Array最新文献 - Book学术

Multi-objective game for fighting against Distributed Reflection DoS attacks in software-defined network 软件定义网络中对抗分布式反射DoS攻击的多目标博弈

IF 2.3

Array Pub Date : 2025-05-20 DOI: 10.1016/j.array.2025.100410

Vianney Kengne Tchendji , Mthulisi Velempini , Priva Chassem Kamdem

{"title":"Multi-objective game for fighting against Distributed Reflection DoS attacks in software-defined network","authors":"Vianney Kengne Tchendji , Mthulisi Velempini , Priva Chassem Kamdem","doi":"10.1016/j.array.2025.100410","DOIUrl":"10.1016/j.array.2025.100410","url":null,"abstract":"<div><div>Distributed Reflection Denial of Service (DrDoS) attack represents one of the most significant threats to network security. This cyber-attack exploits vulnerabilities in existing protocols by using a botnet to send forged query packets to more than one device which are used as reflectors. As a result, a stream of replies is sent to a victim node or subnet which overwhelms it. Several security measures have been proposed to counter such attacks, unfortunately, most of them do not consider the attacker’s dynamics. Furthermore, limiting the growth of the botnet could significantly reduce the impact of such an attack. In this paper, we leverage the advantages of software-defined networks (SDN) to propose a game-theoretic approach that predicts the defender’s best moves based on Nash strategies to mitigate this attack while avoiding botnet expansion. This approach is a non-cooperative multi-objective game between the attacker which aims to (1) compromise more nodes to scale the volume of its attack, (2) launch a volumetric-based DrDoS in the network, and the defender which aims to avoid it. This game results in a mixed-strategy Pareto-Nash equilibrium. It includes a player utility-based algorithm to detect malicious flows (or nodes) and drop them (or patch them). The results of the Matlab simulation show that the proposed model is an effective means of mitigating DrDoS attacks. To the best of our knowledge, this study is the first attempt to design a defense system based on multi-objective game to counter the effects of DrDoS in SDN.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100410"},"PeriodicalIF":2.3,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multimodal data fusion for Alzheimer's disease based on dynamic heterogeneous graph convolutional neural network and generative adversarial network 基于动态异构图卷积神经网络和生成对抗网络的阿尔茨海默病多模态数据融合

IF 2.3

Array Pub Date : 2025-05-20 DOI: 10.1016/j.array.2025.100415

Xiaoyu Chen, Shuaiqun Wang, Wei Kong

{"title":"Multimodal data fusion for Alzheimer's disease based on dynamic heterogeneous graph convolutional neural network and generative adversarial network","authors":"Xiaoyu Chen, Shuaiqun Wang, Wei Kong","doi":"10.1016/j.array.2025.100415","DOIUrl":"10.1016/j.array.2025.100415","url":null,"abstract":"<div><div>Alzheimer's disease (AD) is a complex neurodegenerative disorder, and understanding its pathogenic mechanisms is crucial for accurate diagnosis. Current research has progressed from single-modal data analysis to multi-modal data fusion, leveraging deep learning's efficient data analysis capabilities to handle complex datasets. However, existing deep learning models primarily focus on homogeneous data, facing limitations in classification accuracy and interpretability. The complex and diverse causes of AD make it challenging to fully exploit the complementary information among different data types. To address these challenges, we propose a multi-modal data fusion method based on a Dynamic Heterogeneous Attention Network (DHAN) and Generative Adversarial Networks (GAN). The proposed method designs private graph convolutional layers and shared heterogeneous attention layers, combining dynamic graph structure updates and graph structure regularization to dynamically enhance inter-modal relationships. This approach integrates structural Magnetic Resonance Imaging (sMRI), Single Nucleotide Polymorphism (SNP), and gene expression (GENE) data. Additionally, GANs are utilized to generate synthetic data to augment the training set, enhancing the model's robustness and generalization ability. Experimental results demonstrate that the proposed DHAN-GAN model achieves outstanding performance in AD classification tasks, with an ACC reaching 92.31 %. The classification accuracy exceeds traditional methods by over 10 % and significantly outperforms other comparative models in metrics such as precision, recall, and F1 score. This study provides a novel and effective solution for the application of multi-modal data fusion in Alzheimer's disease classification.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100415"},"PeriodicalIF":2.3,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144137687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An enhanced Walrus Optimizer with opposition-based learning and mutation strategy for data clustering 基于对立学习和突变策略的数据聚类增强Walrus优化器

