kth.sePublications
Change search
Link to record
Permanent link

Direct link
Chen, DeJiu, Associate ProfessorORCID iD iconorcid.org/0000-0001-7048-0108
Alternative names
Publications (10 of 136) Show all publications
Tahmasebi, K. N., Khound, P. & Chen, D. (2024). A Condition-Aware Stochastic Dynamic Control Strategy for Safe Automated Driving. IEEE Transactions on Intelligent Vehicles, 1-11
Open this publication in new window or tab >>A Condition-Aware Stochastic Dynamic Control Strategy for Safe Automated Driving
2024 (English)In: IEEE Transactions on Intelligent Vehicles, ISSN 2379-8858, E-ISSN 2379-8904, p. 1-11Article in journal (Refereed) Epub ahead of print
Abstract [en]

Condition-awareness regarding electrical and electronic components is not only significant for predictive maintenance of automotive vehicles but also plays a crucial role in ensuring the operational safety by supporting the detection of anomalies, faults, and degradations over lifetime. In this paper, we present a novel control strategy that combines stochastic dynamic control method with condition-awareness for safe automated driving. In particular, the effectiveness of condition-awareness is supported by two distinct condition-monitoring functions. The first function involves the monitoring of a vehicle's internal health condition using model-based approaches. The second function involves the monitoring of a vehicle's external surrounding conditions, using machine learning and artificial intelligence approaches. For the quantification of current conditions, the results from these monitoring functions are used to create system health indices, which are then utilized by a safety control function for dynamic behavior regulation. The design of this safety control function is based on a chance-constrained model predictive control model, combined with a control barrier function for ensuring safe operation. The novelty of the proposed method lies in a systematic integration of monitored external and internal conditions, estimated component degradation, and remaining useful life, with the controller's dynamic responsiveness. The efficacy of the proposed strategy is evaluated with adaptive cruise control in the presence of various sensory uncertainties.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering Control Engineering Embedded Systems
Research subject
Industrial Engineering and Management; Industrial Information and Control Systems
Identifiers
urn:nbn:se:kth:diva-347940 (URN)10.1109/tiv.2024.3414860 (DOI)2-s2.0-85196059651 (Scopus ID)
Projects
TRUST-E (EUREKA PENTA Euripides)
Note

QC 20240619

Available from: 2024-06-17 Created: 2024-06-17 Last updated: 2024-07-03Bibliographically approved
Huang, J., Zhu, Z., Su, P., Chen, D., Zheng, L.-R. & Zou, Z. (2024). A Reconfigurable Near-Sensor Processor for Anomaly Detection in Limb Prostheses. IEEE Transactions on Biomedical Circuits and Systems, 18(5), 976-989
Open this publication in new window or tab >>A Reconfigurable Near-Sensor Processor for Anomaly Detection in Limb Prostheses
Show others...
2024 (English)In: IEEE Transactions on Biomedical Circuits and Systems, ISSN 1932-4545, E-ISSN 1940-9990, Vol. 18, no 5, p. 976-989Article in journal (Refereed) Published
Abstract [en]

This paper presents a reconfigurable near-sensor anomaly detection processor to real-time monitor the potential anomalous behaviors of amputees with limb prostheses. The processor is low-power, low-latency, and suitable for equipment on the prostheses and comprises a reconfigurable Variational Autoencoder (VAE), a scalable Self-Organizing Map (SOM) Array, and a window-size-adjustable Markov Chain, which can implement an integrated miniaturized anomaly detection system. With the reconfigurable VAE, the proposed processor can support up to 64 sensor sampling channels programmable by global configuration, which can meet the anomaly detection requirements in different scenarios. A scalable SOM array allows for the selection of different sizes based on the complexity of the data. Unlike traditional time accumulation-based anomaly detection methods, the Markov Chain is utilized to detect time-series-based anomalous data. The processor is designed and fabricated in a UMC 40-nm LP technology with a core area of 1.49 mm2 and a power consumption of 1.81 mW. It achieves real-time detection performance with 0.933 average F1 Score for the FSP dataset within 24.22 s, and 0.956 average F1 Score for the SFDLA-12 dataset within 30.48 s, respectively. The energy dissipation of detection for each input feature is 43.84 nJ with the FSP dataset, and 55.17 nJ with the SFDLA-12 dataset. Compared with ARM Cortex-M4 and ARM Cortex-M33 microcontrollers, the processor achieves energy and area efficiency improvements ranging from 257×, 193× and 11×, 8×, respectively. IEEE

