EUDL

EUDL · the EAI Universal Digital Library
ISSN: 2790-7511
Submit Article
Submission Instructions
Open Access Information
Ethics and Malpractice Statement
Most Recent Issue
2026
Issue 1
2025
Issue 1
2024
Issue 1
2023
Issue 1
2022
Issue 1
Editor(s)-in-Chief: Shuai (Steven) Li

EAI Endorsed Transactions on AI and Robotics (eISSN: 2790-7511) covers all aspects of robotics and knowledge-based AI systems along with interdisciplinary approaches to computer science, control systems, computer vision, machine learning, electrical engineering, intelligent machines, mathematics, and other disciplines. An important goal of this journal is to extend cutting-edge technologies in the control and learning of both symbolic and sensory robots with regard to smart systems. Our journal contains articles on the theoretical, mathematical, computational, and experimental aspects of robotics and intelligent systems.

INDEXING: Scopus (CiteScore: 7.7), CrossRef, Google Scholar, ProQuest, EBSCO, CNKI, Dimensions

  • Editor-in-Chief
  • Shuai (Steven) Li, University of Oulu, Finland
  • Administrative Editor
  • Yiguo Yang, Shanghai University, China
  • Zhendai Huang, University of Oulu, Finland
  • Advisory Board
  • Oubay Hassan, Department of Civil Engineering, Swansea University, UK. Fellow of UK Royal Academy of Engineering
  • Michael Navon, Department of Scientific Computing, Florida State University, USA. Fellow of the American Meteorological Society; Honorary Member of Romanian Academy of Science
  • Jianming Shi, School of Mathematical Sciences, Soochow University, China. School of Management, Tokyo University of Science, Japan. Foreign Member, Engineering Academy of Japan (EAJ)
  • Editors
  • Dunhui Xiao, School of Mathematical Sciences, Tongji University, China
  • Lining Sun, School of Mechanical and Electric Engineering, Soochow University, China. Foreign member of Russian Academy of Engineering
  • Yuhua Zheng, Zhejiang Lab, Hangzhou, China
  • Xingye Yue, School of Mathematical Sciences, Soochow University, China
  • Editorial Board Members
  • Ivona Brajević, University Business Academy in Novi Sad, Serbia
  • Xinwei Cao, School of Management, Shanghai University, China
  • JinLong Fu，Faculty of Science and Engineering, Swansea University, United Kingdom
  • Hewa Majeed Zangana, Duhok Polytechnic University and Nawroz University, Iraq
  • Zhibin Li, Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, China
  • Christian Griffiths, College of Engineering, Swansea University, United Kingdom
  • Hongliang Guo, Agency for Science, Technology and Research, Singapore
  • Wojciech Hunek, Opole University of Technology, Opole, Poland
  • T. Jarin, Department of Electrical Engineering, Jyothi Engineering College, India
  • Chao Jiang, Department of Electrical Engineering, University of Wyoming, USA
  • Vasilios N. Katsikis, Division of Mathematics and Informatics, National and Kapodistrian University of Athens, Greece
  • Ameer Hamza Khan, Department of Computing, Hongkong Polytechnic University, Hong Kong, China
  • Wenqiang Lu, Chongqing Institute of Green and Intelligent Technology, China
  • Zhan Li, Department of Computer Sciences, Swansea University, UK
  • Jianfeng Li, College of Information Science and Engineering, Jishou University, China
  • Mohammed Aquil Mirza, Department of Computing, Hong Kong Polytechnic University, Hong Kong, China
  • Bolin Liao, College of Information Science and Engineering, Jishou University, China
  • Zhenzhong Liu, Tianjin University of Technology, China
  • Md. Asraful Haque, Zakir Hussain College of Engineering & Technology, India
  • Huanfei Ma, School of Mathematical Sciences, Soochow University, China
  • Ata Jahangir Moshayedi, College of Computing, Jiangxi University of Science and Technology, China
  • Muhammad Rehan, Department of Electrical Engineering, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Pakistan
  • Mingsheng Shang, Chongqing Institute of Green and Intelligent Technology, China
  • Predrag S. Stanimirović, Faculty of Sciences and Mathematics, University of Nis, Serbia
  • Xuefeng Zhou, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, China
  • Weiwei Jiang, Beijing University of Posts and Telecommunications, China
  • Ameer Tamoor Khan, Computing Department, University of Copenhagen, Denmark
  • Xiaoli Liu, University of Helsinki, Finland
  • Partha Pratim Ray, Sikkim University, India
  • Yicong Du, Southwest Petroleum University, China

