An Dinh Le
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
An Dinh Le has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Hien Bich Vo
Vietnamese-German University
3 shared publications Anh-Duy Pham
Joint Lab Artificial Intelligence & Data Science, Osnabrück University, Germany
2 shared publications- Chuong Dinh Le
Institute of Computer Science, Universität Bonn, Germany
2 shared publications - Dat Thanh Vo
Department of Mechanical, Automotive and Materials Engineering, University of Windsor, Canada
2 shared publications Hien Bich Vo
Electrical and Computer Engineering Department, Vietnamese-German University, Vietnam
2 shared publications- Hoang Viet Pham
Vietnamese-German University
2 shared publications
Latest Publications
- Open Access
- 22 July 2026
- Published by BON VIEW PUBLISHING PTE in Artificial Intelligence and Applications
- Vol. 4 (3) , 443
Erratum to: Toward a Causal PM2.5 Concentration Forecasting by Inferencing from Local Vehicle Tracking with a Low-Cost End-to-End Sensor System
During the production process, incorrect text was inadvertently introduced into the Conclusion section of the published article [Toward a Causal PM2.5 Concentration Forecasting by Inferencing from Local Vehicle Tracking with a Low-Cost End-to-End Sensor System]. The correct Conclusion should read as follows: This study has successfully demonstrated the feasibility of our novel approach to estimate PM2.5 concentrations using traffic density and readily available hardware, hinting at the possibility of PM2.5 measurement based solely on the amounts of motorbikes and cars. The implementation of a streamlined vehicle counting algorithm based on Yolov7 ensures robust performance in various conditions. For estimation, it is recommended to use the Cubist mode over the mathematical method due to Cubist’s superior performance. By synergizing hardware and algorithmic advancements, we have opened avenues for further research into the determinants of urban air quality. Future work can focus on refining the system design, incorporating additional environmental factors, and exploring more sophisticated machine learning models to further enhance prediction accuracy. The Publisher apologizes to the authors and readers for this error. References [1] Le, C. D., Pham, H. V., Tran, T. G., Le, A. D., Pham, A.-D., Vo, D. T., . . . , & Han, H.-D. (2026). Toward a causal PM2.5 concentration forecasting by inferencing from local vehicle tracking with a low-cost end-to-end sensor system. Artificial Intelligence and Applications, 4(2), 187–196. https://doi.org/10.47852/bonviewAIA62024212
- 22 July 2026
- Published by BON VIEW PUBLISHING PTE in Artificial Intelligence and Applications
- Vol. 4 (3) , 443
Open AccessErratum to: Toward a Causal PM2.5 Concentration Forecasting by Inferencing from Local Vehicle Tracking with a Low-Cost End-to-End Sensor System
During the production process, incorrect text was inadvertently introduced into the Conclusion section of the published article [Toward a Causal PM2.5 Concentration Forecasting by Inferencing from Local Vehicle Tracking with a Low-Cost End-to-End Sensor System]. The correct Conclusion should read as follows: This study has successfully demonstrated the feasibility of our novel approach to estimate PM2.5 concentrations using traffic density and readily available hardware, hinting at the possibility of PM2.5 measurement based solely on the amounts of motorbikes and cars. The implementation of a streamlined vehicle counting algorithm based on Yolov7 ensures robust performance in various conditions. For estimation, it is recommended to use the Cubist mode over the mathematical method due to Cubist’s superior performance. By synergizing hardware and algorithmic advancements, we have opened avenues for further research into the determinants of urban air quality. Future work can focus on refining the system design, incorporating additional environmental factors, and exploring more sophisticated machine learning models to further enhance prediction accuracy. The Publisher apologizes to the authors and readers for this error. References [1] Le, C. D., Pham, H. V., Tran, T. G., Le, A. D., Pham, A.-D., Vo, D. T., . . . , & Han, H.-D. (2026). Toward a causal PM2.5 concentration forecasting by inferencing from local vehicle tracking with a low-cost end-to-end sensor system. Artificial Intelligence and Applications, 4(2), 187–196. https://doi.org/10.47852/bonviewAIA62024212
- Open Access
- 17 March 2026
- Published by BON VIEW PUBLISHING PTE in Artificial Intelligence and Applications
- Vol. 4 (2) , 187-196
Toward a Causal PM2.5 Concentration Forecasting by Inferencing from Local Vehicle Tracking with a Low-Cost End-to-End Sensor System