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:kth:diva-347939 (URN)10.1109/tbcas.2024.3370571 (DOI)001322633800007 ()38416632 (PubMedID)2-s2.0-85187023500 (Scopus ID)
Projects
EU Horizon SocketSense, Grant agreement ID: 825429
Note

QC 20241024

Available from: 2024-06-17 Created: 2024-06-17 Last updated: 2024-10-24Bibliographically approved
Su, P. & Chen, D. (2024). Adopting Graph Neural Networks to Analyze Human–Object Interactions for Inferring Activities of Daily Living. Sensors, 24(8), Article ID 2567.
Open this publication in new window or tab >>Adopting Graph Neural Networks to Analyze Human–Object Interactions for Inferring Activities of Daily Living
2024 (English)In: Sensors, E-ISSN 1424-8220, Vol. 24, no 8, article id 2567Article in journal (Refereed) Published
Abstract [en]

Human Activity Recognition (HAR) refers to a field that aims to identify human activitiesby adopting multiple techniques. In this field, different applications, such as smart homes andassistive robots, are introduced to support individuals in their Activities of Daily Living (ADL)by analyzing data collected from various sensors. Apart from wearable sensors, the adoption ofcamera frames to analyze and classify ADL has emerged as a promising trend for achieving theidentification and classification of ADL. To accomplish this, the existing approaches typically rely onobject classification with pose estimation using the image frames collected from cameras. Given theexistence of inherent correlations between human–object interactions and ADL, further efforts areoften needed to leverage these correlations for more effective and well justified decisions. To this end,this work proposes a framework where Graph Neural Networks (GNN) are adopted to explicitlyanalyze human–object interactions for more effectively recognizing daily activities. By automaticallyencoding the correlations among various interactions detected through some collected relational data,the framework infers the existence of different activities alongside their corresponding environmentalobjects. As a case study, we use the Toyota Smart Home dataset to evaluate the proposed framework.Compared with conventional feed-forward neural networks, the results demonstrate significantlysuperior performance in identifying ADL, allowing for the classification of different daily activitieswith an accuracy of 0.88. Furthermore, the incorporation of encoded information from relational dataenhances object-inference performance compared to the GNN without joint prediction, increasingaccuracy from 0.71 to 0.77. 

Place, publisher, year, edition, pages
MDPI AG, 2024
National Category
Computer Engineering
Identifiers
urn:nbn:se:kth:diva-345773 (URN)10.3390/s24082567 (DOI)001220542200001 ()38676184 (PubMedID)2-s2.0-85191368334 (Scopus ID)
Note

QC 20240527

Available from: 2024-04-18 Created: 2024-04-18 Last updated: 2025-03-20Bibliographically approved
Zhu, W., Liu, Z., Chen, Y., Chen, D. & Lu, Z. (2024). Amputee Gait Phase Recognition Using Multiple GMM-HMM. IEEE Access, 12, 193796-193806
Open this publication in new window or tab >>Amputee Gait Phase Recognition Using Multiple GMM-HMM
Show others...
2024 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 12, p. 193796-193806Article in journal (Refereed) Published
Abstract [en]

Gait analysis helps clinical assessment and achieves comfortable prosthetic designs for lower limb amputees, in which accurate gait phase recognition is a key component. However, gait phase detection remains a challenge due to the individual nature of prosthetic sockets and limbs. For the first time, we present a gait phase recognition approach for transfemoral amputees based on intra-socket pressure measurement. We proposed a multiple GMM-HMM (Hidden Markov Model with Gaussian Mixture Model emissions) method to label the gait events during walking. For each of the gait phases in the gait cycle, a separate GMM-HMM model is trained from the collected pressure data. We use gait phase recognition accuracy as a primary metric. The evaluation of six human subjects during walking shows a high accuracy of over 99% for single-subject, around 97.4% for multiple-subject, and up to 84.5% for unseen-subject scenarios. We compare our approach with the widely used CHMM (Continuous HMM) and LSTM (Long Short-term Memory) based methods, demonstrating better recognition accuracy performance across all scenarios.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024
Keywords
Hidden Markov models, Sockets, Pressure measurement, Prosthetics, Legged locomotion, Accuracy, Gaussian mixture model, Foot, Viterbi algorithm, Phase measurement, Gait phase recognition, hidden Markov model, lower limb prosthesis
National Category
Signal Processing
Identifiers
urn:nbn:se:kth:diva-358816 (URN)10.1109/ACCESS.2024.3516520 (DOI)001383061300030 ()2-s2.0-85212783100 (Scopus ID)
Note