  • Temporal-Structural Stress Testing and Cross-Granularity Robustness Evaluation of Graph AI for Cryptocurrency AML Detection

    Appears in:
    airo 26(1):

    Authors:
    Abu Kowshir Bitto , Md Fokrul Islam Khan , Md Faysal Ahmed , Partha Singha , Md Hossain Jamil , Sabab Islam , Sadia Akter , Sanim Yousuf Fahim

    Published:
    2nd Sep 2026

    Abstract:
    Cryptocurrency anti-money-laundering (AML) is typically framed as a graph-learning problem, since suspicious value flows rarely appear as isolated records. This study examines whether graph AI architectures retain an advantage over strong non-GNN baselines when evaluation is temporal, structurally explicit, and aligned with investigator triage. We answer that question using two public Bitcoin AML datasets: Elliptic, a transaction- node dataset, and Elliptic2, a subgraph-level dataset. Our comparison spans classical models, tree ensembles, graph-derived features, graph embeddings, neural baselines, and GNN variants, evaluated across AUPRC, AUROC, accuracy, precision and recall at an investigation budget, calibration, operating points, and bootstrap uncertainty. On the temporal Elliptic test period, Extra Trees achieves AUPRC 0.570 and AUROC 0.869, while GraphSAGE, the strongest standard GNN baseline, reaches AUPRC 0.311. A strict-temporal GraphSAGE variant improves to AUPRC 0.381 but still falls behind the leading tree ensemble model. The paired bootstrap difference between Extra Trees and GraphSAGE is 0.259 AUPRC, with a 95% interval of [0.222, 0.297]. On the full Elliptic2 subgraph benchmark, Random Forest achieves AUPRC 0.494 and AUROC 0.923 in the main split and remains the strongest model by mean AUPRC across repeated splits. These findings indicate that graph AI for cryptocurrency AML should be stress-tested against capable tree ensemble models and operational metrics before architectural complexity is treated as deployment evidence.

  • Comprehensive Channel Modeling of UAV-Assisted FSO Systems under Fog, AoA Fluctuations, and Pointing Errors

    Appears in:
    airo 26(1):

    Authors:
    Khadijeh Ali Mahmoodi, Seyed Mohammad Sajad Sadough, Mahdi Ataee

    Published:
    20th Aug 2026

    Abstract:
    This paper investigates the outage performance of unmanned aerial vehicle (UAV)-assisted free-space optical (FSO) communication systems operating in foggy channels. The analysis jointly accounts for atmospheric turbulence, fog-induced attenuation, generalized Beckmann-distributed pointing errors (PE), and angle-of-arrival (AoA) fluctuations caused by UAV orientation jitter. A comprehensive statistical channel model is developed, from which closed-form expressions for outage probability and an analytical characterization of outage capacity are derived. The effects of receiver field-of-view (FoV) limitations and multi-UAV amplify-and-forward relaying on link reliability are also investigated. Numerical results validate the proposed analysis and reveal that AoA fluctuations impose a fundamental performance limit, resulting in an outage floor, particularly under dense fog and narrow-FoV conditions. These findings provide practical design insights for improving the reliability of UAV-assisted FSO communication systems in adverse weather environments.

  • A Huber-Regularized Latent Factorization of Tensors Approach for Large-Scale Incomplete Water Quality Data Imputation

    Appears in:
    airo 26(1):

    Authors:
    Tinghui Chen, Zhibin Li, Jinli Li, Hengrui Tu, Xuke Wu

    Published:
    19th Aug 2026

    Abstract:
    An online water quality monitoring network continuously collects multiple key water quality indicators across distributed monitoring sites via wireless sensors, providing essential data support for intelligent water resource management and ecological assessment. These large-scale observations can be naturally represented as a high-dimensional and incomplete (HDI) water quality tensor with frequent missing entries. Such an HDI tensor contains rich multivariate, spatial, and temporal dependencies that can be effectively exploited for missing data recovery. Latent factorization of tensors (LFT) models have demonstrated remarkable capability in extracting latent knowledge from HDI tensors, thereby enabling accurate missing data imputation. However, existing LFT models generally adopt the conventional L2 regularization scheme, making them highly sensitive to sensor outliers that are ubiquitous in real-time monitoring environments. To address this issue, this study proposes a Huber-regularized latent factorization of tensors (HRL) model under the Tucker decomposition framework. Specifically, a Huber regularization scheme is incorporated into the learning objective to improve robustness against outliers while preserving the smoothness of latent factor learning. Empirical studies on eight practical HDI water quality tensors demonstrate that the proposed HRL model consistently outperforms state-of-the-art models in terms of computational efficiency and imputation accuracy, offering an effective and robust solution for large-scale incomplete water quality data reconstruction and facilitating reliable downstream decision-making.