This paper introduces a pioneering, end-to-end system designed for the accurate estimation of PM2.5 concentrations, which uniquely integrates custom-designed hardware with advanced computational algorithms. A central innovation of this work is the development of a seamless data pipeline that connects real-time vehicle tracking with sophisticated air quality prediction, offering a novel and comprehensive solution for urban environmental monitoring. The system employs a cost-effective, custom-built sensor package, including PMS7003 and BME280 sensors alongside a 5MP camera, with a bespoke hardware design specifically engineered to enhance operational stability. For the estimation component, a rigorous comparative analysis was conducted, demonstrating that the Cubist regression model significantly outperforms other contemporary machine learning and traditional mathematical models; this success is attributed to its superior ability to model the complex, nonlinear relationship between observed traffic density and ambient PM2.5 levels. Furthermore, a streamlined vehicle counting algorithm, leveraging a fine-tuned YOLOv7 model, ensures robust and accurate traffic detection performance across various lighting and environmental conditions. This research successfully establishes an optimal PM2.5 estimation pipeline based on real-world vehicle counts, presenting an integrated framework for dynamic urban air quality analysis. Received: 30 August 2024 | Revised: 30 September 2025 | Accepted: 14 January 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/comrang-altf4/PM2.5. Author Contribution Statement Chuong Dinh Le: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Hoang Viet Pham: Conceptualization, Methodology, Software, Investigation, Data curation, Writing – original draft, Visualization. Thinh Gia Tran: Conceptualization, Methodology, Software, Validation, Investigation, Writing – original draft, Visualization. An Dinh Le: Conceptualization, Methodology, Resources, Writing – review & editing, Supervision, Project administration. Anh-Duy Pham: Conceptualization, Methodology, Resources, Supervision, Project administration. Dat Thanh Vo: Software, Writing – original draft, Visualization. Hien Bich Vo: Resources, Supervision. Huy-Dung Han: Supervision.
- 17 March 2026
- Published by BON VIEW PUBLISHING PTE in Artificial Intelligence and Applications
- Vol. 4 (2) , 187-196
Open AccessToward a Causal PM2.5 Concentration Forecasting by Inferencing from Local Vehicle Tracking with a Low-Cost End-to-End Sensor System
This paper introduces a pioneering, end-to-end system designed for the accurate estimation of PM2.5 concentrations, which uniquely integrates custom-designed hardware with advanced computational algorithms. A central innovation of this work is the development of a seamless data pipeline that connects real-time vehicle tracking with sophisticated air quality prediction, offering a novel and comprehensive solution for urban environmental monitoring. The system employs a cost-effective, custom-built sensor package, including PMS7003 and BME280 sensors alongside a 5MP camera, with a bespoke hardware design specifically engineered to enhance operational stability. For the estimation component, a rigorous comparative analysis was conducted, demonstrating that the Cubist regression model significantly outperforms other contemporary machine learning and traditional mathematical models; this success is attributed to its superior ability to model the complex, nonlinear relationship between observed traffic density and ambient PM2.5 levels. Furthermore, a streamlined vehicle counting algorithm, leveraging a fine-tuned YOLOv7 model, ensures robust and accurate traffic detection performance across various lighting and environmental conditions. This research successfully establishes an optimal PM2.5 estimation pipeline based on real-world vehicle counts, presenting an integrated framework for dynamic urban air quality analysis. Received: 30 August 2024 | Revised: 30 September 2025 | Accepted: 14 January 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/comrang-altf4/PM2.5. Author Contribution Statement Chuong Dinh Le: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Hoang Viet Pham: Conceptualization, Methodology, Software, Investigation, Data curation, Writing – original draft, Visualization. Thinh Gia Tran: Conceptualization, Methodology, Software, Validation, Investigation, Writing – original draft, Visualization. An Dinh Le: Conceptualization, Methodology, Resources, Writing – review & editing, Supervision, Project administration. Anh-Duy Pham: Conceptualization, Methodology, Resources, Supervision, Project administration. Dat Thanh Vo: Software, Writing – original draft, Visualization. Hien Bich Vo: Resources, Supervision. Huy-Dung Han: Supervision.
