Artificial Intelligence Review最新文献

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.

Car theft has become a significant issue in modern societies, with far-reaching individual and social consequences. This criminal act causes substantial financial losses for vehicle owners, undermines public trust in security systems, and increases social and governmental costs. Therefore, research on developing innovative and efficient methods for detecting and preventing car theft holds particular importance. In this study, advanced methods for detecting car theft have been evaluated and compared through two main approaches: deep learning and machine learning. First, pre-trained deep neural networks were examined. In the second phase, various image features were extracted using feature extraction methods, such as Edge Direction Histogram (EDH), Edge Oriented Histogram (EOH), and Histogram Oriented Gradient (HOG), followed by the assessment of machine learning approaches. Finally, a hybrid model based on Hybrid Edge and Gradient-Based Features (HFEM) combined with an XGBoost classifier was proposed, achieving an accuracy of 98.6% in predicting car theft.

Facial expression recognition (FER) remains a challenging task due to subtle variations in facial details and unconstrained conditions such as changes in head posture, illumination, and occlusion. Current FER approaches primarily focus on capturing discriminative facial features in vision manner, often neglecting the rich semantic information available in textual modalities. Additionally, these methods typically rely on generic classification templates, which fail to capture instance-specific features, resulting in inadequate representation and fine-grained discrimination ability. To tackle the above issues, we propose a novel emotion-aware adaptation framework that integrates the pre-trained CLIP model for FER, leveraging both visual and textual modalities to enhance representation learning and capture fine-grained emotional details. Specifically, we introduce the Expression-aware adapter module to capture emotion-specific facial representations through task-specific fine-tuning while preserving the generalization capabilities of the CLIP model. Furthermore, the instance-enhanced expression classifier module is proposed to enhance textual descriptors with instance-specific visual embeddings using spherical linear interpolation, creating a more precise and discriminative classifier. Extensive experiments on three in-the-wild FER benchmarks demonstrate superiority of our proposed approach.

Bipedal robots are gaining global recognition due to their potential applications and the rapid advancements in artificial intelligence, particularly through deep reinforcement learning (DRL). While DRL has significantly advanced bipedal locomotion, the development of a unified framework capable of handling a wide range of tasks remains an ongoing challenge. This survey systematically categorises, compares, and analyses existing DRL frameworks for bipedal locomotion, organising them into end-to-end and hierarchical control schemes. End-to-end frameworks are evaluated based on their learning approaches, whereas hierarchical frameworks are examined in terms of their layered structures that integrate learning-based and traditional model-based methods. We provide a detailed evaluation of the composition, strengths, limitations, and capabilities of each framework. Furthermore, this survey identifies key research gaps and proposes future directions aimed at creating a more integrated and efficient unified framework for bipedal locomotion, with broad applicability in real-world environments.

The rapid development of Transformer-based large language models (LLMs) has made them one of the most critical technological infrastructures in modern society. However, this rapid deployment has transformed the risk of privacy breaches from a theoretical concern into a systemic threat spanning the entire lifecycle of LLMs. These risks continually challenge existing data compliance and regulatory frameworks, directly limiting the large-scale adoption of LLMs in highly sensitive and heavily regulated industries. Cryptographic technologies, such as fully homomorphic encryption (FHE) and secure multi-party computation (MPC), have garnered significant attention due to their provable security guarantees, theoretically safeguarding the privacy of sensitive data and LLMs weights. These cryptographic techniques have rapidly permeated key stages of LLMs, including data selection, fine-tuning, and inference. Despite these advancements, there is currently no comprehensive survey summarizing the work related to cryptography-based privacy-preserving LLMs (CPLMs), leaving their research isolated and fragmented. To fill this gap, We provide a comprehensive review of existing CPLMs research and systematically classifies them, enabling researchers to effectively coordinate optimization strategies for the efficient design of CPLMs algorithms. Finally, based on the limitations of current CPLMs research, we outline several promising directions for future exploration.

Patients increasingly rely on easily accessible online resources, often ignoring source credibility. Large Language Models such as ChatGPT and DeepSeek provide free, near human interaction on any imaginable topic, including medical conditions. While the benefits provided by this technology are evident and undeniable, concerns regarding the reliability and safety remain. In this study, we assessed the quality, safety, and reproducibility of responses generated by ChatGPT-4o mini and DeepSeek-R1 on the urolithiasis - an increasingly prevalent condition with complex aetiology and diverse management options. We screened for the most frequently asked questions on kidney stone disease. A set of 76 questions was generated and divided into six categories: general information, risk factors, symptoms, diagnosis, treatment and prognosis. Each question was entered into DeepSeek-R1 and ChatGPT-4o mini. Responses were independently evaluated by two attending urologists using a four-point scale based on clearly defined, pre-established criteria. Discrepancies were resolved by a third expert. Cosine similarity index was applied to evaluate the degree to which LLM responses remained stable over time in wording and meaning. Direct comparisons on the response lengths were conducted. Initial analysis with no category differentiation favoured DeepSeek R1 (p < 0.001). The worst outcomes for both models were recorded in the “treatment” category, yet with DeepSeek’s statistically significant advantage. Moreover, the Chinese LLM provided more accurate responses in “general information” category. The median cosine similarity score for responses generated by DeepSeek-R1 and ChatGPT-4o was 0.7 (IQR 0.655–0.736) and 0.86 (IQR 0.805–0.9), respectively. Responses from DeepSeek-R1 were significantly shorter, with a median word count of 385.5 (330.5–448.5) compared to and 672.5 (438–873.25) words for ChatGPT-4o mini (p < 0.001). Additionally, DeepSeek-R1 responses were more consistent in terms of length exhibiting a narrower distribution when compared to ChatGPT-4o mini. Among the evaluated LLMs available free of charge, DeepSeek-R1 emerged as a more accurate and concise source of patient information, while ChatGPT-4o mini demonstrated significantly greater reproducible responses. The reasoning process of DeepSeek-R1 has the potential to enhance patient comprehension of complex medical concepts thereby improving treatment adherence. Nevertheless, limitations of LLMs such as susceptibility to hallucinations and biases derived from their training data must be carefully considered.

The proliferation of metaheuristic optimization algorithms has led to concerns about their novelty. This study introduces three key contributions to address this challenge: (1) a novel systematic taxonomic framework that employs nineteen rigorously selected, metaphor-free criteria to evaluate algorithmic distinctiveness; (2) a comprehensive clustering methodology that combines Rogers-Tanimoto distance analysis with principal component analysis (PCA) and hierarchical clustering to quantify algorithmic similarities; and (3) an objective assessment method for evaluating genuine algorithmic innovations. Through the analysis of 145 metaheuristic algorithms, we demonstrate that 74 algorithms (51.0%) exhibit distances below the confidence interval threshold, indicating profound structural overlap. Network analysis reveals 26 algorithms with perfect structural identity (distance = 0.0) and 512 algorithm pairs showing high similarity (distance < 0.039), representing 18.9% of all pairwise comparisons. The results show that numerous algorithms claiming innovation deliver only incremental modifications to existing implementation patterns, lacking fundamental methodological advancement. The framework provides both a theoretical foundation for understanding algorithmic similarities and a practical tool for evaluating new algorithmic proposals, potentially transforming how the field assesses and develops novel optimization methods.