  • An Interpretable Feature-Enhancement DeepEnsemble Classifier for Brinjal Disease Detection

    Appears in:
    airo 26(1):

    Authors:
    Abdul Kadar Muhammad Masum, Partha Singha, Hasnur Jahan, Rumana Akhter, Abu Kowshir Bitto, Susmoy Biswas

    Published:
    13rd Aug 2026

    Abstract:
    Artificial intelligence has become an effective tool for improving agricultural productivity through automated crop disease diagnosis. Brinjal (eggplant) cultivation suffers substantial yield losses from diseases such as Shoot and Fruit Borer, Wet Rot, Fruit Cracking, and Phomopsis Blight, yet reliable field-based diagnostic systems remain limited. To address this challenge, we introduce \textit{BrinjalFruitX}, a real-world dataset comprising 1,823 annotated images collected under natural farming conditions in Bangladesh across four disease classes and one healthy class. We propose an interpretable hybrid feature-enhancement deep ensemble framework that integrates image preprocessing, transfer learning, traditional machine learning, class imbalance mitigation, and explainable artificial intelligence. Three preprocessing techniques, Gaussian, Laplacian, and Unsharp Masking, are systematically evaluated, while deep features extracted using pre-trained VGG and ResNet models are classified by Random Forest, K-Nearest Neighbors, and a classifier-level ensemble. The optimal Unsharp--ResNet--Random Forest configuration achieved 80.0\% accuracy with an F1-score of 87.0\%. ADASYN applied in the deep feature space improved minority-class sensitivity, while Grad-CAM and Grad-CAM++ enhanced model interpretability. The proposed framework provides an effective and transparent solution for practical field-level brinjal disease detection and precision agriculture.

  • Evolutionary Feature Reduction and Edge-Optimized CNN Inference for Large-Scale IoT DDoS Detection

    Appears in:
    airo 26(1):

    Authors:
    Pravir Chitre, Premkumar Sivakumar

    Published:
    10th Aug 2026

    Abstract:
    The rapid proliferation of Internet of Things (IoT) deployments has introduced significant security vulnerabilities, particularly due to Distributed Denial-of-Service (DDoS) attacks launched through compromised IoT botnets. Real-time detection of such attacks at the network edge remains challenging because of high feature dimensionality, severe class imbalance between benign and attack traffic, and strict latency constraints of resource-constrained IoT gateways. This paper aims to design and evaluate a unified framework for large-scale IoT DDoS detection that reduces feature dimensionality, improves classification performance under imbalanced conditions, and enables low-latency edge deployment suitable for real-time gateway environments. The proposed framework employs a multi-phase pipeline integrating evolutionary feature reduction, deep learning classification, and edge-optimized deployment. A Weighted Genetic Algorithm (W-GA) is used to select a compact and importance-ranked subset of discriminative features from the original high-dimensional representation. A one-dimensional Convolutional Neural Network (CNN) is then trained on the feature set with reduced weights to capture the characteristic of local co-occurrence patterns of volumetric DDoS traffic. Finally, the trained model is exported and deployed using ONNX Runtime for efficient inference on IoT gateway hardware. Experimental evaluation on the CIC-IoT-2023 dataset demonstrates that the proposed W-GA+CNN framework consistently outperforms baseline classifiers in terms of classification effectiveness and inference throughput while maintaining sub-millisecond edge inference latency. The proposed evolutionary feature reduction and edge-optimized CNN framework provides an effective and deployment-ready solution for real-time large-scale IoT DDoS detection, making it suitable for practical intrusion detection deployment in production IoT gateway environments.