- Open Access
- 22 January 2026
- Published by Springer Nature in Research Square
Breaking the Single-Mosquito Barrier: Synthetic Swarm Data for Acoustic Vector Monitoring
Mosquito-borne diseases pose a significant global health threat, causing more than 700,000 deaths annually and placing increasing pressure on vector surveillance programs. This work presents a proof-of-concept Synthetic Swarm Mosquito Dataset designed for acoustic classification under realistic multi-species and noisy swarm conditions. In contrast to conventional datasets, whose construction requires labor-intensive recording of individual mosquitoes, our synthetic approach enables scalable, reproducible data generation without extensive fieldwork. The core novelty of this study lies in the controlled synthesis of swarm audio, capturing overlapping wingbeat patterns, variable densities, and heterogeneous noise profiles that are difficult to obtain from natural environments. Using log-mel spectrogram representations, we evaluate several lightweight deep learning architectures and demonstrate that these models can reliably classify six major mosquito vectors, even under swarm-induced acoustic interference. Furthermore, the proposed method was validated using real-world mosquito audio collected from a CO2-baited trap in Vung Tau, Vietnam. This field evaluation demonstrates that our synthetic-trained model generalizes effectively to practical deployment conditions, confirming the real-world feasibility of swarm-capable acoustic mosquito surveillance. The public dataset used in this study is available online.
- 22 January 2026
- Published by Springer Nature in Research Square
Open AccessBreaking the Single-Mosquito Barrier: Synthetic Swarm Data for Acoustic Vector Monitoring
Mosquito-borne diseases pose a significant global health threat, causing more than 700,000 deaths annually and placing increasing pressure on vector surveillance programs. This work presents a proof-of-concept Synthetic Swarm Mosquito Dataset designed for acoustic classification under realistic multi-species and noisy swarm conditions. In contrast to conventional datasets, whose construction requires labor-intensive recording of individual mosquitoes, our synthetic approach enables scalable, reproducible data generation without extensive fieldwork. The core novelty of this study lies in the controlled synthesis of swarm audio, capturing overlapping wingbeat patterns, variable densities, and heterogeneous noise profiles that are difficult to obtain from natural environments. Using log-mel spectrogram representations, we evaluate several lightweight deep learning architectures and demonstrate that these models can reliably classify six major mosquito vectors, even under swarm-induced acoustic interference. Furthermore, the proposed method was validated using real-world mosquito audio collected from a CO2-baited trap in Vung Tau, Vietnam. This field evaluation demonstrates that our synthetic-trained model generalizes effectively to practical deployment conditions, confirming the real-world feasibility of swarm-capable acoustic mosquito surveillance. The public dataset used in this study is available online.
- Open Access
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 6, 768-783
Biorthogonal Lattice Tunable Wavelet Units and Their Implementation in Convolutional Neural Networks for Computer Vision Problems
This work introduces a universal wavelet unit constructed with a biorthogonal lattice structure which is a novel tunable wavelet unit to enhance image classification and anomaly detection in convolutional neural networks by reducing information loss during pooling. The unit employs a biorthogonal lattice structure to modify convolution, pooling, and down-sampling operations. Implemented in residual neural networks with 18 layers, it improved detection accuracy on CIFAR10 (by 2.67%), ImageNet1K (by 1.85%), and the Describable Textures dataset (by 11.81%), showcasing its advantages in detecting detailed features. Similar gains are achieved in the implementations for residual neural networks with 34 layers and 50 layers. For anomaly detection on the MVTec Anomaly Detection and TUKPCB datasets, the proposed method achieved a competitive performance and better anomaly localization.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 6, 768-783
Open AccessBiorthogonal Lattice Tunable Wavelet Units and Their Implementation in Convolutional Neural Networks for Computer Vision Problems
This work introduces a universal wavelet unit constructed with a biorthogonal lattice structure which is a novel tunable wavelet unit to enhance image classification and anomaly detection in convolutional neural networks by reducing information loss during pooling. The unit employs a biorthogonal lattice structure to modify convolution, pooling, and down-sampling operations. Implemented in residual neural networks with 18 layers, it improved detection accuracy on CIFAR10 (by 2.67%), ImageNet1K (by 1.85%), and the Describable Textures dataset (by 11.81%), showcasing its advantages in detecting detailed features. Similar gains are achieved in the implementations for residual neural networks with 34 layers and 50 layers. For anomaly detection on the MVTec Anomaly Detection and TUKPCB datasets, the proposed method achieved a competitive performance and better anomaly localization.
