlines future research directions, emphasizing the core role of LLMs as meta-optimizers in driving paradigm shifts toward algorithm design automation and intelligence.

The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret instructions, manage sequential tasks, and adapt through feedback. This review examines recent developments in employing LLMs as autonomous agents and tool users and comprises seven research questions. We only used the papers published between 2023 and 2025 in conferences of the A* and A-ranked and Q1 journals. A structured analysis of the LLM agents’ architectural design principles, dividing their applications into single-agent and multi-agent systems, and strategies for integrating external tools is presented. In addition, the cognitive mechanisms of LLMs, including reasoning, planning, and memory, and the impact of prompting methods and fine-tuning procedures on agent performance are also investigated. Furthermore, we have evaluated current benchmarks and assessment protocols and provided an analysis of 68 publicly available datasets to assess the performance of LLM-based agents in various tasks. In conducting this review, we have identified critical findings on verifiable reasoning of LLMs, the capacity for self-improvement, and the personalization of LLM-based agents. Finally, we have discussed ten future research directions to overcome these gaps.

This paper explores the integration of Artificial Intelligence Generated Content (AIGC), a rapidly evolving branch of generative AI, with Human-Machine intelligence (HMI) to enhance the functionality of Intelligent Transportation Systems (ITS). As transportation systems grow increasingly complex, adaptive decision-making becomes essential for interpreting vast streams of real-time data from vehicles, infrastructure, and users. AIGC plays a transformative role in optimizing traffic flow through dynamic routing and real-time traffic management, while human intelligence ensures these systems remain responsive to evolving real-world conditions. For safety, AIGC is used to simulate complex driving scenarios for autonomous vehicle training and detect traffic anomalies, with human oversight providing contextual decisions in ambiguous situations. For sustainability, AIGC supports data-driven strategies to reduce emissions and energy use, while human expertise ensures alignment with ethical and environmental goals. This synergy enhances real-time decision-making, improving both accuracy and adaptability across ITS scenarios. The paper presents a comprehensive review of core and supporting AIGC technologies and their applications across key ITS domains. Case studies and initiatives from industry leaders demonstrate practical implementations of AIGC-driven HMI collaboration. To guide future deployments, we propose a conceptual five-layer evaluation framework for assessing AIGC-HMI systems, encompassing functional performance, human interaction, explainability, ethical compliance, and robustness. We also address challenges such as legacy system integration, data privacy, model bias, and scalability. The paper concludes by outlining future research directions, emphasizing the need for scalable, interpretable, and ethically aligned AIGC models. This work contributes to the development of intelligent, adaptive, and trustworthy transportation systems.

With the rapid advancement and extensive application of artificial intelligence technology, large language models (LLMs) are extensively used to enhance production, creativity, learning, and work efficiency across various domains. However, the abuse of LLMs also poses potential harm to human society, such as intellectual property rights issues, academic misconduct, false content, and hallucinations. Relevant research has proposed the use of LLM watermarking to achieve IP protection for LLMs and traceability of multimedia data output by LLMs. To our knowledge, this is the first thorough review that investigates and analyzes LLM watermarking technology in detail. This review begins by recounting the history of traditional watermarking technology, then analyzes the current state of LLM watermarking research, and thoroughly examines the inheritance and relevance of these techniques. By analyzing their inheritance and relevance, this review can provide research with ideas for applying traditional digital watermarking techniques to LLM watermarking, to promote the cross-integration and innovation of watermarking technology. In addition, this review examines the pros and cons of LLM watermarking. Considering the current multimodal development trend of LLMs, it provides a detailed analysis of emerging multimodal LLM watermarking, such as visual and audio data, to offer more reference ideas for relevant research. This review delves into the challenges and future prospects of current watermarking technologies, offering valuable insights for future LLM watermarking research and applications.

The Industrial Internet of Things (IIoT) has been spreading across all fields of applicable environments, one of the most crucial ones being the industrial environment. IIoT is the integration of the internet within various industrial fields such as smart manufacturing, supply chain optimization, and predictive maintenance. These applications require two key features to be efficient, that is, real-time processing and connection security and reliability. From this standpoint arise the studies of cyberattack detection in industrial environments. Many methodologies have approached this field using traditional or hybridized machine learning or deep learning algorithms. In this review paper, we explore 36 of the most recent cyber-attack detection systems using metaheuristic models, mainly metaheuristic feature selection (MFS) algorithms. Additionally, we also explore hybrid models of metaheuristics and machine learning or deep learning models that are used to increase the accuracy of the models on various benchmark datasets. Our SLR separates the MFS utilized in this field into four main types, including Swarm Intelligence (SI), Evolutionary Algorithms (EA), Physics-Based (PHY), and Human-Behavior-Inspired (HBI). Our findings showed that SI-MFS dominates the field, with 25/36 case studies proposing it, while EA was proposed in 3/36 and PHY and HBI were each proposed in 2/36. We also demonstrate the most effective methodologies, such as FS-ID, MFS-D, and Novel Hybrid MFS. We also outline potential open challenges and gaps that require resolution.

Large language models (LLMs) are trained on vast and diverse internet corpora that often include inaccurate or misleading content. Consequently, LLMs can generate misinformation, making robust fact-checking essential. This review systematically analyzes how LLM-generated content is evaluated for factual accuracy by exploring key challenges such as hallucinations, dataset limitations, and the reliability of evaluation metrics. The review emphasizes the need for strong fact-checking frameworks that integrate advanced prompting strategies, domain-specific fine-tuning, and retrieval-augmented generation (RAG) methods. It proposes five research questions that guide the analysis of the recent literature from 2020 to 2025, focusing on evaluation methods and mitigation techniques. Instruction tuning, multi-agent reasoning, and RAG frameworks for external knowledge access are also reviewed. The key findings demonstrate the limitations of current metrics, the importance of validated external evidence, and the improvement of factual consistency through domain-specific customization. The review underscores the importance of building more accurate, understandable, and context-aware fact-checking. These insights contribute to the advancement of research toward more trustworthy models.

In the era of smart grids (SGs), as more interconnected energy sources and renewable sources are used, it is becoming increasingly important to have robust and accurate advanced anomaly detection methods. Due to the complexity of modern power systems, anomalies need to be detected more efficiently. This study provides a comprehensive overview of integrating renewable energy sources into SGs and the increasing importance of robust anomaly detection methods in ensuring grid security and reliability. Addressing four key research areas, we explore the current trends in applying machine learning techniques to SG anomaly detection research, identifying anomalies such as electricity theft, cyber-attacks, power system disturbances, and abnormal consumption patterns. We systematically evaluate the utilization of different machine learning models, including supervised, unsupervised, semi-supervised, and reinforcement learning, to detect each anomaly within SG environments. Furthermore, we assess the effectiveness of the anomaly detection algorithms and discuss the potential for further research, emphasizing the need for multidisciplinary collaboration and continuous development to overcome challenges and adapt to evolving grid dynamics and cyber threats. The findings of this study suggest that machine learning significantly contributes to ensuring the resilience and efficiency of SGs in the face of evolving challenges.