IF 2.3

Array Pub Date : 2025-05-19 DOI: 10.1016/j.array.2025.100409

Laith Abualigah , Saleh Ali Alomari , Mohammad H. Almomani , Raed Abu Zitar , Hazem Migdady , Kashif Saleem , Aseel Smerat , Vaclav Snasel , Absalom E. Ezugwu

{"title":"An enhanced Walrus Optimizer with opposition-based learning and mutation strategy for data clustering","authors":"Laith Abualigah , Saleh Ali Alomari , Mohammad H. Almomani , Raed Abu Zitar , Hazem Migdady , Kashif Saleem , Aseel Smerat , Vaclav Snasel , Absalom E. Ezugwu","doi":"10.1016/j.array.2025.100409","DOIUrl":"10.1016/j.array.2025.100409","url":null,"abstract":"<div><div>Data clustering plays a crucial role in various domains, such as image processing, pattern recognition, and data mining. Traditional clustering techniques often suffer from limitations like sensitivity to initialization, poor convergence, and entrapment in local optima. To address these challenges, this paper proposes an Enhanced Walrus Optimizer (IWO) tailored for clustering tasks. The proposed IWO integrates two powerful strategies–Opposition-Based Learning (OBL) and Mutation Search Strategy (MSS)–to improve population diversity and prevent premature convergence, thereby enhancing both exploration and exploitation capabilities. These enhancements enable more accurate and stable identification of cluster centers. The effectiveness of IWO is validated through extensive experiments on multiple benchmark clustering datasets and compared against several state-of-the-art metaheuristic algorithms, including PSO, GWO, AOA, and others. The results demonstrate that IWO achieves better results, indicating improved compactness and separation of clusters. Statistical validation using p-values and ranking scores further confirms the superiority of the proposed method. These findings suggest that IWO offers a robust and flexible framework for solving complex clustering problems. Future work will explore hybrid deep learning-integrated models and parallel implementations to enhance scalability.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100409"},"PeriodicalIF":2.3,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Gesture-controlled omnidirectional autonomous vehicle: A web-based approach for gesture recognition 手势控制的全方位自动驾驶汽车：基于网络的手势识别方法

IF 2.3

Array Pub Date : 2025-05-19 DOI: 10.1016/j.array.2025.100408

Huma Zia, Bara Fteiha, Maha Abdulnasser, Tafleh Saleh, Fatima Suliemn, Kawther Alagha, Jawad Yousaf, Mohammed Ghazal

{"title":"Gesture-controlled omnidirectional autonomous vehicle: A web-based approach for gesture recognition","authors":"Huma Zia, Bara Fteiha, Maha Abdulnasser, Tafleh Saleh, Fatima Suliemn, Kawther Alagha, Jawad Yousaf, Mohammed Ghazal","doi":"10.1016/j.array.2025.100408","DOIUrl":"10.1016/j.array.2025.100408","url":null,"abstract":"<div><div>This paper presents a novel web-based hand/thumb gesture recognition model, validated through the implementation of a gesture-controlled omnidirectional autonomous vehicle. Utilizing a custom-trained YOLOv5s model, the system efficiently translates user gestures into precise control signals, facilitating real-time vehicle operation under five commands: forward, backward, left, right, and stop. Integration with Raspberry Pi hardware, including a camera and peripherals, enables rapid live video processing with a latency of 150–300 ms and stable frame rates of 12–18 FPS. The system demonstrates reliable performance with a classification accuracy of 94.2%, validated across multiple gesture classes through statistical analysis, including confusion matrices and ANOVA testing. A user-friendly web interface, built using TensorFlow.js, Node.js, and WebSocket, enhances usability by providing seamless live video streaming and real-time, device-agnostic control directly in the browser without requiring wearable sensors or external processing. The system’s key contributions include: (1) robust real-time hand gesture recognition using YOLOv5s; (2) seamless Raspberry Pi–Arduino integration; (3) a browser-based interface enabling accessible, scalable deployment; and (4) empirical validation across functional, environmental, and statistical performance metrics. This innovation marks a significant advancement in the practical application of hand gesture control within robotics. It offers a flexible and cost-effective alternative to sensor-based systems and serves as a foundation for future developments in autonomous vehicles, human-machine interaction, assistive technologies, automation, and AI-driven interfaces. By eliminating the existing systems’ need for wearable technology, specialized hardware, or complex setups, this work expands the potential for deploying intuitive, touch-free control systems across diverse real-world domains.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100408"},"PeriodicalIF":2.3,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MobDenseNet: A hybrid deep learning model for brain tumor classification using MRI MobDenseNet：一种用于MRI脑肿瘤分类的混合深度学习模型