  • YOLO-Lychee: A YOLOv8s-Based Detector for Lychee Growth-Stage Detection under Natural Orchard Conditions

    Appears in:
    airo 26(1):

    Authors:
    Huyen-Trang Nguyen, Thi-Nguyen Nguyen, Dinh-Thai Kim, Manh-Tuan Do, Tuan-Minh Nguyen

    Published:
    27th Jul 2026

    Abstract:
    Accurate lychee growth-stage detection in natural orchards is challenging because blossoms and fruits are often small, densely clustered, partially occluded, and visually similar to surrounding foliage. This study proposes YOLO-Lychee, a YOLOv8s-based detector for four developmental stages: blossom, young fruit, green fruit, and ripe fruit. The dataset contains 1,145 original orchard images and 19,422 annotated instances collected in Hai Duong and Bac Giang provinces, Vietnam. To reduce blossom-class imbalance, exposure-based augmentation was applied only to blossom samples in the training subset, resulting in 1,324 images and 20,261 annotations, while the validation and test sets remained unchanged. YOLO-Lychee replaces the original SPPF module with a Spatial and Channel Cross-Transformer module, incorporates a Context Augmentation Module in the neck, and uses EIoU instead of the default CIoU loss for bounding-box regression. Across six random seeds, YOLO-Lychee achieved a Precision of 83.02 ± 2.38%, Recall of 82.19 ± 1.87%, mAP50 of 88.42 ± 0.38%, and mAP50:95 of 72.76 ± 0.45%. Compared with recent YOLO-family detectors under the same protocol, the proposed model obtained the highest mAP50 and competitive mAP50:95 while maintaining real-time inference. Ablation results confirm the complementary contributions of SC3T, CAM, and EIoU, whereas qualitative analysis shows that blossom detection remains the most challenging case. These results demonstrate that YOLO-Lychee is a practical empirical baseline for lychee growth-stage detection and vision-assisted orchard monitoring.

  • XHBot: eXplainable Heterophily-aware Graph Neural Networks for Social Bot Detection

    Appears in:
    airo 26(1):

    Authors:
    Dat Le, Minh Ngoc Dinh, Quang-Vinh Dang, Phuong-Lan Nguyen

    Published:
    7th Jul 2026

    Abstract:
    Social bots threaten the integrity of online ecosystems by engaging in coordinated opinion manipulation. While Graph Neural Networks (GNNs) have become a dominant paradigm for bot detection, modern camouflaged bots strategically follow benign users to evade detection, creating structural heterophily that degrades the performance of standard homophilic GNN aggregators; moreover, many existing detectors offer limited forensic explainability. To address these challenges jointly, we propose XHBot (eXplainable Heterophily-aware Bot detector), a framework that is robust to heterophilic relation camouflage while providing transparent, multi-level forensic evidence for platform moderation. XHBot couples three components: Spectral-Guided Topology Refinement (SGTR), which down-weights camouflage edges by their contribution to the graph’s high-frequency (Dirichlet) energy before aggregation; Tri-Channel Heterophily-Aware Aggregation (THCA), which separates homophilic, heterophilic, and self-identity signals; and Contrastive Prototype Disentanglement (CPD), which decouples behavioural signatures from social positioning. Evaluated on TwiBot-20, TwiBot-22, and Cresci-2017 under a unified protocol, XHBot reaches an F1 score of 0.9474 on TwiBot-20, improving over a competitive suite of recent baselines (including RGT, NeighborSense, and HW-GNN) by 9.64%. Its Hierarchical Forensic Explanation (HFE) module extracts both instance-level subgraphs and community-level diagnostic motifs, which we assess quantitatively (Fidelity, Sparsity) and through qualitative case studies. These results indicate that decoupling behavioural signatures from adversarial social positioning is valuable for modern bot detection, and that combining accuracy with interpretable evidence supports deployment in real-world moderation settings.

  • Smart Agro-ecosystem: A Review of LLM-based Robotic Systems for Sensing and Decision Support in Precision Agriculture

    Appears in:
    airo 26(1):

    Authors:
    Aiman Elragig, Ata Jahangir Moshayedi, Zeashan Khan, Amir Sohail Khan, David Bassir, Amin Kolahdooz

    Published:
    24th Jun 2026

    Abstract:
    Smart agriculture employs emerging technologies to address main challenges such as greenhouse gases emissions, crop yield optimization, and efficient irrigation through optimized resource planning. This paper reviews Large Language Models (LLMs), robots, and multi-sensor data fusion by combining information from multiple sensors to detect real-time gas emissions for decision support in Agricultural Cyber Physical System (ACPS). LLMs are distinct from earlier AI because they understand context and can process data from IoT sensors, drones, and satellites into useful advice for farmers. Robots with gas sensors can effectively monitor the emissions such as CO2, CH4, NH3, and NO2, while adaptive algorithms improve resilience under dynamic field conditions. This paper systematically reviews the current trends in LLM-based natural language processing (NLP) systems, multimodal architectures, and fusion strategies for distributed intelligence. Some case studies are used to demonstrate practical scenarios within the ACPS domain, highlighting AI deployment benefits, e.g. improved environmental parameters and better compliance with climate regulations. Future directions include swarm robotics for scalable monitoring, edge AI for real-time inference and lightweight LLMs for resource-constrained embedded cyber-physical systems. By compiling state-of-the-art research, this review establishes a road-map for LLM-driven, robotics-enabled ecosystem offering transformative potential for climate-smart, resilient agriculture.