- 10 October 2024
- Published by Springer Nature
- p. 32-41
Wavelet Deep Learning Network for Objective Retinal Functional Estimation from Multimodal Retinal Imaging
- 10 October 2024
- Published by Springer Nature
- p. 32-41
Wavelet Deep Learning Network for Objective Retinal Functional Estimation from Multimodal Retinal Imaging
- Open Access
- 24 June 2024
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
AlertTrap: A Study on Object Detection in Remote Insect Trap Monitoring System Using on the Edge Deep Learning Platform
Fruit flies are one of the most harmful insect species to fruit yields. In AlertTrap, implementation of Single-Shot Multibox Detector (SSD) architecture with different state-of-the-art backbone feature extractors such as MobileNetV1 and MobileNetV2 appears to be potential solutions for the real-time detection problem. SSD-MobileNetV1 and SSD-MobileNetV2 perform well and result in AP at 0.5 of 0.957 and 1.0, respectively. You Only Look Once (YOLO) v4-tiny outperforms the SSD family with 1.0 in AP at 0.5; however, its throughput velocity is considerably slower, which shows SSD models are better candidates for real-time implementation. We also tested the models with synthetic test sets simulating expected environmental disturbances. The YOLOv4-tiny had better tolerance to these disturbances than the SSD models. The Raspberry Pi system successfully gathered environmental data and pest counts, sending them via email over 4 G. However, running the full YOLO version in real time on Raspberry Pi is not feasible, indicating the need for a lighter object detection algorithm for future research. Among model candidates, YOLOv4-tiny generally performs best, with SSD MobileNetV2 also comparable and sometimes better, especially in scenarios with synthetic disturbances. SSD models excel in processing time, enabling real-time, high-accuracy detection. TFLITE versions of SSD models also process faster than their inference graph on TPU hardware, suggesting real-time implementation on edge devices like the Google Coral Dev Board. The results demonstrate the feasibility of real-time implementation of the fruit fly detection models on edge devices with high performance. In addition, YOLOv4-tiny is shown to be the most probable candidate because YOLOv4-tiny demonstrates a robust testing performance toward citrus fruit fly detection. Nevertheless, SSD-MobileNetV2 will be the better model, considering the inference time.
- 24 June 2024
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
Open AccessAlertTrap: A Study on Object Detection in Remote Insect Trap Monitoring System Using on the Edge Deep Learning Platform
Fruit flies are one of the most harmful insect species to fruit yields. In AlertTrap, implementation of Single-Shot Multibox Detector (SSD) architecture with different state-of-the-art backbone feature extractors such as MobileNetV1 and MobileNetV2 appears to be potential solutions for the real-time detection problem. SSD-MobileNetV1 and SSD-MobileNetV2 perform well and result in AP at 0.5 of 0.957 and 1.0, respectively. You Only Look Once (YOLO) v4-tiny outperforms the SSD family with 1.0 in AP at 0.5; however, its throughput velocity is considerably slower, which shows SSD models are better candidates for real-time implementation. We also tested the models with synthetic test sets simulating expected environmental disturbances. The YOLOv4-tiny had better tolerance to these disturbances than the SSD models. The Raspberry Pi system successfully gathered environmental data and pest counts, sending them via email over 4 G. However, running the full YOLO version in real time on Raspberry Pi is not feasible, indicating the need for a lighter object detection algorithm for future research. Among model candidates, YOLOv4-tiny generally performs best, with SSD MobileNetV2 also comparable and sometimes better, especially in scenarios with synthetic disturbances. SSD models excel in processing time, enabling real-time, high-accuracy detection. TFLITE versions of SSD models also process faster than their inference graph on TPU hardware, suggesting real-time implementation on edge devices like the Google Coral Dev Board. The results demonstrate the feasibility of real-time implementation of the fruit fly detection models on edge devices with high performance. In addition, YOLOv4-tiny is shown to be the most probable candidate because YOLOv4-tiny demonstrates a robust testing performance toward citrus fruit fly detection. Nevertheless, SSD-MobileNetV2 will be the better model, considering the inference time.
- Open Access
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 88715-88727
A Lattice-Structure-Based Trainable Orthogonal Wavelet Unit for Image Classification
This work introduces Orthogonal-LatticeUwU, a novel trainable wavelet unit for enhancing image classification and anomaly detection in convolutional neural networks by reducing information loss during pooling. The unit employs an orthogonal lattice structure, relaxing the zero-at-π condition and decreasing the number of trainable wavelet coefficients. This innovation is a key novelty of the work. The unit modifies convolution, pooling, and down-sampling operations. Implemented in ResNet18, it improved detection accuracy on CIFAR10 (by 2.67%), ImageNet1K (by 1.85%), and the Describable Textures dataset (by 9.52%), showcasing its advantages in detecting detailed features. Similar gains were seen in ResNet34 and ResNet50 implementations. For anomaly detection in hazelnut images on the MVTec Anomaly Detection dataset, the proposed method achieved a segmentation area under the receiver operating characteristic curve of 97.15% and better anomaly localization. The method excels in detecting detailed features, despite increased trainable parameters from using one-layer fully convolutional networks for feature combination.