IF 2.3

Array Pub Date : 2025-05-16 DOI: 10.1016/j.array.2025.100413

Meher Afroj , M. Rubaiyat Hossain Mondal , Md Riad Hassan , Sworna Akter

{"title":"MobDenseNet: A hybrid deep learning model for brain tumor classification using MRI","authors":"Meher Afroj , M. Rubaiyat Hossain Mondal , Md Riad Hassan , Sworna Akter","doi":"10.1016/j.array.2025.100413","DOIUrl":"10.1016/j.array.2025.100413","url":null,"abstract":"<div><div>This paper presents MobDenseNet, an improved deep learning model that assists medical practitioners in diagnosing brain tumors accurately. The proposed MobDenseNet is developed using the concepts of existing deep learning models: MobileNetV1 and DenseNet; the model incorporates hyperparameter fine-tuning and feature fusion ensemble during the feature extraction phase, consolidating layers like batch normalization, dense layers in the classification step to classify brain tumors. The classification is done into multiple classes, including, gliomas, meningiomas, pituitary, and healthy brain. The performance of the proposed model is assessed on two benchmark datasets. The experiments consider 2757 training and 307 testing images for the first dataset of 3064 MRI images, available on Figshare, having classes of glioma, meningioma, and pituitary. The experiment for the second dataset, has 2937 training and 327 testing images with glioma, meningioma, pituitary, and no tumor classes. The model achieves 98.4 % accuracy, 99.9 % AUC, 98.6 % precision, 98.40 % recall, 98.5 % F1-score for the Figshare dataset, and 96.02 % accuracy, 99.4 % AUC, 96.3 % precision, 95.7 % recall and 95.9 % F1-score for the Sartaj Bhuvaji dataset, respectively. The proposed MobDenseNet shows better accuracy than the existing models considered in the research. To demonstrate the effectiveness of the proposed model on diverse and unseen data, cross-dataset evaluations are conducted, where the model is trained using the Figshare dataset and tested using the Sartaj Bhuvaji and two additional datasets. Results indicate that even for the cross-dataset scenario, the proposed model achieves acceptable classification accuracy and outperforms existing models of MobileNetV1 and DenseNet.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100413"},"PeriodicalIF":2.3,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced small-scale APT knowledge graph embedding via spatio-temporal attribute reasoning and adversarial negative sampling 基于时空属性推理和对抗性负抽样的小规模APT知识图谱嵌入

IF 2.3

Array Pub Date : 2025-05-14 DOI: 10.1016/j.array.2025.100404

Yushun Xie , Haiyan Wang , Xiao Jing , Zhaoquan Gu

{"title":"Enhanced small-scale APT knowledge graph embedding via spatio-temporal attribute reasoning and adversarial negative sampling","authors":"Yushun Xie , Haiyan Wang , Xiao Jing , Zhaoquan Gu","doi":"10.1016/j.array.2025.100404","DOIUrl":"10.1016/j.array.2025.100404","url":null,"abstract":"<div><div>Advanced Persistent Threat (APT) represents a class of highly sophisticated and stealthy cyberattacks that pose significant challenges to traditional defense mechanisms. Knowledge Graph Embedding (KGE) techniques provide a promising approach for APT attack prediction by leveraging existing cybersecurity knowledge to infer potential attack behaviors. However, the effectiveness of existing KGE methods is severely hindered by the scarcity of APT attack knowledge and the sparsity of knowledge graph connectivity, resulting in suboptimal knowledge representation and predictive performance. We propose an enhanced APT knowledge graph embedding method called APT-ST-AN to address the limitations of incomplete and sparse data in small-scale APT knowledge graphs. The proposed model introduces spatio-temporal attribute reasoning to enrich positive APT attack examples, thereby expanding the knowledge base with inferred attack patterns. At the same time, the model utilizes adversarial negative sampling, combining adversarial example generation with synthetic example creation to produce high-quality negative examples that improve the training process of the model. By jointly expanding the APT knowledge from both positive and negative examples, APT-ST-AN improves the expressiveness and generalization of KGE models. Extensive experiments on multiple small-scale APT knowledge graphs demonstrate that APT-ST-AN consistently outperforms existing compared models. Notably, APT-ST-AN achieves a maximum Mean Reciprocal Rank (MRR) of 0.589 and Hits@10 of 0.673, yielding up to a 38.3% improvement over baseline methods. These results demonstrate that APT-ST-AN exhibits high predictive accuracy in APT attack inference, thereby enhancing the ability of cybersecurity systems to anticipate and mitigate sophisticated cyber threats.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100404"},"PeriodicalIF":2.3,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Few-shot relation extraction approach for threat intelligence based on multi-level attention mechanism and hybrid prototypical network 基于多级注意机制和混合原型网络的威胁情报少镜头关系提取方法