  • Methodologies enabling Mobile Robots Collective Motion: A Comprehensive Review

    Appears in:
    airo 26(1):

    Authors:
    Thabo Semong, Dimane Mpoeleng, Maikano Kenneth Oganne

    Published:
    15th Jun 2026

    Abstract:
    The demand for multi-robotic systems continues to grow. As a result, there is a notable interest among researchers and industry experts to develop control methods or policies to determine how multi-robot system members should cooperate in order to enforce cohesion. These methods can be classified as nature-inspired, self-propelled particles (SPP) based, and learning-based algorithms. This paper presents a comprehensive review of these methods. The main aim is to identify, analyze and discuss the strengths and weaknesses of these methods. Additionally, this paper aims to suggest the optimal control method for enabling effective collective motion of multiple robots and to highlight the identified research gaps and suggest how they can be addressed. Nature inspired algorithms such as ant colony optimization (ACO) are simple and easy to implement when compared to others. However, they require careful parameter tuning for them to operate optimally. On the other hand, self-propelled particles (SPP) based algorithms are decentralized, easy to configure, and produce naturalistic emergent behavior, but suffer from high oscillation when experiencing inaccurate sensor readings and communication delays. Addressing the limitations of nature-inspired and SPP based algorithms should focus on developing control methods with learning abilities. Although learning-based methods are computationally intensive, they are capable of handling sensor inaccuracies and communication latency, making them well suited for the collective motion requirements of mobile robots, particularly in highly dynamic environments. Various strategies, including network pruning, the use of TinyML, and Central Training with Distributed Execution (CTDE), can be employed to optimize learning based methods for robots with limited resources.

  • AC-Seq2Net: A Math-Guided Hybrid Deep Learning Framework for Explainable Geometric Pattern Recognition in Financial Time Series

    Appears in:
    airo 26(1):

    Authors:
    Abdul Kadar Muhammad Masum, Najmus Saadat, Md Fazlur Rahman, Esrat Jahan, Md Faysal Ahmed, Md. Abul Kalam Azad

    Published:
    8th Jun 2026

    Abstract:
    Financial market data is usually rough and volatile. This noise makes it difficult to detect clear price structures from raw intraday records. Traders still rely on geometric patterns such as symmetrical triangles to describe consolidation and potential breakouts. Deep learning models are able to acknowledge market internal conditions with high scores though they tend to acquire concealed relations. They do not capture the triangle geometry in an explicit form. This introduces a gap of representation and lowering interpretability. In order to overcome this problem, we proposed AC-Seq2Net. It is a math-guided hybrid symmetrical triangle recognition model in intraday price data. The pipeline segments the price stream into rolling windows and applies local min-max normalization to keep the scale consistent across different price levels. Ground truth labels are produced through geometric boundary extraction using ordinary least squares trendlines, upon which slope convergence and volatility contraction are derived as explicit engineered features. Unlike purely black-box sequence models, AC-Seq2Net integrates these geometric descriptors alongside hybrid temporal representation learning. A two-stage 1D-CNN extracts local structural patterns, a Bidirectional LSTM captures temporal dependencies, and an Attention mechanism highlights critical convergence boundaries. This design encodes symmetrical triangle geometry directly rather than approximating it through latent feature learning alone, bridging deep learning performance with trader-interpretable geometric reasoning validated through SHAP-based explainability. The triangle probability is produced using a sigmoid layer. Experiments on longitudinal S&P 500 and NASDAQ 100 data report 97.70% accuracy and 0.9947 AUC, confirming that geometric signals rather than random fluctuations drive model decisions.

