case
Artificial Intelligence and Autonomous Systems

ISSN: 2959-0744 (Print)

ISSN: 2959-0752 (Online)

CODEN: AIASBB

Article
Open Access
Global confidence degree based graph neural network for financial fraud detection
Jiaxun LiuYue TianGuanjun Liu

DOI:10.55092/aias20250004

Received

12 Mar 2025

Accepted

16 Apr 2025

Published

25 Apr 2025
PDF
Graph Neural Networks (GNNs) are widely used in financial fraud detection due to their excellent ability on handling graph-structured financial data and modeling multilayer connections by aggregating information of neighbors. However, these GNN-based methods focus on extracting neighbor-level information but neglect a global perspective. This paper presents the concept and calculation formula of Global Confidence Degree (GCD) and thus designs GCD-based GNN (GCD-GNN) that can address the challenges of camouflage in fraudulent activities and thus can capture more global information. To obtain a precise GCD for each node, we use a multilayer perceptron to transform features and then the new features and the corresponding prototype are used to eliminate unnecessary information. The GCD of a node evaluates the typicality of the node and thus we can leverage GCD to generate attention values for message aggregation. This process is carried out through both the original GCD and its inverse, allowing us to capture both the typical neighbors with high GCD and the atypical ones with low GCD. Extensive experiments on two public datasets demonstrate that GCD-GNN outperforms state-of-the-art baselines, highlighting the effectiveness of GCD. We also design a lightweight GCD-GNN (GCD-GNNlight ) that also outperforms the baselines but is slightly weaker than GCD-GNN on fraud detection performance. However, GCD-GNNlight obviously outperforms GCD-GNN on convergence and inference speed.
Survey
Open Access
A survey on deep learning-based lidar place recognition
Weizhong JiangShubin SiHanzhang XueYiming NieZhipeng XiaoQi ZhuLiang Xiao

DOI:10.55092/aias20250003

Received

12 Dec 2024

Accepted

27 Feb 2025

Published

31 Mar 2025
PDF
LiDAR-based place recognition (LPR) technology processes 3D LiDAR point clouds and encodes them into feature descriptors, enabling mobile robots to recognize previously visited locations. This capability supports critical tasks such as loop closure detection and re-localization. With the rapid advancements in deep learning, deep learning-based LiDAR place recognition (DL-LPR) has emerged as the dominant research direction in this field. However, existing reviews on DL-LPR remain limited in scope. To address this gap, this paper focuses on DL-LPR, introducing its core concepts, system structures, and applications. It presents a coarse-to-fine classification framework to systematically categorize and review existing methods, based on two dimensions: input data structure and model architecture. Furthermore, this paper summarizes commonly used datasets and performance evaluation metrics, along with performance comparisons of representative methods. Finally, it provides an in-depth analysis of the challenges faced by DL-LPR in complex environments, such as long-term, large-scale, and dynamic settings, and offers insights into future development trends.
Article
Open Access
Bridging human emotion processing and deep neural networks: insights from representational similarity analysis
Lu NieKe ChenYue LiYonghong TianYixuan Ku

DOI:10.55092/aias20250002

Received

03 Jan 2025

Accepted

07 Mar 2025

Published

27 Mar 2025
PDF
Emotion is a complex psychophysiological response to external stimuli, essential for human survival, social interaction, and human-computer interaction. Emotion recognition plays a critical role in both biological systems and artificial agents. However, existing research often treats these systems independently, limiting opportunities for interaction and hindering the development of more advanced models. This study employs representational similarity analysis (RSA) to bridge this gap by comparing emotional representations between the human brain and neural networks, aiming to improve understanding of emotion recognition in deep learning models. By correlating the emotion recognition model EmoNet with EEG signals from the human brain during emotional image processing and introducing AlexNet for comparison, we reveal EmoNet’s human-like representation for emotional images and its hierarchical structure for emotion recognition. The results show that RSA effectively aligns human emotional processing with deep neural networks, offering new avenues for improving the interpretability and performance of emotional AI models. Moreover, they underscore EmoNet’s potential to simulate human emotional responses, paving the way for future research to enhance emotion recognition models by incorporating human emotional evaluations into their training processes, thereby improving efficiency and specificity.
Article
Open Access
Enhanced safety and efficiency in traction elevators: a real-time monitoring system with anomaly detection
Safa OzdemirOsamah N. NeamahRaif Bayir