QC 20250122

Available from: 2025-01-22 Created: 2025-01-22 Last updated: 2025-01-22Bibliographically approved
Chen, D., Ottikkutti, S. & Tahmasebi, K. N. (2024). Developing a Mechatronics-Twin Framework for Effective Exploration of Operational Behaviors of Prosthetic Sockets. SN Computer Science, 5(2), Article ID 205.
Open this publication in new window or tab >>Developing a Mechatronics-Twin Framework for Effective Exploration of Operational Behaviors of Prosthetic Sockets
2024 (English)In: SN Computer Science, E-ISSN 2661-8907, Vol. 5, no 2, article id 205Article in journal (Refereed) Published
Place, publisher, year, edition, pages
Springer Nature, 2024
National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-342371 (URN)10.1007/s42979-023-02485-7 (DOI)2-s2.0-85182205316 (Scopus ID)
Funder
KTH Royal Institute of Technology
Note

QC 20240118

Available from: 2024-01-17 Created: 2024-01-17 Last updated: 2024-01-25Bibliographically approved
Su, P., Yeqi, W., Conglei, X., Erik, W., Madhav, M. & Chen, D. (2024). Enhanced Prognostics and Health Management in Automated Driving Systems: Using Graph Neural Networks to Recognize Operational Contexts. In: Proceedings 2024 Prognostics and System Health Management Conference (PHM): . Paper presented at 2024 Prognostics and System Health Management Conference (PHM), Stockholm, Sweden, 28-31 May 2024. Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Enhanced Prognostics and Health Management in Automated Driving Systems: Using Graph Neural Networks to Recognize Operational Contexts
Show others...
2024 (English)In: Proceedings 2024 Prognostics and System Health Management Conference (PHM), Institute of Electrical and Electronics Engineers (IEEE) , 2024Conference paper, Published paper (Refereed)
Abstract [en]

Prognostics and health management (PHM) is an engineering discipline that aims to maintain system behaviour and function and ensure mission success, safety and effectiveness. Addressing the challenges in prognostics and health management for modern intelligent systems, especially automated driving systems, is complex due to the contextual nature of faults. This complexity necessitates a thorough understanding of spatial, and temporal conditions, and relationships within operational scenarios and life-cycle stages. This paper introduces a framework designed to automatically recognize driving scenarios in automated driving systems using graph neural networks (GNNs). The framework extracts relational data from image frames, constructing graph-based models and transforming unstructured sensory data into structured data with diverse node types and relationships. A specific graph neural network processes the graph model to reveal and detect operational conditions and relationships. The proposed framework is evaluated using the KITTI dataset, demonstrating superior performance compared to conventional feed-forward networks such as MLP, particularly in handling relational data.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024
Keywords
Graph neural networks;Data models;Safety;Complexity theory;Data mining;Prognostics and health management;Intelligent systems;Automated driving system;Graph neural network;Operational context;PHM;Recognition
National Category
Embedded Systems Other Electrical Engineering, Electronic Engineering, Information Engineering Reliability and Maintenance
Research subject
Machine Design; Computer Science; Electrical Engineering
Identifiers
urn:nbn:se:kth:diva-353355 (URN)10.1109/PHM61473.2024.00079 (DOI)2-s2.0-85214654312 (Scopus ID)
Conference
2024 Prognostics and System Health Management Conference (PHM), Stockholm, Sweden, 28-31 May 2024
Projects
Trust-E (Ref: 2020-05117), EUREKA EURIPIDES.
Funder
Vinnova, 2020-05117
Note