  • Deep Learning Application Pros And Cons Over Algorithm Deep Learning Application Pros And Cons Over Algorithm

    Appears in:
    airo 22(1): 7

    Authors:
    Atanu Shuvam Roy, Yang Shuxin, Ata Jahangir Moshayedi, Amin Kolahdooz

    Downloads:
    3744

    Abstract:
    Deep learning is a new area of machine learning research. Deep learning technology applies the nonlinear and advanced transformation of model abstraction into a large database. The latest development shows that deep learning in various fields and greatly contributed to artificial intelligence so far. This article reviews the contributions and new applications of deep learning. The main target of this review is to give the summarize points for scholars to have the analysis about applications and algorithms. Then review tries to investigate the main applications and uses algorithms. In addition, the advantages of using the method of deep learning and its hierarchical and nonlinear functioning are introduced and compared to traditional algorithms in common applications. The following three criteria should be taken into consideration when choosing the area of application. (1) expertise or knowledge of the author; (2) the successful application of deep learning technology has changed the field of application, such as voice recognition, chat robots, search technology and vision; and (3) deep learning can have a significant impact on the application domain and benefit from recent research with natural language and text processing, information recovery and multimodal information processing resulting from multitasking deep learning. This review provides a general overview of a new concept and the growing benefits and popularity of deep learning, which can help researchers and students interested in deep learning methods. Deep learning is a new area of machine learning research. Deep learning technology applies the nonlinear and advanced transformation of model abstraction into a large database. The latest development shows that deep learning in various fields and greatly contributed to artificial intelligence so far. This article reviews the contributions and new applications of deep learning. The main target of this review is to give the summarize points for scholars to have the analysis about applications and algorithms. Then review tries to investigate the main applications and uses algorithms. In addition, the advantages of using the method of deep learning and its hierarchical and nonlinear functioning are introduced and compared to traditional algorithms in common applications. The following three criteria should be taken into consideration when choosing the area of application. (1) expertise or knowledge of the author; (2) the successful application of deep learning technology has changed the field of application, such as voice recognition, chat robots, search technology and vision; and (3) deep learning can have a significant impact on the application domain and benefit from recent research with natural language and text processing, information recovery and multimodal information processing resulting from multitasking deep learning. This review provides a general overview of a new concept and the growing benefits and popularity of deep learning, which can help researchers and students interested in deep learning methods.

  • A Brief Analysis of “ChatGPT” – A Revolutionary Tool Designed by OpenAI

    Appears in:
    airo 23(1): e15

    Authors:
    Md. Asraful Haque

    Downloads:
    3076

    Abstract:
    The ChatGPT, a powerful conversational tool trained by OpenAI is considered to be a revolutionary model in the field of artificial intelligence and natural language processing. It has received a lot of attention because of its potential to automate a variety of tasks and possibly have an impact on sectors like translation, customer service, and content creation. It uses GPT-3 (Generative Pre-training Transformer 3) language model to process user queries. GPT-3 has been trained on a very large dataset, which includes a wide range of texts from the internet and other sources. This has given it a broad knowledge base and has allowed it to generate responses to a wide range of prompts that are coherent and human-like. GPT-3 is one of the largest and most powerful language models to date, and it has the ability to perform a wide range of natural language processing tasks. After its release, ChatGPT has become a trending tool for the public to experiment and explore what it is capable of. In this article, we want to clarify what ChatGPT is. How does it work? What makes it different from other chatbots or search engines like Google? What are the major challenges and future prospects for it?

  • Review of Image Classification Algorithms Based on Graph Convolutional Networks

    Appears in:
    airo 23(1):

    Authors:
    Wenhao Tang

    Downloads:
    2894

    Abstract:
    In recent years, graph convolutional networks (GCNs) have gained widespread attention and applications in image classification tasks. While traditional convolutional neural networks (CNNs) usually represent images as a two-dimensional grid of pixels when processing image data, the classical model of graph neural networks (GNNs), GCNs, can effectively handle data with graph structure, such as social networks, recommender systems, and molecular structures. In this paper, we will introduce the problems that graph convolutional networks have had, such as over-smoothing, and the methods to solve them, and suggest some possible future directions.

  • The Object Detection, Perspective and Obstacles In Robotic: A Review

    Appears in:
    airo 22(1): e13

    Authors:
    Ata Jahangir Moshayedi, Ge Xu, Amir Sohail Khan, Yang Shuxin, Xiaohong Zhang

    Downloads:
    2852

    Abstract:
    A few years back, when the image processing hardware and software were created, it was limited, and most of the time, object detection would fail., But as with time, the advancement in technology has significantly changed the scenario. A lot of researchers worked in this field to carry out a solution through which they can detect objects in any field, especially in the robotic domain [1]. In today's world, with so much research in the field of deep learning, it is very easy to identify and detect any object using computer vision. This paper focuses on the various deep learning technologies and algorithms through which object detection can be done. A new and advanced deep learning technology known as salient object detection has been discussed. Also, the 3D object detection and the end-to-end approach for object detection are discussed. The existing methods of deep learning through which object detection can be done. The applications in which object detection is being used and the importance of object detection. It also reports; what the predecessors have done, what problems have been solved by them, how they solved these problems, the characteristics of the predecessors' methods and their future work.