IF 2.3

Array Pub Date : 2025-05-10 DOI: 10.1016/j.array.2025.100405

Yushun Xie , Junchi Bao , Rui Zong , Zhaoquan Gu , Haiyan Wang

{"title":"Few-shot relation extraction approach for threat intelligence based on multi-level attention mechanism and hybrid prototypical network","authors":"Yushun Xie , Junchi Bao , Rui Zong , Zhaoquan Gu , Haiyan Wang","doi":"10.1016/j.array.2025.100405","DOIUrl":"10.1016/j.array.2025.100405","url":null,"abstract":"<div><div>With the increasing complexity of cyberattacks, the frequency and severity of cybersecurity incidents have escalated dramatically. Cyber Threat Intelligence (CTI) relation extraction plays a critical role in cybersecurity event analysis by identifying semantic relationships between security-related entities, thereby converting unstructured information into structured data formats. Nevertheless, within the domain of CTI, labeled datasets are limited, and the process of manual labeling incurs substantial costs, rendering it impractical on a large scale. To address these challenges, we propose a novel few-shot relation extraction method for small-scale threat intelligence data, termed RETI-MA-HP, which is based on a multi-level attention mechanism and a hybrid prototypical network. By integrating these advanced techniques, the RETI-MA-HP model is capable of learning from limited data and rapidly generalize to new relation classification tasks. To enhance the representational capacity of feature vectors, RETI-MA-HP incorporates a self-training module to refine the BERT-based encoder. Meanwhile, to mitigate misclassification arising from syntactically similar sentences, RETI-MA-HP employ contrastive learning to strengthen the hybrid prototypical network. Furthermore, we constructed a dedicated CTI dataset. Extensive experiments demonstrate that RETI-MA-HP achieves excellent performance across multiple tasks, attaining a maximum relation extraction accuracy of 75.44%, which constitutes a 15.5% improvement over compared models. These results prove that the effectiveness of RETI-MA-HP for relation extraction within the CTI domain.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100405"},"PeriodicalIF":2.3,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Application of artificial intelligence in agri-tech, environmental and biodiversity conservation 人工智能在农业技术、环境和生物多样性保护中的应用

IF 2.3

Array Pub Date : 2025-05-09 DOI: 10.1016/j.array.2025.100412

Chatrabhuj , Kundan Meshram , Umank Mishra , Upaka Rathnayake

{"title":"Application of artificial intelligence in agri-tech, environmental and biodiversity conservation","authors":"Chatrabhuj , Kundan Meshram , Umank Mishra , Upaka Rathnayake","doi":"10.1016/j.array.2025.100412","DOIUrl":"10.1016/j.array.2025.100412","url":null,"abstract":"<div><div>New agricultural technologies have increased agricultural capacity and efficiency. Artificial intelligence-based methodologies have been widely adopted in agricultural systems, resulting in successes in smart crop management, smart plant breeding, smart livestock farming, precision aquaculture farming, and agricultural robotics. However, machine learning models are limited by their dependence on huge, expensive labelled datasets for training, specialized skills for development and maintenance, and task-specificity, limiting their generalizability. Nevertheless, sustainable agriculture solutions are essential as climate change and population growth increase. Smart agriculture, which uses technology and data analytics, can improve social, economic, and environmental sustainability. This paper presents a comprehensive investigation of smart technologies in agriculture, their impact on sustainability, architectural design, and major variables influencing their adoption based on recent research. We critically analyze smart agriculture to show how it might reduce environmental impact, boost economic growth, and promote social inclusivity. This research highlights the importance of artificial intelligence in agriculture and its domains.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100412"},"PeriodicalIF":2.3,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Explainable deep learning-based meta-classifier approach for multi-label classification of retinal diseases 视网膜疾病多标签分类的可解释深度学习元分类器方法