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 88715-88727
Open AccessA Lattice-Structure-Based Trainable Orthogonal Wavelet Unit for Image Classification
This work introduces Orthogonal-LatticeUwU, a novel trainable wavelet unit for enhancing image classification and anomaly detection in convolutional neural networks by reducing information loss during pooling. The unit employs an orthogonal lattice structure, relaxing the zero-at-π condition and decreasing the number of trainable wavelet coefficients. This innovation is a key novelty of the work. The unit modifies convolution, pooling, and down-sampling operations. Implemented in ResNet18, it improved detection accuracy on CIFAR10 (by 2.67%), ImageNet1K (by 1.85%), and the Describable Textures dataset (by 9.52%), showcasing its advantages in detecting detailed features. Similar gains were seen in ResNet34 and ResNet50 implementations. For anomaly detection in hazelnut images on the MVTec Anomaly Detection dataset, the proposed method achieved a segmentation area under the receiver operating characteristic curve of 97.15% and better anomaly localization. The method excels in detecting detailed features, despite increased trainable parameters from using one-layer fully convolutional networks for feature combination.
- Open Access
A PM2.5 concentration prediction framework with vehicle tracking system: From cause to effect
Air pollution is an emerging problem that needs to be solved especially in developed and developing countries. In Vietnam, air pollution is also a concerning issue in big cities such as Hanoi and Ho Chi Minh cities where air pollution comes mostly from vehicles such as cars and motorbikes. In order to tackle the problem, the paper focuses on developing a solution that can estimate the emitted PM2.5 pollutants by counting the number of vehicles in the traffic. We first investigated among the recent object detection models and developed our own traffic surveillance system. The observed traffic density showed a similar trend to the measured PM2.5 with a certain lagging in time, suggesting a relation between traffic density and PM2.5. We further express this relationship with a mathematical model which can estimate the PM2.5 value based on the observed traffic density. The estimated result showed a great correlation with the measured PM2.5 plots in the urban area context.
Open AccessA PM2.5 concentration prediction framework with vehicle tracking system: From cause to effect
Air pollution is an emerging problem that needs to be solved especially in developed and developing countries. In Vietnam, air pollution is also a concerning issue in big cities such as Hanoi and Ho Chi Minh cities where air pollution comes mostly from vehicles such as cars and motorbikes. In order to tackle the problem, the paper focuses on developing a solution that can estimate the emitted PM2.5 pollutants by counting the number of vehicles in the traffic. We first investigated among the recent object detection models and developed our own traffic surveillance system. The observed traffic density showed a similar trend to the measured PM2.5 with a certain lagging in time, suggesting a relation between traffic density and PM2.5. We further express this relationship with a mathematical model which can estimate the PM2.5 value based on the observed traffic density. The estimated result showed a great correlation with the measured PM2.5 plots in the urban area context.
- Open Access
AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform
Fruit flies are one of the most harmful insect species to fruit yields. In AlertTrap, implementation of SSD architecture with different state-of-the-art backbone feature extractors such as MobileNetV1 and MobileNetV2 appear to be potential solutions for the real-time detection problem. SSD-MobileNetV1 and SSD-MobileNetV2 perform well and result in AP@0.5 of 0.957 and 1.0 respectively. YOLOv4-tiny outperforms the SSD family with 1.0 in AP@0.5; however, its throughput velocity is slightly slower.
Open AccessAlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform
Fruit flies are one of the most harmful insect species to fruit yields. In AlertTrap, implementation of SSD architecture with different state-of-the-art backbone feature extractors such as MobileNetV1 and MobileNetV2 appear to be potential solutions for the real-time detection problem. SSD-MobileNetV1 and SSD-MobileNetV2 perform well and result in AP@0.5 of 0.957 and 1.0 respectively. YOLOv4-tiny outperforms the SSD family with 1.0 in AP@0.5; however, its throughput velocity is slightly slower.