  • The Role of Biometric in Banking: A Review

    Appears in:
    airo 23(1):

    Authors:
    Masoumeh Soleimani, Mehdi Marani, Atajahangir Moshayedi, Mina Bahadori

    Downloads:
    2103

    Abstract:
    Biometrics plays a pivotal role in enhancing security, ensuring accurate identification, and offering convenient solutions across diverse industries. Its uniqueness, reliability, and potential for future advancements establish it as a crucial and valuable field in today's digital landscape. Fingerprint authentication in ATMs presents primary advantages such as heightened security through distinctive identification and user convenience by eliminating the reliance on PINs or passwords. This research paper focuses on conducting a comprehensive review and comparative analysis of various approaches for fingerprint identification, aiming to contribute to the understanding of effective and efficient methods in the context of ATM authentication.

  • Review On: The Service Robot Mathematical Model

    Appears in:
    airo 22(1): 8

    Authors:
    Liefa Liao, Ata Jahangir Moshayedi, Atanu Shuvam Roy, Yangwan Zhong, Sithembiso Khaya Sambo

    Downloads:
    2097

    Abstract:
    After nearly 30 years of development, service robot technology has made important achievements in the interdisciplinary aspects of machinery, information, materials, control, medicine, etc. These robot types have different shapes, and mainly in some are shaped based on application. Till today various structure are proposed which for the better analysis’s need to have the mathematical equation that can model the structure and later the behaviour of them after implementing the controlling strategy. The current paper discusses the various shape and applications of all available service robots and briefly summarizes the research progress of key points such as robot dynamics, robot types, and different dynamic models of the differential types of service robots. The current review study can be helpful as an initial node for all researchers in this topic and help them to have the better simulation and analyses. Besides the current research shows some application that can specify the service robot model over the application.

  • LQG, PID controller, ANN for single axis gimbal actuator

    Appears in:
    airo 22(1): e12

    Authors:
    Nguyen Cong Danh

    Downloads:
    2043

    Abstract:
    Gimbal or other stable platforms have structures that move according to its functions. This is for the purpose of keeping track of the goals to the fullest. Tracking targets can become difficult as the subject moves further and further away and they are out of the gimbal’s allowable viewing range. Besides, under the influence of noise signals form outside space, it becomes even more difficult to observe the gimbal’s targets. To overcome above disadvantages, this paper is presented an adjustment method to limit above risks. Adjusting Linear Quadratic Gaussian (LQG) for expensive gimbal systems, noise signals are processed purely by Kalman filters to improve the function of observing targets. In addition, proportional- integral-derivative (PID) controller, artificial neural network in this case is also considered to verify the effectiveness of  control methods listed below. In particular, ANN is the most effective control method today to deal with unwanted signals. These unwanted signals can cause worsening conditions during the operation of systems.Therefore, artificial network (ANN) is a solution to information and communication security problems. Simulation is done by Matlab. Novelty of the work: no previous research has been published for this  genre. The study of this genre with the use of artificial intelligence is suggestive of the study of artificial intellligence technologies at a higher level. This category is also a suggestion for studying a smoother control method based on existing data.

  • Peaks Detector Algorithm after CFAR for Multiple Targets Detection

    Appears in:
    airo 22(1): 11

    Authors:
    Syed Waqar Hameed

    Downloads:
    1818

    Abstract:
    The constant false alarm rate (CFAR) algorithm is a strong technique to detect and track dynamic targets in an environment of an unknown noise floor. Multiple reflections of a pulse from a target and different signal processing techniques applied to the received pulse, make it spread along the range and/or Doppler axis. Spreading of a pulse results in a cluster of targets detection for a single target when the CFAR technique is applied to it. This causes difficulties in calculating those target’s parameters which require only a single maximum peak for a target, such as Radar cross-section (RCS), relative phase, etc. This manuscript proposes a solution, which extracts a single independent peak for a target that had clusters of peaks after CFAR. The novelty of the algorithm is that it works well to extract a single peak for each of all targets in the multiple targets environment, as compared to the conventional global maxima finding techniques which outputs only one target of the maximum amplitude while suppressing the rest of the small targets. The algorithm is basically a local maxima finder algorithm termed as peaks detector algorithm. An attractive feature of this algorithm is that it neither disturbs the Probability of false alarm rate (Pfa) of CFAR nor it affects the probability of detection (Pd) of a target. The algorithm is tested and its performance is evaluated in a multiple targets environment on the output of 1D and 2D CFAR.