IF 2.3

Array Pub Date : 2025-05-08 DOI: 10.1016/j.array.2025.100402

Md. Moniruzzaman Hemal, Suman Saha

{"title":"Explainable deep learning-based meta-classifier approach for multi-label classification of retinal diseases","authors":"Md. Moniruzzaman Hemal, Suman Saha","doi":"10.1016/j.array.2025.100402","DOIUrl":"10.1016/j.array.2025.100402","url":null,"abstract":"<div><div>Early diagnosis of retinal diseases is important to prevent vision loss. This study introduces a novel multi-label classification system for detecting multiple retinal diseases using two publicly available datasets. The process begins with data collection and preprocessing, including image resizing and noise filtering to enable effective feature extraction. To develop and train the models, we apply a transfer learning approach to several state-of-the-art deep learning models, including MobileNetV2, InceptionV3, NASNetMobile, DenseNet169, EfficientNetB4, DenseNet121, ConvNeXt, and Xception. The two best-performing models were selected based on the validation results and were used as base models, which are subsequently combined using a meta-classifier. The experimental results demonstrate that the proposed model achieved an impressive performance, with 0.981 accuracy, 0.982 precision, 0.981 sensitivity, 0.981 F1 score and 0.994 specificity in the Eye Diseases Classification dataset and 0.977 accuracy, 0.978 precision, 0.977 sensitivity, 0.977 F1 score, and 0.978 specificity on the Retinal Fundus Images dataset. These results highlight the model’s high accuracy, reliability, and robustness, with statistically significant improvements validated by a paired t-test, outperforming state-of-the-art methods in retinal disease classification. Given the importance of model interpretability, especially in the healthcare field, this study utilizes Local Interpretable Model Agnostic Explanation to visually evaluate the model predictions using superpixels. This approach enhances transparency and trust in the model’s decision-making process. With excellent accuracy, statistical robustness, and interpretability, the proposed system assists medical practitioners in the early diagnosis of retinal diseases and contributes to improved patient care outcomes through the advancement of automated diagnostic systems in ophthalmology.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100402"},"PeriodicalIF":2.3,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The role of agentic AI in shaping a smart future: A systematic review 人工智能在塑造智能未来中的作用：系统回顾

IF 2.3

Array Pub Date : 2025-05-08 DOI: 10.1016/j.array.2025.100399

Soodeh Hosseini , Hossein Seilani

{"title":"The role of agentic AI in shaping a smart future: A systematic review","authors":"Soodeh Hosseini , Hossein Seilani","doi":"10.1016/j.array.2025.100399","DOIUrl":"10.1016/j.array.2025.100399","url":null,"abstract":"<div><div>Artificial intelligence (AI), particularly Agentic AI, is increasingly critical for addressing the demand for speed, efficiency, and customer focus in modern organizations. However, the rapid evolution of Agentic AI, including Generative AI (GenAI) agents, has outpaced a cohesive understanding of its applications, challenges, and strategic implications. This narrative review explores the role of Agentic AI in shaping an intelligent future, focusing on its key attributes—autonomy, reactivity, proactivity, and learning ability—and its potential to transform organizational performance. We identify a research gap in synthesizing the diverse capabilities of Agentic AI (e.g., multimodal processing, hierarchical architectures, and machine learning outsourcing) and providing actionable strategies for adoption. The paper examines how Agentic AI enables autonomous decision-making, automates processes, and enhances efficiency through tools like LangChain, CrewAI, AutoGen, and AutoGPT. It highlights the transition from assisted (\"Copilot\") to autonomous (\"Autopilot\") models and the importance of hierarchical agent structures for system coordination. Key contributions include a framework for organizations to formulate GenAI strategies, addressing business needs, tool selection, human resource training, and risk management. Findings reveal that Agentic AI significantly improves productivity, reduces costs, and drives innovation, though challenges such as privacy, security, and ethical concerns remain. Future research should focus on industry-specific case studies to deepen understanding, explore the ethical and social impacts (e.g., privacy, data security, labor market effects), and investigate the integration of Agentic AI with emerging technologies like quantum computing. This review provides a foundation for researchers and practitioners to leverage Agentic AI effectively while addressing its limitations and opportunities.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100399"},"PeriodicalIF":2.3,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0