DOI:10.55092/aias20250001

Received

15 Nov 2024

Accepted

21 Jan 2025

Published

13 Feb 2025
PDF
This study presents the design and implementation of a real-time monitoring system for traction elevators, leveraging piezoelectric sensors for vibration measurement and speed sensors for velocity data acquisition. The system is powered by a LattePanda dashboard equipped with an integrated Real-Time Clock (RTC), ensuring precise data collection and timestamping. Vibration data is captured through piezoelectric sensors, while velocity data from speed sensors is used to calculate acceleration. The collected data is stored locally and can also be transmitted remotely. Aimed at improving elevator safety and efficiency, the system detects potential issues such as misalignments and mechanical wear. Given the increasing number of elevator accidents, this study focuses on enhancing monitoring capabilities using advanced technologies. Data from an electric elevator was analyzed with three anomaly detection algorithms: Isolation Forest, Support Vector Machine (SVM), and Z-score. The results revealed that Isolation Forest identified 15 anomalies (1.06% of the data), SVM detected 25 anomalies (1.77% of the data), and Z-score identified 86 anomalies (6.08% of the data). This research not only enhances elevator condition monitoring but also lays the groundwork for future digital twin systems in passenger elevator applications.
Article
Open Access
Deep reinforcement learning Lane-Change Decision-Making for autonomous vehicles based on motion primitives library in hierarchical action space
Guizhe JinZhuoren LiBo LengMinhua Shao

DOI:10.55092/aias20240009

Received

20 Jun 2024

Accepted

10 Dec 2024

Published

24 Dec 2024
PDF
Deep Reinforcement Learning (DRL) is capable of learning a policy with great scene adaptation ability through interactions with the environment, and has application potential in the field of autonomous driving. However, using DRL to directly control the vehicle motion command is easy to lead to fluctuation and non-smoothness. Discrete DRL decision-making method can generate stable behavior but lose some maneuverability. Thus, the trade-off between flexibility and stability to enhance the performance of DRL policy is an important issue. In this paper, a Deep Reinforcement Learning Decision-Making algorithm based on Motion Primitives Library (MPL) in hierarchical action space is proposed to provide flexible and reliable maneuvers for autonomous driving. The upper action space contains discrete lane-changing targets, and the lower action space is mapped as a motion primitives library. In addition, model predictive control method (MPC) based on the vehicle kinematics model is used to optimize the motion primitives instantly. The performance of the proposed method is evaluated through highway simulation. The results show that the method can make the autonomous driving lane changing process safer, more efficient and more comfortable.
Article
Open Access
Dynamic lane-changing trajectory planning for autonomous vehicles in mixed traffic
Zhen WangJianquan ChenPengchao LiuBo DaiGuanqun WangZhilin Han

DOI:10.55092/aias20240008

Received

14 May 2024

Accepted

30 Oct 2024

Published

05 Dec 2024
PDF
This paper presents a novel dynamic lane-changing trajectory planning (DLCTP) model for autonomous vehicle (AV) running in the mixed traffic environment. The proposed model fully considers the dynamics of surrounding human-driven vehicles and can work on both straight and curved roads. The first step of the DLCTP model is to decide when and where to make the lane change based on the car-following model and safety constraints. Upon decision-making, an optimal lane-changing trajectory that accounts for safety, comfort, and efficiency is generated at each time step until the lane-changing procedure is completed. CarSim-Simulink based simulation platform and three typical traffic scenarios are applied to validate the proposed DLCTP model. Experimental results show that the proposed DLCTP model can generate smooth, safe, and comfort trajectories even in complex traffic situations. The proposed DLCTP model can be employed directly on real AVs because it is easy to implement and can adapt to complex traffic environments.
Planning, Control, and Learning in Mobile Robots
Special Issue Editor Yingbai Hu, Chengxi Zhang, Jin Wu, Shugen Ma, Xin Xu
Aerial Robotics
Special Issue Editor Roberto Naldi, Witold Pedrycz
Intelligent Transportation Systems
Special Issue Editor Tao Liu, Senlei Wang, Meng Xu, Chengzhong Xu