  • Immersive Horizons: Exploring the Transformative Power of Virtual Reality Across Economic Sectors

    Appears in:
    airo 23(1): e6

    Authors:
    Abdullah Nawaz, Amin Kolahdooz, Ata Jahangir Moshayedi, Abiodun Durojaye

    Downloads:
    1688

    Abstract:
    The scholarly discourse surrounding the manifold advantages, applications, and limitations of implementing Virtual Reality (VR) in the contemporary milieu has burgeoned over time. VR holds immense potential, attracting fervent interest from governmental and private entities alike. Nevertheless, the existing body of literature pertaining to the expanding utilization of VR in diverse economic sectors remains scant. Therefore, the primary objective of this study is to furnish a comprehensive literature review encompassing VR applications across various economic domains while elucidating concerns surrounding its integration within engineering education. A total of 108 publications were extracted from prominent databases such as Scopus, Elsevier, Science Direct, and Google Scholar, with a subsequent review of 51 relevant works. These scrutinized journals were published between 2015 and 2022 and were predominantly authored in English. The reviewed publications encompassed VR applications in education, robotics, healthcare, transportation, sports, agriculture, governance, security, and media. The study’s findings unveiled significant advancements in VR implementation within engineering education, medical training, cognitive augmentation, aircraft assembly, governance, and diverse other spheres. Notwithstanding these achievements, impediments to VR deployment were identified, stemming from financial exigencies, cultural and conventional norms, with scant evidence of VR’s prevalence in underdeveloped nations, given that all the assessed research originated from developed economies. Additionally, the limitations of this review encompassed a small sample size and a narrowly focused demographic in the examined articles. Nevertheless, despite these constraints, the research highlights substantial progress in VR utilization over the preceding decade.

  • The Potential Use of ChatGPT for Debugging and Bug Fixing The Potential Use of ChatGPT for Debugging and Bug Fixing

    Appears in:
    airo 23(1):

    Authors:
    Md. Asraful Haque, Shuai Li, Shuai Li, MD ASRAFUL HAQUE

    Downloads:
    1610

    Abstract:
    ChatGPT is a cutting-edge language model that has been making waves in the field of natural language processing. However, its capabilities extend far beyond language-based applications. ChatGPT can also be used as a powerful tool for debugging software code. As software applications become increasingly complex, the need for efficient and accurate debugging tools has become more pressing. ChatGPT's ability to analyze and understand code makes it a promising solution to this challenge. Debugging is a critical part of the software development process. Bugs, or errors in code, can have serious consequences for the functionality and security of software applications. Identifying and fixing bugs can be a time-consuming and labor-intensive process, requiring the expertise of experienced developers. ChatGPT has the potential to streamline this process and make it more accessible to a wider range of developers, regardless of their experience level. In this article, we will explore the capabilities of ChatGPT as a debugging tool, the advantages and limitations of using it, and best practices for integrating it into the software development workflow. ChatGPT is a cutting-edge language model that has been making waves in the field of natural language processing. However, its capabilities extend far beyond language-based applications. ChatGPT can also be used as a powerful tool for debugging software code. As software applications become increasingly complex, the need for efficient and accurate debugging tools has become more pressing. ChatGPT's ability to analyze and understand code makes it a promising solution to this challenge. Debugging is a critical part of the software development process. Bugs, or errors in code, can have serious consequences for the functionality and security of software applications. Identifying and fixing bugs can be a time-consuming and labor-intensive process, requiring the expertise of experienced developers. ChatGPT has the potential to streamline this process and make it more accessible to a wider range of developers, regardless of their experience level. In this article, we will explore the capabilities of ChatGPT as a debugging tool, the advantages and limitations of using it, and best practices for integrating it into the software development workflow.
Publisher
EAI
ISSN
2790-7511
Number of Volumes
5
Last Published
2025-12-08
EAI Logo

About EAI

Community

Publish with EAI