Part of ISBN 979-8-3503-6058-5

QC 20240924

Available from: 2024-09-18 Created: 2024-09-18 Last updated: 2025-01-23Bibliographically approved
Chen, Y., Zhu, W., Chen, D., Mohammed, O., Khound, P. & Lu, Z. (2024). Impact of Image Sensor Input Faults on Pruned Neural Networks for Object Detection. In: 37th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2024: . Paper presented at 37th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2024, Didcot, United Kingdom of Great Britain and Northern Ireland, Oct 8 2024 - Oct 10 2024. Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Impact of Image Sensor Input Faults on Pruned Neural Networks for Object Detection
Show others...
2024 (English)In: 37th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2024, Institute of Electrical and Electronics Engineers (IEEE) , 2024Conference paper, Published paper (Refereed)
Abstract [en]

Object detection is one of the most fundamental problems in computer vision, and image sensors are commonly used for this. In this paper, we present the impact of image sensor faults on pruned neural networks for object detection. We compare the error sensitivities of networks after network slimming, networks after magnitude-based pruning, and native compact models. We also explore different spatial fault types with three intensities. Furthermore, we have developed a temporal error model based on realistic aging image sensor faults. The results illuminate that the performance on clean images is important as the mean Average Precision (mAP) experiences a decrease with an increase in injected faults. Additionally, we demonstrate that the size of the model does not invariably yield a decisive impact on error tolerance when comparing small models such as pruned models and native compact models.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024
Keywords
Error sensitivity, Image Sensor Fault, Network Pruning, Network Slimming, Object Detection
National Category
Computer Sciences Computer Engineering Computer Systems
Identifiers
urn:nbn:se:kth:diva-358142 (URN)10.1109/DFT63277.2024.10753547 (DOI)2-s2.0-85212421051 (Scopus ID)
Conference
37th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2024, Didcot, United Kingdom of Great Britain and Northern Ireland, Oct 8 2024 - Oct 10 2024
Note

Part of ISBN 9798350366884

QC 20250114

Available from: 2025-01-07 Created: 2025-01-07 Last updated: 2025-01-14Bibliographically approved
Su, P., Yuan, H., Lu, Z. & Chen, D. (2024). Integrating Self-Organizing Map and Graph Neural Networks to Detect Anomalies in Time-series Data. IEEE Sensors Journal, 1-1
Open this publication in new window or tab >>Integrating Self-Organizing Map and Graph Neural Networks to Detect Anomalies in Time-series Data
2024 (English)In: IEEE Sensors Journal, ISSN 1530-437X, E-ISSN 1558-1748, p. 1-1Article in journal (Refereed) Epub ahead of print
Abstract [en]

Anomaly detection is essential in Industrial Cyber-Physical Systems (ICPS) for monitoring both system and environmental conditions. However, effective anomaly detection remains a continuous challenge due to the complexity and diversity of operational features in both spatial and temporal domains of such systems. Current data-driven approaches utilize Artificial Intelligence (AI)-enabled methods, such as Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), to process and analyze the collected operational data. From the industrial perspective, a key challenge lies in enhancing the effectiveness and explainability, as these methods often exhibit opaque and sophisticated network structures when dealing with complex operational data. Meanwhile, recent advancements in Graph Neural Networks (GNN) demonstrate its effectiveness of supporting the analysis of complex relationships and dependencies. The adoption of GNN poses however inherent challenges when the data are unstructured. This paper designs a novel framework that integrates Self-Organizing Maps (SOM) and GNN for the analysis of complex operational relationships and dependencies. In particular, the adoption of SOM allows the generation graph-structured data from unstructured raw datasets and thereby enhances a GNN’s ability to differentiate normal and anomalous conditions effectively. As case studies, we select multiple public datasets to compare the performance of the proposed framework with other benchmark methods. The results show that the proposed methods present promising results. Additionally, compared to other baseline methods that use GNN-based structures to detect anomalies, the proposed framework achieves the highest F1-Score.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024
National Category
Computer Engineering
Identifiers
urn:nbn:se:kth:diva-357661 (URN)10.1109/jsen.2024.3509632 (DOI)2-s2.0-85212300113 (Scopus ID)
Note

QC 20241216

Available from: 2024-12-11 Created: 2024-12-11 Last updated: 2025-03-20Bibliographically approved
Su, P., Warg, F. & Chen, D. (2023). A Simulation-Aided Approach to Safety Analysis of Learning-Enabled Components in Automated Driving Systems. In: 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023: . Paper presented at 26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023, Bilbao, Spain, Sep 24 2023 - Sep 28 2023 (pp. 6152-6157). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>A Simulation-Aided Approach to Safety Analysis of Learning-Enabled Components in Automated Driving Systems
2023 (English)In: 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023, Institute of Electrical and Electronics Engineers (IEEE) , 2023, p. 6152-6157Conference paper, Published paper (Refereed)
Abstract [en]

Artificial Intelligence (AI) techniques through Learning-Enabled Components (LEC) are widely employed in Automated Driving Systems (ADS) to support operation perception and other driving tasks relating to planning and control. Therefore, the risk management plays a critical role in assuring the operational safety of ADS. However, the probabilistic and nondeterministic nature of LEC challenges the safety analysis. Especially, the impacts of their functional faults and incompatible external conditions are often difficult to identify. To address this issue, this article presents a simulation-aided approach as follows: 1) A simulation-aided operational data generation service with the operational parameters extracted from the corresponding system models and specifications; 2) A Fault Injection (FI) service aimed at high-dimensional sensor data to evaluate the robustness and residual risks of LEC. 3) A Variational Bayesian (VB) method for encoding the collected operational data and supporting an effective estimation of the likelihood of operational conditions. As a case study, the paper presents the results of one experiment, where the behaviour of an Autonomous Emergency Braking (AEB) system is simulated under various weather conditions based on the CARLA driving simulator. A set of fault types of cameras, including solid occlusion, water drop, salt and pepper, are modelled and injected into the perception module of the AEB system in different weather conditions. The results indicate that our framework enables to identify the critical faults under various operational conditions. To approximate the critical faults in undefined weather, we also propose Variational Autoencoder (VAE) to encode the pixel-level data and estimate the likelihood.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:kth:diva-344364 (URN)10.1109/ITSC57777.2023.10422697 (DOI)2-s2.0-85186489885 (Scopus ID)
Conference
26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023, Bilbao, Spain, Sep 24 2023 - Sep 28 2023
Note

Part of ISBN 9798350399462

QC 20240315

Available from: 2024-03-13 Created: 2024-03-13 Last updated: 2025-03-20Bibliographically approved
Su, P., Lu, Z. & Chen, D. (2023). Combining Self-Organizing Map with Reinforcement Learning for Multivariate Time Series Anomaly Detection. In: Proceedings 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC): . Paper presented at 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), October 1-4, 2023, Honolulu, Oahu, Hawaii, USA.
Open this publication in new window or tab >>Combining Self-Organizing Map with Reinforcement Learning for Multivariate Time Series Anomaly Detection
2023 (English)In: Proceedings 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2023Conference paper, Published paper (Refereed)
Abstract [en]

Anomaly detection plays a critical role in condition monitors to support the trustworthiness of Cyber-Physical Systems (CPS). Detecting multivariate anomalous data in such systems is challenging due to the lack of a complete comprehension of anomalous behaviors and features. This paper proposes a framework to address time series multivariate anomaly detection problems by combining the Self-Organizing Map (SOM) with Deep Reinforcement Learning (DRL). By clustering the multivariate data, SOM creates an environment to enable the DRL agents interacting with the collected system  operational data in terms of a tabular dataset. In this environment, Markov chains reveal the likely anomalous features to support the DRL agent exploring and exploiting the state-action space to maximize anomaly detection performance. We use a time series dataset, Skoltech Anomaly Benchmark (SKAB), to evaluate our framework. Compared with the best results by some currently applied methods, our framework improves the F1 score by 9%, from 0.67 to 0.73. 

National Category
Engineering and Technology
Identifiers
urn:nbn:se:kth:diva-341478 (URN)
Conference
2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), October 1-4, 2023, Honolulu, Oahu, Hawaii, USA
Note

QC 20231220

Available from: 2023-12-20 Created: 2023-12-20 Last updated: 2024-01-30Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-7048-0108

Search in DiVA

Show all publications